diff options
Diffstat (limited to 'youtube_dl/extractor')
345 files changed, 15057 insertions, 4115 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5ab89a1bf..6866f06d4 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,15 +1,18 @@ +from __future__ import unicode_literals + from .abc import ABCIE from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .anitube import AnitubeIE +from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aparat import AparatIE from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE -from .ard import ARDIE +from .ard import ARDIE, ARDMediathekIE from .arte import ( ArteTvIE, ArteTVPlus7IE, @@ -19,17 +22,25 @@ from .arte import ( ArteTVDDCIE, ArteTVEmbedIE, ) +from .audiomack import AudiomackIE from .auengine import AUEngineIE +from .azubu import AzubuIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE from .bbccouk import BBCCoUkIE +from .beeg import BeegIE +from .behindkink import BehindKinkIE +from .bet import BetIE +from .bild import BildIE from .bilibili import BiliBiliIE from .blinkx import BlinkxIE from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE +from .bpb import BpbIE from .br import BRIE from .breakcom import BreakIE from .brightcove import BrightcoveIE +from .buzzfeed import BuzzFeedIE from .byutv import BYUtvIE from .c56 import C56IE from .canal13cl import Canal13clIE @@ -40,10 +51,11 @@ from .cbsnews import CBSNewsIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE -from .cinemassacre import CinemassacreIE +from .cinchcast import CinchcastIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE +from .cloudy import CloudyIE from .clubic import ClubicIE from .cmt import CMTIE from .cnet import CNETIE @@ -56,19 +68,25 @@ from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .condenast import CondeNastIE from .cracked import CrackedIE from .criterion import CriterionIE -from .crunchyroll import CrunchyrollIE +from .crunchyroll import ( + CrunchyrollIE, + CrunchyrollShowPlaylistIE +) from .cspan import CSpanIE -from .d8 import D8IE from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, DailymotionUserIE, ) from .daum import DaumIE +from .dbtv import DBTVIE +from .deezer import DeezerPlaylistIE from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +from .drtuber import DrTuberIE from .drtv import DRTVIE +from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE @@ -76,13 +94,20 @@ from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE +from .einthusan import EinthusanIE from .eitb import EitbIE +from .ellentv import ( + EllenTVIE, + EllenTVClipsIE, +) from .elpais import ElPaisIE -from .empflix import EmpflixIE +from .empflix import EMPFlixIE from .engadget import EngadgetIE +from .eporner import EpornerIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE +from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE @@ -96,7 +121,10 @@ from .fktv import ( FKTVPosteckeIE, ) from .flickr import FlickrIE +from .folketinget import FolketingetIE from .fourtube import FourTubeIE +from .foxgay import FoxgayIE +from .foxnews import FoxNewsIE from .franceculture import FranceCultureIE from .franceinter import FranceInterIE from .francetv import ( @@ -108,24 +136,38 @@ from .francetv import ( ) from .freesound import FreesoundIE from .freespeech import FreespeechIE +from .freevideo import FreeVideoIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE -from .gameone import GameOneIE +from .gameone import ( + GameOneIE, + GameOnePlaylistIE, +) from .gamespot import GameSpotIE from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE +from .giantbomb import GiantBombIE +from .glide import GlideIE +from .globo import GloboIE from .godtube import GodTubeIE +from .goldenmoustache import GoldenMoustacheIE +from .golem import GolemIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE +from .grooveshark import GroovesharkIE from .hark import HarkIE +from .heise import HeiseIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .hornbunny import HornBunnyIE +from .hostingbulk import HostingBulkIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE +from .howstuffworks import HowStuffWorksIE from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE @@ -143,10 +185,11 @@ from .ivi import ( IviIE, IviCompilationIE ) +from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE +from .jove import JoveIE from .jukebox import JukeboxIE -from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE from .kankan import KankanIE from .keezmovies import KeezMoviesIE @@ -157,6 +200,7 @@ from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE from .la7 import LA7IE +from .laola1tv import Laola1TvIE from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE from .livestream import ( @@ -164,6 +208,7 @@ from .livestream import ( LivestreamOriginalIE, LivestreamShortenerIE, ) +from .lrt import LRTIE from .lynda import ( LyndaIE, LyndaCourseIE @@ -175,15 +220,23 @@ from .malemotion import MalemotionIE from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE +from .mgoon import MgoonIE +from .minhateca import MinhatecaIE +from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mitele import MiTeleIE from .mixcloud import MixcloudIE from .mlb import MLBIE from .mpora import MporaIE +from .moevideo import MoeVideoIE from .mofosex import MofosexIE +from .mojvideo import MojvideoIE +from .moniker import MonikerIE from .mooshare import MooshareIE from .morningstar import MorningstarIE from .motherless import MotherlessIE from .motorsport import MotorsportIE +from .movieclips import MovieClipsIE from .moviezine import MoviezineIE from .movshare import MovShareIE from .mtv import ( @@ -191,11 +244,14 @@ from .mtv import ( MTVServicesEmbeddedIE, MTVIggyIE, ) +from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE +from .musicvault import MusicVaultIE from .muzu import MuzuTVIE -from .myspace import MySpaceIE +from .myspace import MySpaceIE, MySpaceAlbumIE from .myspass import MySpassIE from .myvideo import MyVideoIE +from .myvidster import MyVidsterIE from .naver import NaverIE from .nba import NBAIE from .nbc import ( @@ -207,15 +263,20 @@ from .ndtv import NDTVIE from .newgrounds import NewgroundsIE from .newstube import NewstubeIE from .nfb import NFBIE +from .nfl import NFLIE from .nhl import NHLIE, NHLVideocenterIE -from .niconico import NiconicoIE +from .niconico import NiconicoIE, NiconicoPlaylistIE from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE +from .nosvideo import NosVideoIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE -from .npo import NPOIE +from .npo import ( + NPOIE, + TegenlichtVproIE, +) from .nrk import ( NRKIE, NRKTVIE, @@ -223,19 +284,32 @@ from .nrk import ( from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE -from .oe1 import OE1IE +from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE -from .orf import ORFIE +from .orf import ( + ORFTVthekIE, + ORFOE1IE, + ORFFM4IE, +) from .parliamentliveuk import ParliamentLiveUKIE +from .patreon import PatreonIE from .pbs import PBSIE +from .phoenix import PhoenixIE from .photobucket import PhotobucketIE +from .planetaplay import PlanetaPlayIE +from .played import PlayedIE +from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE from .pornhd import PornHdIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .pornoxo import PornoXOIE +from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE +from .quickvid import QuickVidIE +from .radiode import RadioDeIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE @@ -246,9 +320,10 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE -from .rtve import RTVEALaCartaIE +from .rtve import RTVEALaCartaIE, RTVELiveIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, @@ -259,10 +334,15 @@ from .rutube import ( from .rutv import RUTVIE from .sapo import SapoIE from .savefrom import SaveFromIE +from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE +from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE from .servingsys import ServingSysIE +from .sexu import SexuIE +from .sexykarma import SexyKarmaIE from .shared import SharedIE +from .sharesix import ShareSixIE from .sina import SinaIE from .slideshare import SlideshareIE from .slutload import SlutloadIE @@ -288,17 +368,24 @@ from .southpark import ( ) from .space import SpaceIE from .spankwire import SpankwireIE -from .spiegel import SpiegelIE +from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE +from .sport5 import Sport5IE +from .sportbox import SportBoxIE +from .sportdeutschland import SportDeutschlandIE +from .srmediathek import SRMediathekIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .sunporno import SunPornoIE from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE from .tagesschau import TagesschauIE +from .tapely import TapelyIE +from .tass import TassIE from .teachertube import ( TeacherTubeIE, TeacherTubeUserIE, @@ -307,13 +394,24 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .telebruxelles import TeleBruxellesIE +from .telecinco import TelecincoIE +from .telemb import TeleMBIE from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE +from .theonion import TheOnionIE from .theplatform import ThePlatformIE +from .thesixtyone import TheSixtyOneIE from .thisav import ThisAVIE from .tinypic import TinyPicIE from .tlc import TlcIE, TlcDeIE +from .tmz import TMZIE +from .tnaflix import TNAFlixIE +from .thvideo import ( + THVideoIE, + THVideoPlaylistIE +) from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE @@ -322,10 +420,15 @@ from .trutube import TruTubeIE from .tube8 import Tube8IE from .tudou import TudouIE from .tumblr import TumblrIE +from .tunein import TuneInIE +from .turbo import TurboIE from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE from .tvplay import TVPlayIE +from .twentyfourvideo import TwentyFourVideoIE +from .twitch import TwitchIE +from .ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE @@ -338,22 +441,28 @@ from .veehd import VeeHDIE from .veoh import VeohIE from .vesti import VestiIE from .vevo import VevoIE +from .vgtv import VGTVIE from .vh1 import VH1IE +from .vice import ViceIE from .viddler import ViddlerIE from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE +from .videomega import VideoMegaIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE +from .vidme import VidmeIE +from .vidzi import VidziIE from .vimeo import ( VimeoIE, - VimeoChannelIE, - VimeoUserIE, VimeoAlbumIE, + VimeoChannelIE, VimeoGroupsIE, + VimeoLikesIE, VimeoReviewIE, + VimeoUserIE, VimeoWatchLaterIE, ) from .vimple import VimpleIE @@ -362,13 +471,20 @@ from .vine import ( VineUserIE, ) from .viki import VikiIE -from .vk import VKIE +from .vk import ( + VKIE, + VKUserVideosIE, +) from .vodlocker import VodlockerIE +from .vporn import VpornIE +from .vrt import VRTIE from .vube import VubeIE from .vuclip import VuClipIE from .vulture import VultureIE +from .walla import WallaIE from .washingtonpost import WashingtonPostIE from .wat import WatIE +from .wayofthemaster import WayOfTheMasterIE from .wdr import ( WDRIE, WDRMobileIE, @@ -380,18 +496,21 @@ from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .wrzuta import WrzutaIE from .xbef import XBefIE +from .xboxclips import XboxClipsIE from .xhamster import XHamsterIE +from .xminus import XMinusIE from .xnxx import XNXXIE from .xvideos import XVideosIE from .xtube import XTubeUserIE, XTubeIE from .yahoo import ( YahooIE, - YahooNewsIE, YahooSearchIE, ) +from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE from .youporn import YouPornIE +from .yourupload import YourUploadIE from .youtube import ( YoutubeIE, YoutubeChannelIE, @@ -409,9 +528,11 @@ from .youtube import ( YoutubeUserIE, YoutubeWatchLaterIE, ) - -from .zdf import ZDFIE - +from .zdf import ZDFIE, ZDFChannelIE +from .zingmp3 import ( + ZingMp3SongIE, + ZingMp3AlbumIE, +) _ALL_CLASSES = [ klass @@ -430,4 +551,4 @@ def gen_extractors(): def get_info_extractor(ie_name): """Returns the info extractor class with the given ie_name""" - return globals()[ie_name+'IE'] + return globals()[ie_name + 'IE'] diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 7d89f44ee..dc0fb85d6 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -11,19 +11,18 @@ class ABCIE(InfoExtractor): _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)' _TEST = { - 'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716', - 'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742', + 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334', + 'md5': 'cb3dd03b18455a661071ee1e28344d9f', 'info_dict': { - 'id': '5624716', + 'id': '5868334', 'ext': 'mp4', - 'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor', - 'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af', + 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', + 'description': 'md5:809ad29c67a05f54eb41f2a105693a67', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) urls_info_json = self._search_regex( diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index 59d3bbba4..47313fba8 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -1,4 +1,5 @@ from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,17 +8,25 @@ from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)' IE_NAME = 'AcademicEarth:Course' + _TEST = { + 'url': 'http://academicearth.org/playlists/laws-of-nature/', + 'info_dict': { + 'id': 'laws-of-nature', + 'title': 'Laws of Nature', + 'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.', + }, + 'playlist_count': 4, + } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - playlist_id = m.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) title = self._html_search_regex( - r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title') + r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title') description = self._html_search_regex( r'<p class="excerpt"[^>]*?>(.*?)</p>', - webpage, u'description', fatal=False) + webpage, 'description', fatal=False) urls = re.findall( r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">', webpage) diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py index fcf296057..203936e54 100644 --- a/youtube_dl/extractor/addanime.py +++ b/youtube_dl/extractor/addanime.py @@ -3,19 +3,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_HTTPError, compat_str, compat_urllib_parse, compat_urllib_parse_urlparse, - +) +from ..utils import ( ExtractorError, ) class AddAnimeIE(InfoExtractor): - - _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)' + _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)' _TEST = { 'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', 'md5': '72954ea10bc979ab5e2eb288b21425a0', @@ -28,9 +28,9 @@ class AddAnimeIE(InfoExtractor): } def _real_extract(self, url): + video_id = self._match_id(url) + try: - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') webpage = self._download_webpage(url, video_id) except ExtractorError as ee: if not isinstance(ee.cause, compat_HTTPError) or \ @@ -48,7 +48,7 @@ class AddAnimeIE(InfoExtractor): r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', redir_webpage) if av is None: - raise ExtractorError(u'Cannot find redirect math task') + raise ExtractorError('Cannot find redirect math task') av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3)) parsed_url = compat_urllib_parse_urlparse(url) diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index a00bfcb35..39e4ca296 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -2,118 +2,147 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + class AdultSwimIE(InfoExtractor): - _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' - _TEST = { - 'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', + _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?' + + _TESTS = [{ + 'url': 'http://adultswim.com/videos/rick-and-morty/pilot', 'playlist': [ { - 'md5': '4da359ec73b58df4575cd01a610ba5dc', + 'md5': '247572debc75c7652f253c8daa51a14d', 'info_dict': { - 'id': '8a250ba1450996e901453d7f02ca02f5', + 'id': 'rQxZvXQ4ROaSOqq-or2Mow-0', 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } + 'title': 'Rick and Morty - Pilot Part 1', + 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " + }, }, { - 'md5': 'ffbdf55af9331c509d95350bd0cc1819', + 'md5': '77b0e037a4b20ec6b98671c4c379f48d', 'info_dict': { - 'id': '8a250ba1450996e901453d7f4bd102f6', + 'id': 'rQxZvXQ4ROaSOqq-or2Mow-3', 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } - }, - { - 'md5': 'b92409635540304280b4b6c36bd14a0a', - 'info_dict': { - 'id': '8a250ba1450996e901453d7fa73c02f7', - 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } + 'title': 'Rick and Morty - Pilot Part 4', + 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " + }, }, + ], + 'info_dict': { + 'title': 'Rick and Morty - Pilot', + 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " + } + }, { + 'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/', + 'playlist': [ { - 'md5': 'e8818891d60e47b29cd89d7b0278156d', + 'md5': '2eb5c06d0f9a1539da3718d897f13ec5', 'info_dict': { - 'id': '8a250ba1450996e901453d7fc8ba02f8', + 'id': '-t8CamQlQ2aYZ49ItZCFog-0', 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } + 'title': 'American Dad - Putting Francine Out of Business', + 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].' + }, } - ] - } - - _video_extensions = { - '3500': 'flv', - '640': 'mp4', - '150': 'mp4', - 'ipad': 'm3u8', - 'iphone': 'm3u8' - } - _video_dimensions = { - '3500': (1280, 720), - '640': (480, 270), - '150': (320, 180) - } + ], + 'info_dict': { + 'title': 'American Dad - Putting Francine Out of Business', + 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].' + }, + }] + + @staticmethod + def find_video_info(collection, slug): + for video in collection.get('videos'): + if video.get('slug') == slug: + return video + + @staticmethod + def find_collection_by_linkURL(collections, linkURL): + for collection in collections: + if collection.get('linkURL') == linkURL: + return collection + + @staticmethod + def find_collection_containing_video(collections, slug): + for collection in collections: + for video in collection.get('videos'): + if video.get('slug') == slug: + return collection, video def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_path = mobj.group('path') - - webpage = self._download_webpage(url, video_path) - episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id') - title = self._og_search_title(webpage) - - index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id - idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') - - episode_el = idoc.find('.//episode') - show_title = episode_el.attrib.get('collectionTitle') - episode_title = episode_el.attrib.get('title') - thumbnail = episode_el.attrib.get('thumbnailUrl') - description = episode_el.find('./description').text.strip() + show_path = mobj.group('show_path') + episode_path = mobj.group('episode_path') + is_playlist = True if mobj.group('is_playlist') else False + + webpage = self._download_webpage(url, episode_path) + + # Extract the value of `bootstrappedData` from the Javascript in the page. + bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path) + + try: + bootstrappedData = json.loads(bootstrappedDataJS) + except ValueError as ve: + errmsg = '%s: Failed to parse JSON ' % episode_path + raise ExtractorError(errmsg, cause=ve) + + # Downloading videos from a /videos/playlist/ URL needs to be handled differently. + # NOTE: We are only downloading one video (the current one) not the playlist + if is_playlist: + collections = bootstrappedData['playlists']['collections'] + collection = self.find_collection_by_linkURL(collections, show_path) + video_info = self.find_video_info(collection, episode_path) + + show_title = video_info['showTitle'] + segment_ids = [video_info['videoPlaybackID']] + else: + collections = bootstrappedData['show']['collections'] + collection, video_info = self.find_collection_containing_video(collections, episode_path) + + show = bootstrappedData['show'] + show_title = show['title'] + segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']] + + episode_id = video_info['id'] + episode_title = video_info['title'] + episode_description = video_info['description'] + episode_duration = video_info.get('duration') entries = [] - segment_els = episode_el.findall('./segments/segment') + for part_num, segment_id in enumerate(segment_ids): + segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id + + segment_title = '%s - %s' % (show_title, episode_title) + if len(segment_ids) > 1: + segment_title += ' Part %d' % (part_num + 1) - for part_num, segment_el in enumerate(segment_els): - segment_id = segment_el.attrib.get('id') - segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) - thumbnail = segment_el.attrib.get('thumbnailUrl') - duration = segment_el.attrib.get('duration') + idoc = self._download_xml( + segment_url, segment_title, + 'Downloading segment information', 'Unable to download segment information') - segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id - idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information') + segment_duration = idoc.find('.//trt').text.strip() formats = [] file_els = idoc.findall('.//files/file') for file_el in file_els: bitrate = file_el.attrib.get('bitrate') - type = file_el.attrib.get('type') - width, height = self._video_dimensions.get(bitrate, (None, None)) + ftype = file_el.attrib.get('type') + formats.append({ - 'format_id': '%s-%s' % (bitrate, type), - 'url': file_el.text, - 'ext': self._video_extensions.get(bitrate, 'mp4'), + 'format_id': '%s_%s' % (bitrate, ftype), + 'url': file_el.text.strip(), # The bitrate may not be a number (for example: 'iphone') 'tbr': int(bitrate) if bitrate.isdigit() else None, - 'height': height, - 'width': width + 'quality': 1 if ftype == 'hd' else -1 }) self._sort_formats(formats) @@ -122,18 +151,16 @@ class AdultSwimIE(InfoExtractor): 'id': segment_id, 'title': segment_title, 'formats': formats, - 'uploader': show_title, - 'thumbnail': thumbnail, - 'duration': duration, - 'description': description + 'duration': segment_duration, + 'description': episode_description }) return { '_type': 'playlist', 'id': episode_id, - 'display_id': video_path, + 'display_id': episode_path, 'entries': entries, - 'title': '%s %s' % (show_title, episode_title), - 'description': description, - 'thumbnail': thumbnail + 'title': '%s - %s' % (show_title, episode_title), + 'description': episode_description, + 'duration': episode_duration } diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index 7bd797884..398e93bfb 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -22,7 +22,7 @@ class AllocineIE(InfoExtractor): 'id': '19546517', 'ext': 'mp4', 'title': 'Astérix - Le Domaine des Dieux Teaser VF', - 'description': 'md5:4a754271d9c6f16c72629a8a993ee884', + 'description': 'md5:abcd09ce503c6560512c14ebfdb720d2', 'thumbnail': 're:http://.*\.jpg', }, }, { diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py new file mode 100644 index 000000000..ad86d6e58 --- /dev/null +++ b/youtube_dl/extractor/anysex.py @@ -0,0 +1,61 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class AnySexIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://anysex.com/156592/', + 'md5': '023e9fbb7f7987f5529a394c34ad3d3d', + 'info_dict': { + 'id': '156592', + 'ext': 'mp4', + 'title': 'Busty and sexy blondie in her bikini strips for you', + 'description': 'md5:de9e418178e2931c10b62966474e1383', + 'categories': ['Erotic'], + 'duration': 270, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') + + title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + description = self._html_search_regex( + r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) + + categories = re.findall( + r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) + + duration = parse_duration(self._search_regex( + r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index a7bfe5a5c..47f8e4157 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -21,7 +21,7 @@ class AolIE(InfoExtractor): (?:$|\?) ''' - _TEST = { + _TESTS = [{ 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', 'md5': '18ef68f48740e86ae94b98da815eec42', 'info_dict': { @@ -30,7 +30,14 @@ class AolIE(InfoExtractor): 'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam', }, 'add_ie': ['FiveMin'], - } + }, { + 'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316', + 'info_dict': { + 'id': '152147', + 'title': 'Brace Yourself - Today\'s Weirdest News', + }, + 'playlist_mincount': 10, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 7e93bc4df..15006336f 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,4 +1,5 @@ -#coding: utf-8 +# coding: utf-8 +from __future__ import unicode_literals import re @@ -13,39 +14,39 @@ class AparatIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' _TEST = { - u'url': u'http://www.aparat.com/v/wP8On', - u'file': u'wP8On.mp4', - u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1', - u'info_dict': { - u"title": u"تیم گلکسی 11 - زومیت", + 'url': 'http://www.aparat.com/v/wP8On', + 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1', + 'info_dict': { + 'id': 'wP8On', + 'ext': 'mp4', + 'title': 'تیم گلکسی 11 - زومیت', }, - #u'skip': u'Extremely unreliable', + # 'skip': 'Extremely unreliable', } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id # but the URL in there does not work - embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' + - video_id + u'/vt/frame') + embed_url = ('http://www.aparat.com/video/video/embed/videohash/' + + video_id + '/vt/frame') webpage = self._download_webpage(embed_url, video_id) video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) for i, video_url in enumerate(video_urls): req = HEADRequest(video_url) res = self._request_webpage( - req, video_id, note=u'Testing video URL %d' % i, errnote=False) + req, video_id, note='Testing video URL %d' % i, errnote=False) if res: break else: - raise ExtractorError(u'No working video URLs found') + raise ExtractorError('No working video URLs found') - title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title') + title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title') thumbnail = self._search_regex( - r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False) + r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index dc8657b67..0c01fa1a1 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -6,6 +6,7 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, + int_or_none, ) @@ -69,15 +70,17 @@ class AppleTrailersIE(InfoExtractor): uploader_id = mobj.group('company') playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') + def fix_html(s): s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s) s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) # The ' in the onClick attributes are not escaped, it couldn't be parsed # like: http://trailers.apple.com/trailers/wb/gravity/ + def _clean_json(m): return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') s = re.sub(self._JSON_RE, _clean_json, s) - s = '<html>' + s + u'</html>' + s = '<html>%s</html>' % s return s doc = self._download_xml(playlist_url, movie, transform_source=fix_html) @@ -85,7 +88,7 @@ class AppleTrailersIE(InfoExtractor): for li in doc.findall('./div/ul/li'): on_click = li.find('.//a').attrib['onClick'] trailer_info_json = self._search_regex(self._JSON_RE, - on_click, 'trailer info') + on_click, 'trailer info') trailer_info = json.loads(trailer_info_json) title = trailer_info['title'] video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() @@ -110,8 +113,8 @@ class AppleTrailersIE(InfoExtractor): formats.append({ 'url': format_url, 'format': format['type'], - 'width': format['width'], - 'height': int(format['height']), + 'width': int_or_none(format['width']), + 'height': int_or_none(format['height']), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 30a85c8c1..967bd865c 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -4,14 +4,21 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, qualities, + int_or_none, + parse_duration, + unified_strdate, + xpath_text, + parse_xml, ) -class ARDIE(InfoExtractor): +class ARDMediathekIE(InfoExtractor): + IE_NAME = 'ARD:mediathek' _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ @@ -46,6 +53,14 @@ class ARDIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: + raise ExtractorError('Video %s is no longer available' % video_id, expected=True) + + if re.search(r'[\?&]rss($|[=&])', url): + doc = parse_xml(webpage) + if doc.tag == 'rss': + return GenericIE()._extract_rss(url, video_id, doc) + title = self._html_search_regex( [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', r'<meta name="dcterms.title" content="(.*?)"/>', @@ -120,3 +135,60 @@ class ARDIE(InfoExtractor): 'formats': formats, 'thumbnail': thumbnail, } + + +class ARDIE(InfoExtractor): + _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html' + _TEST = { + 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', + 'md5': 'd216c3a86493f9322545e045ddc3eb35', + 'info_dict': { + 'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge', + 'id': '100', + 'ext': 'mp4', + 'duration': 2600, + 'title': 'Die Story im Ersten: Mission unter falscher Flagge', + 'upload_date': '20140804', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + player_url = mobj.group('mainurl') + '~playerXml.xml' + doc = self._download_xml(player_url, display_id) + video_node = doc.find('./video') + upload_date = unified_strdate(xpath_text( + video_node, './broadcastDate')) + thumbnail = xpath_text(video_node, './/teaserImage//variant/url') + + formats = [] + for a in video_node.findall('.//asset'): + f = { + 'format_id': a.attrib['type'], + 'width': int_or_none(a.find('./frameWidth').text), + 'height': int_or_none(a.find('./frameHeight').text), + 'vbr': int_or_none(a.find('./bitrateVideo').text), + 'abr': int_or_none(a.find('./bitrateAudio').text), + 'vcodec': a.find('./codecVideo').text, + 'tbr': int_or_none(a.find('./totalBitrate').text), + } + if a.find('./serverPrefix').text: + f['url'] = a.find('./serverPrefix').text + f['playpath'] = a.find('./fileName').text + else: + f['url'] = a.find('./fileName').text + formats.append(f) + self._sort_formats(formats) + + return { + 'id': mobj.group('id'), + 'formats': formats, + 'display_id': display_id, + 'title': video_node.find('./title').text, + 'duration': parse_duration(video_node.find('./duration').text), + 'upload_date': upload_date, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 9591bad8a..219631b9b 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -5,16 +5,15 @@ import re from .common import InfoExtractor from ..utils import ( - ExtractorError, find_xpath_attr, unified_strdate, - determine_ext, get_element_by_id, - compat_str, get_element_by_attribute, + int_or_none, + qualities, ) -# There are different sources of video in arte.tv, the extraction process +# There are different sources of video in arte.tv, the extraction process # is different for each one. The videos usually expire in 7 days, so we can't # add tests. @@ -78,111 +77,104 @@ class ArteTVPlus7IE(InfoExtractor): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex( - r'arte_vp_url="(.*?)"', webpage, 'json vp url') + [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'], + webpage, 'json vp url') return self._extract_from_json_url(json_url, video_id, lang) def _extract_from_json_url(self, json_url, video_id, lang): info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] + upload_date_str = player_info.get('shootingDate') + if not upload_date_str: + upload_date_str = player_info.get('VDA', '').split(' ')[0] + + title = player_info['VTI'].strip() + subtitle = player_info.get('VSU', '').strip() + if subtitle: + title += ' - %s' % subtitle + info_dict = { 'id': player_info['VID'], - 'title': player_info['VTI'], + 'title': title, 'description': player_info.get('VDE'), - 'upload_date': unified_strdate(player_info.get('VDA', '').split(' ')[0]), + 'upload_date': unified_strdate(upload_date_str), 'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'), } - - all_formats = player_info['VSR'].values() - # Some formats use the m3u8 protocol - all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats)) - def _match_lang(f): - if f.get('versionCode') is None: - return True - # Return true if that format is in the language of the url - if lang == 'fr': - l = 'F' - elif lang == 'de': - l = 'A' - else: - l = lang - regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l] - return any(re.match(r, f['versionCode']) for r in regexes) - # Some formats may not be in the same language as the url - formats = filter(_match_lang, all_formats) - formats = list(formats) # in python3 filter returns an iterator - if not formats: - # Some videos are only available in the 'Originalversion' - # they aren't tagged as being in French or German - if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats): - formats = all_formats - else: - raise ExtractorError(u'The formats list is empty') - - if re.match(r'[A-Z]Q', formats[0]['quality']) is not None: - def sort_key(f): - return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality']) - else: - def sort_key(f): - versionCode = f.get('versionCode') - if versionCode is None: - versionCode = '' - return ( - # Sort first by quality - int(f.get('height', -1)), - int(f.get('bitrate', -1)), - # The original version with subtitles has lower relevance - re.match(r'VO-ST(F|A)', versionCode) is None, - # The version with sourds/mal subtitles has also lower relevance - re.match(r'VO?(F|A)-STM\1', versionCode) is None, - # Prefer http downloads over m3u8 - 0 if f['url'].endswith('m3u8') else 1, - ) - formats = sorted(formats, key=sort_key) - def _format(format_info): - quality = '' - height = format_info.get('height') - if height is not None: - quality = compat_str(height) - bitrate = format_info.get('bitrate') - if bitrate is not None: - quality += '-%d' % bitrate - if format_info.get('versionCode') is not None: - format_id = '%s-%s' % (quality, format_info['versionCode']) - else: - format_id = quality - info = { + qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ']) + + formats = [] + for format_id, format_dict in player_info['VSR'].items(): + f = dict(format_dict) + versionCode = f.get('versionCode') + + langcode = { + 'fr': 'F', + 'de': 'A', + }.get(lang, lang) + lang_rexs = [r'VO?%s' % langcode, r'VO?.-ST%s' % langcode] + lang_pref = ( + None if versionCode is None else ( + 10 if any(re.match(r, versionCode) for r in lang_rexs) + else -10)) + source_pref = 0 + if versionCode is not None: + # The original version with subtitles has lower relevance + if re.match(r'VO-ST(F|A)', versionCode): + source_pref -= 10 + # The version with sourds/mal subtitles has also lower relevance + elif re.match(r'VO?(F|A)-STM\1', versionCode): + source_pref -= 9 + format = { 'format_id': format_id, - 'format_note': format_info.get('versionLibelle'), - 'width': format_info.get('width'), - 'height': height, + 'preference': -10 if f.get('videoFormat') == 'M3U8' else None, + 'language_preference': lang_pref, + 'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')), + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'tbr': int_or_none(f.get('bitrate')), + 'quality': qfunc(f['quality']), + 'source_preference': source_pref, } - if format_info['mediaType'] == 'rtmp': - info['url'] = format_info['streamer'] - info['play_path'] = 'mp4:' + format_info['url'] - info['ext'] = 'flv' + + if f.get('mediaType') == 'rtmp': + format['url'] = f['streamer'] + format['play_path'] = 'mp4:' + f['url'] + format['ext'] = 'flv' else: - info['url'] = format_info['url'] - info['ext'] = determine_ext(info['url']) - return info - info_dict['formats'] = [_format(f) for f in formats] + format['url'] = f['url'] + formats.append(format) + + self._sort_formats(formats) + + info_dict['formats'] = formats return info_dict # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:creative' - _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)' + _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)' - _TEST = { + _TESTS = [{ 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', 'info_dict': { - 'id': '050489-002', + 'id': '72176', 'ext': 'mp4', - 'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design', + 'title': 'Folge 2 - Corporate Design', + 'upload_date': '20131004', }, - } + }, { + 'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion', + 'info_dict': { + 'id': '160676', + 'ext': 'mp4', + 'title': 'Monty Python live (mostly)', + 'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n', + 'upload_date': '20140805', + } + }] class ArteTVFutureIE(ArteTVPlus7IE): diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py new file mode 100644 index 000000000..622b20989 --- /dev/null +++ b/youtube_dl/extractor/audiomack.py @@ -0,0 +1,69 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .soundcloud import SoundcloudIE +from ..utils import ExtractorError + +import time + + +class AudiomackIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)' + IE_NAME = 'audiomack' + _TESTS = [ + # hosted on audiomack + { + 'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary', + 'info_dict': + { + 'id': 'roosh-williams/extraordinary', + 'ext': 'mp3', + 'title': 'Roosh Williams - Extraordinary' + } + }, + # hosted on soundcloud via audiomack + { + 'add_ie': ['Soundcloud'], + 'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare', + 'info_dict': { + 'id': '172419696', + 'ext': 'mp3', + 'description': 'md5:1fc3272ed7a635cce5be1568c2822997', + 'title': 'Young Thug ft Lil Wayne - Take Kare', + 'uploader': 'Young Thug World', + 'upload_date': '20141016', + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + api_response = self._download_json( + "http://www.audiomack.com/api/music/url/song/%s?_=%d" % ( + video_id, time.time()), + video_id) + + if "url" not in api_response: + raise ExtractorError("Unable to deduce api url of song") + realurl = api_response["url"] + + # Audiomack wraps a lot of soundcloud tracks in their branded wrapper + # - if so, pass the work off to the soundcloud extractor + if SoundcloudIE.suitable(realurl): + return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'} + + webpage = self._download_webpage(url, video_id) + artist = self._html_search_regex( + r'<span class="artist">(.*?)</span>', webpage, "artist") + songtitle = self._html_search_regex( + r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>', + webpage, "title") + title = artist + " - " + songtitle + + return { + 'id': video_id, + 'title': title, + 'url': realurl, + } diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 20bf12550..1c765532a 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -24,8 +24,7 @@ class AUEngineIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title') diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py new file mode 100644 index 000000000..0961d339f --- /dev/null +++ b/youtube_dl/extractor/azubu.py @@ -0,0 +1,93 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import float_or_none + + +class AzubuIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1', + 'md5': 'a88b42fcf844f29ad6035054bd9ecaf4', + 'info_dict': { + 'id': '15575', + 'ext': 'mp4', + 'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1', + 'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01', + 'thumbnail': 're:^https?://.*\.jpe?g', + 'timestamp': 1417523507.334, + 'upload_date': '20141202', + 'duration': 9988.7, + 'uploader': 'GSL', + 'uploader_id': 414310, + 'view_count': int, + }, + }, + { + 'url': 'http://www.azubu.tv/FnaticTV#!/play/9344/-fnatic-at-worlds-2014:-toyz---%22i-love-rekkles,-he-has-amazing-mechanics%22-', + 'md5': 'b72a871fe1d9f70bd7673769cdb3b925', + 'info_dict': { + 'id': '9344', + 'ext': 'mp4', + 'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"', + 'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af', + 'thumbnail': 're:^https?://.*\.jpe?g', + 'timestamp': 1410530893.320, + 'upload_date': '20140912', + 'duration': 172.385, + 'uploader': 'FnaticTV', + 'uploader_id': 272749, + 'view_count': int, + }, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + data = self._download_json( + 'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data'] + + title = data['title'].strip() + description = data['description'] + thumbnail = data['thumbnail'] + view_count = data['view_count'] + uploader = data['user']['username'] + uploader_id = data['user']['id'] + + stream_params = json.loads(data['stream_params']) + + timestamp = float_or_none(stream_params['creationDate'], 1000) + duration = float_or_none(stream_params['length'], 1000) + + renditions = stream_params.get('renditions') or [] + video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength') + if video: + renditions.append(video) + + formats = [{ + 'url': fmt['url'], + 'width': fmt['frameWidth'], + 'height': fmt['frameHeight'], + 'vbr': float_or_none(fmt['encodingRate'], 1000), + 'filesize': fmt['size'], + 'vcodec': fmt['videoCodec'], + 'container': fmt['videoContainer'], + } for fmt in renditions if fmt['url']] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index ccd31c4c7..1ca0b7cf2 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -18,7 +18,7 @@ class BambuserIE(InfoExtractor): _TEST = { 'url': 'http://bambuser.com/v/4050584', # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388 - #u'md5': 'fba8f7693e48fd4e8641b3fd5539a641', + # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641', 'info_dict': { 'id': '4050584', 'ext': 'flv', @@ -38,7 +38,7 @@ class BambuserIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') info_url = ('http://player-c.api.bambuser.com/getVideo.json?' - '&api_key=%s&vid=%s' % (self._API_KEY, video_id)) + '&api_key=%s&vid=%s' % (self._API_KEY, video_id)) info_json = self._download_webpage(info_url, video_id) info = json.loads(info_json)['result'] @@ -59,6 +59,13 @@ class BambuserChannelIE(InfoExtractor): _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)' # The maximum number we can get with each request _STEP = 50 + _TEST = { + 'url': 'http://bambuser.com/channel/pixelversity', + 'info_dict': { + 'title': 'pixelversity', + }, + 'playlist_mincount': 60, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -66,17 +73,18 @@ class BambuserChannelIE(InfoExtractor): urls = [] last_id = '' for i in itertools.count(1): - req_url = ('http://bambuser.com/xhr-api/index.php?username={user}' + req_url = ( + 'http://bambuser.com/xhr-api/index.php?username={user}' '&sort=created&access_mode=0%2C1%2C2&limit={count}' '&method=broadcast&format=json&vid_older_than={last}' - ).format(user=user, count=self._STEP, last=last_id) + ).format(user=user, count=self._STEP, last=last_id) req = compat_urllib_request.Request(req_url) # Without setting this header, we wouldn't get any result req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) - info_json = self._download_webpage(req, user, - 'Downloading page %d' % i) - results = json.loads(info_json)['result'] - if len(results) == 0: + data = self._download_json( + req, user, 'Downloading page %d' % i) + results = data['result'] + if not results: break last_id = results[-1]['vid'] urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index dcbbdef43..acddbc8f1 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -15,13 +15,23 @@ class BandcampIE(InfoExtractor): _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)' _TESTS = [{ 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', - 'file': '1812978515.mp3', 'md5': 'c557841d5e50261777a6585648adf439', 'info_dict': { - "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", - "duration": 9.8485, + 'id': '1812978515', + 'ext': 'mp3', + 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", + 'duration': 9.8485, }, '_skip': 'There is a limit of 200 free downloads / month for the test song' + }, { + 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', + 'md5': '2b68e5851514c20efdff2afc5603b8b4', + 'info_dict': { + 'id': '2650410135', + 'ext': 'mp3', + 'title': 'Lanius (Battle)', + 'uploader': 'Ben Prunty Music', + }, }] def _real_extract(self, url): @@ -59,9 +69,9 @@ class BandcampIE(InfoExtractor): raise ExtractorError('No free songs found') download_link = m_download.group(1) - video_id = re.search( - r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', - webpage, re.MULTILINE | re.DOTALL).group('id') + video_id = self._search_regex( + r'var TralbumData = {.*?id: (?P<id>\d+),?$', + webpage, 'video id', flags=re.MULTILINE | re.DOTALL) download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page') # We get the dictionary of the track from some javascript code @@ -73,12 +83,12 @@ class BandcampIE(InfoExtractor): initial_url = mp3_info['url'] re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' m_url = re.match(re_url, initial_url) - #We build the url we will use to get the final track url + # We build the url we will use to get the final track url # This url is build in Bandcamp in the script download_bunde_*.js request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts')) final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') # If we could correctly generate the .rand field the url would be - #in the "download_url" key + # in the "download_url" key final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) return { @@ -96,29 +106,40 @@ class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' - _TEST = { + _TESTS = [{ 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', 'playlist': [ { - 'file': '1353101989.mp3', 'md5': '39bc1eded3476e927c724321ddf116cf', 'info_dict': { + 'id': '1353101989', + 'ext': 'mp3', 'title': 'Intro', } }, { - 'file': '38097443.mp3', 'md5': '1a2c32e2691474643e912cc6cd4bffaa', 'info_dict': { + 'id': '38097443', + 'ext': 'mp3', 'title': 'Kero One - Keep It Alive (Blazo remix)', } }, ], + 'info_dict': { + 'title': 'Jazz Format Mixtape vol.1', + }, 'params': { 'playlistend': 2 }, 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' - } + }, { + 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave', + 'info_dict': { + 'title': 'Hierophany of the Open Grave', + }, + 'playlist_mincount': 9, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index 75e608f99..01c02d360 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -1,9 +1,10 @@ from __future__ import unicode_literals -import re +import xml.etree.ElementTree from .subtitles import SubtitlesInfoExtractor from ..utils import ExtractorError +from ..compat import compat_HTTPError class BBCCoUkIE(SubtitlesInfoExtractor): @@ -55,7 +56,22 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'skip_download': True, }, 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', - } + }, + { + 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', + 'info_dict': { + 'id': 'b03k3pb7', + 'ext': 'flv', + 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", + 'description': '2. Invasion', + 'duration': 3600, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', + }, ] def _extract_asx_playlist(self, connection, programme_id): @@ -102,6 +118,10 @@ class BBCCoUkIE(SubtitlesInfoExtractor): return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') def _extract_medias(self, media_selection): + error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') + if error is not None: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True) return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') def _extract_connections(self, media): @@ -158,54 +178,73 @@ class BBCCoUkIE(SubtitlesInfoExtractor): subtitles[lang] = srt return subtitles - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - group_id = mobj.group('id') - - webpage = self._download_webpage(url, group_id, 'Downloading video page') - if re.search(r'id="emp-error" class="notinuk">', webpage): - raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only', - expected=True) - - playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id, - 'Downloading playlist XML') - - no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') - if no_items is not None: - reason = no_items.get('reason') - if reason == 'preAvailability': - msg = 'Episode %s is not yet available' % group_id - elif reason == 'postAvailability': - msg = 'Episode %s is no longer available' % group_id + def _download_media_selector(self, programme_id): + try: + media_selection = self._download_xml( + 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, + programme_id, 'Downloading media selection XML') + except ExtractorError as ee: + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: + media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8')) else: - msg = 'Episode %s is not available: %s' % (group_id, reason) - raise ExtractorError(msg, expected=True) + raise formats = [] subtitles = None - for item in self._extract_items(playlist): - kind = item.get('kind') - if kind != 'programme' and kind != 'radioProgramme': - continue - title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text - description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text + for media in self._extract_medias(media_selection): + kind = media.get('kind') + if kind == 'audio': + formats.extend(self._extract_audio(media, programme_id)) + elif kind == 'video': + formats.extend(self._extract_video(media, programme_id)) + elif kind == 'captions': + subtitles = self._extract_captions(media, programme_id) - programme_id = item.get('identifier') - duration = int(item.get('duration')) + return formats, subtitles - media_selection = self._download_xml( - 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, - programme_id, 'Downloading media selection XML') + def _real_extract(self, url): + group_id = self._match_id(url) + + webpage = self._download_webpage(url, group_id, 'Downloading video page') - for media in self._extract_medias(media_selection): - kind = media.get('kind') - if kind == 'audio': - formats.extend(self._extract_audio(media, programme_id)) - elif kind == 'video': - formats.extend(self._extract_video(media, programme_id)) - elif kind == 'captions': - subtitles = self._extract_captions(media, programme_id) + programme_id = self._search_regex( + r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False) + if programme_id: + player = self._download_json( + 'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id, + group_id)['jsConf']['player'] + title = player['title'] + description = player['subtitle'] + duration = player['duration'] + formats, subtitles = self._download_media_selector(programme_id) + else: + playlist = self._download_xml( + 'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, + group_id, 'Downloading playlist XML') + + no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') + if no_items is not None: + reason = no_items.get('reason') + if reason == 'preAvailability': + msg = 'Episode %s is not yet available' % group_id + elif reason == 'postAvailability': + msg = 'Episode %s is no longer available' % group_id + elif reason == 'noMedia': + msg = 'Episode %s is not currently available' % group_id + else: + msg = 'Episode %s is not available: %s' % (group_id, reason) + raise ExtractorError(msg, expected=True) + + for item in self._extract_items(playlist): + kind = item.get('kind') + if kind != 'programme' and kind != 'radioProgramme': + continue + title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text + description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text + programme_id = item.get('identifier') + duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) if self._downloader.params.get('listsubtitles', False): self._list_available_subtitles(programme_id, subtitles) @@ -220,4 +259,4 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'duration': duration, 'formats': formats, 'subtitles': subtitles, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py new file mode 100644 index 000000000..4e79fea8f --- /dev/null +++ b/youtube_dl/extractor/beeg.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class BeegIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://beeg.com/5416503', + 'md5': '634526ae978711f6b748fe0dd6c11f57', + 'info_dict': { + 'id': '5416503', + 'ext': 'mp4', + 'title': 'Sultry Striptease', + 'description': 'md5:6db3c6177972822aaba18652ff59c773', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + quality_arr = self._search_regex( + r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats') + + formats = [{ + 'url': fmt[1], + 'format_id': fmt[0], + 'height': int(fmt[0][:-1]), + } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)] + + self._sort_formats(formats) + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title') + + description = self._html_search_regex( + r'<meta name="description" content="([^"]*)"', + webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'\'previewer.url\'\s*:\s*"([^"]*)"', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_regex( + r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/behindkink.py b/youtube_dl/extractor/behindkink.py new file mode 100644 index 000000000..1bdc25812 --- /dev/null +++ b/youtube_dl/extractor/behindkink.py @@ -0,0 +1,46 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import url_basename + + +class BehindKinkIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)' + _TEST = { + 'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/', + 'md5': '507b57d8fdcd75a41a9a7bdb7989c762', + 'info_dict': { + 'id': '37127', + 'ext': 'mp4', + 'title': 'What are you passionate about – Marley Blaze', + 'description': 'md5:aee8e9611b4ff70186f752975d9b94b4', + 'upload_date': '20141205', + 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r'<source src="([^"]+)"', webpage, 'video URL') + video_id = url_basename(video_url).split('_')[0] + upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day') + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), + 'upload_date': upload_date, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py new file mode 100644 index 000000000..c1fc433f7 --- /dev/null +++ b/youtube_dl/extractor/bet.py @@ -0,0 +1,108 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + xpath_text, + xpath_with_ns, + int_or_none, + parse_iso8601, +) + + +class BetIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' + _TESTS = [ + { + 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html', + 'info_dict': { + 'id': '417cd61c-c793-4e8e-b006-e445ecc45add', + 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism', + 'ext': 'flv', + 'title': 'BET News Presents: A Conversation With President Obama', + 'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6', + 'duration': 1534, + 'timestamp': 1418075340, + 'upload_date': '20141208', + 'uploader': 'admin', + 'thumbnail': 're:(?i)^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', + 'info_dict': { + 'id': '4160e53b-ad41-43b1-980f-8d85f63121f4', + 'display_id': 'justice-for-ferguson-a-community-reacts', + 'ext': 'flv', + 'title': 'Justice for Ferguson: A Community Reacts', + 'description': 'A BET News special.', + 'duration': 1696, + 'timestamp': 1416942360, + 'upload_date': '20141125', + 'uploader': 'admin', + 'thumbnail': 're:(?i)^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + media_url = compat_urllib_parse.unquote(self._search_regex( + [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], + webpage, 'media URL')) + + mrss = self._download_xml(media_url, display_id) + + item = mrss.find('./channel/item') + + NS_MAP = { + 'dc': 'http://purl.org/dc/elements/1.1/', + 'media': 'http://search.yahoo.com/mrss/', + 'ka': 'http://kickapps.com/karss', + } + + title = xpath_text(item, './title', 'title') + description = xpath_text( + item, './description', 'description', fatal=False) + + video_id = xpath_text(item, './guid', 'video id', fatal=False) + + timestamp = parse_iso8601(xpath_text( + item, xpath_with_ns('./dc:date', NS_MAP), + 'upload date', fatal=False)) + uploader = xpath_text( + item, xpath_with_ns('./dc:creator', NS_MAP), + 'uploader', fatal=False) + + media_content = item.find( + xpath_with_ns('./media:content', NS_MAP)) + duration = int_or_none(media_content.get('duration')) + smil_url = media_content.get('url') + + thumbnail = media_content.find( + xpath_with_ns('./media:thumbnail', NS_MAP)).get('url') + + formats = self._extract_smil_formats(smil_url, display_id) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'uploader': uploader, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/bild.py b/youtube_dl/extractor/bild.py new file mode 100644 index 000000000..77b562d99 --- /dev/null +++ b/youtube_dl/extractor/bild.py @@ -0,0 +1,39 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class BildIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html' + IE_DESC = 'Bild.de' + _TEST = { + 'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html', + 'md5': 'dd495cbd99f2413502a1713a1156ac8a', + 'info_dict': { + 'id': '38184146', + 'ext': 'mp4', + 'title': 'BILD hat sie getestet', + 'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg', + 'duration': 196, + 'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml" + doc = self._download_xml(xml_url, video_id) + + duration = int_or_none(doc.attrib.get('duration'), scale=1000) + + return { + 'id': video_id, + 'title': doc.attrib['ueberschrift'], + 'description': doc.attrib.get('text'), + 'url': doc.attrib['src'], + 'thumbnail': doc.attrib.get('img'), + 'duration': duration, + } diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index acfc4ad73..14b814120 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -4,18 +4,22 @@ import re from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( + +from ..compat import ( + compat_str, compat_urllib_request, - unescapeHTML, - parse_iso8601, compat_urlparse, +) +from ..utils import ( clean_html, - compat_str, + int_or_none, + parse_iso8601, + unescapeHTML, ) class BlipTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))' + _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))' _TESTS = [ { @@ -49,20 +53,70 @@ class BlipTVIE(SubtitlesInfoExtractor): 'uploader_id': '792887', 'duration': 279, } - } + }, + { + # https://bugzilla.redhat.com/show_bug.cgi?id=967465 + 'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI', + 'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6', + 'info_dict': { + 'id': '6573122', + 'ext': 'mov', + 'upload_date': '20130520', + 'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.', + 'title': 'Red vs. Blue Season 11 Trailer', + 'timestamp': 1369029609, + 'uploader': 'redvsblue', + 'uploader_id': '792887', + } + }, + { + 'url': 'http://blip.tv/play/gbk766dkj4Yn', + 'md5': 'fe0a33f022d49399a241e84a8ea8b8e3', + 'info_dict': { + 'id': '1749452', + 'ext': 'mp4', + 'upload_date': '20090208', + 'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.', + 'title': 'Nostalgia Critic: Transformers', + 'timestamp': 1234068723, + 'uploader': 'NostalgiaCritic', + 'uploader_id': '246467', + } + }, + { + # https://github.com/rg3/youtube-dl/pull/4404 + 'note': 'Audio only', + 'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982', + 'md5': '76c0a56f24e769ceaab21fbb6416a351', + 'info_dict': { + 'id': '7103299', + 'ext': 'flv', + 'title': 'Weekly Manga Recap: Kingdom', + 'description': 'And then Shin breaks the enemy line, and he's all like HWAH! And then he slices a guy and it's all like FWASHING! And... it's really hard to describe the best parts of this series without breaking down into sound effects, okay?', + 'timestamp': 1417660321, + 'upload_date': '20141204', + 'uploader': 'The Rollo T', + 'uploader_id': '407429', + 'duration': 7251, + 'vcodec': 'none', + } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) lookup_id = mobj.group('lookup_id') - # See https://github.com/rg3/youtube-dl/issues/857 + # See https://github.com/rg3/youtube-dl/issues/857 and + # https://github.com/rg3/youtube-dl/issues/4197 if lookup_id: - info_page = self._download_webpage( - 'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id') - video_id = self._search_regex(r'data-episode-id="([0-9]+)', info_page, 'video_id') - else: - video_id = mobj.group('id') + urlh = self._request_webpage( + 'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id') + url = compat_urlparse.urlparse(urlh.geturl()) + qs = compat_urlparse.parse_qs(url.query) + mobj = re.match(self._VALID_URL, qs['file'][0]) + + video_id = mobj.group('id') rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS') @@ -98,7 +152,7 @@ class BlipTVIE(SubtitlesInfoExtractor): msg = self._download_webpage( url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url', video_id, 'Resolving URL for %s' % role) - real_url = compat_urlparse.parse_qs(msg)['message'][0] + real_url = compat_urlparse.parse_qs(msg.strip())['message'][0] media_type = media_content.get('type') if media_type == 'text/srt' or url.endswith('.srt'): @@ -113,11 +167,11 @@ class BlipTVIE(SubtitlesInfoExtractor): 'url': real_url, 'format_id': role, 'format_note': media_type, - 'vcodec': media_content.get(blip('vcodec')), + 'vcodec': media_content.get(blip('vcodec')) or 'none', 'acodec': media_content.get(blip('acodec')), 'filesize': media_content.get('filesize'), - 'width': int(media_content.get('width')), - 'height': int(media_content.get('height')), + 'width': int_or_none(media_content.get('width')), + 'height': int_or_none(media_content.get('height')), }) self._sort_formats(formats) @@ -150,9 +204,17 @@ class BlipTVIE(SubtitlesInfoExtractor): class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' + _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' _PAGE_SIZE = 12 IE_NAME = 'blip.tv:user' + _TEST = { + 'url': 'http://blip.tv/actone', + 'info_dict': { + 'id': 'actone', + 'title': 'Act One: The Series', + }, + 'playlist_count': 5, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -163,6 +225,7 @@ class BlipTVUserIE(InfoExtractor): page = self._download_webpage(url, username, 'Downloading user page') mobj = re.search(r'data-users-id="([^"]+)"', page) page_base = page_base % mobj.group(1) + title = self._og_search_title(page) # Download video ids using BlipTV Ajax calls. Result size per # query is limited (currently to 12 videos) so we need to query @@ -199,4 +262,5 @@ class BlipTVUserIE(InfoExtractor): urls = ['http://blip.tv/%s' % video_id for video_id in video_ids] url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] - return [self.playlist_result(url_entries, playlist_title=username)] + return self.playlist_result( + url_entries, playlist_title=title, playlist_id=username) diff --git a/youtube_dl/extractor/bpb.py b/youtube_dl/extractor/bpb.py new file mode 100644 index 000000000..510813f76 --- /dev/null +++ b/youtube_dl/extractor/bpb.py @@ -0,0 +1,37 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class BpbIE(InfoExtractor): + IE_DESC = 'Bundeszentrale für politische Bildung' + _VALID_URL = r'http://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/' + + _TEST = { + 'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr', + 'md5': '0792086e8e2bfbac9cdf27835d5f2093', + 'info_dict': { + 'id': '297', + 'ext': 'mp4', + 'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR', + 'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<h2 class="white">(.*?)</h2>', webpage, 'title') + video_url = self._html_search_regex( + r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)', + webpage, 'video URL') + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': self._og_search_description(webpage), + } diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 86f0c2861..45ba51732 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( ExtractorError, @@ -26,17 +24,8 @@ class BRIE(InfoExtractor): 'title': 'Wenn das Traditions-Theater wackelt', 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt', 'duration': 34, - } - }, - { - 'url': 'http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html', - 'md5': 'ab451b09d861dbed7d7cc9ab0be19ebe', - 'info_dict': { - 'id': '2c060e69-3a27-4e13-b0f0-668fac17d812', - 'ext': 'mp4', - 'title': 'Über den Pass', - 'description': 'Die Eroberung der Alpen: Über den Pass', - 'duration': 2588, + 'uploader': 'BR', + 'upload_date': '20140802', } }, { @@ -77,8 +66,7 @@ class BRIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') + display_id = self._match_id(url) page = self._download_webpage(url, display_id) xml_url = self._search_regex( r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL') diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 1bfc9f35b..4bcc897c9 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -4,37 +4,60 @@ import re import json from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_age_limit, +) class BreakIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)' - _TEST = { + _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)' + _TESTS = [{ 'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056', - 'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b', 'info_dict': { 'id': '2468056', 'ext': 'mp4', 'title': 'When Girls Act Like D-Bags', } - } + }, { + 'url': 'http://www.break.com/video/ugc/baby-flex-2773063', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1).split("-")[-1] - embed_url = 'http://www.break.com/embed/%s' % video_id - webpage = self._download_webpage(embed_url, video_id) - info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>', - webpage, 'info json', flags=re.DOTALL) - info = json.loads(info_json) - video_url = info['videoUri'] + video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://www.break.com/embed/%s' % video_id, video_id) + info = json.loads(self._search_regex( + r'var embedVars = ({.*})\s*?</script>', + webpage, 'info json', flags=re.DOTALL)) + youtube_id = info.get('youtubeId') if youtube_id: return self.url_result(youtube_id, 'Youtube') - final_url = video_url + '?' + info['AuthToken'] + formats = [{ + 'url': media['uri'] + '?' + info['AuthToken'], + 'tbr': media['bitRate'], + 'width': media['width'], + 'height': media['height'], + } for media in info['media']] + + if not formats: + formats.append({ + 'url': info['videoUri'] + }) + + self._sort_formats(formats) + + duration = int_or_none(info.get('videoLengthInSeconds')) + age_limit = parse_age_limit(info.get('audienceRating')) + return { 'id': video_id, - 'url': final_url, 'title': info['contentName'], 'thumbnail': info['thumbUri'], + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, } diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 419951b62..bf18a97e0 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -14,6 +14,7 @@ from ..utils import ( compat_str, compat_urllib_request, compat_parse_qs, + compat_urllib_parse_urlparse, determine_ext, ExtractorError, @@ -23,7 +24,7 @@ from ..utils import ( class BrightcoveIE(InfoExtractor): - _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)' + _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P<query>.*)' _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' _TESTS = [ @@ -87,6 +88,15 @@ class BrightcoveIE(InfoExtractor): 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals', }, }, + { + # playlist test + # from http://support.brightcove.com/en/video-cloud/docs/playlist-support-single-video-players + 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=3550052898001&playerKey=AQ%7E%7E%2CAAABmA9XpXk%7E%2C-Kp7jNgisre1fG5OdqpAFUTcs0lP_ZoL', + 'info_dict': { + 'title': 'Sealife', + }, + 'playlist_mincount': 7, + }, ] @classmethod @@ -101,6 +111,8 @@ class BrightcoveIE(InfoExtractor): lambda m: m.group(1) + '/>', object_str) # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608 object_str = object_str.replace('<--', '<!--') + # remove namespace to simplify extraction + object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str) object_str = fix_xml_ampersands(object_str) object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8')) @@ -154,12 +166,14 @@ class BrightcoveIE(InfoExtractor): def _extract_brightcove_urls(cls, webpage): """Return a list of all Brightcove URLs from the webpage """ - url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage) + url_m = re.search( + r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"', + webpage) if url_m: url = unescapeHTML(url_m.group(1)) # Some sites don't add it, we can't download with this url, for example: # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/ - if 'playerKey' in url: + if 'playerKey' in url or 'videoId' in url: return [url] matches = re.findall( @@ -188,9 +202,13 @@ class BrightcoveIE(InfoExtractor): referer = smuggled_data.get('Referer', url) return self._get_video_info( videoPlayer[0], query_str, query, referer=referer) - else: + elif 'playerKey' in query: player_key = query['playerKey'] return self._get_playlist_info(player_key[0]) + else: + raise ExtractorError( + 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', + expected=True) def _get_video_info(self, video_id, query_str, query, referer=None): request_url = self._FEDERATED_URL_TEMPLATE % query_str @@ -202,6 +220,13 @@ class BrightcoveIE(InfoExtractor): req.add_header('Referer', referer) webpage = self._download_webpage(req, video_id) + error_msg = self._html_search_regex( + r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage, + 'error message', default=None) + if error_msg is not None: + raise ExtractorError( + 'brightcove said: %s' % error_msg, expected=True) + self.report_extraction(video_id) info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json') info = json.loads(info)['data'] @@ -238,12 +263,21 @@ class BrightcoveIE(InfoExtractor): formats = [] for rend in renditions: url = rend['defaultURL'] + if not url: + continue + ext = None if rend['remote']: - # This type of renditions are served through akamaihd.net, - # but they don't use f4m manifests - url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB' - ext = 'flv' - else: + url_comp = compat_urllib_parse_urlparse(url) + if url_comp.path.endswith('.m3u8'): + formats.extend( + self._extract_m3u8_formats(url, info['id'], 'mp4')) + continue + elif 'akamaihd.net' in url_comp.netloc: + # This type of renditions are served through + # akamaihd.net, but they don't use f4m manifests + url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB' + ext = 'flv' + if ext is None: ext = determine_ext(url) size = rend.get('size') formats.append({ diff --git a/youtube_dl/extractor/buzzfeed.py b/youtube_dl/extractor/buzzfeed.py new file mode 100644 index 000000000..a40a1bbc4 --- /dev/null +++ b/youtube_dl/extractor/buzzfeed.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor + + +class BuzzFeedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)' + _TESTS = [{ + 'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia', + 'info_dict': { + 'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss', + 'title': 'This Angry Ram Destroys A Punching Bag Like A Boss', + 'description': 'Rambro!', + }, + 'playlist': [{ + 'info_dict': { + 'id': 'aVCR29aE_OQ', + 'ext': 'mp4', + 'upload_date': '20141024', + 'uploader_id': 'Buddhanz1', + 'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl', + 'uploader': 'Buddhanz', + 'title': 'Angry Ram destroys a punching bag', + } + }] + }, { + 'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia', + 'params': { + 'skip_download': True, # Got enough YouTube download tests + }, + 'info_dict': { + 'description': 'Munchkin the Teddy Bear is back !', + 'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill', + }, + 'playlist': [{ + 'info_dict': { + 'id': 'mVmBL8B-In0', + 'ext': 'mp4', + 'upload_date': '20141124', + 'uploader_id': 'CindysMunchkin', + 'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu', + 'uploader': 'Munchkin the Shih Tzu', + 'title': 'Munchkin the Teddy Bear gets her exercise', + }, + }] + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + all_buckets = re.findall( + r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'', + webpage) + + entries = [] + for bd_json in all_buckets: + bd = json.loads(bd_json) + video = bd.get('video') or bd.get('progload_video') + if not video: + continue + entries.append(self.url_result(video['url'])) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'entries': entries, + } diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index cf19b7b0c..6252be05b 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -10,12 +10,12 @@ from ..utils import ExtractorError class BYUtvIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)' _TEST = { - 'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking', + 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5', 'info_dict': { - 'id': 'granite-flats-talking', + 'id': 'studio-c-season-5-episode-5', 'ext': 'mp4', - 'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c', - 'title': 'Talking', + 'description': 'md5:5438d33774b6bdc662f9485a340401cc', + 'title': 'Season 5 Episode 5', 'thumbnail': 're:^https?://.*promo.*' }, 'params': { diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 0202078b0..9873728df 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -7,15 +7,21 @@ from .common import InfoExtractor from ..utils import ( unified_strdate, url_basename, + qualities, ) class CanalplusIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' - _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' - IE_NAME = 'canalplus.fr' + IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' + _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' + _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s' + _SITE_ID_MAP = { + 'canalplus.fr': 'cplus', + 'piwiplus.fr': 'teletoon', + 'd8.tv': 'd8', + } - _TEST = { + _TESTS = [{ 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470', 'md5': '3db39fb48b9685438ecf33a1078023e4', 'info_dict': { @@ -25,36 +31,73 @@ class CanalplusIE(InfoExtractor): 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013', 'upload_date': '20130826', }, - } + }, { + 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190', + 'info_dict': { + 'id': '1108190', + 'ext': 'flv', + 'title': 'Le labyrinthe - Boing super ranger', + 'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff', + 'upload_date': '20140724', + }, + 'skip': 'Only works from France', + }, { + 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html', + 'info_dict': { + 'id': '966289', + 'ext': 'flv', + 'title': 'Campagne intime - Documentaire exceptionnel', + 'description': 'md5:d2643b799fb190846ae09c61e59a859f', + 'upload_date': '20131108', + }, + 'skip': 'videos get deleted after a while', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.groupdict().get('id') + site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal'] + # Beware, some subclasses do not define an id group display_id = url_basename(mobj.group('path')) if video_id is None: webpage = self._download_webpage(url, display_id) - video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id') + video_id = self._search_regex( + r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id') - info_url = self._VIDEO_INFO_TEMPLATE % video_id + info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id) doc = self._download_xml(info_url, video_id, 'Downloading video XML') video_info = [video for video in doc if video.find('ID').text == video_id][0] media = video_info.find('MEDIA') infos = video_info.find('INFOS') - preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'] + preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']) - formats = [ - { - 'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text, - 'format_id': fmt.tag, - 'ext': 'mp4' if fmt.tag == 'HLS' else 'flv', - 'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1, - } for fmt in media.find('VIDEOS') if fmt.text - ] + formats = [] + for fmt in media.find('VIDEOS'): + format_url = fmt.text + if not format_url: + continue + format_id = fmt.tag + if format_id == 'HLS': + hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv') + for fmt in hls_formats: + fmt['preference'] = preference(format_id) + formats.extend(hls_formats) + elif format_id == 'HDS': + hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id) + for fmt in hds_formats: + fmt['preference'] = preference(format_id) + formats.extend(hds_formats) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'preference': preference(format_id), + }) self._sort_formats(formats) return { @@ -69,4 +112,4 @@ class CanalplusIE(InfoExtractor): 'like_count': int(infos.find('NB_LIKES').text), 'comment_count': int(infos.find('NB_COMMENTS').text), 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 822f9a7be..e43756ec6 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -25,7 +25,7 @@ class CBSIE(InfoExtractor): }, { 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/', 'info_dict': { - 'id': 'P9gjWjelt6iP', + 'id': 'WWF_5KqY3PK1', 'ext': 'flv', 'title': 'Live on Letterman - St. Vincent', 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.', @@ -45,4 +45,4 @@ class CBSIE(InfoExtractor): real_id = self._search_regex( r"video\.settings\.pid\s*=\s*'([^']+)';", webpage, 'real video ID') - return self.url_result(u'theplatform:%s' % real_id) + return self.url_result('theplatform:%s' % real_id) diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 0bce7937f..7e47960ab 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -84,4 +84,4 @@ class CBSNewsIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 90a3dddb9..97feb6704 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -92,7 +92,7 @@ class CeskaTelevizeIE(InfoExtractor): req.add_header('Referer', url) playlist = self._download_xml(req, video_id) - + formats = [] for i in playlist.find('smilRoot/body'): if 'AD' not in i.attrib['id']: diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index 4f000292b..3dfc24f5b 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ExtractorError + class Channel9IE(InfoExtractor): ''' Common extractor for channel9.msdn.com. @@ -27,11 +28,11 @@ class Channel9IE(InfoExtractor): 'title': 'Developer Kick-Off Session: Stuff We Love', 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f', 'duration': 4576, - 'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg', + 'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg', 'session_code': 'KOS002', 'session_day': 'Day 1', 'session_room': 'Arena 1A', - 'session_speakers': [ 'Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen' ], + 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'], }, }, { @@ -43,8 +44,8 @@ class Channel9IE(InfoExtractor): 'title': 'Self-service BI with Power BI - nuclear testing', 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', 'duration': 1540, - 'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg', - 'authors': [ 'Mike Wilmot' ], + 'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg', + 'authors': ['Mike Wilmot'], }, } ] @@ -83,7 +84,7 @@ class Channel9IE(InfoExtractor): 'format_id': x.group('quality'), 'format_note': x.group('note'), 'format': '%s (%s)' % (x.group('quality'), x.group('note')), - 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate + 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate 'preference': self._known_formats.index(x.group('quality')), 'vcodec': 'none' if x.group('note') == 'Audio only' else None, } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats] @@ -94,7 +95,7 @@ class Channel9IE(InfoExtractor): def _extract_title(self, html): title = self._html_search_meta('title', html, 'title') - if title is None: + if title is None: title = self._og_search_title(html) TITLE_SUFFIX = ' (Channel 9)' if title is not None and title.endswith(TITLE_SUFFIX): @@ -115,7 +116,7 @@ class Channel9IE(InfoExtractor): return self._html_search_meta('description', html, 'description') def _extract_duration(self, html): - m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html) + m = re.search(r'"length": *"(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html) return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None def _extract_slides(self, html): @@ -167,7 +168,7 @@ class Channel9IE(InfoExtractor): return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html) def _extract_content(self, html, content_path): - # Look for downloadable content + # Look for downloadable content formats = self._formats_from_html(html) slides = self._extract_slides(html) zip_ = self._extract_zip(html) @@ -187,32 +188,33 @@ class Channel9IE(InfoExtractor): view_count = self._extract_view_count(html) comment_count = self._extract_comment_count(html) - common = {'_type': 'video', - 'id': content_path, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'avg_rating': avg_rating, - 'rating_count': rating_count, - 'view_count': view_count, - 'comment_count': comment_count, - } + common = { + '_type': 'video', + 'id': content_path, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'avg_rating': avg_rating, + 'rating_count': rating_count, + 'view_count': view_count, + 'comment_count': comment_count, + } result = [] if slides is not None: d = common.copy() - d.update({ 'title': title + '-Slides', 'url': slides }) + d.update({'title': title + '-Slides', 'url': slides}) result.append(d) if zip_ is not None: d = common.copy() - d.update({ 'title': title + '-Zip', 'url': zip_ }) + d.update({'title': title + '-Zip', 'url': zip_}) result.append(d) if len(formats) > 0: d = common.copy() - d.update({ 'title': title, 'formats': formats }) + d.update({'title': title, 'formats': formats}) result.append(d) return result @@ -234,16 +236,17 @@ class Channel9IE(InfoExtractor): if contents is None: return contents - session_meta = {'session_code': self._extract_session_code(html), - 'session_day': self._extract_session_day(html), - 'session_room': self._extract_session_room(html), - 'session_speakers': self._extract_session_speakers(html), - } + session_meta = { + 'session_code': self._extract_session_code(html), + 'session_day': self._extract_session_day(html), + 'session_room': self._extract_session_room(html), + 'session_speakers': self._extract_session_speakers(html), + } for content in contents: content.update(session_meta) - return contents + return self.playlist_result(contents) def _extract_list(self, content_path): rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS') @@ -258,16 +261,17 @@ class Channel9IE(InfoExtractor): webpage = self._download_webpage(url, content_path, 'Downloading web page') - page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage) - if page_type_m is None: - raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True) - - page_type = page_type_m.group('pagetype') - if page_type == 'List': # List page, may contain list of 'item'-like objects + page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage) + if page_type_m is not None: + page_type = page_type_m.group('pagetype') + if page_type == 'Entry': # Any 'item'-like page, may contain downloadable content + return self._extract_entry_item(webpage, content_path) + elif page_type == 'Session': # Event session page, may contain downloadable content + return self._extract_session(webpage, content_path) + elif page_type == 'Event': + return self._extract_list(content_path) + else: + raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True) + + else: # Assuming list return self._extract_list(content_path) - elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content - return self._extract_entry_item(webpage, content_path) - elif page_type == 'Session': # Event session page, may contain downloadable content - return self._extract_session(webpage, content_path) - else: - raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)
\ No newline at end of file diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py index a62395d4b..c922f6959 100644 --- a/youtube_dl/extractor/chilloutzone.py +++ b/youtube_dl/extractor/chilloutzone.py @@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor): 'id': '85523671', 'ext': 'mp4', 'title': 'The Sunday Times - Icons', - 'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84', + 'description': 're:(?s)^Watch the making of - makingoficons.com.{300,}', 'uploader': 'Us', 'uploader_id': 'usfilms', 'upload_date': '20140131' diff --git a/youtube_dl/extractor/cinchcast.py b/youtube_dl/extractor/cinchcast.py new file mode 100644 index 000000000..0c9a24bef --- /dev/null +++ b/youtube_dl/extractor/cinchcast.py @@ -0,0 +1,52 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + xpath_text, +) + + +class CinchcastIE(InfoExtractor): + _VALID_URL = r'https?://player\.cinchcast\.com/.*?assetId=(?P<id>[0-9]+)' + _TEST = { + # Actual test is run in generic, look for undergroundwellness + 'url': 'http://player.cinchcast.com/?platformId=1&assetType=single&assetId=7141703', + 'only_matching': True, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + doc = self._download_xml( + 'http://www.blogtalkradio.com/playerasset/mrss?assetType=single&assetId=%s' % video_id, + video_id) + + item = doc.find('.//item') + title = xpath_text(item, './title', fatal=True) + date_str = xpath_text( + item, './{http://developer.longtailvideo.com/trac/}date') + upload_date = unified_strdate(date_str, day_first=False) + # duration is present but wrong + formats = [] + formats.append({ + 'format_id': 'main', + 'url': item.find( + './{http://search.yahoo.com/mrss/}content').attrib['url'], + }) + backup_url = xpath_text( + item, './{http://developer.longtailvideo.com/trac/}backupContent') + if backup_url: + formats.append({ + 'preference': 2, # seems to be more reliable + 'format_id': 'backup', + 'url': backup_url, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'upload_date': upload_date, + 'formats': formats, + } diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py deleted file mode 100644 index 496271be4..000000000 --- a/youtube_dl/extractor/cinemassacre.py +++ /dev/null @@ -1,100 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - int_or_none, -) - - -class CinemassacreIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': '19911', - 'ext': 'mp4', - 'upload_date': '20121110', - 'title': '“Angry Video Game Nerd: The Movie” – Trailer', - 'description': 'md5:fb87405fcb42a331742a0dce2708560b', - }, - }, - { - 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'md5': 'd72f10cd39eac4215048f62ab477a511', - 'info_dict': { - 'id': '521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - } - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - - webpage = self._download_webpage(url, display_id) - video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') - mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage) - if not mobj: - raise ExtractorError('Can\'t extract embed url and video id') - playerdata_url = mobj.group('embed_url') - video_id = mobj.group('video_id') - - video_title = self._html_search_regex( - r'<title>(?P<title>.+?)\|', webpage, 'title') - video_description = self._html_search_regex( - r'<div class="entry-content">(?P<description>.+?)</div>', - webpage, 'description', flags=re.DOTALL, fatal=False) - - playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') - video_thumbnail = self._search_regex( - r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) - sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') - videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url') - - videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') - - formats = [] - baseurl = sd_url[:sd_url.rfind('/')+1] - for video in videolist.findall('.//video'): - src = video.get('src') - if not src: - continue - file_ = src.partition(':')[-1] - width = int_or_none(video.get('width')) - height = int_or_none(video.get('height')) - bitrate = int_or_none(video.get('system-bitrate')) - format = { - 'url': baseurl + file_, - 'format_id': src.rpartition('.')[0].rpartition('_')[-1], - } - if width or height: - format.update({ - 'tbr': bitrate // 1000 if bitrate else None, - 'width': width, - 'height': height, - }) - else: - format.update({ - 'abr': bitrate // 1000 if bitrate else None, - 'vcodec': 'none', - }) - formats.append(format) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': video_title, - 'formats': formats, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - } diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 669919a2c..a5c3cb7c6 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -24,7 +24,7 @@ class ClipfishIE(InfoExtractor): 'title': 'FIFA 14 - E3 2013 Trailer', 'duration': 82, }, - u'skip': 'Blocked in the US' + 'skip': 'Blocked in the US' } def _real_extract(self, url): @@ -34,7 +34,7 @@ class ClipfishIE(InfoExtractor): info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' % (video_id, int(time.time()))) doc = self._download_xml( - info_url, video_id, note=u'Downloading info page') + info_url, video_id, note='Downloading info page') title = doc.find('title').text video_url = doc.find('filename').text if video_url is None: diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 58846e8e7..2edab90a3 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,11 +1,12 @@ from __future__ import unicode_literals +import json import re from .common import InfoExtractor -translation_table = { +_translation_table = { 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', 'y': 'l', 'z': 'i', @@ -13,6 +14,10 @@ translation_table = { } +def _decode(s): + return ''.join(_translation_table.get(c, c) for c in s) + + class CliphunterIE(InfoExtractor): IE_NAME = 'cliphunter' @@ -22,35 +27,66 @@ class CliphunterIE(InfoExtractor): ''' _TEST = { 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', - 'file': '1012420.flv', - 'md5': '15e7740f30428abf70f4223478dc1225', + 'md5': 'a2ba71eebf523859fe527a61018f723e', 'info_dict': { + 'id': '1012420', + 'ext': 'mp4', 'title': 'Fun Jynx Maze solo', + 'thumbnail': 're:^https?://.*\.jpg$', + 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + video_title = self._search_regex( + r'mediaTitle = "([^"]+)"', webpage, 'title') + pl_fiji = self._search_regex( r'pl_fiji = \'([^\']+)\'', webpage, 'video data') pl_c_qual = self._search_regex( r'pl_c_qual = "(.)"', webpage, 'video quality') - video_title = self._search_regex( - r'mediaTitle = "([^"]+)"', webpage, 'title') - - video_url = ''.join(translation_table.get(c, c) for c in pl_fiji) - + video_url = _decode(pl_fiji) formats = [{ 'url': video_url, - 'format_id': pl_c_qual, + 'format_id': 'default-%s' % pl_c_qual, }] + qualities_json = self._search_regex( + r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info') + qualities_data = json.loads(qualities_json) + + for i, t in enumerate( + re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)): + quality_id, crypted_url = t + video_url = _decode(crypted_url) + f = { + 'format_id': quality_id, + 'url': video_url, + 'quality': i, + } + if quality_id in qualities_data: + qd = qualities_data[quality_id] + m = re.match( + r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b> + \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd) + if m: + f['width'] = int(m.group('width')) + f['height'] = int(m.group('height')) + f['tbr'] = int(m.group('tbr')) + formats.append(f) + self._sort_formats(formats) + + thumbnail = self._search_regex( + r"var\s+mov_thumb\s*=\s*'([^']+)';", + webpage, 'thumbnail', fatal=False) + return { 'id': video_id, 'title': video_title, 'formats': formats, + 'age_limit': self._rta_search(webpage), + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/clipsyndicate.py b/youtube_dl/extractor/clipsyndicate.py index 02a1667fa..d07d544ea 100644 --- a/youtube_dl/extractor/clipsyndicate.py +++ b/youtube_dl/extractor/clipsyndicate.py @@ -39,6 +39,7 @@ class ClipsyndicateIE(InfoExtractor): transform_source=fix_xml_ampersands) track_doc = pdoc.find('trackList/track') + def find_param(name): node = find_xpath_attr(track_doc, './/param', 'name', name) if node is not None: diff --git a/youtube_dl/extractor/cloudy.py b/youtube_dl/extractor/cloudy.py new file mode 100644 index 000000000..abf8cc280 --- /dev/null +++ b/youtube_dl/extractor/cloudy.py @@ -0,0 +1,110 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse, + compat_HTTPError, +) +from ..utils import ( + ExtractorError, + HEADRequest, + remove_end, +) + + +class CloudyIE(InfoExtractor): + _IE_DESC = 'cloudy.ec and videoraj.ch' + _VALID_URL = r'''(?x) + https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/ + (?:v/|embed\.php\?id=) + (?P<id>[A-Za-z0-9]+) + ''' + _EMBED_URL = 'http://www.%s/embed.php?id=%s' + _API_URL = 'http://www.%s/api/player.api.php?%s' + _MAX_TRIES = 2 + _TESTS = [ + { + 'url': 'https://www.cloudy.ec/v/af511e2527aac', + 'md5': '5cb253ace826a42f35b4740539bedf07', + 'info_dict': { + 'id': 'af511e2527aac', + 'ext': 'flv', + 'title': 'Funny Cats and Animals Compilation june 2013', + } + }, + { + 'url': 'http://www.videoraj.ch/v/47f399fd8bb60', + 'md5': '7d0f8799d91efd4eda26587421c3c3b0', + 'info_dict': { + 'id': '47f399fd8bb60', + 'ext': 'flv', + 'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?', + } + } + ] + + def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0): + + if try_num > self._MAX_TRIES - 1: + raise ExtractorError('Unable to extract video URL', expected=True) + + form = { + 'file': video_id, + 'key': file_key, + } + + if error_url: + form.update({ + 'numOfErrors': try_num, + 'errorCode': '404', + 'errorUrl': error_url, + }) + + data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form)) + player_data = self._download_webpage( + data_url, video_id, 'Downloading player data') + data = compat_parse_qs(player_data) + + try_num += 1 + + if 'error' in data: + raise ExtractorError( + '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])), + expected=True) + + title = data.get('title', [None])[0] + if title: + title = remove_end(title, '&asdasdas').strip() + + video_url = data.get('url', [None])[0] + + if video_url: + try: + self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL') + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]: + self.report_warning('Invalid video URL, requesting another', video_id) + return self._extract_video(video_host, video_id, file_key, video_url, try_num) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_host = mobj.group('host') + video_id = mobj.group('id') + + url = self._EMBED_URL % (video_host, video_id) + webpage = self._download_webpage(url, video_id) + + file_key = self._search_regex( + r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key') + + return self._extract_video(video_host, video_id, file_key) diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 710d5009b..3145b3051 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -2,12 +2,10 @@ from __future__ import unicode_literals import json -import re from .common import InfoExtractor from ..utils import ( ExtractorError, - int_or_none, ) @@ -15,23 +13,24 @@ class CNETIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' _TEST = { 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', - 'md5': '041233212a0d06b179c87cbcca1577b8', 'info_dict': { 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Hands-on with Microsoft Windows 8.1 Update', 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', 'thumbnail': 're:^http://.*/flmswindows8.jpg$', - 'uploader_id': 'sarah.mitroff@cbsinteractive.com', + 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861', 'uploader': 'Sarah Mitroff', + }, + 'params': { + 'skip_download': 'requires rtmpdump', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - + display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) + data_json = self._html_search_regex( r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'", webpage, 'data json') @@ -42,37 +41,31 @@ class CNETIE(InfoExtractor): if not vdata: raise ExtractorError('Cannot find video data') + mpx_account = data['config']['players']['default']['mpx_account'] + vid = vdata['files']['rtmp'] + tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid) + video_id = vdata['id'] title = vdata.get('headline') if title is None: title = vdata.get('title') if title is None: raise ExtractorError('Cannot find title!') - description = vdata.get('dek') thumbnail = vdata.get('image', {}).get('path') author = vdata.get('author') if author: uploader = '%s %s' % (author['firstName'], author['lastName']) - uploader_id = author.get('email') + uploader_id = author.get('id') else: uploader = None uploader_id = None - formats = [{ - 'format_id': '%s-%s-%s' % ( - f['type'], f['format'], - int_or_none(f.get('bitrate'), 1000, default='')), - 'url': f['uri'], - 'tbr': int_or_none(f.get('bitrate'), 1000), - } for f in vdata['files']['data']] - self._sort_formats(formats) - return { + '_type': 'url_transparent', + 'url': tp_link, 'id': video_id, 'display_id': display_id, 'title': title, - 'formats': formats, - 'description': description, 'uploader': uploader, 'uploader_id': uploader_id, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index dae40c136..81142ee41 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -12,24 +12,25 @@ from ..utils import ( class CNNIE(InfoExtractor): _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/ - (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' + (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))''' _TESTS = [{ 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', - 'file': 'sports_2013_06_09_nadal-1-on-1.cnn.mp4', 'md5': '3e6121ea48df7e2259fe73a0628605c4', 'info_dict': { + 'id': 'sports_2013_06_09_nadal-1-on-1.cnn', + 'ext': 'mp4', 'title': 'Nadal wins 8th French Open title', 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', 'duration': 135, 'upload_date': '20130609', }, - }, - { + }, { "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", - "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", "md5": "b5cc60c60a3477d185af8f19a2a26f4e", "info_dict": { + 'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology', + 'ext': 'mp4', "title": "Student's epic speech stuns new freshmen", "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", "upload_date": "20130821", diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py index 6f866e7fc..002b24037 100644 --- a/youtube_dl/extractor/collegehumor.py +++ b/youtube_dl/extractor/collegehumor.py @@ -10,47 +10,46 @@ from ..utils import int_or_none class CollegeHumorIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$' - _TESTS = [{ - 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', - 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd', - 'info_dict': { - 'id': '6902724', - 'ext': 'mp4', - 'title': 'Comic-Con Cosplay Catastrophe', - 'description': "Fans get creative this year at San Diego. Too creative. And yes, that's really Joss Whedon.", - 'age_limit': 13, - 'duration': 187, + _TESTS = [ + { + 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', + 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd', + 'info_dict': { + 'id': '6902724', + 'ext': 'mp4', + 'title': 'Comic-Con Cosplay Catastrophe', + 'description': "Fans get creative this year at San Diego. Too creative. And yes, that's really Joss Whedon.", + 'age_limit': 13, + 'duration': 187, + }, + }, { + 'url': 'http://www.collegehumor.com/video/3505939/font-conference', + 'md5': '72fa701d8ef38664a4dbb9e2ab721816', + 'info_dict': { + 'id': '3505939', + 'ext': 'mp4', + 'title': 'Font Conference', + 'description': "This video wasn't long enough, so we made it double-spaced.", + 'age_limit': 10, + 'duration': 179, + }, + }, { + # embedded youtube video + 'url': 'http://www.collegehumor.com/embed/6950306', + 'info_dict': { + 'id': 'Z-bao9fg6Yc', + 'ext': 'mp4', + 'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!', + 'uploader': 'Mark Dice', + 'uploader_id': 'MarkDice', + 'description': 'md5:62c3dab9351fac7bb44b53b69511d87f', + 'upload_date': '20140127', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Youtube'], }, - }, - { - 'url': 'http://www.collegehumor.com/video/3505939/font-conference', - 'md5': '72fa701d8ef38664a4dbb9e2ab721816', - 'info_dict': { - 'id': '3505939', - 'ext': 'mp4', - 'title': 'Font Conference', - 'description': "This video wasn't long enough, so we made it double-spaced.", - 'age_limit': 10, - 'duration': 179, - }, - }, - # embedded youtube video - { - 'url': 'http://www.collegehumor.com/embed/6950306', - 'info_dict': { - 'id': 'Z-bao9fg6Yc', - 'ext': 'mp4', - 'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!', - 'uploader': 'Mark Dice', - 'uploader_id': 'MarkDice', - 'description': 'md5:62c3dab9351fac7bb44b53b69511d87f', - 'upload_date': '20140127', - }, - 'params': { - 'skip_download': True, - }, - 'add_ie': ['Youtube'], - }, ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index c81ce5a96..2e3ef3fda 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor from .mtv import MTVServicesInfoExtractor from ..utils import ( compat_str, @@ -31,7 +30,7 @@ class ComedyCentralIE(MTVServicesInfoExtractor): } -class ComedyCentralShowsIE(InfoExtractor): +class ComedyCentralShowsIE(MTVServicesInfoExtractor): IE_DESC = 'The Daily Show / The Colbert Report' # urls can be abbreviations like :thedailyshow or :colbert # urls for episodes like: @@ -43,14 +42,14 @@ class ComedyCentralShowsIE(InfoExtractor): (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| (?P<clip> - (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+)) + (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+)) |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) )| (?P<interview> extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) (?:[?#].*|$)''' - _TEST = { + _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', 'info_dict': { @@ -61,7 +60,34 @@ class ComedyCentralShowsIE(InfoExtractor): 'uploader': 'thedailyshow', 'title': 'thedailyshow kristen-stewart part 1', } - } + }, { + 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel', + 'only_matching': True, + }] _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] @@ -82,18 +108,8 @@ class ComedyCentralShowsIE(InfoExtractor): '400': (384, 216), } - @staticmethod - def _transform_rtmp_url(rtmp_video_url): - m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url) - if not m: - raise ExtractorError('Cannot transform RTMP url') - base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' - return base + m.group('finalid') - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) + mobj = re.match(self._VALID_URL, url) if mobj.group('shortname'): if mobj.group('shortname') in ('tds', 'thedailyshow'): diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 342bfb8b3..d302fe45f 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,4 +1,7 @@ +from __future__ import unicode_literals + import base64 +import datetime import hashlib import json import netrc @@ -9,15 +12,19 @@ import sys import time import xml.etree.ElementTree -from ..utils import ( +from ..compat import ( + compat_cookiejar, compat_http_client, compat_urllib_error, compat_urllib_parse_urlparse, + compat_urlparse, compat_str, - +) +from ..utils import ( clean_html, compiled_regex_type, ExtractorError, + float_or_none, int_or_none, RegexNotFoundError, sanitize_filename, @@ -37,7 +44,11 @@ class InfoExtractor(object): information possibly downloading the video to the file system, among other possible outcomes. - The dictionaries must include the following fields: + The type field determines the the type of the result. + By far the most common value (and the default if _type is missing) is + "video", which indicates a single video. + + For a video, the dictionaries must include the following fields: id: Video identifier. title: Video title, unescaped. @@ -67,6 +78,7 @@ class InfoExtractor(object): * acodec Name of the audio codec in use * asr Audio sampling rate in Hertz * vbr Average video bitrate in KBit/s + * fps Frame rate * vcodec Name of the video codec in use * container Name of the container format * filesize The number of bytes, if known in advance @@ -80,10 +92,25 @@ class InfoExtractor(object): by this field, regardless of all other values. -1 for default (order by other properties), -2 or smaller for less than default. + * language_preference Is this in the correct requested + language? + 10 if it's what the URL is about, + -1 for default (don't know), + -10 otherwise, other values reserved for now. * quality Order number of the video quality of this format, irrespective of the file format. -1 for default (order by other properties), -2 or smaller for less than default. + * source_preference Order number for this video source + (quality takes higher priority) + -1 for default (order by other properties), + -2 or smaller for less than default. + * http_referer HTTP Referer header value to set. + * http_method HTTP method to use for the download. + * http_headers A dictionary of additional HTTP headers + to add to the request. + * http_post_data Additional data to send with a POST + request. url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) @@ -91,6 +118,7 @@ class InfoExtractor(object): The following fields are optional: + alt_title: A secondary title of the video. display_id An alternative identifier for the video, not necessarily unique, but available before title. Typically, id is something like "4234987", title "Dancing naked mole rats", @@ -102,13 +130,13 @@ class InfoExtractor(object): * "resolution" (optional, string "{width}x{height"}, deprecated) thumbnail: Full URL to a video thumbnail image. - description: One-line video description. + description: Full video description. uploader: Full name of the video uploader. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. - location: Physical location of the video. + location: Physical location where the video was filmed. subtitles: The subtitle file contents as a dictionary in the format {language: subtitles}. duration: Length of the video in seconds, as an integer. @@ -122,9 +150,46 @@ class InfoExtractor(object): by YoutubeDL if it's missing) categories: A list of categories that the video falls in, for example ["Sports", "Berlin"] + is_live: True, False, or None (=unknown). Whether this video is a + live stream that goes on instead of a fixed-length video. Unless mentioned otherwise, the fields should be Unicode strings. + Unless mentioned otherwise, None is equivalent to absence of information. + + + _type "playlist" indicates multiple videos. + There must be a key "entries", which is a list, an iterable, or a PagedList + object, each element of which is a valid dictionary by this specification. + + Additionally, playlists can have "title" and "id" attributes with the same + semantics as videos (see above). + + + _type "multi_video" indicates that there are multiple videos that + form a single show, for examples multiple acts of an opera or TV episode. + It must have an entries key like a playlist and contain all the keys + required for a video at the same time. + + + _type "url" indicates that the video must be extracted from another + location, possibly by a different extractor. Its only required key is: + "url" - the next URL to extract. + The key "ie_key" can be set to the class name (minus the trailing "IE", + e.g. "Youtube") if the extractor class is known in advance. + Additionally, the dictionary may have any properties of the resolved entity + known in advance, for example "title" if the title of the referred video is + known ahead of time. + + + _type "url_transparent" entities have the same specification as "url", but + indicate that the given additional information is more precise than the one + associated with the resolved URL. + This is useful when a site employs a video service that hosts the video and + its technical metadata, but that video service does not embed a useful + title, description etc. + + Subclasses of this one should re-define the _real_initialize() and _real_extract() methods and define a _VALID_URL regexp. Probably, they should also be added to the list of extractors. @@ -154,6 +219,14 @@ class InfoExtractor(object): return cls._VALID_URL_RE.match(url) is not None @classmethod + def _match_id(cls, url): + if '_VALID_URL_RE' not in cls.__dict__: + cls._VALID_URL_RE = re.compile(cls._VALID_URL) + m = cls._VALID_URL_RE.match(url) + assert m + return m.group('id') + + @classmethod def working(cls): """Getter method for _WORKING.""" return cls._WORKING @@ -196,17 +269,17 @@ class InfoExtractor(object): self.report_download_webpage(video_id) elif note is not False: if video_id is None: - self.to_screen(u'%s' % (note,)) + self.to_screen('%s' % (note,)) else: - self.to_screen(u'%s: %s' % (video_id, note)) + self.to_screen('%s: %s' % (video_id, note)) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if errnote is False: return False if errnote is None: - errnote = u'Unable to download webpage' - errmsg = u'%s: %s' % (errnote, compat_str(err)) + errnote = 'Unable to download webpage' + errmsg = '%s: %s' % (errnote, compat_str(err)) if fatal: raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) else: @@ -215,7 +288,6 @@ class InfoExtractor(object): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns a tuple (page content as string, URL handle) """ - # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] @@ -224,8 +296,14 @@ class InfoExtractor(object): if urlh is False: assert not fatal return False + content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal) + return (content, urlh) + + def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None): content_type = urlh.headers.get('Content-Type', '') webpage_bytes = urlh.read() + if prefix is not None: + webpage_bytes = prefix + webpage_bytes m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) if m: encoding = m.group(1) @@ -243,7 +321,7 @@ class InfoExtractor(object): url = url_or_request.get_full_url() except AttributeError: url = url_or_request - self.to_screen(u'Dumping request to ' + url) + self.to_screen('Dumping request to ' + url) dump = base64.b64encode(webpage_bytes).decode('ascii') self._downloader.to_screen(dump) if self._downloader.params.get('write_pages', False): @@ -253,11 +331,17 @@ class InfoExtractor(object): url = url_or_request basen = '%s_%s' % (video_id, url) if len(basen) > 240: - h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest() + h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest() basen = basen[:240 - len(h)] + h raw_filename = basen + '.dump' filename = sanitize_filename(raw_filename, restricted=True) - self.to_screen(u'Saving request to ' + filename) + self.to_screen('Saving request to ' + filename) + # Working around MAX_PATH limitation on Windows (see + # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx) + if os.name == 'nt': + absfilepath = os.path.abspath(filename) + if len(absfilepath) > 259: + filename = '\\\\?\\' + absfilepath with open(filename, 'wb') as outf: outf.write(webpage_bytes) @@ -266,17 +350,17 @@ class InfoExtractor(object): except LookupError: content = webpage_bytes.decode('utf-8', 'replace') - if (u'<title>Access to this site is blocked</title>' in content and - u'Websense' in content[:512]): - msg = u'Access to this webpage has been blocked by Websense filtering software in your network.' + if ('<title>Access to this site is blocked</title>' in content and + 'Websense' in content[:512]): + msg = 'Access to this webpage has been blocked by Websense filtering software in your network.' blocked_iframe = self._html_search_regex( r'<iframe src="([^"]+)"', content, - u'Websense information URL', default=None) + 'Websense information URL', default=None) if blocked_iframe: - msg += u' Visit %s for more details' % blocked_iframe + msg += ' Visit %s for more details' % blocked_iframe raise ExtractorError(msg, expected=True) - return (content, urlh) + return content def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the data of the page as a string """ @@ -288,7 +372,7 @@ class InfoExtractor(object): return content def _download_xml(self, url_or_request, video_id, - note=u'Downloading XML', errnote=u'Unable to download XML', + note='Downloading XML', errnote='Unable to download XML', transform_source=None, fatal=True): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( @@ -300,59 +384,68 @@ class InfoExtractor(object): return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) def _download_json(self, url_or_request, video_id, - note=u'Downloading JSON metadata', - errnote=u'Unable to download JSON metadata', + note='Downloading JSON metadata', + errnote='Unable to download JSON metadata', transform_source=None, fatal=True): json_string = self._download_webpage( url_or_request, video_id, note, errnote, fatal=fatal) if (not fatal) and json_string is False: return None + return self._parse_json( + json_string, video_id, transform_source=transform_source, fatal=fatal) + + def _parse_json(self, json_string, video_id, transform_source=None, fatal=True): if transform_source: json_string = transform_source(json_string) try: return json.loads(json_string) except ValueError as ve: - raise ExtractorError('Failed to download JSON', cause=ve) + errmsg = '%s: Failed to parse JSON ' % video_id + if fatal: + raise ExtractorError(errmsg, cause=ve) + else: + self.report_warning(errmsg + str(ve)) def report_warning(self, msg, video_id=None): - idstr = u'' if video_id is None else u'%s: ' % video_id + idstr = '' if video_id is None else '%s: ' % video_id self._downloader.report_warning( - u'[%s] %s%s' % (self.IE_NAME, idstr, msg)) + '[%s] %s%s' % (self.IE_NAME, idstr, msg)) def to_screen(self, msg): """Print msg to screen, prefixing it with '[ie_name]'""" - self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) + self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg)) def report_extraction(self, id_or_name): """Report information extraction.""" - self.to_screen(u'%s: Extracting information' % id_or_name) + self.to_screen('%s: Extracting information' % id_or_name) def report_download_webpage(self, video_id): """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) + self.to_screen('%s: Downloading webpage' % video_id) def report_age_confirmation(self): """Report attempt to confirm age.""" - self.to_screen(u'Confirming age') + self.to_screen('Confirming age') def report_login(self): """Report attempt to log in.""" - self.to_screen(u'Logging in') + self.to_screen('Logging in') - #Methods for following #608 + # Methods for following #608 @staticmethod def url_result(url, ie=None, video_id=None): """Returns a url that points to a page that should be processed""" - #TODO: ie should be the class used for getting the info + # TODO: ie should be the class used for getting the info video_info = {'_type': 'url', 'url': url, 'ie_key': ie} if video_id is not None: video_info['id'] = video_id return video_info + @staticmethod - def playlist_result(entries, playlist_id=None, playlist_title=None): + def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None): """Returns a playlist""" video_info = {'_type': 'playlist', 'entries': entries} @@ -360,9 +453,11 @@ class InfoExtractor(object): video_info['id'] = playlist_id if playlist_title: video_info['title'] = playlist_title + if playlist_description: + video_info['description'] = playlist_description return video_info - def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0): + def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): """ Perform a regex search on the given string, using a single or a list of patterns returning the first matching group. @@ -378,27 +473,30 @@ class InfoExtractor(object): break if os.name != 'nt' and sys.stderr.isatty(): - _name = u'\033[0;34m%s\033[0m' % name + _name = '\033[0;34m%s\033[0m' % name else: _name = name if mobj: - # return the first matching group - return next(g for g in mobj.groups() if g is not None) + if group is None: + # return the first matching group + return next(g for g in mobj.groups() if g is not None) + else: + return mobj.group(group) elif default is not _NO_DEFAULT: return default elif fatal: - raise RegexNotFoundError(u'Unable to extract %s' % _name) + raise RegexNotFoundError('Unable to extract %s' % _name) else: - self._downloader.report_warning(u'unable to extract %s; ' - u'please report this issue on http://yt-dl.org/bug' % _name) + self._downloader.report_warning('unable to extract %s; ' + 'please report this issue on http://yt-dl.org/bug' % _name) return None - def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0): + def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): """ Like _search_regex, but strips HTML tags and unescapes entities. """ - res = self._search_regex(pattern, string, name, default, fatal, flags) + res = self._search_regex(pattern, string, name, default, fatal, flags, group) if res: return clean_html(res).strip() else: @@ -430,10 +528,26 @@ class InfoExtractor(object): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) - + self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) + return (username, password) + def _get_tfa_info(self): + """ + Get the two-factor authentication info + TODO - asking the user will be required for sms/phone verify + currently just uses the command line option + If there's no info available, return None + """ + if self._downloader is None: + return None + downloader_params = self._downloader.params + + if downloader_params.get('twofactor', None) is not None: + return downloader_params['twofactor'] + + return None + # Helper functions for extracting OpenGraph info @staticmethod def _og_regexes(prop): @@ -454,7 +568,7 @@ class InfoExtractor(object): return unescapeHTML(escaped) def _og_search_thumbnail(self, html, **kargs): - return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs) + return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs) def _og_search_description(self, html, **kargs): return self._og_search_property('description', html, fatal=False, **kargs) @@ -463,8 +577,9 @@ class InfoExtractor(object): return self._og_search_property('title', html, **kargs) def _og_search_video_url(self, html, name='video url', secure=True, **kargs): - regexes = self._og_regexes('video') - if secure: regexes = self._og_regexes('video:secure_url') + regexes + regexes = self._og_regexes('video') + self._og_regexes('video:url') + if secure: + regexes = self._og_regexes('video:secure_url') + regexes return self._html_search_regex(regexes, html, name, **kargs) def _og_search_url(self, html, **kargs): @@ -475,9 +590,9 @@ class InfoExtractor(object): display_name = name return self._html_search_regex( r'''(?ix)<meta - (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?) - [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), - html, display_name, fatal=fatal, **kwargs) + (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1) + [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name), + html, display_name, fatal=fatal, group='content', **kwargs) def _dc_search_uploader(self, html): return self._html_search_meta('dc.creator', html, 'uploader') @@ -508,11 +623,11 @@ class InfoExtractor(object): def _twitter_search_player(self, html): return self._html_search_meta('twitter:player', html, - 'twitter card player') + 'twitter card player') def _sort_formats(self, formats): if not formats: - raise ExtractorError(u'No video formats found') + raise ExtractorError('No video formats found') def _formats_key(f): # TODO remove the following workaround @@ -532,9 +647,9 @@ class InfoExtractor(object): if f.get('vcodec') == 'none': # audio only if self._downloader.params.get('prefer_free_formats'): - ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus'] + ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus'] else: - ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a'] + ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a'] ext_preference = 0 try: audio_ext_preference = ORDER.index(f['ext']) @@ -542,9 +657,9 @@ class InfoExtractor(object): audio_ext_preference = -1 else: if self._downloader.params.get('prefer_free_formats'): - ORDER = [u'flv', u'mp4', u'webm'] + ORDER = ['flv', 'mp4', 'webm'] else: - ORDER = [u'webm', u'flv', u'mp4'] + ORDER = ['webm', 'flv', 'mp4'] try: ext_preference = ORDER.index(f['ext']) except ValueError: @@ -553,6 +668,7 @@ class InfoExtractor(object): return ( preference, + f.get('language_preference') if f.get('language_preference') is not None else -1, f.get('quality') if f.get('quality') is not None else -1, f.get('height') if f.get('height') is not None else -1, f.get('width') if f.get('width') is not None else -1, @@ -561,14 +677,16 @@ class InfoExtractor(object): f.get('vbr') if f.get('vbr') is not None else -1, f.get('abr') if f.get('abr') is not None else -1, audio_ext_preference, + f.get('fps') if f.get('fps') is not None else -1, f.get('filesize') if f.get('filesize') is not None else -1, f.get('filesize_approx') if f.get('filesize_approx') is not None else -1, + f.get('source_preference') if f.get('source_preference') is not None else -1, f.get('format_id'), ) formats.sort(key=_formats_key) def http_scheme(self): - """ Either "https:" or "https:", depending on the user's preferences """ + """ Either "http:" or "https:", depending on the user's preferences """ return ( 'http:' if self._downloader.params.get('prefer_insecure', False) @@ -586,7 +704,7 @@ class InfoExtractor(object): def _sleep(self, timeout, video_id, msg_template=None): if msg_template is None: - msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds' + msg_template = '%(video_id)s: Waiting for %(timeout)s seconds' msg = msg_template % {'video_id': video_id, 'timeout': timeout} self.to_screen(msg) time.sleep(timeout) @@ -597,11 +715,15 @@ class InfoExtractor(object): 'Unable to download f4m manifest') formats = [] - for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'): + media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') + for i, media_el in enumerate(media_nodes): + tbr = int_or_none(media_el.attrib.get('bitrate')) + format_id = 'f4m-%d' % (i if tbr is None else tbr) formats.append({ + 'format_id': format_id, 'url': manifest_url, 'ext': 'flv', - 'tbr': int_or_none(media_el.attrib.get('bitrate')), + 'tbr': tbr, 'width': int_or_none(media_el.attrib.get('width')), 'height': int_or_none(media_el.attrib.get('height')), }) @@ -609,6 +731,150 @@ class InfoExtractor(object): return formats + def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, + entry_protocol='m3u8', preference=None): + + formats = [{ + 'format_id': 'm3u8-meta', + 'url': m3u8_url, + 'ext': ext, + 'protocol': 'm3u8', + 'preference': -1, + 'resolution': 'multiple', + 'format_note': 'Quality selection URL', + }] + + format_url = lambda u: ( + u + if re.match(r'^https?://', u) + else compat_urlparse.urljoin(m3u8_url, u)) + + m3u8_doc = self._download_webpage( + m3u8_url, video_id, + note='Downloading m3u8 information', + errnote='Failed to download m3u8 information') + last_info = None + kv_rex = re.compile( + r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)') + for line in m3u8_doc.splitlines(): + if line.startswith('#EXT-X-STREAM-INF:'): + last_info = {} + for m in kv_rex.finditer(line): + v = m.group('val') + if v.startswith('"'): + v = v[1:-1] + last_info[m.group('key')] = v + elif line.startswith('#') or not line.strip(): + continue + else: + if last_info is None: + formats.append({'url': format_url(line)}) + continue + tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000) + + f = { + 'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)), + 'url': format_url(line.strip()), + 'tbr': tbr, + 'ext': ext, + 'protocol': entry_protocol, + 'preference': preference, + } + codecs = last_info.get('CODECS') + if codecs: + # TODO: looks like video codec is not always necessarily goes first + va_codecs = codecs.split(',') + if va_codecs[0]: + f['vcodec'] = va_codecs[0].partition('.')[0] + if len(va_codecs) > 1 and va_codecs[1]: + f['acodec'] = va_codecs[1].partition('.')[0] + resolution = last_info.get('RESOLUTION') + if resolution: + width_str, height_str = resolution.split('x') + f['width'] = int(width_str) + f['height'] = int(height_str) + formats.append(f) + last_info = {} + self._sort_formats(formats) + return formats + + # TODO: improve extraction + def _extract_smil_formats(self, smil_url, video_id): + smil = self._download_xml( + smil_url, video_id, 'Downloading SMIL file', + 'Unable to download SMIL file') + + base = smil.find('./head/meta').get('base') + + formats = [] + rtmp_count = 0 + for video in smil.findall('./body/switch/video'): + src = video.get('src') + if not src: + continue + bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) + width = int_or_none(video.get('width')) + height = int_or_none(video.get('height')) + proto = video.get('proto') + if not proto: + if base: + if base.startswith('rtmp'): + proto = 'rtmp' + elif base.startswith('http'): + proto = 'http' + ext = video.get('ext') + if proto == 'm3u8': + formats.extend(self._extract_m3u8_formats(src, video_id, ext)) + elif proto == 'rtmp': + rtmp_count += 1 + streamer = video.get('streamer') or base + formats.append({ + 'url': streamer, + 'play_path': src, + 'ext': 'flv', + 'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate), + 'tbr': bitrate, + 'width': width, + 'height': height, + }) + self._sort_formats(formats) + + return formats + + def _live_title(self, name): + """ Generate the title for a live video """ + now = datetime.datetime.now() + now_str = now.strftime("%Y-%m-%d %H:%M") + return name + ' ' + now_str + + def _int(self, v, name, fatal=False, **kwargs): + res = int_or_none(v, **kwargs) + if 'get_attr' in kwargs: + print(getattr(v, kwargs['get_attr'])) + if res is None: + msg = 'Failed to extract %s: Could not parse value %r' % (name, v) + if fatal: + raise ExtractorError(msg) + else: + self._downloader.report_warning(msg) + return res + + def _float(self, v, name, fatal=False, **kwargs): + res = float_or_none(v, **kwargs) + if res is None: + msg = 'Failed to extract %s: Could not parse value %r' % (name, v) + if fatal: + raise ExtractorError(msg) + else: + self._downloader.report_warning(msg) + return res + + def _set_cookie(self, domain, name, value, expire_time=None): + cookie = compat_cookiejar.Cookie( + 0, name, value, None, None, domain, None, + None, '/', True, False, expire_time, '', None, None, None) + self._downloader.cookiejar.set_cookie(cookie) + class SearchInfoExtractor(InfoExtractor): """ @@ -628,7 +894,7 @@ class SearchInfoExtractor(InfoExtractor): def _real_extract(self, query): mobj = re.match(self._make_valid_url(), query) if mobj is None: - raise ExtractorError(u'Invalid search query "%s"' % query) + raise ExtractorError('Invalid search query "%s"' % query) prefix = mobj.group('prefix') query = mobj.group('query') @@ -639,9 +905,9 @@ class SearchInfoExtractor(InfoExtractor): else: n = int(prefix) if n <= 0: - raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query)) + raise ExtractorError('invalid download number %s for query "%s"' % (n, query)) elif n > self._MAX_RESULTS: - self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) + self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) n = self._MAX_RESULTS return self._get_n_results(query, n) diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index ffbe4903b..7a7e79360 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -34,6 +34,8 @@ class CondeNastIE(InfoExtractor): _VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys()) IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values())) + EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed)/.+?' % '|'.join(_SITES.keys()) + _TEST = { 'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led', 'md5': '1921f713ed48aabd715691f774c451f7', diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py index 74b880ffc..cf763ee7e 100644 --- a/youtube_dl/extractor/cracked.py +++ b/youtube_dl/extractor/cracked.py @@ -54,7 +54,7 @@ class CrackedIE(InfoExtractor): return { 'id': video_id, - 'url':video_url, + 'url': video_url, 'title': title, 'description': description, 'timestamp': timestamp, @@ -62,4 +62,4 @@ class CrackedIE(InfoExtractor): 'comment_count': comment_count, 'height': height, 'width': width, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 026a9177e..d7e2b841e 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,10 +5,11 @@ import re import json import base64 import zlib +import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor -from .common import InfoExtractor +from .subtitles import SubtitlesInfoExtractor from ..utils import ( ExtractorError, compat_urllib_parse, @@ -16,15 +17,16 @@ from ..utils import ( bytes_to_intlist, intlist_to_bytes, unified_strdate, - clean_html, + urlencode_postdata, ) from ..aes import ( aes_cbc_decrypt, inc, ) +from .common import InfoExtractor -class CrunchyrollIE(InfoExtractor): +class CrunchyrollIE(SubtitlesInfoExtractor): _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' _TEST = { 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', @@ -37,6 +39,7 @@ class CrunchyrollIE(InfoExtractor): 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', 'uploader': 'Yomiuri Telecasting Corporation (YTV)', 'upload_date': '20131013', + 'url': 're:(?!.*&)', }, 'params': { # rtmp @@ -51,6 +54,24 @@ class CrunchyrollIE(InfoExtractor): '1080': ('80', '108'), } + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + login_url = 'https://www.crunchyroll.com/?a=formhandler' + data = urlencode_postdata({ + 'formname': 'RpcApiUser_Login', + 'name': username, + 'password': password, + }) + login_request = compat_urllib_request.Request(login_url, data) + login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(login_request, None, False, 'Wrong login info') + + def _real_initialize(self): + self._login() + def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(data) iv = bytes_to_intlist(iv) @@ -76,8 +97,10 @@ class CrunchyrollIE(InfoExtractor): return shaHash + [0] * 12 key = obfuscate_key(id) + class Counter: __value = iv + def next_value(self): temp = self.__value self.__value = inc(self.__value) @@ -85,19 +108,82 @@ class CrunchyrollIE(InfoExtractor): decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv)) return zlib.decompress(decrypted_data) - def _convert_subtitles_to_srt(self, subtitles): + def _convert_subtitles_to_srt(self, sub_root): output = '' - for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1): - start = start.replace('.', ',') - end = end.replace('.', ',') - text = clean_html(text) - text = text.replace('\\N', '\n') - if not text: - continue + + for i, event in enumerate(sub_root.findall('./events/event'), 1): + start = event.attrib['start'].replace('.', ',') + end = event.attrib['end'].replace('.', ',') + text = event.attrib['text'].replace('\\N', '\n') output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text) return output - def _real_extract(self,url): + def _convert_subtitles_to_ass(self, sub_root): + output = '' + + def ass_bool(strvalue): + assvalue = '0' + if strvalue == '1': + assvalue = '-1' + return assvalue + + output = '[Script Info]\n' + output += 'Title: %s\n' % sub_root.attrib["title"] + output += 'ScriptType: v4.00+\n' + output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"] + output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"] + output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"] + output += """ScaledBorderAndShadow: yes + +[V4+ Styles] +Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding +""" + for style in sub_root.findall('./styles/style'): + output += 'Style: ' + style.attrib["name"] + output += ',' + style.attrib["font_name"] + output += ',' + style.attrib["font_size"] + output += ',' + style.attrib["primary_colour"] + output += ',' + style.attrib["secondary_colour"] + output += ',' + style.attrib["outline_colour"] + output += ',' + style.attrib["back_colour"] + output += ',' + ass_bool(style.attrib["bold"]) + output += ',' + ass_bool(style.attrib["italic"]) + output += ',' + ass_bool(style.attrib["underline"]) + output += ',' + ass_bool(style.attrib["strikeout"]) + output += ',' + style.attrib["scale_x"] + output += ',' + style.attrib["scale_y"] + output += ',' + style.attrib["spacing"] + output += ',' + style.attrib["angle"] + output += ',' + style.attrib["border_style"] + output += ',' + style.attrib["outline"] + output += ',' + style.attrib["shadow"] + output += ',' + style.attrib["alignment"] + output += ',' + style.attrib["margin_l"] + output += ',' + style.attrib["margin_r"] + output += ',' + style.attrib["margin_v"] + output += ',' + style.attrib["encoding"] + output += '\n' + + output += """ +[Events] +Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text +""" + for event in sub_root.findall('./events/event'): + output += 'Dialogue: 0' + output += ',' + event.attrib["start"] + output += ',' + event.attrib["end"] + output += ',' + event.attrib["style"] + output += ',' + event.attrib["name"] + output += ',' + event.attrib["margin_l"] + output += ',' + event.attrib["margin_r"] + output += ',' + event.attrib["margin_v"] + output += ',' + event.attrib["effect"] + output += ',' + event.attrib["text"] + output += '\n' + + return output + + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -140,27 +226,31 @@ class CrunchyrollIE(InfoExtractor): formats = [] for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] - video_format = fmt+'p' + video_format = fmt + 'p' streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') # urlencode doesn't work! - streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format + streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') streamdata_req.add_header('Content-Length', str(len(streamdata_req.data))) - streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format) - video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url') - video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path') + streamdata = self._download_xml( + streamdata_req, video_id, + note='Downloading media info for %s' % video_format) + video_url = streamdata.find('.//host').text + video_play_path = streamdata.find('.//file').text formats.append({ 'url': video_url, - 'play_path': video_play_path, + 'play_path': video_play_path, 'ext': 'flv', 'format': video_format, 'format_id': video_format, }) subtitles = {} + sub_format = self._downloader.params.get('subtitlesformat', 'srt') for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): - sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ - video_id, note='Downloading subtitles for '+sub_name) + sub_page = self._download_webpage( + 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id, + video_id, note='Downloading subtitles for ' + sub_name) id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False) iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False) data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False) @@ -174,15 +264,60 @@ class CrunchyrollIE(InfoExtractor): lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue - subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + sub_root = xml.etree.ElementTree.fromstring(subtitle) + if sub_format == 'ass': + subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root) + else: + subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root) + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return return { - 'id': video_id, - 'title': video_title, + 'id': video_id, + 'title': video_title, 'description': video_description, - 'thumbnail': video_thumbnail, - 'uploader': video_uploader, + 'thumbnail': video_thumbnail, + 'uploader': video_uploader, 'upload_date': video_upload_date, - 'subtitles': subtitles, - 'formats': formats, + 'subtitles': subtitles, + 'formats': formats, + } + + +class CrunchyrollShowPlaylistIE(InfoExtractor): + IE_NAME = "crunchyroll:playlist" + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$' + + _TESTS = [{ + 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', + 'info_dict': { + 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', + 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi' + }, + 'playlist_count': 13, + }] + + def _real_extract(self, url): + show_id = self._match_id(url) + + webpage = self._download_webpage(url, show_id) + title = self._html_search_regex( + r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>', + webpage, 'title') + episode_paths = re.findall( + r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"', + webpage) + entries = [ + self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll') + for ep in episode_paths + ] + entries.reverse() + + return { + '_type': 'playlist', + 'id': show_id, + 'title': title, + 'entries': entries, } diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index b6552c542..541106684 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -34,6 +34,13 @@ class CSpanIE(InfoExtractor): 'title': 'International Health Care Models', 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', } + }, { + 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', + 'info_dict': { + 'id': '342759', + 'title': 'General Motors Ignition Switch Recall', + }, + 'playlist_duration_sum': 14855, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/d8.py b/youtube_dl/extractor/d8.py deleted file mode 100644 index 6b26ff2e3..000000000 --- a/youtube_dl/extractor/d8.py +++ /dev/null @@ -1,25 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -from .canalplus import CanalplusIE - - -class D8IE(CanalplusIE): - _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)' - _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s' - IE_NAME = 'd8.tv' - - _TEST = { - 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html', - 'file': '966289.flv', - 'info_dict': { - 'title': 'Campagne intime - Documentaire exceptionnel', - 'description': 'md5:d2643b799fb190846ae09c61e59a859f', - 'upload_date': '20131108', - }, - 'params': { - # rtmp - 'skip_download': True, - }, - 'skip': 'videos get deleted after a while', - } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 5d0bfe454..936c13cd6 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,3 +1,6 @@ +# coding: utf-8 +from __future__ import unicode_literals + import re import json import itertools @@ -15,6 +18,7 @@ from ..utils import ( unescapeHTML, ) + class DailymotionBaseInfoExtractor(InfoExtractor): @staticmethod def _build_request(url): @@ -24,64 +28,63 @@ class DailymotionBaseInfoExtractor(InfoExtractor): request.add_header('Cookie', 'ff=off') return request + class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)' - IE_NAME = u'dailymotion' + IE_NAME = 'dailymotion' _FORMATS = [ - (u'stream_h264_ld_url', u'ld'), - (u'stream_h264_url', u'standard'), - (u'stream_h264_hq_url', u'hq'), - (u'stream_h264_hd_url', u'hd'), - (u'stream_h264_hd1080_url', u'hd180'), + ('stream_h264_ld_url', 'ld'), + ('stream_h264_url', 'standard'), + ('stream_h264_hq_url', 'hq'), + ('stream_h264_hd_url', 'hd'), + ('stream_h264_hd1080_url', 'hd180'), ] _TESTS = [ { - u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', - u'file': u'x33vw9.mp4', - u'md5': u'392c4b85a60a90dc4792da41ce3144eb', - u'info_dict': { - u"uploader": u"Amphora Alex and Van .", - u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\"" + 'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', + 'md5': '392c4b85a60a90dc4792da41ce3144eb', + 'info_dict': { + 'id': 'x33vw9', + 'ext': 'mp4', + 'uploader': 'Amphora Alex and Van .', + 'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"', } }, # Vevo video { - u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi', - u'file': u'USUV71301934.mp4', - u'info_dict': { - u'title': u'Roar (Official)', - u'uploader': u'Katy Perry', - u'upload_date': u'20130905', + 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi', + 'info_dict': { + 'title': 'Roar (Official)', + 'id': 'USUV71301934', + 'ext': 'mp4', + 'uploader': 'Katy Perry', + 'upload_date': '20130905', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'VEVO is only available in some countries', + 'skip': 'VEVO is only available in some countries', }, # age-restricted video { - u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband', - u'file': u'xyh2zz.mp4', - u'md5': u'0d667a7b9cebecc3c89ee93099c4159d', - u'info_dict': { - u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]', - u'uploader': 'HotWaves1012', - u'age_limit': 18, + 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband', + 'md5': '0d667a7b9cebecc3c89ee93099c4159d', + 'info_dict': { + 'id': 'xyh2zz', + 'ext': 'mp4', + 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]', + 'uploader': 'HotWaves1012', + 'age_limit': 18, } - } ] def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'http://www.dailymotion.com/video/%s' % video_id # Retrieve video webpage to extract further information @@ -93,12 +96,12 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): # It may just embed a vevo video: m_vevo = re.search( - r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\w]*)', + r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)', webpage) if m_vevo is not None: vevo_id = m_vevo.group('id') - self.to_screen(u'Vevo video detected: %s' % vevo_id) - return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo') + self.to_screen('Vevo video detected: %s' % vevo_id) + return self.url_result('vevo:%s' % vevo_id, ie='Vevo') age_limit = self._rta_search(webpage) @@ -109,9 +112,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id embed_page = self._download_webpage(embed_url, video_id, - u'Downloading embed page') + 'Downloading embed page') info = self._search_regex(r'var info = ({.*?}),$', embed_page, - 'video info', flags=re.MULTILINE) + 'video info', flags=re.MULTILINE) info = json.loads(info) if info.get('error') is not None: msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title'] @@ -134,7 +137,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'height': height, }) if not formats: - raise ExtractorError(u'Unable to extract video URL') + raise ExtractorError('Unable to extract video URL') # subtitles video_subtitles = self.extract_subtitles(video_id, webpage) @@ -142,18 +145,23 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): self._list_available_subtitles(video_id, webpage) return - view_count = self._search_regex( - r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False) - if view_count is not None: - view_count = str_to_int(view_count) + view_count = str_to_int(self._search_regex( + r'video_views_count[^>]+>\s+([\d\.,]+)', + webpage, 'view count', fatal=False)) + + title = self._og_search_title(webpage, default=None) + if title is None: + title = self._html_search_regex( + r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage, + 'title') return { - 'id': video_id, + 'id': video_id, 'formats': formats, 'uploader': info['owner.screenname'], - 'upload_date': video_upload_date, - 'title': self._og_search_title(webpage), - 'subtitles': video_subtitles, + 'upload_date': video_upload_date, + 'title': title, + 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'], 'age_limit': age_limit, 'view_count': view_count, @@ -165,35 +173,42 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) return {} info = json.loads(sub_list) if (info['total'] > 0): sub_lang_list = dict((l['language'], l['url']) for l in info['list']) return sub_lang_list - self._downloader.report_warning(u'video doesn\'t have subtitles') + self._downloader.report_warning('video doesn\'t have subtitles') return {} class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): - IE_NAME = u'dailymotion:playlist' + IE_NAME = 'dailymotion:playlist' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' + _TESTS = [{ + 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', + 'info_dict': { + 'title': 'SPORT', + }, + 'playlist_mincount': 20, + }] def _extract_entries(self, id): video_ids = [] for pagenum in itertools.count(1): request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum)) webpage = self._download_webpage(request, - id, u'Downloading page %s' % pagenum) + id, 'Downloading page %s' % pagenum) video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage)) if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') - for video_id in orderedSet(video_ids)] + for video_id in orderedSet(video_ids)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -209,9 +224,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): - IE_NAME = u'dailymotion:user' + IE_NAME = 'dailymotion:user' _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' + _TESTS = [{ + 'url': 'https://www.dailymotion.com/user/nqtv', + 'info_dict': { + 'id': 'nqtv', + 'title': 'Rémi Gaillard', + }, + 'playlist_mincount': 100, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -219,7 +242,7 @@ class DailymotionUserIE(DailymotionPlaylistIE): webpage = self._download_webpage(url, user) full_user = unescapeHTML(self._html_search_regex( r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user), - webpage, u'user', flags=re.DOTALL)) + webpage, 'user')) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 6033cd94a..45d66e2e6 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -11,10 +11,10 @@ from ..utils import ( class DaumIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)' + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)' IE_NAME = 'daum.net' - _TEST = { + _TESTS = [{ 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', 'info_dict': { 'id': '52554690', @@ -24,11 +24,17 @@ class DaumIE(InfoExtractor): 'upload_date': '20130831', 'duration': 3868, }, - } + }, { + 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz', + 'only_matching': True, + }, { + 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = mobj.group('id') canonical_url = 'http://tvpot.daum.net/v/%s' % video_id webpage = self._download_webpage(canonical_url, video_id) full_id = self._search_regex( @@ -42,7 +48,6 @@ class DaumIE(InfoExtractor): 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query, video_id, 'Downloading video formats info') - self.to_screen(u'%s: Getting video urls' % video_id) formats = [] for format_el in urls.findall('result/output_list/output_list'): profile = format_el.attrib['profile'] @@ -52,7 +57,7 @@ class DaumIE(InfoExtractor): }) url_doc = self._download_xml( 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, - video_id, note=False) + video_id, note='Downloading video data for %s format' % profile) format_url = url_doc.find('result/url').text formats.append({ 'url': format_url, diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py new file mode 100644 index 000000000..1d3e2ff08 --- /dev/null +++ b/youtube_dl/extractor/dbtv.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, + clean_html, +) + + +class DBTVIE(InfoExtractor): + _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)' + _TEST = { + 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc', + 'info_dict': { + 'id': '33100', + 'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'ext': 'mp4', + 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', + 'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1404039863.438, + 'upload_date': '20140629', + 'duration': 69.544, + 'view_count': int, + 'categories': list, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + data = self._download_json( + 'http://api.dbtv.no/discovery/%s' % video_id, display_id) + + video = data['playlist'][0] + + formats = [{ + 'url': f['URL'], + 'vcodec': f.get('container'), + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'vbr': float_or_none(f.get('rate'), 1000), + 'filesize': int_or_none(f.get('size')), + } for f in video['renditions'] if 'URL' in f] + + if not formats: + for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]: + if url_key in video: + formats.append({ + 'url': video[url_key], + 'format_id': format_id, + }) + + self._sort_formats(formats) + + return { + 'id': video['id'], + 'display_id': display_id, + 'title': video['title'], + 'description': clean_html(video['desc']), + 'thumbnail': video.get('splash') or video.get('thumb'), + 'timestamp': float_or_none(video.get('publishedAt'), 1000), + 'duration': float_or_none(video.get('length'), 1000), + 'view_count': int_or_none(video.get('views')), + 'categories': video.get('tags'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/deezer.py b/youtube_dl/extractor/deezer.py new file mode 100644 index 000000000..c3205ff5f --- /dev/null +++ b/youtube_dl/extractor/deezer.py @@ -0,0 +1,89 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, + orderedSet, +) + + +class DeezerPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.deezer.com/playlist/176747451', + 'info_dict': { + 'id': '176747451', + 'title': 'Best!', + 'uploader': 'Anonymous', + 'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$', + }, + 'playlist_count': 30, + 'skip': 'Only available in .de', + } + + def _real_extract(self, url): + if 'test' not in self._downloader.params: + self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!') + + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + geoblocking_msg = self._html_search_regex( + r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message', + default=None) + if geoblocking_msg is not None: + raise ExtractorError( + 'Deezer said: %s' % geoblocking_msg, expected=True) + + data_json = self._search_regex( + r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON') + data = json.loads(data_json) + + playlist_title = data.get('DATA', {}).get('TITLE') + playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME') + playlist_thumbnail = self._search_regex( + r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage, + 'playlist thumbnail') + + preview_pattern = self._search_regex( + r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage, + 'preview URL pattern', fatal=False) + entries = [] + for s in data['SONGS']['data']: + puid = s['MD5_ORIGIN'] + preview_video_url = preview_pattern.\ + replace('{0}', puid[0]).\ + replace('{1}', puid).\ + replace('{2}', s['MEDIA_VERSION']) + formats = [{ + 'format_id': 'preview', + 'url': preview_video_url, + 'preference': -100, # Only the first 30 seconds + 'ext': 'mp3', + }] + self._sort_formats(formats) + artists = ', '.join( + orderedSet(a['ART_NAME'] for a in s['ARTISTS'])) + entries.append({ + 'id': s['SNG_ID'], + 'duration': int_or_none(s.get('DURATION')), + 'title': '%s - %s' % (artists, s['SNG_TITLE']), + 'uploader': s['ART_NAME'], + 'uploader_id': s['ART_ID'], + 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0, + 'formats': formats, + }) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': playlist_title, + 'uploader': playlist_uploader, + 'thumbnail': playlist_thumbnail, + 'entries': entries, + } diff --git a/youtube_dl/extractor/defense.py b/youtube_dl/extractor/defense.py index c5529f8d4..5e50c63d9 100644 --- a/youtube_dl/extractor/defense.py +++ b/youtube_dl/extractor/defense.py @@ -9,7 +9,7 @@ from .common import InfoExtractor class DefenseGouvFrIE(InfoExtractor): IE_NAME = 'defense.gouv.fr' _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/' - r'ligthboxvideo/base-de-medias/webtv/(.*)') + r'ligthboxvideo/base-de-medias/webtv/(.*)') _TEST = { 'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1', @@ -26,13 +26,13 @@ class DefenseGouvFrIE(InfoExtractor): video_id = self._search_regex( r"flashvars.pvg_id=\"(\d+)\";", webpage, 'ID') - + json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/' - + video_id) + + video_id) info = self._download_webpage(json_url, title, - 'Downloading JSON config') + 'Downloading JSON config') video_url = json.loads(info)['renditions'][0]['url'] - + return {'id': video_id, 'ext': 'mp4', 'url': video_url, diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py index cb8e06822..8049779b0 100644 --- a/youtube_dl/extractor/dfb.py +++ b/youtube_dl/extractor/dfb.py @@ -30,7 +30,7 @@ class DFBIE(InfoExtractor): video_id) video_info = player_info.find('video') - f4m_info = self._download_xml(video_info.find('url').text, video_id) + f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) token_el = f4m_info.find('token') manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 554df6735..52c2d7ddf 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -16,9 +16,9 @@ class DiscoveryIE(InfoExtractor): 'ext': 'mp4', 'title': 'MythBusters: Mission Impossible Outtakes', 'description': ('Watch Jamie Hyneman and Adam Savage practice being' - ' each other -- to the point of confusing Jamie\'s dog -- and ' - 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' - ' back.'), + ' each other -- to the point of confusing Jamie\'s dog -- and ' + 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' + ' back.'), 'duration': 156, }, } @@ -29,7 +29,7 @@ class DiscoveryIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_list_json = self._search_regex(r'var videoListJSON = ({.*?});', - webpage, 'video list', flags=re.DOTALL) + webpage, 'video list', flags=re.DOTALL) video_list = json.loads(video_list_json) info = video_list['clips'][0] formats = [] diff --git a/youtube_dl/extractor/divxstage.py b/youtube_dl/extractor/divxstage.py index 4ca3f37a2..b88379e06 100644 --- a/youtube_dl/extractor/divxstage.py +++ b/youtube_dl/extractor/divxstage.py @@ -7,7 +7,7 @@ class DivxStageIE(NovaMovIE): IE_NAME = 'divxstage' IE_DESC = 'DivxStage' - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'} _HOST = 'www.divxstage.eu' @@ -24,4 +24,4 @@ class DivxStageIE(NovaMovIE): 'title': 'youtubedl test video', 'description': 'This is a test video for youtubedl.', } - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/dotsub.py b/youtube_dl/extractor/dotsub.py index 5ae0ad5b6..638bb33cd 100644 --- a/youtube_dl/extractor/dotsub.py +++ b/youtube_dl/extractor/dotsub.py @@ -27,7 +27,7 @@ class DotsubIE(InfoExtractor): video_id = mobj.group('id') info_url = "https://dotsub.com/api/media/%s/metadata" % video_id info = self._download_json(info_url, video_id) - date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds + date = time.gmtime(info['dateCreated'] / 1000) # The timestamp is in miliseconds return { 'id': video_id, diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py index 9f569aa93..14b6c00b0 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -5,27 +5,33 @@ import os.path import re from .common import InfoExtractor -from ..utils import compat_urllib_parse_unquote +from ..compat import compat_urllib_parse_unquote +from ..utils import url_basename class DropboxIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)' - _TEST = { - 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4', - 'md5': '8a3d905427a6951ccb9eb292f154530b', - 'info_dict': { - 'id': 'nelirfsxnmcfbfh', - 'ext': 'mp4', - 'title': 'youtube-dl test video \'ä"BaW_jenozKc' - } - } + _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*' + _TESTS = [ + { + 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0', + 'info_dict': { + 'id': 'nelirfsxnmcfbfh', + 'ext': 'mp4', + 'title': 'youtube-dl test video \'ä"BaW_jenozKc' + } + }, { + 'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - fn = compat_urllib_parse_unquote(mobj.group('title')) + fn = compat_urllib_parse_unquote(url_basename(url)) title = os.path.splitext(fn)[0] - video_url = url + '?dl=1' + video_url = re.sub(r'[?&]dl=0', '', url) + video_url += ('?' if '?' not in video_url else '&') + 'dl=1' return { 'id': video_id, diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py new file mode 100644 index 000000000..ca274dff6 --- /dev/null +++ b/youtube_dl/extractor/drtuber.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import str_to_int + + +class DrTuberIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', + 'md5': '93e680cf2536ad0dfb7e74d94a89facd', + 'info_dict': { + 'id': '1740434', + 'display_id': 'hot-perky-blonde-naked-golf', + 'ext': 'mp4', + 'title': 'Hot Perky Blonde Naked Golf', + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'], + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._html_search_regex( + r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Free', webpage, 'title') + + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + like_count = str_to_int(self._html_search_regex( + r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', + webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<span class="comments_count">([\d,\.]+)</span>', + webpage, 'comment count', fatal=False)) + + cats_str = self._search_regex( + r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False) + categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'categories': categories, + 'age_limit': self._rta_search(webpage), + } diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index cdccfd376..93b3c9f36 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,14 +1,12 @@ from __future__ import unicode_literals -import re - from .subtitles import SubtitlesInfoExtractor from .common import ExtractorError from ..utils import parse_iso8601 class DRTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/[^/]+/(?P<id>[\da-z-]+)' + _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)' _TEST = { 'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8', @@ -25,8 +23,7 @@ class DRTVIE(SubtitlesInfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) programcard = self._download_json( 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON') @@ -35,7 +32,7 @@ class DRTVIE(SubtitlesInfoExtractor): title = data['Title'] description = data['Description'] - timestamp = parse_iso8601(data['CreatedTime'][:-5]) + timestamp = parse_iso8601(data['CreatedTime']) thumbnail = None duration = None diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py new file mode 100644 index 000000000..6b651778a --- /dev/null +++ b/youtube_dl/extractor/dump.py @@ -0,0 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DumpIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/' + + _TEST = { + 'url': 'http://www.dump.com/oneus/', + 'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99', + 'info_dict': { + 'id': 'oneus', + 'ext': 'flv', + 'title': "He's one of us.", + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex( + r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL') + + thumb = self._og_search_thumbnail(webpage) + title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumb, + } diff --git a/youtube_dl/extractor/ebaumsworld.py b/youtube_dl/extractor/ebaumsworld.py index 877113d63..63c2549d3 100644 --- a/youtube_dl/extractor/ebaumsworld.py +++ b/youtube_dl/extractor/ebaumsworld.py @@ -1,19 +1,21 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import determine_ext class EbaumsWorldIE(InfoExtractor): _VALID_URL = r'https?://www\.ebaumsworld\.com/video/watch/(?P<id>\d+)' _TEST = { - u'url': u'http://www.ebaumsworld.com/video/watch/83367677/', - u'file': u'83367677.mp4', - u'info_dict': { - u'title': u'A Giant Python Opens The Door', - u'description': u'This is how nightmares start...', - u'uploader': u'jihadpizza', + 'url': 'http://www.ebaumsworld.com/video/watch/83367677/', + 'info_dict': { + 'id': '83367677', + 'ext': 'mp4', + 'title': 'A Giant Python Opens The Door', + 'description': 'This is how nightmares start...', + 'uploader': 'jihadpizza', }, } @@ -28,7 +30,6 @@ class EbaumsWorldIE(InfoExtractor): 'id': video_id, 'title': config.find('title').text, 'url': video_url, - 'ext': determine_ext(video_url), 'description': config.find('description').text, 'thumbnail': config.find('image').text, 'uploader': config.find('username').text, diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index f8f49a013..b766e17f2 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -28,7 +28,7 @@ class EHowIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', - webpage, 'video URL') + webpage, 'video URL') final_url = compat_urllib_parse.unquote(video_url) uploader = self._html_search_meta('uploader', webpage) title = self._og_search_title(webpage).replace(' | eHow', '') diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index 88f5526b8..f4c1e2a72 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -1,10 +1,13 @@ +# coding: utf-8 +from __future__ import unicode_literals + import json import random import re from .common import InfoExtractor from ..utils import ( - ExtractorError, + compat_str, ) @@ -12,86 +15,98 @@ class EightTracksIE(InfoExtractor): IE_NAME = '8tracks' _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' _TEST = { - u"name": u"EightTracks", - u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a", - u"playlist": [ + "name": "EightTracks", + "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a", + "info_dict": { + 'id': '1336550', + 'display_id': 'youtube-dl-test-tracks-a', + "description": "test chars: \"'/\\ä↭", + "title": "youtube-dl test tracks \"'/\\ä↭<>", + }, + "playlist": [ { - u"file": u"11885610.m4a", - u"md5": u"96ce57f24389fc8734ce47f4c1abcc55", - u"info_dict": { - u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "96ce57f24389fc8734ce47f4c1abcc55", + "info_dict": { + "id": "11885610", + "ext": "m4a", + "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885608.m4a", - u"md5": u"4ab26f05c1f7291ea460a3920be8021f", - u"info_dict": { - u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "4ab26f05c1f7291ea460a3920be8021f", + "info_dict": { + "id": "11885608", + "ext": "m4a", + "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885679.m4a", - u"md5": u"d30b5b5f74217410f4689605c35d1fd7", - u"info_dict": { - u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "d30b5b5f74217410f4689605c35d1fd7", + "info_dict": { + "id": "11885679", + "ext": "m4a", + "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885680.m4a", - u"md5": u"4eb0a669317cd725f6bbd336a29f923a", - u"info_dict": { - u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "4eb0a669317cd725f6bbd336a29f923a", + "info_dict": { + "id": "11885680", + "ext": "m4a", + "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885682.m4a", - u"md5": u"1893e872e263a2705558d1d319ad19e8", - u"info_dict": { - u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "1893e872e263a2705558d1d319ad19e8", + "info_dict": { + "id": "11885682", + "ext": "m4a", + "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885683.m4a", - u"md5": u"b673c46f47a216ab1741ae8836af5899", - u"info_dict": { - u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "b673c46f47a216ab1741ae8836af5899", + "info_dict": { + "id": "11885683", + "ext": "m4a", + "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885684.m4a", - u"md5": u"1d74534e95df54986da7f5abf7d842b7", - u"info_dict": { - u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "1d74534e95df54986da7f5abf7d842b7", + "info_dict": { + "id": "11885684", + "ext": "m4a", + "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885685.m4a", - u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0", - u"info_dict": { - u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "f081f47af8f6ae782ed131d38b9cd1c0", + "info_dict": { + "id": "11885685", + "ext": "m4a", + "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } } ] } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL) + json_like = self._search_regex( + r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information') data = json.loads(json_like) session = str(random.randint(0, 1000000000)) @@ -99,21 +114,30 @@ class EightTracksIE(InfoExtractor): track_count = data['tracks_count'] first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) next_url = first_url - res = [] + entries = [] for i in range(track_count): - api_json = self._download_webpage(next_url, playlist_id, - note=u'Downloading song information %s/%s' % (str(i+1), track_count), - errnote=u'Failed to download song information') + api_json = self._download_webpage( + next_url, playlist_id, + note='Downloading song information %d/%d' % (i + 1, track_count), + errnote='Failed to download song information') api_data = json.loads(api_json) - track_data = api_data[u'set']['track'] + track_data = api_data['set']['track'] info = { - 'id': track_data['id'], + 'id': compat_str(track_data['id']), 'url': track_data['track_file_stream_url'], - 'title': track_data['performer'] + u' - ' + track_data['name'], + 'title': track_data['performer'] + ' - ' + track_data['name'], 'raw_title': track_data['name'], 'uploader_id': data['user']['login'], 'ext': 'm4a', } - res.append(info) - next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) - return res + entries.append(info) + next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % ( + session, mix_id, track_data['id']) + return { + '_type': 'playlist', + 'entries': entries, + 'id': compat_str(mix_id), + 'display_id': playlist_id, + 'title': data.get('name'), + 'description': data.get('description'), + } diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py new file mode 100644 index 000000000..5dfea0d39 --- /dev/null +++ b/youtube_dl/extractor/einthusan.py @@ -0,0 +1,61 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class EinthusanIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)' + _TESTS = [ + { + 'url': 'http://www.einthusan.com/movies/watch.php?id=2447', + 'md5': 'af244f4458cd667205e513d75da5b8b1', + 'info_dict': { + 'id': '2447', + 'ext': 'mp4', + 'title': 'Ek Villain', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'md5:9d29fc91a7abadd4591fb862fa560d93', + } + }, + { + 'url': 'http://www.einthusan.com/movies/watch.php?id=1671', + 'md5': 'ef63c7a803e22315880ed182c10d1c5c', + 'info_dict': { + 'id': '1671', + 'ext': 'mp4', + 'title': 'Soodhu Kavvuum', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'md5:05d8a0c0281a4240d86d76e14f2f4d51', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex( + r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title') + + video_url = self._html_search_regex( + r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''', + webpage, 'video url') + + description = self._html_search_meta('description', webpage) + thumbnail = self._html_search_regex( + r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', + webpage, "thumbnail url", fatal=False) + if thumbnail is not None: + thumbnail = thumbnail.replace('..', 'http://www.einthusan.com') + + return { + 'id': video_id, + 'title': video_title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py index 4ba323148..2cba82532 100644 --- a/youtube_dl/extractor/eitb.py +++ b/youtube_dl/extractor/eitb.py @@ -1,4 +1,6 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,20 +9,20 @@ from ..utils import ExtractorError class EitbIE(InfoExtractor): - IE_NAME = u'eitb.tv' + IE_NAME = 'eitb.tv' _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)' _TEST = { - u'add_ie': ['Brightcove'], - u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', - u'md5': u'edf4436247185adee3ea18ce64c47998', - u'info_dict': { - u'id': u'2743577154001', - u'ext': u'mp4', - u'title': u'60 minutos (Lasa y Zabala, 30 años)', + 'add_ie': ['Brightcove'], + 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', + 'md5': 'edf4436247185adee3ea18ce64c47998', + 'info_dict': { + 'id': '2743577154001', + 'ext': 'mp4', + 'title': '60 minutos (Lasa y Zabala, 30 años)', # All videos from eitb has this description in the brightcove info - u'description': u'.', - u'uploader': u'Euskal Telebista', + 'description': '.', + 'uploader': 'Euskal Telebista', }, } @@ -30,7 +32,7 @@ class EitbIE(InfoExtractor): webpage = self._download_webpage(url, chapter_id) bc_url = BrightcoveIE._extract_brightcove_url(webpage) if bc_url is None: - raise ExtractorError(u'Could not extract the Brightcove url') + raise ExtractorError('Could not extract the Brightcove url') # The BrightcoveExperience object doesn't contain the video id, we set # it manually bc_url += '&%40videoPlayer={0}'.format(chapter_id) diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py new file mode 100644 index 000000000..3e7923648 --- /dev/null +++ b/youtube_dl/extractor/ellentv.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) + + +class EllenTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', + 'md5': 'e4af06f3bf0d5f471921a18db5764642', + 'info_dict': { + 'id': '0-7jqrsr18', + 'ext': 'mp4', + 'title': 'What\'s Wrong with These Photos? A Whole Lot', + 'timestamp': 1406876400, + 'upload_date': '20140801', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + timestamp = parse_iso8601(self._search_regex( + r'<span class="publish-date"><time datetime="([^"]+)">', + webpage, 'timestamp')) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'url': self._html_search_meta('VideoURL', webpage, 'url'), + 'timestamp': timestamp, + } + + +class EllenTVClipsIE(InfoExtractor): + IE_NAME = 'EllenTV:clips' + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', + 'info_dict': { + 'id': 'meryl-streep-vanessa-hudgens', + 'title': 'Meryl Streep, Vanessa Hudgens', + }, + 'playlist_mincount': 9, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + playlist = self._extract_playlist(webpage) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': self._og_search_title(webpage), + 'entries': self._extract_entries(playlist) + } + + def _extract_playlist(self, webpage): + json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') + try: + return json.loads("[{" + json_string + "}]") + except ValueError as ve: + raise ExtractorError('Failed to download JSON', cause=ve) + + def _extract_entries(self, playlist): + return [self.url_result(item['url'], 'EllenTV') for item in playlist] diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index e6952588f..70f8efe27 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -1,54 +1,25 @@ from __future__ import unicode_literals -import re +from .tnaflix import TNAFlixIE -from .common import InfoExtractor +class EMPFlixIE(TNAFlixIE): + _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html' + + _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"' + _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' -class EmpflixIE(InfoExtractor): - _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _TEST = { 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'info_dict': { 'id': '33051', + 'display_id': 'Amateur-Finger-Fuck', 'ext': 'mp4', 'title': 'Amateur Finger Fuck', 'description': 'Amateur solo finger fucking.', + 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) - - video_title = self._html_search_regex( - r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') - video_description = self._html_search_regex( - r'name="description" value="([^"]*)"', webpage, 'description', fatal=False) - - cfg_url = self._html_search_regex( - r'flashvars\.config = escape\("([^"]+)"', - webpage, 'flashvars.config') - - cfg_xml = self._download_xml( - cfg_url, video_id, note='Downloading metadata') - - formats = [ - { - 'url': item.find('videoLink').text, - 'format_id': item.find('res').text, - } for item in cfg_xml.findall('./quality/item') - ] - - return { - 'id': video_id, - 'title': video_title, - 'description': video_description, - 'formats': formats, - 'age_limit': age_limit, - } diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py new file mode 100644 index 000000000..4de8d4bc5 --- /dev/null +++ b/youtube_dl/extractor/eporner.py @@ -0,0 +1,73 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class EpornerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', + 'md5': '39d486f046212d8e1b911c52ab4691f8', + 'info_dict': { + 'id': '95008', + 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', + 'ext': 'mp4', + 'title': 'Infamous Tiffany Teen Strip Tease Video', + 'duration': 1838, + 'view_count': int, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + title = self._html_search_regex( + r'<title>(.*?) - EPORNER', webpage, 'title') + + redirect_code = self._html_search_regex( + r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id, + webpage, 'redirect_code') + redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code) + player_code = self._download_webpage( + redirect_url, display_id, note='Downloading player config') + + sources = self._search_regex( + r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources') + + formats = [] + for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources): + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + duration = parse_duration(self._html_search_meta('duration', webpage)) + view_count = str_to_int(self._search_regex( + r'id="cinemaviews">\s*([0-9,]+)\s*<small>views', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + 'age_limit': self._rta_search(webpage), + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 272dfe1f6..476fc22b9 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -36,7 +36,7 @@ class EscapistIE(InfoExtractor): r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False) - playerUrl = self._og_search_video_url(webpage, name=u'player URL') + playerUrl = self._og_search_video_url(webpage, name='player URL') title = self._html_search_regex( r'<meta name="title" content="([^"]*)"', diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index 12829cbcc..d237a8281 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -12,10 +12,11 @@ from ..utils import ( class EveryonesMixtapeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P<id>[0-9a-zA-Z]+)(?:/(?P<songnr>[0-9]))?$' - _TEST = { + _TESTS = [{ 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', - 'file': '5bfseWNmlds.mp4', "info_dict": { + 'id': '5bfseWNmlds', + 'ext': 'mp4', "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)", "uploader": "FKR.TV", "uploader_id": "frenchkissrecords", @@ -25,7 +26,14 @@ class EveryonesMixtapeIE(InfoExtractor): 'params': { 'skip_download': True, # This is simply YouTube } - } + }, { + 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi', + 'info_dict': { + 'id': 'm7m0jJAbMQi', + 'title': 'Driving', + }, + 'playlist_count': 24 + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/expotv.py b/youtube_dl/extractor/expotv.py new file mode 100644 index 000000000..a38b773e8 --- /dev/null +++ b/youtube_dl/extractor/expotv.py @@ -0,0 +1,73 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class ExpoTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])' + _TEST = { + 'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561', + 'md5': '2985e6d7a392b2f7a05e0ca350fe41d0', + 'info_dict': { + 'id': '17561', + 'ext': 'mp4', + 'upload_date': '20060212', + 'title': 'My Favorite Online Scrapbook Store', + 'view_count': int, + 'description': 'You\'ll find most everything you need at this virtual store front.', + 'uploader': 'Anna T.', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_key = self._search_regex( + r'<param name="playerKey" value="([^"]+)"', webpage, 'player key') + config_url = 'http://client.expotv.com/video/config/%s/%s' % ( + video_id, player_key) + config = self._download_json( + config_url, video_id, + note='Downloading video configuration') + + formats = [{ + 'url': fcfg['file'], + 'height': int_or_none(fcfg.get('height')), + 'format_note': fcfg.get('label'), + 'ext': self._search_regex( + r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'], + 'file extension', default=None), + } for fcfg in config['sources']] + self._sort_formats(formats) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = config.get('image') + view_count = int_or_none(self._search_regex( + r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts')) + uploader = self._search_regex( + r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader', + fatal=False) + upload_date = unified_strdate(self._search_regex( + r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date', + fatal=False)) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'description': description, + 'view_count': view_count, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index 14a196ffc..aacbf1414 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -7,6 +7,7 @@ from ..utils import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, + str_to_int, ) @@ -20,6 +21,7 @@ class ExtremeTubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', 'uploader': 'unknown', + 'view_count': int, 'age_limit': 18, } }, { @@ -39,8 +41,12 @@ class ExtremeTubeIE(InfoExtractor): video_title = self._html_search_regex( r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title') uploader = self._html_search_regex( - r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader', - fatal=False) + r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>', + webpage, 'uploader', fatal=False) + view_count = str_to_int(self._html_search_regex( + r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>', + webpage, 'view count', fatal=False)) + video_url = compat_urllib_parse.unquote(self._html_search_regex( r'video_url=(.+?)&', webpage, 'video_url')) path = compat_urllib_parse_urlparse(video_url).path @@ -51,6 +57,7 @@ class ExtremeTubeIE(InfoExtractor): 'id': video_id, 'title': video_title, 'uploader': uploader, + 'view_count': view_count, 'url': video_url, 'format': format, 'format_id': format, diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f0cd8f156..1ad4e77a8 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -5,39 +5,52 @@ import re import socket from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_http_client, compat_str, compat_urllib_error, compat_urllib_parse, compat_urllib_request, - urlencode_postdata, - +) +from ..utils import ( ExtractorError, + int_or_none, + limit_length, + urlencode_postdata, ) class FacebookIE(InfoExtractor): _VALID_URL = r'''(?x) https?://(?:\w+\.)?facebook\.com/ - (?:[^#?]*\#!/)? - (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) + (?:[^#]*?\#!/)? + (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?) (?:v|video_id)=(?P<id>[0-9]+) (?:.*)''' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' IE_NAME = 'facebook' - _TEST = { - 'url': 'https://www.facebook.com/photo.php?v=120708114770723', - 'md5': '48975a41ccc4b7a581abd68651c1a5a8', + _TESTS = [{ + 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', + 'md5': '6a40d33c0eccbb1af76cf0485a052659', 'info_dict': { - 'id': '120708114770723', + 'id': '637842556329505', 'ext': 'mp4', - 'duration': 279, - 'title': 'PEOPLE ARE AWESOME 2013', + 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', } - } + }, { + 'note': 'Video without discernible title', + 'url': 'https://www.facebook.com/video.php?v=274175099429670', + 'info_dict': { + 'id': '274175099429670', + 'ext': 'mp4', + 'title': 'Facebook video #274175099429670', + } + }, { + 'url': 'https://www.facebook.com/video.php?v=10204634152394104', + 'only_matching': True, + }] def _login(self): (useremail, password) = self._get_login_info() @@ -47,8 +60,8 @@ class FacebookIE(InfoExtractor): login_page_req = compat_urllib_request.Request(self._LOGIN_URL) login_page_req.add_header('Cookie', 'locale=en_US') login_page = self._download_webpage(login_page_req, None, - note='Downloading login page', - errnote='Unable to download login page') + note='Downloading login page', + errnote='Unable to download login page') lsd = self._search_regex( r'<input type="hidden" name="lsd" value="([^"]*)"', login_page, 'lsd') @@ -64,25 +77,26 @@ class FacebookIE(InfoExtractor): 'legacy_return': '1', 'timezone': '-60', 'trynum': '1', - } + } request = compat_urllib_request.Request(self._LOGIN_URL, urlencode_postdata(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') try: login_results = self._download_webpage(request, None, - note='Logging in', errnote='unable to fetch login page') + note='Logging in', errnote='unable to fetch login page') if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') return check_form = { 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'), - 'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'), + 'h': self._search_regex( + r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'), 'name_action_selected': 'dont_save', } check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') check_response = self._download_webpage(check_req, None, - note='Confirming login') + note='Confirming login') if re.search(r'id="checkpointSubmitButton"', check_response) is not None: self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -93,9 +107,7 @@ class FacebookIE(InfoExtractor): self._login() def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'https://www.facebook.com/video/video.php?v=%s' % video_id webpage = self._download_webpage(url, video_id) @@ -121,12 +133,20 @@ class FacebookIE(InfoExtractor): raise ExtractorError('Cannot find video URL') video_title = self._html_search_regex( - r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title') + r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title', + fatal=False) + if not video_title: + video_title = self._html_search_regex( + r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', + webpage, 'alternative title', default=None) + video_title = limit_length(video_title, 80) + if not video_title: + video_title = 'Facebook video #%s' % video_id return { 'id': video_id, 'title': video_title, 'url': video_url, - 'duration': int(video_data['video_duration']), - 'thumbnail': video_data['thumbnail_src'], + 'duration': int_or_none(video_data.get('video_duration')), + 'thumbnail': video_data.get('thumbnail_src'), } diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index c6ab6952e..3c39ca451 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -1,49 +1,48 @@ # encoding: utf-8 -import re +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - determine_ext, -) class FazIE(InfoExtractor): - IE_NAME = u'faz.net' + IE_NAME = 'faz.net' _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html' _TEST = { - u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', - u'file': u'12610585.mp4', - u'info_dict': { - u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher', - u'description': u'md5:1453fbf9a0d041d985a47306192ea253', + 'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', + 'info_dict': { + 'id': '12610585', + 'ext': 'mp4', + 'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher', + 'description': 'md5:1453fbf9a0d041d985a47306192ea253', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - self.to_screen(video_id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage, - u'config xml url') - config = self._download_xml(config_xml_url, video_id, - u'Downloading config xml') + config_xml_url = self._search_regex( + r'writeFLV\(\'(.+?)\',', webpage, 'config xml url') + config = self._download_xml( + config_xml_url, video_id, 'Downloading config xml') encodings = config.find('ENCODINGS') formats = [] - for code in ['LOW', 'HIGH', 'HQ']: + for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): encoding = encodings.find(code) if encoding is None: continue encoding_url = encoding.find('FILENAME').text formats.append({ 'url': encoding_url, - 'ext': determine_ext(encoding_url), 'format_id': code.lower(), + 'quality': pref, }) + self._sort_formats(formats) - descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description') + descr = self._html_search_regex( + r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False) return { 'id': video_id, 'title': self._og_search_title(webpage), diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index c663a0f81..6f5d23559 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -40,7 +40,7 @@ class FC2IE(InfoExtractor): info_url = ( "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&". - format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E'))) + format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.', '%2E'))) info_webpage = self._download_webpage( info_url, video_id, note='Downloading info page') diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py index 6d73c8a4a..af439ccfe 100644 --- a/youtube_dl/extractor/firedrive.py +++ b/youtube_dl/extractor/firedrive.py @@ -42,7 +42,6 @@ class FiredriveIE(InfoExtractor): fields = dict(re.findall(r'''(?x)<input\s+ type="hidden"\s+ name="([^"]+)"\s+ - (?:id="[^"]+"\s+)? value="([^"]*)" ''', webpage)) @@ -66,7 +65,7 @@ class FiredriveIE(InfoExtractor): ext = self._search_regex(r'type:\s?\'([^\']+)\',', webpage, 'extension', fatal=False) video_url = self._search_regex( - r'file:\s?\'(http[^\']+)\',', webpage, 'file url') + r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url') formats = [{ 'format_id': 'sd', diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py index c2e987ff7..08ceee4ed 100644 --- a/youtube_dl/extractor/firsttv.py +++ b/youtube_dl/extractor/firsttv.py @@ -44,9 +44,9 @@ class FirstTVIE(InfoExtractor): duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False) like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]', - webpage, 'like count', fatal=False) + webpage, 'like count', fatal=False) dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]', - webpage, 'dislike count', fatal=False) + webpage, 'dislike count', fatal=False) return { 'id': video_id, @@ -57,4 +57,4 @@ class FirstTVIE(InfoExtractor): 'duration': int_or_none(duration), 'like_count': int_or_none(like_count), 'dislike_count': int_or_none(dislike_count), - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index 3a50bab5c..f9c127ce6 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -50,7 +50,7 @@ class FiveMinIE(InfoExtractor): video_id = mobj.group('id') embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed page') + 'Downloading embed page') sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid') query = compat_urllib_parse.urlencode({ 'func': 'GetResults', diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index d7048c8c1..d09d1c13a 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,25 +1,27 @@ +from __future__ import unicode_literals + import re import random import json from .common import InfoExtractor from ..utils import ( - determine_ext, get_element_by_id, clean_html, ) class FKTVIE(InfoExtractor): - IE_NAME = u'fernsehkritik.tv' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' + IE_NAME = 'fernsehkritik.tv' + _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' _TEST = { - u'url': u'http://fernsehkritik.tv/folge-1', - u'file': u'00011.flv', - u'info_dict': { - u'title': u'Folge 1 vom 10. April 2007', - u'description': u'md5:fb4818139c7cfe6907d4b83412a6864f', + 'url': 'http://fernsehkritik.tv/folge-1', + 'info_dict': { + 'id': '00011', + 'ext': 'flv', + 'title': 'Folge 1 vom 10. April 2007', + 'description': 'md5:fb4818139c7cfe6907d4b83412a6864f', }, } @@ -30,9 +32,9 @@ class FKTVIE(InfoExtractor): server = random.randint(2, 4) video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode, - episode) + episode) playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage, - u'playlist', flags=re.DOTALL) + 'playlist', flags=re.DOTALL) files = json.loads(re.sub('{[^{}]*?}', '{}', playlist)) # TODO: return a single multipart video videos = [] @@ -42,7 +44,6 @@ class FKTVIE(InfoExtractor): videos.append({ 'id': video_id, 'url': video_url, - 'ext': determine_ext(video_url), 'title': clean_html(get_element_by_id('eptitle', start_webpage)), 'description': clean_html(get_element_by_id('contentlist', start_webpage)), 'thumbnail': video_thumbnail @@ -51,14 +52,15 @@ class FKTVIE(InfoExtractor): class FKTVPosteckeIE(InfoExtractor): - IE_NAME = u'fernsehkritik.tv:postecke' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' + IE_NAME = 'fernsehkritik.tv:postecke' + _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' _TEST = { - u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', - u'file': u'0120.flv', - u'md5': u'262f0adbac80317412f7e57b4808e5c4', - u'info_dict': { - u"title": u"Postecke 120" + 'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', + 'md5': '262f0adbac80317412f7e57b4808e5c4', + 'info_dict': { + 'id': '0120', + 'ext': 'flv', + 'title': 'Postecke 120', } } @@ -71,8 +73,7 @@ class FKTVPosteckeIE(InfoExtractor): video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode) video_title = 'Postecke %d' % episode return { - 'id': video_id, - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': video_title, + 'id': video_id, + 'url': video_url, + 'title': video_title, } diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 21ea5ec2b..0c858b654 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -10,15 +10,15 @@ from ..utils import ( class FlickrIE(InfoExtractor): - """Information Extractor for Flickr videos""" - _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' + _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' _TEST = { 'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', - 'file': '5645318632.mp4', 'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b', 'info_dict': { - "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", - "uploader_id": "forestwander-nature-pictures", + 'id': '5645318632', + 'ext': 'mp4', + "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", + "uploader_id": "forestwander-nature-pictures", "title": "Dark Hollow Waterfalls" } } @@ -37,7 +37,7 @@ class FlickrIE(InfoExtractor): first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage') node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>', - first_xml, 'node_id') + first_xml, 'node_id') second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage') @@ -49,12 +49,12 @@ class FlickrIE(InfoExtractor): raise ExtractorError('Unable to extract video url') video_url = mobj.group(1) + unescapeHTML(mobj.group(2)) - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': self._og_search_title(webpage), + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': self._og_search_title(webpage), 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), 'uploader_id': video_uploader_id, - }] + } diff --git a/youtube_dl/extractor/folketinget.py b/youtube_dl/extractor/folketinget.py new file mode 100644 index 000000000..68e2db943 --- /dev/null +++ b/youtube_dl/extractor/folketinget.py @@ -0,0 +1,75 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_parse_qs +from ..utils import ( + int_or_none, + parse_duration, + parse_iso8601, + xpath_text, +) + + +class FolketingetIE(InfoExtractor): + IE_DESC = 'Folketinget (ft.dk; Danish parliament)' + _VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx' + _TEST = { + 'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player', + 'info_dict': { + 'id': '1165642', + 'ext': 'mp4', + 'title': 'Åbent samråd i Erhvervsudvalget', + 'description': 'Åbent samråd med erhvervs- og vækstministeren om regeringens politik på teleområdet', + 'view_count': int, + 'width': 768, + 'height': 432, + 'tbr': 928000, + 'timestamp': 1416493800, + 'upload_date': '20141120', + 'duration': 3960, + }, + 'params': { + 'skip_download': 'rtmpdump required', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'(?s)<div class="video-item-agenda"[^>]*>(.*?)<', + webpage, 'description', fatal=False) + + player_params = compat_parse_qs(self._search_regex( + r'<embed src="http://ft\.arkena\.tv/flash/ftplayer\.swf\?([^"]+)"', + webpage, 'player params')) + xml_url = player_params['xml'][0] + doc = self._download_xml(xml_url, video_id) + + timestamp = parse_iso8601(xpath_text(doc, './/date')) + duration = parse_duration(xpath_text(doc, './/duration')) + width = int_or_none(xpath_text(doc, './/width')) + height = int_or_none(xpath_text(doc, './/height')) + view_count = int_or_none(xpath_text(doc, './/views')) + + formats = [{ + 'format_id': n.attrib['bitrate'], + 'url': xpath_text(n, './url', fatal=True), + 'tbr': int_or_none(n.attrib['bitrate']), + } for n in doc.findall('.//streams/stream')] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'timestamp': timestamp, + 'width': width, + 'height': height, + 'duration': duration, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index 7d56b9be9..b22ce2acb 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -55,7 +55,7 @@ class FourTubeIE(InfoExtractor): description = self._html_search_meta('description', webpage, 'description') if description: upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date', - fatal=False) + fatal=False) if upload_date: upload_date = unified_strdate(upload_date) view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False) @@ -65,9 +65,9 @@ class FourTubeIE(InfoExtractor): token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources)) headers = { - b'Content-Type': b'application/x-www-form-urlencoded', - b'Origin': b'http://www.4tube.com', - } + b'Content-Type': b'application/x-www-form-urlencoded', + b'Origin': b'http://www.4tube.com', + } token_req = compat_urllib_request.Request(token_url, b'{}', headers) tokens = self._download_json(token_req, video_id) @@ -76,7 +76,7 @@ class FourTubeIE(InfoExtractor): 'format_id': format + 'p', 'resolution': format + 'p', 'quality': int(format), - } for format in sources] + } for format in sources] self._sort_formats(formats) @@ -92,4 +92,4 @@ class FourTubeIE(InfoExtractor): 'duration': duration, 'age_limit': 18, 'webpage_url': webpage_url, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/foxgay.py b/youtube_dl/extractor/foxgay.py new file mode 100644 index 000000000..08b8ea362 --- /dev/null +++ b/youtube_dl/extractor/foxgay.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class FoxgayIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml' + _TEST = { + 'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml', + 'md5': '80d72beab5d04e1655a56ad37afe6841', + 'info_dict': { + 'id': '2582', + 'ext': 'mp4', + 'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a', + 'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf', + 'age_limit': 18, + 'thumbnail': 're:https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<title>(?P<title>.*?)</title>', + webpage, 'title', fatal=False) + description = self._html_search_regex( + r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>', + webpage, 'description', fatal=False) + + # Find the URL for the iFrame which contains the actual video. + iframe = self._download_webpage( + self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'), + video_id) + video_url = self._html_search_regex( + r"v_path = '(?P<vid>http://.*?)'", iframe, 'url') + thumb_url = self._html_search_regex( + r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'description': description, + 'thumbnail': thumb_url, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py new file mode 100644 index 000000000..917f76b1e --- /dev/null +++ b/youtube_dl/extractor/foxnews.py @@ -0,0 +1,94 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + int_or_none, +) + + +class FoxNewsIE(InfoExtractor): + _VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips', + 'md5': '32aaded6ba3ef0d1c04e238d01031e5e', + 'info_dict': { + 'id': '3937480', + 'ext': 'flv', + 'title': 'Frozen in Time', + 'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler', + 'duration': 265, + 'timestamp': 1304411491, + 'upload_date': '20110503', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips', + 'md5': '5846c64a1ea05ec78175421b8323e2df', + 'info_dict': { + 'id': '3922535568001', + 'ext': 'mp4', + 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal", + 'description': "Congressman discusses the president's executive action", + 'duration': 292, + 'timestamp': 1417662047, + 'upload_date': '20141204', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % video_id, video_id) + + item = video['channel']['item'] + title = item['title'] + description = item['description'] + timestamp = parse_iso8601(item['dc-date']) + + media_group = item['media-group'] + duration = None + formats = [] + for media in media_group['media-content']: + attributes = media['@attributes'] + video_url = attributes['url'] + if video_url.endswith('.f4m'): + formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id)) + elif video_url.endswith('.m3u8'): + formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv')) + elif not video_url.endswith('.smil'): + duration = int_or_none(attributes.get('duration')) + formats.append({ + 'url': video_url, + 'format_id': media['media-category']['@attributes']['label'], + 'preference': 1, + 'vbr': int_or_none(attributes.get('bitrate')), + 'filesize': int_or_none(attributes.get('fileSize')) + }) + self._sort_formats(formats) + + media_thumbnail = media_group['media-thumbnail']['@attributes'] + thumbnails = [{ + 'url': media_thumbnail['url'], + 'width': int_or_none(media_thumbnail.get('width')), + 'height': int_or_none(media_thumbnail.get('height')), + }] if media_thumbnail else [] + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'thumbnails': thumbnails, + } diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index deb1b0b9d..6613ee17a 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -4,16 +4,21 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import int_or_none class FranceInterIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})' + _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)' _TEST = { 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', - 'file': '793962.mp3', 'md5': '4764932e466e6f6c79c317d2e74f6884', "info_dict": { - "title": "L’Histoire dans les jeux vidéo", + 'id': '793962', + 'ext': 'mp3', + 'title': 'L’Histoire dans les jeux vidéo', + 'description': 'md5:7e93ddb4451e7530022792240a3049c7', + 'timestamp': 1387369800, + 'upload_date': '20131218', }, } @@ -22,17 +27,26 @@ class FranceInterIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - title = self._html_search_regex( - r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title') + path = self._search_regex( - r'&urlAOD=(.*?)&startTime', webpage, 'video url') + r'<a id="player".+?href="([^"]+)"', webpage, 'video url') video_url = 'http://www.franceinter.fr/' + path + title = self._html_search_regex( + r'<span class="title">(.+?)</span>', webpage, 'title') + description = self._html_search_regex( + r'<span class="description">(.*?)</span>', + webpage, 'description', fatal=False) + timestamp = int_or_none(self._search_regex( + r'data-date="(\d+)"', webpage, 'upload date', fatal=False)) + return { 'id': video_id, + 'title': title, + 'description': description, + 'timestamp': timestamp, 'formats': [{ 'url': video_url, 'vcodec': 'none', }], - 'title': title, } diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 1b0e8e5d5..e0420a48f 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -8,45 +8,85 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, + ExtractorError, + clean_html, + parse_duration, + compat_urllib_parse_urlparse, + int_or_none, ) class FranceTVBaseInfoExtractor(InfoExtractor): - def _extract_video(self, video_id): - info = self._download_xml( - 'http://www.francetvinfo.fr/appftv/webservices/video/' - 'getInfosOeuvre.php?id-diffusion=' - + video_id, video_id, 'Downloading XML config') - - manifest_url = info.find('videos/video/url').text - manifest_url = manifest_url.replace('/z/', '/i/') - - if manifest_url.startswith('rtmp'): - formats = [{'url': manifest_url, 'ext': 'flv'}] + def _extract_video(self, video_id, catalogue): + info = self._download_json( + 'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s' + % (video_id, catalogue), + video_id, 'Downloading video JSON') + + if info.get('status') == 'NOK': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True) + allowed_countries = info['videos'][0].get('geoblocage') + if allowed_countries: + georestricted = True + geo_info = self._download_json( + 'http://geo.francetv.fr/ws/edgescape.json', video_id, + 'Downloading geo restriction info') + country = geo_info['reponse']['geo_info']['country_code'] + if country not in allowed_countries: + raise ExtractorError( + 'The video is not available from your location', + expected=True) else: - formats = [] - available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats') - for index, format_descr in enumerate(available_formats.split(',')): - format_info = { - 'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index), - 'ext': 'mp4', - } - m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr) - if m_resolution is not None: - format_info.update({ - 'width': int(m_resolution.group('width')), - 'height': int(m_resolution.group('height')), - }) - formats.append(format_info) - - thumbnail_path = info.find('image').text + georestricted = False + + formats = [] + for video in info['videos']: + if video['statut'] != 'ONLINE': + continue + video_url = video['url'] + if not video_url: + continue + format_id = video['format'] + if video_url.endswith('.f4m'): + if georestricted: + # See https://github.com/rg3/youtube-dl/issues/3963 + # m3u8 urls work fine + continue + video_url_parsed = compat_urllib_parse_urlparse(video_url) + f4m_url = self._download_webpage( + 'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path, + video_id, 'Downloading f4m manifest token', fatal=False) + if f4m_url: + f4m_formats = self._extract_f4m_formats(f4m_url, video_id) + for f4m_format in f4m_formats: + f4m_format['preference'] = 1 + formats.extend(f4m_formats) + elif video_url.endswith('.m3u8'): + formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4')) + elif video_url.startswith('rtmp'): + formats.append({ + 'url': video_url, + 'format_id': 'rtmp-%s' % format_id, + 'ext': 'flv', + 'preference': 1, + }) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'preference': -1, + }) + self._sort_formats(formats) return { 'id': video_id, - 'title': info.find('titre').text, + 'title': info['titre'], + 'description': clean_html(info['synopsis']), + 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']), + 'duration': parse_duration(info['duree']), + 'timestamp': int_or_none(info['diffusion']['timestamp']), 'formats': formats, - 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), - 'description': info.find('synopsis').text, } @@ -61,7 +101,7 @@ class PluzzIE(FranceTVBaseInfoExtractor): webpage = self._download_webpage(url, title) video_id = self._search_regex( r'data-diffusion="(\d+)"', webpage, 'ID') - return self._extract_video(video_id) + return self._extract_video(video_id, 'Pluzz') class FranceTvInfoIE(FranceTVBaseInfoExtractor): @@ -72,11 +112,10 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', 'info_dict': { 'id': '84981923', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Soir 3', - }, - 'params': { - 'skip_download': True, + 'upload_date': '20130826', + 'timestamp': 1377548400, }, }, { 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html', @@ -88,15 +127,17 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): }, 'params': { 'skip_download': 'HLS (reqires ffmpeg)' - } + }, + 'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.', }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) - video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id') - return self._extract_video(video_id) + video_id, catalogue = self._search_regex( + r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@') + return self._extract_video(video_id, catalogue) class FranceTVIE(FranceTVBaseInfoExtractor): @@ -112,91 +153,77 @@ class FranceTVIE(FranceTVBaseInfoExtractor): # france2 { 'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', - 'file': '75540104.mp4', + 'md5': 'c03fc87cb85429ffd55df32b9fc05523', 'info_dict': { - 'title': '13h15, le samedi...', - 'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'id': '109169362', + 'ext': 'flv', + 'title': '13h15, le dimanche...', + 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7', + 'upload_date': '20140914', + 'timestamp': 1410693600, }, }, # france3 { 'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575', + 'md5': '679bb8f8921f8623bd658fa2f8364da0', 'info_dict': { 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Le scandale du prix des médicaments', 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce', - }, - 'params': { - # rtmp download - 'skip_download': True, + 'upload_date': '20131113', + 'timestamp': 1384380000, }, }, # france4 { 'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + 'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c', 'info_dict': { 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Hero Corp Making of - Extrait 1', 'description': 'md5:c87d54871b1790679aec1197e73d650a', - }, - 'params': { - # rtmp download - 'skip_download': True, + 'upload_date': '20131106', + 'timestamp': 1383766500, }, }, # france5 { 'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968', + 'md5': '78f0f4064f9074438e660785bbf2c5d9', 'info_dict': { - 'id': '92837968', - 'ext': 'mp4', + 'id': '108961659', + 'ext': 'flv', 'title': 'C à dire ?!', - 'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81', + 'upload_date': '20140915', + 'timestamp': 1410795000, }, }, # franceo { 'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013', + 'md5': '52f0bfe202848b15915a2f39aaa8981b', 'info_dict': { - 'id': '92327925', - 'ext': 'mp4', - 'title': 'Infô-Afrique', + 'id': '108634970', + 'ext': 'flv', + 'title': 'Infô Afrique', 'description': 'md5:ebf346da789428841bee0fd2a935ea55', + 'upload_date': '20140915', + 'timestamp': 1410822000, }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'skip': 'The id changes frequently', }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj.group('key'): - webpage = self._download_webpage(url, mobj.group('key')) - id_res = [ - (r'''(?x)<div\s+class="video-player">\s* - <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+ - class="francetv-video-player">'''), - (r'<a id="player_direct" href="http://info\.francetelevisions' - '\.fr/\?id-video=([^"/&]+)'), - (r'<a class="video" id="ftv_player_(.+?)"'), - ] - video_id = self._html_search_regex(id_res, webpage, 'video ID') - else: - video_id = mobj.group('id') - return self._extract_video(video_id) + webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id')) + video_id, catalogue = self._html_search_regex( + r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', + webpage, 'video ID').split('@') + return self._extract_video(video_id, catalogue) class GenerationQuoiIE(InfoExtractor): @@ -224,7 +251,7 @@ class GenerationQuoiIE(InfoExtractor): info_json = self._download_webpage(info_url, name) info = json.loads(info_json) return self.url_result('http://www.dailymotion.com/video/%s' % info['id'], - ie='Dailymotion') + ie='Dailymotion') class CultureboxIE(FranceTVBaseInfoExtractor): @@ -232,16 +259,15 @@ class CultureboxIE(FranceTVBaseInfoExtractor): _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' _TEST = { - 'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813', + 'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553', + 'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6', 'info_dict': { - 'id': 'EV_6785', - 'ext': 'mp4', - 'title': 'Einstein on the beach au Théâtre du Châtelet', - 'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'id': 'EV_22853', + 'ext': 'flv', + 'title': 'Dans les jardins de William Christie - Le Camus', + 'description': 'md5:4710c82315c40f0c865ca8b9a68b5299', + 'upload_date': '20140829', + 'timestamp': 1409317200, }, } @@ -249,5 +275,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') webpage = self._download_webpage(url, name) - video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id') - return self._extract_video(video_id) + video_id, catalogue = self._search_regex( + r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@') + + return self._extract_video(video_id, catalogue) diff --git a/youtube_dl/extractor/freevideo.py b/youtube_dl/extractor/freevideo.py new file mode 100644 index 000000000..f755e3c4a --- /dev/null +++ b/youtube_dl/extractor/freevideo.py @@ -0,0 +1,38 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class FreeVideoIE(InfoExtractor): + _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])' + + _TEST = { + 'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html', + 'info_dict': { + 'id': 'vysukany-zadecek-22033', + 'ext': 'mp4', + "title": "vysukany-zadecek-22033", + "age_limit": 18, + }, + 'skip': 'Blocked outside .cz', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage, handle = self._download_webpage_handle(url, video_id) + if '//www.czechav.com/' in handle.geturl(): + raise ExtractorError( + 'Access to freevideo is blocked from your location', + expected=True) + + video_url = self._search_regex( + r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"', + webpage, 'video URL') + + return { + 'id': video_id, + 'url': video_url, + 'title': video_id, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 721e5fce0..a49fc1151 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -8,7 +8,7 @@ from ..utils import ExtractorError class FunnyOrDieIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])' + _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|articles|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])' _TESTS = [{ 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', @@ -21,7 +21,6 @@ class FunnyOrDieIE(InfoExtractor): }, }, { 'url': 'http://www.funnyordie.com/embed/e402820827', - 'md5': 'ff4d83318f89776ed0250634cfaa8d36', 'info_dict': { 'id': 'e402820827', 'ext': 'mp4', @@ -29,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor): 'description': 'Please use this to sell something. www.jonlajoie.com', 'thumbnail': 're:^http:.*\.jpg$', }, + }, { + 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man', + 'only_matching': True, }] def _real_extract(self, url): @@ -37,7 +39,7 @@ class FunnyOrDieIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage) + links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage) if not links: raise ExtractorError('No media links available for %s' % video_id) diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index 11fee3d31..cf8e90d7d 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -11,7 +11,7 @@ class GamekingsIE(InfoExtractor): 'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/', # MD5 is flaky, seems to change regularly # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3', - u'info_dict': { + 'info_dict': { 'id': '20130811', 'ext': 'mp4', 'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review', diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py index b580f52fb..3022f539d 100644 --- a/youtube_dl/extractor/gameone.py +++ b/youtube_dl/extractor/gameone.py @@ -88,3 +88,28 @@ class GameOneIE(InfoExtractor): 'age_limit': age_limit, 'timestamp': timestamp, } + + +class GameOnePlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$' + IE_NAME = 'gameone:playlist' + _TEST = { + 'url': 'http://www.gameone.de/tv', + 'info_dict': { + 'title': 'GameOne', + }, + 'playlist_mincount': 294, + } + + def _real_extract(self, url): + webpage = self._download_webpage('http://www.gameone.de/tv', 'TV') + max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage))) + entries = [ + self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne') + for video_id in range(max_id, 0, -1)] + + return { + '_type': 'playlist', + 'title': 'GameOne', + 'entries': entries, + } diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 3d67b9d60..d570e3f6a 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -8,12 +8,11 @@ from ..utils import ( compat_urllib_parse, compat_urlparse, unescapeHTML, - get_meta_content, ) class GameSpotIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?' + _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?' _TEST = { 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -26,10 +25,10 @@ class GameSpotIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('page_id') + page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) - data_video_json = self._search_regex(r'data-video=["\'](.*?)["\']', webpage, 'data video') + data_video_json = self._search_regex( + r'data-video=["\'](.*?)["\']', webpage, 'data video') data_video = json.loads(unescapeHTML(data_video_json)) # Transform the manifest url to a link to the mp4 files @@ -41,7 +40,8 @@ class GameSpotIE(InfoExtractor): http_path = f4m_path[1:].split('/', 1)[1] http_template = re.sub(QUALITIES_RE, r'%s', http_path) http_template = http_template.replace('.csmil/manifest.f4m', '') - http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template) + http_template = compat_urlparse.urljoin( + 'http://video.gamespotcdn.com/', http_template) formats = [] for q in qualities: formats.append({ @@ -52,8 +52,9 @@ class GameSpotIE(InfoExtractor): return { 'id': data_video['guid'], + 'display_id': page_id, 'title': compat_urllib_parse.unquote(data_video['title']), 'formats': formats, - 'description': get_meta_content('description', webpage), + 'description': self._html_search_meta('description', webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index bcb076594..2b4d8c62f 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,25 +7,29 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE -from ..utils import ( - compat_urllib_error, +from ..compat import ( compat_urllib_parse, - compat_urllib_request, compat_urlparse, compat_xml_parse_error, - +) +from ..utils import ( + determine_ext, ExtractorError, + float_or_none, HEADRequest, + orderedSet, parse_xml, smuggle_url, unescapeHTML, unified_strdate, + unsmuggle_url, url_basename, ) from .brightcove import BrightcoveIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .smotri import SmotriIE +from .condenast import CondeNastIE class GenericIE(InfoExtractor): @@ -96,6 +100,22 @@ class GenericIE(InfoExtractor): 'uploader': 'Championat', }, }, + { + # https://github.com/rg3/youtube-dl/issues/3541 + 'add_ie': ['Brightcove'], + 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', + 'info_dict': { + 'id': '3866516442001', + 'ext': 'mp4', + 'title': 'Leer mij vrouwen kennen: Aflevering 1', + 'description': 'Leer mij vrouwen kennen: Aflevering 1', + 'uploader': 'SBS Broadcasting', + }, + 'skip': 'Restricted to Netherlands', + 'params': { + 'skip_download': True, # m3u8 download + }, + }, # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', @@ -153,7 +173,6 @@ class GenericIE(InfoExtractor): # funnyordie embed { 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns', - 'md5': '7cf780be104d40fea7bae52eed4a470e', 'info_dict': { 'id': '18e820ec3f', 'ext': 'mp4', @@ -178,13 +197,13 @@ class GenericIE(InfoExtractor): # Embedded TED video { 'url': 'http://en.support.wordpress.com/videos/ted-talks/', - 'md5': 'deeeabcc1085eb2ba205474e7235a3d5', + 'md5': '65fdff94098e4a607385a60c5177c638', 'info_dict': { - 'id': '981', + 'id': '1969', 'ext': 'mp4', - 'title': 'My web playroom', - 'uploader': 'Ze Frank', - 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b', + 'title': 'Hidden miracles of the natural world', + 'uploader': 'Louie Schwartzberg', + 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', } }, # Embeded Ustream video @@ -224,21 +243,6 @@ class GenericIE(InfoExtractor): 'skip_download': 'Requires rtmpdump' } }, - # smotri embed - { - 'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml', - 'md5': 'ec40048448e9284c9a1de77bb188108b', - 'info_dict': { - 'id': 'v27008541fad', - 'ext': 'mp4', - 'title': 'Крым и Севастополь вошли в состав России', - 'description': 'md5:fae01b61f68984c7bd2fa741e11c3175', - 'duration': 900, - 'upload_date': '20140318', - 'uploader': 'rbctv_2012_4', - 'uploader_id': 'rbctv_2012_4', - }, - }, # Condé Nast embed { 'url': 'http://www.wired.com/2014/04/honda-asimo/', @@ -289,70 +293,197 @@ class GenericIE(InfoExtractor): 'description': 'Mario\'s life in the fast lane has never looked so good.', }, }, + # YouTube embed via <data-embed-url=""> + { + 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', + 'info_dict': { + 'id': '4vAffPZIT44', + 'ext': 'mp4', + 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!', + 'uploader': 'Gameloft', + 'uploader_id': 'gameloft', + 'upload_date': '20140828', + 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4', + }, + 'params': { + 'skip_download': True, + } + }, + # Camtasia studio + { + 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/', + 'playlist': [{ + 'md5': '0c5e352edabf715d762b0ad4e6d9ee67', + 'info_dict': { + 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1', + 'ext': 'flv', + 'duration': 2235.90, + } + }, { + 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63', + 'info_dict': { + 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP', + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip', + 'ext': 'flv', + 'duration': 2235.93, + } + }], + 'info_dict': { + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', + } + }, + # Flowplayer + { + 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html', + 'md5': '9d65602bf31c6e20014319c7d07fba27', + 'info_dict': { + 'id': '5123ea6d5e5a7', + 'ext': 'mp4', + 'age_limit': 18, + 'uploader': 'www.handjobhub.com', + 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', + } + }, + # RSS feed + { + 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'info_dict': { + 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'title': 'Zero Punctuation', + 'description': 're:' + }, + 'playlist_mincount': 11, + }, + # Multiple brightcove videos + # https://github.com/rg3/youtube-dl/issues/2283 + { + 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', + 'info_dict': { + 'id': 'always-never', + 'title': 'Always / Never - The New Yorker', + }, + 'playlist_count': 3, + 'params': { + 'extract_flat': False, + 'skip_download': True, + } + }, + # MLB embed + { + 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/', + 'md5': '96f09a37e44da40dd083e12d9a683327', + 'info_dict': { + 'id': '33322633', + 'ext': 'mp4', + 'title': 'Ump changes call to ball', + 'description': 'md5:71c11215384298a172a6dcb4c2e20685', + 'duration': 48, + 'timestamp': 1401537900, + 'upload_date': '20140531', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + # Wistia embed + { + 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', + 'md5': '8788b683c777a5cf25621eaf286d0c23', + 'info_dict': { + 'id': '1cfaf6b7ea', + 'ext': 'mov', + 'title': 'md5:51364a8d3d009997ba99656004b5e20d', + 'duration': 643.0, + 'filesize': 182808282, + 'uploader': 'education-portal.com', + }, + }, + { + 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz', + 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4', + 'info_dict': { + 'id': 'uxjb0lwrcz', + 'ext': 'mp4', + 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', + 'duration': 1715.0, + 'uploader': 'thoughtworks.wistia.com', + }, + }, + # Direct download with broken HEAD + { + 'url': 'http://ai-radio.org:8000/radio.opus', + 'info_dict': { + 'id': 'radio', + 'ext': 'opus', + 'title': 'radio', + }, + 'params': { + 'skip_download': True, # infinite live stream + }, + 'expected_warnings': [ + r'501.*Not Implemented' + ], + }, + # Soundcloud embed + { + 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', + 'info_dict': { + 'id': '174391317', + 'ext': 'mp3', + 'description': 'md5:ff867d6b555488ad3c52572bb33d432c', + 'uploader': 'Sophos Security', + 'title': 'Chet Chat 171 - Oct 29, 2014', + 'upload_date': '20141029', + } + }, + # Livestream embed + { + 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast', + 'info_dict': { + 'id': '67864563', + 'ext': 'flv', + 'upload_date': '20141112', + 'title': 'Rosetta #CometLanding webcast HL 10', + } + }, + # LazyYT + { + 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986', + 'info_dict': { + 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse', + }, + 'playlist_mincount': 2, + }, + # Direct link with incorrect MIME type + { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'md5': '4ccbebe5f36706d85221f204d7eb5913', + 'info_dict': { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'id': '5_Lennart_Poettering_-_Systemd', + 'ext': 'webm', + 'title': '5_Lennart_Poettering_-_Systemd', + 'upload_date': '20141120', + }, + 'expected_warnings': [ + 'URL could be a direct video link, returning it as such.' + ] + }, + # Cinchcast embed + { + 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/', + 'info_dict': { + 'id': '7141703', + 'ext': 'mp3', + 'upload_date': '20141126', + 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing', + } + }, ] - def report_download_webpage(self, video_id): - """Report webpage download.""" - if not self._downloader.params.get('test', False): - self._downloader.report_warning('Falling back on generic information extractor.') - super(GenericIE, self).report_download_webpage(video_id) - def report_following_redirect(self, new_url): """Report information extraction.""" self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) - def _send_head(self, url): - """Check if it is a redirect, like url shorteners, in case return the new url.""" - - class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): - """ - Subclass the HTTPRedirectHandler to make it use our - HEADRequest also on the redirected URL - """ - def redirect_request(self, req, fp, code, msg, headers, newurl): - if code in (301, 302, 303, 307): - newurl = newurl.replace(' ', '%20') - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - try: - # This function was deprecated in python 3.3 and removed in 3.4 - origin_req_host = req.get_origin_req_host() - except AttributeError: - origin_req_host = req.origin_req_host - return HEADRequest(newurl, - headers=newheaders, - origin_req_host=origin_req_host, - unverifiable=True) - else: - raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) - - class HTTPMethodFallback(compat_urllib_request.BaseHandler): - """ - Fallback to GET if HEAD is not allowed (405 HTTP error) - """ - def http_error_405(self, req, fp, code, msg, headers): - fp.read() - fp.close() - - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - return self.parent.open(compat_urllib_request.Request(req.get_full_url(), - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True)) - - # Build our opener - opener = compat_urllib_request.OpenerDirector() - for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, - HTTPMethodFallback, HEADRedirectHandler, - compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: - opener.add_handler(handler()) - - response = opener.open(HEADRequest(url)) - if response is None: - raise ExtractorError('Invalid URL protocol') - return response - def _extract_rss(self, url, video_id, doc): playlist_title = doc.find('./channel/title').text playlist_desc_el = doc.find('./channel/description') @@ -372,6 +503,43 @@ class GenericIE(InfoExtractor): 'entries': entries, } + def _extract_camtasia(self, url, video_id, webpage): + """ Returns None if no camtasia video can be found. """ + + camtasia_cfg = self._search_regex( + r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);', + webpage, 'camtasia configuration file', default=None) + if camtasia_cfg is None: + return None + + title = self._html_search_meta('DC.title', webpage, fatal=True) + + camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg) + camtasia_cfg = self._download_xml( + camtasia_url, video_id, + note='Downloading camtasia configuration', + errnote='Failed to download camtasia configuration') + fileset_node = camtasia_cfg.find('./playlist/array/fileset') + + entries = [] + for n in fileset_node.getchildren(): + url_n = n.find('./uri') + if url_n is None: + continue + + entries.append({ + 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0], + 'title': '%s - %s' % (title, n.tag), + 'url': compat_urlparse.urljoin(url, url_n.text), + 'duration': float_or_none(n.find('./duration').text), + }) + + return { + '_type': 'playlist', + 'entries': entries, + 'title': title, + } + def _real_extract(self, url): if url.startswith('//'): return { @@ -402,53 +570,88 @@ class GenericIE(InfoExtractor): if default_search in ('error', 'fixup_error'): raise ExtractorError( - ('%r is not a valid URL. ' - 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' - ) % (url, url), expected=True) + '%r is not a valid URL. ' + 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' + % (url, url), expected=True) else: - assert ':' in default_search + if ':' not in default_search: + default_search += ':' return self.url_result(default_search + url) - video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] + + url, smuggled_data = unsmuggle_url(url) + force_videoid = None + is_intentional = smuggled_data and smuggled_data.get('to_generic') + if smuggled_data and 'force_videoid' in smuggled_data: + force_videoid = smuggled_data['force_videoid'] + video_id = force_videoid + else: + video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] self.to_screen('%s: Requesting header' % video_id) - try: - response = self._send_head(url) + head_req = HEADRequest(url) + head_response = self._request_webpage( + head_req, video_id, + note=False, errnote='Could not send HEAD request to %s' % url, + fatal=False) + if head_response is not False: # Check for redirect - new_url = response.geturl() + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) + if force_videoid: + new_url = smuggle_url( + new_url, {'force_videoid': force_videoid}) return self.url_result(new_url) - # Check for direct link to a video - content_type = response.headers.get('Content-Type', '') - m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) - if m: - upload_date = response.headers.get('Last-Modified') - if upload_date: - upload_date = unified_strdate(upload_date) - return { - 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], - 'formats': [{ - 'format_id': m.group('format_id'), - 'url': url, - 'vcodec': 'none' if m.group('type') == 'audio' else None - }], - 'upload_date': upload_date, - } + full_response = None + if head_response is False: + full_response = self._request_webpage(url, video_id) + head_response = full_response + + # Check for direct link to a video + content_type = head_response.headers.get('Content-Type', '') + m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) + if m: + upload_date = unified_strdate( + head_response.headers.get('Last-Modified')) + return { + 'id': video_id, + 'title': os.path.splitext(url_basename(url))[0], + 'direct': True, + 'formats': [{ + 'format_id': m.group('format_id'), + 'url': url, + 'vcodec': 'none' if m.group('type') == 'audio' else None + }], + 'upload_date': upload_date, + } - except compat_urllib_error.HTTPError: - # This may be a stupid server that doesn't like HEAD, our UA, or so - pass + if not self._downloader.params.get('test', False) and not is_intentional: + self._downloader.report_warning('Falling back on generic information extractor.') - try: - webpage = self._download_webpage(url, video_id) - except ValueError: - # since this is the last-resort InfoExtractor, if - # this error is thrown, it'll be thrown here - raise ExtractorError('Failed to download URL: %s' % url) + if not full_response: + full_response = self._request_webpage(url, video_id) + + # Maybe it's a direct link to a video? + # Be careful not to download the whole thing! + first_bytes = full_response.read(512) + if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')): + self._downloader.report_warning( + 'URL could be a direct video link, returning it as such.') + upload_date = unified_strdate( + head_response.headers.get('Last-Modified')) + return { + 'id': video_id, + 'title': os.path.splitext(url_basename(url))[0], + 'direct': True, + 'url': url, + 'upload_date': upload_date, + } + + webpage = self._webpage_read_content( + full_response, url, video_id, prefix=first_bytes) self.report_extraction(video_id) @@ -460,6 +663,11 @@ class GenericIE(InfoExtractor): except compat_xml_parse_error: pass + # Is it a Camtasia project? + camtasia_res = self._extract_camtasia(url, video_id, webpage) + if camtasia_res is not None: + return camtasia_res + # Sometimes embedded video player is hidden behind percent encoding # (e.g. https://github.com/rg3/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way @@ -475,10 +683,28 @@ class GenericIE(InfoExtractor): r'(?s)<title>(.*?)</title>', webpage, 'video title', default='video') + # Try to detect age limit automatically + age_limit = self._rta_search(webpage) + # And then there are the jokers who advertise that they use RTA, + # but actually don't. + AGE_LIMIT_MARKERS = [ + r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>', + ] + if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): + age_limit = 18 + # video uploader is domain name video_uploader = self._search_regex( r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') + # Helper method + def _playlist_from_matches(matches, getter, ie=None): + urlrs = orderedSet( + self.url_result(self._proto_relative_url(getter(m)), ie) + for m in matches) + return self.playlist_result( + urlrs, playlist_id=video_id, playlist_title=video_title) + # Look for BrightCove: bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) if bc_urls: @@ -502,58 +728,85 @@ class GenericIE(InfoExtractor): if mobj: player_url = unescapeHTML(mobj.group('url')) surl = smuggle_url(player_url, {'Referer': url}) - return self.url_result(surl, 'Vimeo') + return self.url_result(surl) # Look for embedded (swf embed) Vimeo player mobj = re.search( - r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) + r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) if mobj: - return self.url_result(mobj.group(1), 'Vimeo') + return self.url_result(mobj.group(1)) # Look for embedded YouTube player matches = re.findall(r'''(?x) (?: <iframe[^>]+?src=| + data-video-url=| <embed[^>]+?src=| - embedSWF\(?:\s* + embedSWF\(?:\s*| + new\s+SWFObject\( ) (["\']) - (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/ - (?:embed|v)/.+?) + (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ + (?:embed|v|p)/.+?) \1''', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') - for tuppl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, lambda m: unescapeHTML(m[1])) + + # Look for lazyYT YouTube embed + matches = re.findall( + r'class="lazyYT" data-youtube-id="([^"]+)"', webpage) + if matches: + return _playlist_from_matches(matches, lambda m: unescapeHTML(m)) # Look for embedded Dailymotion player matches = re.findall( r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(tuppl[1])) - for tuppl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, lambda m: unescapeHTML(m[1])) + + # Look for embedded Dailymotion playlist player (#3822) + m = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage) + if m: + playlists = re.findall( + r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url'))) + if playlists: + return _playlist_from_matches( + playlists, lambda p: '//dailymotion.com/playlist/%s' % p) # Look for embedded Wistia player match = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) if match: + embed_url = self._proto_relative_url( + unescapeHTML(match.group('url'))) return { '_type': 'url_transparent', - 'url': unescapeHTML(match.group('url')), + 'url': embed_url, 'ie_key': 'Wistia', 'uploader': video_uploader, 'title': video_title, 'id': video_id, } + match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) + if match: + return { + '_type': 'url_transparent', + 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), + 'ie_key': 'Wistia', + 'uploader': video_uploader, + 'title': video_title, + 'id': match.group('id') + } + # Look for embedded blip.tv player mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) if mobj: - return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage) + return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV') + mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) if mobj: return self.url_result(mobj.group(1), 'BlipTV') @@ -588,7 +841,7 @@ class GenericIE(InfoExtractor): # Look for Ooyala videos mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or - re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)) + re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)) if mobj is not None: return OoyalaIE._build_url_result(mobj.group('ec')) @@ -648,10 +901,8 @@ class GenericIE(InfoExtractor): # Look for funnyordie embed matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie') - for eurl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, getter=unescapeHTML, ie='FunnyOrDie') # Look for embedded RUTV player rutv_url = RUTVIE._extract_url(webpage) @@ -684,7 +935,7 @@ class GenericIE(InfoExtractor): # Look for embeded soundcloud player mobj = re.search( - r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', + r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', webpage) if mobj is not None: url = unescapeHTML(mobj.group('url')) @@ -706,40 +957,97 @@ class GenericIE(InfoExtractor): url = unescapeHTML(mobj.group('url')) return self.url_result(url, ie='MTVServicesEmbedded') + # Look for embedded yahoo player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Yahoo') + + # Look for embedded sbs.com.au player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'SBS') + + # Look for embedded Cinchcast player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Cinchcast') + + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'MLB') + + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL, + webpage) + if mobj is not None: + return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast') + + mobj = re.search( + r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Livestream') + + def check_video(vurl): + vpath = compat_urlparse.urlparse(vurl).path + vext = determine_ext(vpath) + return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') + + def filter_video(urls): + return list(filter(check_video, urls)) + # Start with something easy: JW Player in SWFObject - found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) + found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)) if not found: # Look for gorilla-vid style embedding - found = re.findall(r'''(?sx) + found = filter_video(re.findall(r'''(?sx) (?: jw_plugins| JWPlayerOptions| jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup ) - .*?file\s*:\s*["\'](.*?)["\']''', webpage) + .*?file\s*:\s*["\'](.*?)["\']''', webpage)) if not found: # Broaden the search a little bit - found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) + found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)) if not found: # Broaden the findall a little bit: JWPlayer JS loader - found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage) + found = filter_video(re.findall( + r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)) + if not found: + # Flow player + found = filter_video(re.findall(r'''(?xs) + flowplayer\("[^"]+",\s* + \{[^}]+?\}\s*, + \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s* + ["']?url["']?\s*:\s*["']([^"']+)["'] + ''', webpage)) if not found: # Try to find twitter cards info - found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) + found = filter_video(re.findall( + r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)) if not found: # We look for Open Graph info: # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am) m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage) # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: if m_video_type is not None: - found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) + found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)) if not found: # HTML5 video - found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage) + found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage) if not found: found = re.search( r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' - r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"', + r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)', webpage) if found: new_url = found.group(1) @@ -769,6 +1077,7 @@ class GenericIE(InfoExtractor): 'url': video_url, 'uploader': video_uploader, 'title': video_title, + 'age_limit': age_limit, }) if len(entries) == 1: @@ -780,4 +1089,3 @@ class GenericIE(InfoExtractor): '_type': 'playlist', 'entries': entries, } - diff --git a/youtube_dl/extractor/giantbomb.py b/youtube_dl/extractor/giantbomb.py new file mode 100644 index 000000000..87cd19147 --- /dev/null +++ b/youtube_dl/extractor/giantbomb.py @@ -0,0 +1,81 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + unescapeHTML, + qualities, + int_or_none, +) + + +class GiantBombIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)' + _TEST = { + 'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/', + 'md5': '57badeface303ecf6b98b812de1b9018', + 'info_dict': { + 'id': '2300-9782', + 'display_id': 'quick-look-destiny-the-dark-below', + 'ext': 'mp4', + 'title': 'Quick Look: Destiny: The Dark Below', + 'description': 'md5:0aa3aaf2772a41b91d44c63f30dfad24', + 'duration': 2399, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + video = json.loads(unescapeHTML(self._search_regex( + r'data-video="([^"]+)"', webpage, 'data-video'))) + + duration = int_or_none(video.get('lengthSeconds')) + + quality = qualities([ + 'f4m_low', 'progressive_low', 'f4m_high', + 'progressive_high', 'f4m_hd', 'progressive_hd']) + + formats = [] + for format_id, video_url in video['videoStreams'].items(): + if format_id == 'f4m_stream': + continue + if video_url.endswith('.f4m'): + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.3.1', display_id) + if f4m_formats: + f4m_formats[0]['quality'] = quality(format_id) + formats.extend(f4m_formats) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'quality': quality(format_id), + }) + + if not formats: + youtube_id = video.get('youtubeID') + if youtube_id: + return self.url_result(youtube_id, 'Youtube') + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/glide.py b/youtube_dl/extractor/glide.py new file mode 100644 index 000000000..9561ed5fb --- /dev/null +++ b/youtube_dl/extractor/glide.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class GlideIE(InfoExtractor): + IE_DESC = 'Glide mobile video messages (glide.me)' + _VALID_URL = r'https?://share\.glide\.me/(?P<id>[A-Za-z0-9\-=_+]+)' + _TEST = { + 'url': 'http://share.glide.me/UZF8zlmuQbe4mr+7dCiQ0w==', + 'md5': '4466372687352851af2d131cfaa8a4c7', + 'info_dict': { + 'id': 'UZF8zlmuQbe4mr+7dCiQ0w==', + 'ext': 'mp4', + 'title': 'Damon Timm\'s Glide message', + 'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<title>(.*?)</title>', webpage, 'title') + video_url = self.http_scheme() + self._search_regex( + r'<source src="(.*?)" type="video/mp4">', webpage, 'video URL') + thumbnail_url = self._search_regex( + r'<img id="video-thumbnail" src="(.*?)"', + webpage, 'thumbnail url', fatal=False) + thumbnail = ( + thumbnail_url if thumbnail_url is None + else self.http_scheme() + thumbnail_url) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py new file mode 100644 index 000000000..6949a57c7 --- /dev/null +++ b/youtube_dl/extractor/globo.py @@ -0,0 +1,400 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import random +import math + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_chr, + compat_ord, +) +from ..utils import ( + ExtractorError, + float_or_none, +) + + +class GloboIE(InfoExtractor): + _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)' + + _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist' + _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=2.9.9.50&resource_id=%s' + + _VIDEOID_REGEXES = [ + r'\bdata-video-id="(\d+)"', + r'\bdata-player-videosids="(\d+)"', + r'<div[^>]+\bid="(\d+)"', + ] + + _RESIGN_EXPIRATION = 86400 + + _TESTS = [ + { + 'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/', + 'md5': '03ebf41cb7ade43581608b7d9b71fab0', + 'info_dict': { + 'id': '3654973', + 'ext': 'mp4', + 'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão', + 'duration': 251.585, + 'uploader': 'SporTV', + 'uploader_id': 698, + 'like_count': int, + } + }, + { + 'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/', + 'md5': 'b3ccc801f75cd04a914d51dadb83a78d', + 'info_dict': { + 'id': '3607726', + 'ext': 'mp4', + 'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa', + 'duration': 103.204, + 'uploader': 'Globo.com', + 'uploader_id': 265, + 'like_count': int, + } + }, + { + 'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html', + 'md5': '307fdeae4390ccfe6ba1aa198cf6e72b', + 'info_dict': { + 'id': '3652183', + 'ext': 'mp4', + 'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião', + 'duration': 110.711, + 'uploader': 'Rede Globo', + 'uploader_id': 196, + 'like_count': int, + } + }, + ] + + class MD5(): + HEX_FORMAT_LOWERCASE = 0 + HEX_FORMAT_UPPERCASE = 1 + BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = '' + BASE64_PAD_CHARACTER_RFC_COMPLIANCE = '=' + PADDING = '=0xFF01DD' + hexcase = 0 + b64pad = '' + + def __init__(self): + pass + + class JSArray(list): + def __getitem__(self, y): + try: + return list.__getitem__(self, y) + except IndexError: + return 0 + + def __setitem__(self, i, y): + try: + return list.__setitem__(self, i, y) + except IndexError: + self.extend([0] * (i - len(self) + 1)) + self[-1] = y + + @classmethod + def hex_md5(cls, param1): + return cls.rstr2hex(cls.rstr_md5(cls.str2rstr_utf8(param1))) + + @classmethod + def b64_md5(cls, param1, param2=None): + return cls.rstr2b64(cls.rstr_md5(cls.str2rstr_utf8(param1, param2))) + + @classmethod + def any_md5(cls, param1, param2): + return cls.rstr2any(cls.rstr_md5(cls.str2rstr_utf8(param1)), param2) + + @classmethod + def rstr_md5(cls, param1): + return cls.binl2rstr(cls.binl_md5(cls.rstr2binl(param1), len(param1) * 8)) + + @classmethod + def rstr2hex(cls, param1): + _loc_2 = '0123456789ABCDEF' if cls.hexcase else '0123456789abcdef' + _loc_3 = '' + for _loc_5 in range(0, len(param1)): + _loc_4 = compat_ord(param1[_loc_5]) + _loc_3 += _loc_2[_loc_4 >> 4 & 15] + _loc_2[_loc_4 & 15] + return _loc_3 + + @classmethod + def rstr2b64(cls, param1): + _loc_2 = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_' + _loc_3 = '' + _loc_4 = len(param1) + for _loc_5 in range(0, _loc_4, 3): + _loc_6_1 = compat_ord(param1[_loc_5]) << 16 + _loc_6_2 = compat_ord(param1[_loc_5 + 1]) << 8 if _loc_5 + 1 < _loc_4 else 0 + _loc_6_3 = compat_ord(param1[_loc_5 + 2]) if _loc_5 + 2 < _loc_4 else 0 + _loc_6 = _loc_6_1 | _loc_6_2 | _loc_6_3 + for _loc_7 in range(0, 4): + if _loc_5 * 8 + _loc_7 * 6 > len(param1) * 8: + _loc_3 += cls.b64pad + else: + _loc_3 += _loc_2[_loc_6 >> 6 * (3 - _loc_7) & 63] + return _loc_3 + + @staticmethod + def rstr2any(param1, param2): + _loc_3 = len(param2) + _loc_4 = [] + _loc_9 = [0] * ((len(param1) >> 2) + 1) + for _loc_5 in range(0, len(_loc_9)): + _loc_9[_loc_5] = compat_ord(param1[_loc_5 * 2]) << 8 | compat_ord(param1[_loc_5 * 2 + 1]) + + while len(_loc_9) > 0: + _loc_8 = [] + _loc_7 = 0 + for _loc_5 in range(0, len(_loc_9)): + _loc_7 = (_loc_7 << 16) + _loc_9[_loc_5] + _loc_6 = math.floor(_loc_7 / _loc_3) + _loc_7 -= _loc_6 * _loc_3 + if len(_loc_8) > 0 or _loc_6 > 0: + _loc_8[len(_loc_8)] = _loc_6 + + _loc_4[len(_loc_4)] = _loc_7 + _loc_9 = _loc_8 + + _loc_10 = '' + _loc_5 = len(_loc_4) - 1 + while _loc_5 >= 0: + _loc_10 += param2[_loc_4[_loc_5]] + _loc_5 -= 1 + + return _loc_10 + + @classmethod + def str2rstr_utf8(cls, param1, param2=None): + _loc_3 = '' + _loc_4 = -1 + if not param2: + param2 = cls.PADDING + param1 = param1 + param2[1:9] + while True: + _loc_4 += 1 + if _loc_4 >= len(param1): + break + _loc_5 = compat_ord(param1[_loc_4]) + _loc_6 = compat_ord(param1[_loc_4 + 1]) if _loc_4 + 1 < len(param1) else 0 + if 55296 <= _loc_5 <= 56319 and 56320 <= _loc_6 <= 57343: + _loc_5 = 65536 + ((_loc_5 & 1023) << 10) + (_loc_6 & 1023) + _loc_4 += 1 + if _loc_5 <= 127: + _loc_3 += compat_chr(_loc_5) + continue + if _loc_5 <= 2047: + _loc_3 += compat_chr(192 | _loc_5 >> 6 & 31) + compat_chr(128 | _loc_5 & 63) + continue + if _loc_5 <= 65535: + _loc_3 += compat_chr(224 | _loc_5 >> 12 & 15) + compat_chr(128 | _loc_5 >> 6 & 63) + compat_chr( + 128 | _loc_5 & 63) + continue + if _loc_5 <= 2097151: + _loc_3 += compat_chr(240 | _loc_5 >> 18 & 7) + compat_chr(128 | _loc_5 >> 12 & 63) + compat_chr( + 128 | _loc_5 >> 6 & 63) + compat_chr(128 | _loc_5 & 63) + return _loc_3 + + @staticmethod + def rstr2binl(param1): + _loc_2 = [0] * ((len(param1) >> 2) + 1) + for _loc_3 in range(0, len(_loc_2)): + _loc_2[_loc_3] = 0 + for _loc_3 in range(0, len(param1) * 8, 8): + _loc_2[_loc_3 >> 5] |= (compat_ord(param1[_loc_3 // 8]) & 255) << _loc_3 % 32 + return _loc_2 + + @staticmethod + def binl2rstr(param1): + _loc_2 = '' + for _loc_3 in range(0, len(param1) * 32, 8): + _loc_2 += compat_chr(param1[_loc_3 >> 5] >> _loc_3 % 32 & 255) + return _loc_2 + + @classmethod + def binl_md5(cls, param1, param2): + param1 = cls.JSArray(param1) + param1[param2 >> 5] |= 128 << param2 % 32 + param1[(param2 + 64 >> 9 << 4) + 14] = param2 + _loc_3 = 1732584193 + _loc_4 = -271733879 + _loc_5 = -1732584194 + _loc_6 = 271733878 + for _loc_7 in range(0, len(param1), 16): + _loc_8 = _loc_3 + _loc_9 = _loc_4 + _loc_10 = _loc_5 + _loc_11 = _loc_6 + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 0], 7, -680876936) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 1], 12, -389564586) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 2], 17, 606105819) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 3], 22, -1044525330) + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 4], 7, -176418897) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 5], 12, 1200080426) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 6], 17, -1473231341) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 7], 22, -45705983) + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 8], 7, 1770035416) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 9], 12, -1958414417) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 10], 17, -42063) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 11], 22, -1990404162) + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 12], 7, 1804603682) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 13], 12, -40341101) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 14], 17, -1502002290) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 15], 22, 1236535329) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 1], 5, -165796510) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 6], 9, -1069501632) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 11], 14, 643717713) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 0], 20, -373897302) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 5], 5, -701558691) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 10], 9, 38016083) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 15], 14, -660478335) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 4], 20, -405537848) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 9], 5, 568446438) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 14], 9, -1019803690) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 3], 14, -187363961) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 8], 20, 1163531501) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 13], 5, -1444681467) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 2], 9, -51403784) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 7], 14, 1735328473) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 12], 20, -1926607734) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 5], 4, -378558) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 8], 11, -2022574463) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 11], 16, 1839030562) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 14], 23, -35309556) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 1], 4, -1530992060) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 4], 11, 1272893353) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 7], 16, -155497632) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 10], 23, -1094730640) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 13], 4, 681279174) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 0], 11, -358537222) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 3], 16, -722521979) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 6], 23, 76029189) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 9], 4, -640364487) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 12], 11, -421815835) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 15], 16, 530742520) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 2], 23, -995338651) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 0], 6, -198630844) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 7], 10, 1126891415) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 14], 15, -1416354905) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 5], 21, -57434055) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 12], 6, 1700485571) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 3], 10, -1894986606) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 10], 15, -1051523) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 1], 21, -2054922799) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 8], 6, 1873313359) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 15], 10, -30611744) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 6], 15, -1560198380) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 13], 21, 1309151649) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 4], 6, -145523070) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 11], 10, -1120210379) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 2], 15, 718787259) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 9], 21, -343485551) + _loc_3 = cls.safe_add(_loc_3, _loc_8) + _loc_4 = cls.safe_add(_loc_4, _loc_9) + _loc_5 = cls.safe_add(_loc_5, _loc_10) + _loc_6 = cls.safe_add(_loc_6, _loc_11) + return [_loc_3, _loc_4, _loc_5, _loc_6] + + @classmethod + def md5_cmn(cls, param1, param2, param3, param4, param5, param6): + return cls.safe_add( + cls.bit_rol(cls.safe_add(cls.safe_add(param2, param1), cls.safe_add(param4, param6)), param5), param3) + + @classmethod + def md5_ff(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param2 & param3 | ~param2 & param4, param1, param2, param5, param6, param7) + + @classmethod + def md5_gg(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param2 & param4 | param3 & ~param4, param1, param2, param5, param6, param7) + + @classmethod + def md5_hh(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param2 ^ param3 ^ param4, param1, param2, param5, param6, param7) + + @classmethod + def md5_ii(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param3 ^ (param2 | ~param4), param1, param2, param5, param6, param7) + + @classmethod + def safe_add(cls, param1, param2): + _loc_3 = (param1 & 65535) + (param2 & 65535) + _loc_4 = (param1 >> 16) + (param2 >> 16) + (_loc_3 >> 16) + return cls.lshift(_loc_4, 16) | _loc_3 & 65535 + + @classmethod + def bit_rol(cls, param1, param2): + return cls.lshift(param1, param2) | (param1 & 0xFFFFFFFF) >> (32 - param2) + + @staticmethod + def lshift(value, count): + r = (0xFFFFFFFF & value) << count + return -(~(r - 1) & 0xFFFFFFFF) if r > 0x7FFFFFFF else r + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id') + + video = self._download_json( + self._API_URL_TEMPLATE % video_id, video_id)['videos'][0] + + title = video['title'] + duration = float_or_none(video['duration'], 1000) + like_count = video['likes'] + uploader = video['channel'] + uploader_id = video['channel_id'] + + formats = [] + + for resource in video['resources']: + resource_id = resource.get('_id') + if not resource_id: + continue + + security = self._download_json( + self._SECURITY_URL_TEMPLATE % (video_id, resource_id), + video_id, 'Downloading security hash for %s' % resource_id) + + security_hash = security.get('hash') + if not security_hash: + message = security.get('message') + if message: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, message), expected=True) + continue + + hash_code = security_hash[:2] + received_time = int(security_hash[2:12]) + received_random = security_hash[12:22] + received_md5 = security_hash[22:] + + sign_time = received_time + self._RESIGN_EXPIRATION + padding = '%010d' % random.randint(1, 10000000000) + + signed_md5 = self.MD5.b64_md5(received_md5 + compat_str(sign_time) + padding) + signed_hash = hash_code + compat_str(received_time) + received_random + compat_str(sign_time) + padding + signed_md5 + + formats.append({ + 'url': '%s?h=%s&k=%s' % (resource['url'], signed_hash, 'flash'), + 'format_id': resource_id, + 'height': resource['height'] + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'like_count': like_count, + 'formats': formats + } diff --git a/youtube_dl/extractor/godtube.py b/youtube_dl/extractor/godtube.py index 73bd6d890..363dc6608 100644 --- a/youtube_dl/extractor/godtube.py +++ b/youtube_dl/extractor/godtube.py @@ -36,16 +36,16 @@ class GodTubeIE(InfoExtractor): 'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(), video_id, 'Downloading player config XML') - video_url = config.find('.//file').text - uploader = config.find('.//author').text - timestamp = parse_iso8601(config.find('.//date').text) - duration = parse_duration(config.find('.//duration').text) - thumbnail = config.find('.//image').text + video_url = config.find('file').text + uploader = config.find('author').text + timestamp = parse_iso8601(config.find('date').text) + duration = parse_duration(config.find('duration').text) + thumbnail = config.find('image').text media = self._download_xml( 'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML') - title = media.find('.//title').text + title = media.find('title').text return { 'id': video_id, diff --git a/youtube_dl/extractor/goldenmoustache.py b/youtube_dl/extractor/goldenmoustache.py new file mode 100644 index 000000000..0fb509724 --- /dev/null +++ b/youtube_dl/extractor/goldenmoustache.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class GoldenMoustacheIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/', + 'md5': '0f904432fa07da5054d6c8beb5efb51a', + 'info_dict': { + 'id': '3700', + 'ext': 'mp4', + 'title': 'Suricate - Le Poker', + 'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, { + 'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/', + 'md5': '27f0c50fb4dd5f01dc9082fc67cd5700', + 'info_dict': { + 'id': '55249', + 'ext': 'mp4', + 'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)', + 'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a', + 'thumbnail': 're:^https?://.*\.(?:png|jpg)$', + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL') + title = self._html_search_regex( + r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/golem.py b/youtube_dl/extractor/golem.py new file mode 100644 index 000000000..53714f47f --- /dev/null +++ b/youtube_dl/extractor/golem.py @@ -0,0 +1,69 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + determine_ext, +) + + +class GolemIE(InfoExtractor): + _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/' + _TEST = { + 'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html', + 'md5': 'c1a2c0a3c863319651c7c992c5ee29bf', + 'info_dict': { + 'id': '14095', + 'format_id': 'high', + 'ext': 'mp4', + 'title': 'iPhone 6 und 6 Plus - Test', + 'duration': 300.44, + 'filesize': 65309548, + } + } + + _PREFIX = 'http://video.golem.de' + + def _real_extract(self, url): + video_id = self._match_id(url) + + config = self._download_xml( + 'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id) + + info = { + 'id': video_id, + 'title': config.findtext('./title', 'golem'), + 'duration': self._float(config.findtext('./playtime'), 'duration'), + } + + formats = [] + for e in config: + url = e.findtext('./url') + if not url: + continue + + formats.append({ + 'format_id': e.tag, + 'url': compat_urlparse.urljoin(self._PREFIX, url), + 'height': self._int(e.get('height'), 'height'), + 'width': self._int(e.get('width'), 'width'), + 'filesize': self._int(e.findtext('filesize'), 'filesize'), + 'ext': determine_ext(e.findtext('./filename')), + }) + self._sort_formats(formats) + info['formats'] = formats + + thumbnails = [] + for e in config.findall('.//teaser'): + url = e.findtext('./url') + if not url: + continue + thumbnails.append({ + 'url': compat_urlparse.urljoin(self._PREFIX, url), + 'width': self._int(e.get('width'), 'thumbnail width'), + 'height': self._int(e.get('height'), 'thumbnail height'), + }) + info['thumbnails'] = thumbnails + + return info diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py index 07d994b44..fcefe54cd 100644 --- a/youtube_dl/extractor/googleplus.py +++ b/youtube_dl/extractor/googleplus.py @@ -1,13 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import datetime import re +import codecs from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) +from ..utils import unified_strdate class GooglePlusIE(InfoExtractor): @@ -19,74 +17,57 @@ class GooglePlusIE(InfoExtractor): 'info_dict': { 'id': 'ZButuJc6CtH', 'ext': 'flv', + 'title': '嘆きの天使 降臨', 'upload_date': '20120613', 'uploader': '井上ヨシマサ', - 'title': '嘆きの天使 降臨', } } def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') + video_id = self._match_id(url) # Step 1, Retrieve post webpage to extract further information webpage = self._download_webpage(url, video_id, 'Downloading entry webpage') - self.report_extraction(video_id) - - # Extract update date - upload_date = self._html_search_regex( + title = self._og_search_description(webpage).splitlines()[0] + upload_date = unified_strdate(self._html_search_regex( r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*> ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''', - webpage, 'upload date', fatal=False, flags=re.VERBOSE) - if upload_date: - # Convert timestring to a format suitable for filename - upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") - upload_date = upload_date.strftime('%Y%m%d') - - # Extract uploader - uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>', - webpage, 'uploader', fatal=False) - - # Extract title - # Get the first line for title - video_title = self._og_search_description(webpage).splitlines()[0] + webpage, 'upload date', fatal=False, flags=re.VERBOSE)) + uploader = self._html_search_regex( + r'rel="author".*?>(.*?)</a>', webpage, 'uploader', fatal=False) # Step 2, Simulate clicking the image box to launch video DOMAIN = 'https://plus.google.com/' - video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN), + video_page = self._search_regex( + r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN), webpage, 'video page URL') if not video_page.startswith(DOMAIN): video_page = DOMAIN + video_page webpage = self._download_webpage(video_page, video_id, 'Downloading video page') - # Extract video links all sizes - pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' - mobj = re.findall(pattern, webpage) - if len(mobj) == 0: - raise ExtractorError('Unable to extract video links') - - # Sort in resolution - links = sorted(mobj) + def unicode_escape(s): + decoder = codecs.getdecoder('unicode_escape') + return re.sub( + r'\\u[0-9a-fA-F]{4,}', + lambda m: decoder(m.group(0))[0], + s) - # Choose the lowest of the sort, i.e. highest resolution - video_url = links[-1] - # Only get the url. The resolution part in the tuple has no use anymore - video_url = video_url[-1] - # Treat escaped \u0026 style hex - try: - video_url = video_url.decode("unicode_escape") - except AttributeError: # Python 3 - video_url = bytes(video_url, 'ascii').decode('unicode-escape') + # Extract video links all sizes + formats = [{ + 'url': unicode_escape(video_url), + 'ext': 'flv', + 'width': int(width), + 'height': int(height), + } for width, height, video_url in re.findall( + r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)] + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, + 'title': title, 'uploader': uploader, 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', + 'formats': formats, } diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index 383032d81..469e1f935 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -14,6 +14,14 @@ class GoogleSearchIE(SearchInfoExtractor): _MAX_RESULTS = 1000 IE_NAME = 'video.google:search' _SEARCH_KEY = 'gvsearch' + _TEST = { + 'url': 'gvsearch15:python language', + 'info_dict': { + 'id': 'python language', + 'title': 'python language', + }, + 'playlist_count': 15, + } def _get_n_results(self, query, n): """Get a specified number of results for a query""" diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py index ca5f7c417..1ac1da856 100644 --- a/youtube_dl/extractor/gorillavid.py +++ b/youtube_dl/extractor/gorillavid.py @@ -5,27 +5,31 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, determine_ext, compat_urllib_parse, compat_urllib_request, + int_or_none, ) class GorillaVidIE(InfoExtractor): - IE_DESC = 'GorillaVid.in and daclips.in' + IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in' _VALID_URL = r'''(?x) https?://(?P<host>(?:www\.)? - (?:daclips\.in|gorillavid\.in))/ + (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/ (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? ''' + _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<' + _TESTS = [{ 'url': 'http://gorillavid.in/06y9juieqpmi', 'md5': '5ae4a3580620380619678ee4875893ba', 'info_dict': { 'id': '06y9juieqpmi', 'ext': 'flv', - 'title': 'Rebecca Black My Moment Official Music Video Reaction', + 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', 'thumbnail': 're:http://.*\.jpg', }, }, { @@ -43,9 +47,22 @@ class GorillaVidIE(InfoExtractor): 'info_dict': { 'id': '3rso4kdn6f9m', 'ext': 'mp4', - 'title': 'Micro Pig piglets ready on 16th July 2009', + 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', + 'thumbnail': 're:http://.*\.jpg', + } + }, { + # video with countdown timeout + 'url': 'http://fastvideo.in/1qmdn1lmsmbw', + 'md5': '8b87ec3f6564a3108a0e8e66594842ba', + 'info_dict': { + 'id': '1qmdn1lmsmbw', + 'ext': 'mp4', + 'title': 'Man of Steel - Trailer', 'thumbnail': 're:http://.*\.jpg', }, + }, { + 'url': 'http://movpod.in/0wguyyxi1yca', + 'only_matching': True, }] def _real_extract(self, url): @@ -54,14 +71,23 @@ class GorillaVidIE(InfoExtractor): webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id) + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + fields = dict(re.findall(r'''(?x)<input\s+ type="hidden"\s+ name="([^"]+)"\s+ (?:id="[^"]+"\s+)? value="([^"]*)" ''', webpage)) - + if fields['op'] == 'download1': + countdown = int_or_none(self._search_regex( + r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>', + webpage, 'countdown', default=None)) + if countdown: + self._sleep(countdown, video_id) + post = compat_urllib_parse.urlencode(fields) req = compat_urllib_request.Request(url, post) @@ -69,14 +95,18 @@ class GorillaVidIE(InfoExtractor): webpage = self._download_webpage(req, video_id, 'Downloading video page') - title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title') - thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail') - url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url') + title = self._search_regex( + r'style="z-index: [0-9]+;">([^<]+)</span>', + webpage, 'title', default=None) or self._og_search_title(webpage) + video_url = self._search_regex( + r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url') + thumbnail = self._search_regex( + r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False) formats = [{ 'format_id': 'sd', - 'url': url, - 'ext': determine_ext(url), + 'url': video_url, + 'ext': determine_ext(video_url), 'quality': 1, }] diff --git a/youtube_dl/extractor/goshgay.py b/youtube_dl/extractor/goshgay.py index 7bca21ad0..b116d251d 100644 --- a/youtube_dl/extractor/goshgay.py +++ b/youtube_dl/extractor/goshgay.py @@ -1,73 +1,53 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, +) from ..utils import ( - compat_urlparse, - str_to_int, - ExtractorError, + parse_duration, ) -import json class GoshgayIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)www.goshgay.com/video(?P<id>\d+?)($|/)' + _VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)' _TEST = { - 'url': 'http://www.goshgay.com/video4116282', - 'md5': '268b9f3c3229105c57859e166dd72b03', + 'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video', + 'md5': '027fcc54459dff0feb0bc06a7aeda680', 'info_dict': { - 'id': '4116282', + 'id': '299069', 'ext': 'flv', - 'title': 'md5:089833a4790b5e103285a07337f245bf', - 'thumbnail': 're:http://.*\.jpg', + 'title': 'DIESEL SFW XXX Video', + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 79, 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title') - player_config = self._search_regex( - r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings') - player_vars = json.loads(player_config.replace("'", '"')) - width = str_to_int(player_vars.get('width')) - height = str_to_int(player_vars.get('height')) - config_uri = player_vars.get('config') + title = self._html_search_regex( + r'<h2>(.*?)<', webpage, 'title') + duration = parse_duration(self._html_search_regex( + r'<span class="duration">\s*-?\s*(.*?)</span>', + webpage, 'duration', fatal=False)) + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, default='false') - if config_uri is None: - raise ExtractorError('Missing config URI') - node = self._download_xml(config_uri, video_id, 'Downloading player config XML', - errnote='Unable to download XML') - if node is None: - raise ExtractorError('Missing config XML') - if node.tag != 'config': - raise ExtractorError('Missing config attribute') - fns = node.findall('file') - imgs = node.findall('image') - if len(fns) != 1: - raise ExtractorError('Missing media URI') - video_url = fns[0].text - if len(imgs) < 1: - thumbnail = None - else: - thumbnail = imgs[0].text - - url_comp = compat_urlparse.urlparse(url) - ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2]) + flashvars = compat_parse_qs(self._html_search_regex( + r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"', + webpage, 'flashvars')) + thumbnail = flashvars.get('url_bigthumb', [None])[0] + video_url = flashvars['flv_url'][0] return { 'id': video_id, 'url': video_url, 'title': title, - 'width': width, - 'height': height, 'thumbnail': thumbnail, - 'http_referer': ref, - 'age_limit': 18, + 'duration': duration, + 'age_limit': 0 if family_friendly == 'true' else 18, } diff --git a/youtube_dl/extractor/grooveshark.py b/youtube_dl/extractor/grooveshark.py new file mode 100644 index 000000000..fff74a70a --- /dev/null +++ b/youtube_dl/extractor/grooveshark.py @@ -0,0 +1,191 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import time +import math +import os.path +import re + + +from .common import InfoExtractor +from ..compat import ( + compat_html_parser, + compat_urllib_parse, + compat_urllib_request, + compat_urlparse, +) +from ..utils import ExtractorError + + +class GroovesharkHtmlParser(compat_html_parser.HTMLParser): + def __init__(self): + self._current_object = None + self.objects = [] + compat_html_parser.HTMLParser.__init__(self) + + def handle_starttag(self, tag, attrs): + attrs = dict((k, v) for k, v in attrs) + if tag == 'object': + self._current_object = {'attrs': attrs, 'params': []} + elif tag == 'param': + self._current_object['params'].append(attrs) + + def handle_endtag(self, tag): + if tag == 'object': + self.objects.append(self._current_object) + self._current_object = None + + @classmethod + def extract_object_tags(cls, html): + p = cls() + p.feed(html) + p.close() + return p.objects + + +class GroovesharkIE(InfoExtractor): + _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)' + _TEST = { + 'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5', + 'md5': '7ecf8aefa59d6b2098517e1baa530023', + 'info_dict': { + 'id': '6SS1DW', + 'title': 'Jolene (Tenth Key Remix ft. Will Sessions)', + 'ext': 'mp3', + 'duration': 227, + } + } + + do_playerpage_request = True + do_bootstrap_request = True + + def _parse_target(self, target): + uri = compat_urlparse.urlparse(target) + hash = uri.fragment[1:].split('?')[0] + token = os.path.basename(hash.rstrip('/')) + return (uri, hash, token) + + def _build_bootstrap_url(self, target): + (uri, hash, token) = self._parse_target(target) + query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts) + return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token) + + def _build_meta_url(self, target): + (uri, hash, token) = self._parse_target(target) + query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts) + return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token) + + def _build_stream_url(self, meta): + return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None)) + + def _build_swf_referer(self, target, obj): + (uri, _, _) = self._parse_target(target) + return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None)) + + def _transform_bootstrap(self, js): + return re.split('(?m)^\s*try\s*{', js)[0] \ + .split(' = ', 1)[1].strip().rstrip(';') + + def _transform_meta(self, js): + return js.split('\n')[0].split('=')[1].rstrip(';') + + def _get_meta(self, target): + (meta_url, token) = self._build_meta_url(target) + self.to_screen('Metadata URL: %s' % meta_url) + + headers = {'Referer': compat_urlparse.urldefrag(target)[0]} + req = compat_urllib_request.Request(meta_url, headers=headers) + res = self._download_json(req, token, + transform_source=self._transform_meta) + + if 'getStreamKeyWithSong' not in res: + raise ExtractorError( + 'Metadata not found. URL may be malformed, or Grooveshark API may have changed.') + + if res['getStreamKeyWithSong'] is None: + raise ExtractorError( + 'Metadata download failed, probably due to Grooveshark anti-abuse throttling. Wait at least an hour before retrying from this IP.', + expected=True) + + return res['getStreamKeyWithSong'] + + def _get_bootstrap(self, target): + (bootstrap_url, token) = self._build_bootstrap_url(target) + + headers = {'Referer': compat_urlparse.urldefrag(target)[0]} + req = compat_urllib_request.Request(bootstrap_url, headers=headers) + res = self._download_json(req, token, fatal=False, + note='Downloading player bootstrap data', + errnote='Unable to download player bootstrap data', + transform_source=self._transform_bootstrap) + return res + + def _get_playerpage(self, target): + (_, _, token) = self._parse_target(target) + + webpage = self._download_webpage( + target, token, + note='Downloading player page', + errnote='Unable to download player page', + fatal=False) + + if webpage is not None: + # Search (for example German) error message + error_msg = self._html_search_regex( + r'<div id="content">\s*<h2>(.*?)</h2>', webpage, + 'error message', default=None) + if error_msg is not None: + error_msg = error_msg.replace('\n', ' ') + raise ExtractorError('Grooveshark said: %s' % error_msg) + + if webpage is not None: + o = GroovesharkHtmlParser.extract_object_tags(webpage) + return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']) + + return (webpage, None) + + def _real_initialize(self): + self.ts = int(time.time() * 1000) # timestamp in millis + + def _real_extract(self, url): + (target_uri, _, token) = self._parse_target(url) + + # 1. Fill cookiejar by making a request to the player page + swf_referer = None + if self.do_playerpage_request: + (_, player_objs) = self._get_playerpage(url) + if player_objs is not None: + swf_referer = self._build_swf_referer(url, player_objs[0]) + self.to_screen('SWF Referer: %s' % swf_referer) + + # 2. Ask preload.php for swf bootstrap data to better mimic webapp + if self.do_bootstrap_request: + bootstrap = self._get_bootstrap(url) + self.to_screen('CommunicationToken: %s' % bootstrap['getCommunicationToken']) + + # 3. Ask preload.php for track metadata. + meta = self._get_meta(url) + + # 4. Construct stream request for track. + stream_url = self._build_stream_url(meta) + duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000)) + post_dict = {'streamKey': meta['streamKey']['streamKey']} + post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8') + headers = { + 'Content-Length': len(post_data), + 'Content-Type': 'application/x-www-form-urlencoded' + } + if swf_referer is not None: + headers['Referer'] = swf_referer + + return { + 'id': token, + 'title': meta['song']['Name'], + 'http_method': 'POST', + 'url': stream_url, + 'ext': 'mp3', + 'format': 'mp3 audio', + 'duration': duration, + 'http_post_data': post_data, + 'http_headers': headers, + } diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py index 5bdd08afa..b6cc15b6f 100644 --- a/youtube_dl/extractor/hark.py +++ b/youtube_dl/extractor/hark.py @@ -1,37 +1,33 @@ # -*- coding: utf-8 -*- - -import re -import json +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext + class HarkIE(InfoExtractor): - _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+' + _VALID_URL = r'https?://www\.hark\.com/clips/(?P<id>.+?)-.+' _TEST = { - u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', - u'file': u'mmbzyhkgny.mp3', - u'md5': u'6783a58491b47b92c7c1af5a77d4cbee', - u'info_dict': { - u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013", - u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', - u'duration': 11, + 'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', + 'md5': '6783a58491b47b92c7c1af5a77d4cbee', + 'info_dict': { + 'id': 'mmbzyhkgny', + 'ext': 'mp3', + 'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013', + 'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', + 'duration': 11, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) - json_url = "http://www.hark.com/clips/%s.json" %(video_id) - info_json = self._download_webpage(json_url, video_id) - info = json.loads(info_json) - final_url = info['url'] + video_id = self._match_id(url) + data = self._download_json( + 'http://www.hark.com/clips/%s.json' % video_id, video_id) - return {'id': video_id, - 'url' : final_url, - 'title': info['name'], - 'ext': determine_ext(final_url), - 'description': info['description'], - 'thumbnail': info['image_original'], - 'duration': info['duration'], - } + return { + 'id': video_id, + 'url': data['url'], + 'title': data['name'], + 'description': data.get('description'), + 'thumbnail': data.get('image_original'), + 'duration': data.get('duration'), + } diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py new file mode 100644 index 000000000..278d9f527 --- /dev/null +++ b/youtube_dl/extractor/heise.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + parse_iso8601, +) + + +class HeiseIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:www\.)?heise\.de/video/artikel/ + .+?(?P<id>[0-9]+)\.html(?:$|[?#]) + ''' + _TEST = { + 'url': ( + 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html' + ), + 'md5': 'ffed432483e922e88545ad9f2f15d30e', + 'info_dict': { + 'id': '2404147', + 'ext': 'mp4', + 'title': ( + "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone" + ), + 'format_id': 'mp4_720p', + 'timestamp': 1411812600, + 'upload_date': '20140927', + 'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.', + 'thumbnail': 're:^https?://.*\.jpe?g$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + container_id = self._search_regex( + r'<div class="videoplayerjw".*?data-container="([0-9]+)"', + webpage, 'container ID') + sequenz_id = self._search_regex( + r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"', + webpage, 'sequenz ID') + data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id) + doc = self._download_xml(data_url, video_id) + + info = { + 'id': video_id, + 'thumbnail': self._og_search_thumbnail(webpage), + 'timestamp': parse_iso8601( + self._html_search_meta('date', webpage)), + 'description': self._og_search_description(webpage), + } + + title = self._html_search_meta('fulltitle', webpage) + if title: + info['title'] = title + else: + info['title'] = self._og_search_title(webpage) + + formats = [] + for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'): + label = source_node.attrib['label'] + height = int_or_none(self._search_regex( + r'^(.*?_)?([0-9]+)p$', label, 'height', default=None)) + video_url = source_node.attrib['file'] + ext = determine_ext(video_url, '') + formats.append({ + 'url': video_url, + 'format_note': label, + 'format_id': '%s_%s' % (ext, label), + 'height': height, + }) + self._sort_formats(formats) + info['formats'] = formats + + return info diff --git a/youtube_dl/extractor/helsinki.py b/youtube_dl/extractor/helsinki.py index 5268efa49..93107b306 100644 --- a/youtube_dl/extractor/helsinki.py +++ b/youtube_dl/extractor/helsinki.py @@ -2,9 +2,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import js_to_json class HelsinkiIE(InfoExtractor): @@ -24,39 +23,21 @@ class HelsinkiIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - formats = [] - - mobj = re.search(r'file=((\w+):[^&]+)', webpage) - if mobj: - formats.append({ - 'ext': mobj.group(2), - 'play_path': mobj.group(1), - 'url': 'rtmp://flashvideo.it.helsinki.fi/vod/', - 'player_url': 'http://video.helsinki.fi/player.swf', - 'format_note': 'sd', - 'quality': 0, - }) - - mobj = re.search(r'hd\.file=((\w+):[^&]+)', webpage) - if mobj: - formats.append({ - 'ext': mobj.group(2), - 'play_path': mobj.group(1), - 'url': 'rtmp://flashvideo.it.helsinki.fi/vod/', - 'player_url': 'http://video.helsinki.fi/player.swf', - 'format_note': 'hd', - 'quality': 1, - }) + params = self._parse_json(self._html_search_regex( + r'(?s)jwplayer\("player"\).setup\((\{.*?\})\);', + webpage, 'player code'), video_id, transform_source=js_to_json) + formats = [{ + 'url': s['file'], + 'ext': 'mp4', + } for s in params['sources']] self._sort_formats(formats) return { 'id': video_id, 'title': self._og_search_title(webpage).replace('Video: ', ''), 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, } diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py new file mode 100644 index 000000000..5b6efb27e --- /dev/null +++ b/youtube_dl/extractor/hornbunny.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, +) + + +class HornBunnyIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html' + _TEST = { + 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html', + 'md5': '95e40865aedd08eff60272b704852ad7', + 'info_dict': { + 'id': '5227', + 'ext': 'flv', + 'title': 'panty slut jerk off instruction', + 'duration': 550, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage( + url, video_id, note='Downloading initial webpage') + title = self._html_search_regex( + r'class="title">(.*?)</h2>', webpage, 'title') + redirect_url = self._html_search_regex( + r'pg&settings=(.*?)\|0"\);', webpage, 'title') + webpage2 = self._download_webpage(redirect_url, video_id) + video_url = self._html_search_regex( + r'flvMask:(.*?);', webpage2, 'video_url') + + duration = parse_duration(self._search_regex( + r'<strong>Runtime:</strong>\s*([0-9:]+)</div>', + webpage, 'duration', fatal=False)) + view_count = int_or_none(self._search_regex( + r'<strong>Views:</strong>\s*(\d+)</div>', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': 'flv', + 'duration': duration, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py new file mode 100644 index 000000000..8e812b669 --- /dev/null +++ b/youtube_dl/extractor/hostingbulk.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + int_or_none, + urlencode_postdata, +) + + +class HostingBulkIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:www\.)?hostingbulk\.com/ + (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html''' + _FILE_DELETED_REGEX = r'<b>File Not Found</b>' + _TEST = { + 'url': 'http://hostingbulk.com/n0ulw1hv20fm.html', + 'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f', + 'info_dict': { + 'id': 'n0ulw1hv20fm', + 'ext': 'mp4', + 'title': 'md5:5afeba33f48ec87219c269e054afd622', + 'filesize': 6816081, + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://hostingbulk.com/{0:}.html'.format(video_id) + + # Custom request with cookie to set language to English, so our file + # deleted regex would work. + request = compat_urllib_request.Request( + url, headers={'Cookie': 'lang=english'}) + webpage = self._download_webpage(request, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title') + filesize = int_or_none( + self._search_regex( + r'<small>\((\d+)\sbytes?\)</small>', + webpage, + 'filesize', + fatal=False + ) + ) + thumbnail = self._search_regex( + r'<img src="([^"]+)".+?class="pic"', + webpage, 'thumbnail', fatal=False) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + value="([^"]*)" + ''', webpage)) + + request = compat_urllib_request.Request(url, urlencode_postdata(fields)) + request.add_header('Content-type', 'application/x-www-form-urlencoded') + response = self._request_webpage(request, video_id, + 'Submiting download request') + video_url = response.geturl() + + formats = [{ + 'format_id': 'sd', + 'filesize': filesize, + 'url': video_url, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py index 80b48b1b3..651784b73 100644 --- a/youtube_dl/extractor/hotnewhiphop.py +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -1,12 +1,13 @@ from __future__ import unicode_literals -import re import base64 from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, HEADRequest, ) @@ -16,25 +17,24 @@ class HotNewHipHopIE(InfoExtractor): _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html' _TEST = { 'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html', - 'file': '1435540.mp3', 'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96', 'info_dict': { + 'id': '1435540', + 'ext': 'mp3', 'title': 'Freddie Gibbs - Lay It Down' } } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') - - webpage_src = self._download_webpage(url, video_id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) video_url_base64 = self._search_regex( - r'data-path="(.*?)"', webpage_src, u'video URL', fatal=False) + r'data-path="(.*?)"', webpage, 'video URL', default=None) if video_url_base64 is None: video_url = self._search_regex( - r'"contentUrl" content="(.*?)"', webpage_src, u'video URL') + r'"contentUrl" content="(.*?)"', webpage, 'content URL') return self.url_result(video_url, ie='Youtube') reqdata = compat_urllib_parse.urlencode([ @@ -59,11 +59,11 @@ class HotNewHipHopIE(InfoExtractor): if video_url.endswith('.html'): raise ExtractorError('Redirect failed') - video_title = self._og_search_title(webpage_src).strip() + video_title = self._og_search_title(webpage).strip() return { 'id': video_id, 'url': video_url, 'title': video_title, - 'thumbnail': self._og_search_thumbnail(webpage_src), + 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/howcast.py b/youtube_dl/extractor/howcast.py index 6ae04782c..3f7d6666c 100644 --- a/youtube_dl/extractor/howcast.py +++ b/youtube_dl/extractor/howcast.py @@ -13,7 +13,7 @@ class HowcastIE(InfoExtractor): 'info_dict': { 'id': '390161', 'ext': 'mp4', - 'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', + 'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', 'title': 'How to Tie a Square Knot Properly', } } @@ -27,10 +27,10 @@ class HowcastIE(InfoExtractor): self.report_extraction(video_id) video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)', - webpage, 'video URL') + webpage, 'video URL') video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'', - webpage, 'description', fatal=False) + webpage, 'description', fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/howstuffworks.py b/youtube_dl/extractor/howstuffworks.py new file mode 100644 index 000000000..e97339121 --- /dev/null +++ b/youtube_dl/extractor/howstuffworks.py @@ -0,0 +1,103 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + find_xpath_attr, + int_or_none, + js_to_json, + unescapeHTML, +) + + +class HowStuffWorksIE(InfoExtractor): + _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm' + _TESTS = [ + { + 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm', + 'info_dict': { + 'id': '450221', + 'ext': 'flv', + 'title': 'Cool Jobs - Iditarod Musher', + 'description': 'Cold sleds, freezing temps and warm dog breath... an Iditarod musher\'s dream. Kasey-Dee Gardner jumps on a sled to find out what the big deal is.', + 'display_id': 'cool-jobs-iditarod-musher', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 161, + }, + }, + { + 'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm', + 'info_dict': { + 'id': '453464', + 'ext': 'mp4', + 'title': 'Survival Zone: Food and Water In the Savanna', + 'description': 'Learn how to find both food and water while trekking in the African savannah. In this video from the Discovery Channel.', + 'display_id': 'survival-zone-food-and-water-in-the-savanna', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm', + 'info_dict': { + 'id': '440011', + 'ext': 'flv', + 'title': 'Sword Swallowing #1 by Dan Meyer', + 'description': 'Video footage (1 of 3) used by permission of the owner Dan Meyer through Sword Swallowers Association International <www.swordswallow.org>', + 'display_id': 'sword-swallowing-1-by-dan-meyer', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + clip_js = self._search_regex( + r'(?s)var clip = ({.*?});', webpage, 'clip info') + clip_info = self._parse_json( + clip_js, display_id, transform_source=js_to_json) + + video_id = clip_info['content_id'] + formats = [] + m3u8_url = clip_info.get('m3u8') + if m3u8_url: + formats += self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') + for video in clip_info.get('mp4', []): + formats.append({ + 'url': video['src'], + 'format_id': video['bitrate'], + 'vbr': int(video['bitrate'].rstrip('k')), + }) + + if not formats: + smil = self._download_xml( + 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % video_id, + video_id, 'Downloading video SMIL') + + http_base = find_xpath_attr( + smil, + './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'), + 'name', + 'httpBase').get('content') + + URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=A&g=A' + + for video in smil.findall( + './{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')): + vbr = int_or_none(video.attrib['system-bitrate'], scale=1000) + formats.append({ + 'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX), + 'format_id': '%dk' % vbr, + 'vbr': vbr, + }) + + self._sort_formats(formats) + + return { + 'id': '%s' % video_id, + 'display_id': display_id, + 'title': unescapeHTML(clip_info['clip_title']), + 'description': unescapeHTML(clip_info.get('caption')), + 'thumbnail': clip_info.get('video_still_url'), + 'duration': clip_info.get('duration'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/huffpost.py b/youtube_dl/extractor/huffpost.py index 94e7cf790..4ccf6b9b8 100644 --- a/youtube_dl/extractor/huffpost.py +++ b/youtube_dl/extractor/huffpost.py @@ -33,8 +33,7 @@ class HuffPostIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) api_url = 'http://embed.live.huffingtonpost.com/api/segments/%s.json' % video_id data = self._download_json(api_url, video_id)['data'] diff --git a/youtube_dl/extractor/iconosquare.py b/youtube_dl/extractor/iconosquare.py index 1d5a10a3b..370e86e5a 100644 --- a/youtube_dl/extractor/iconosquare.py +++ b/youtube_dl/extractor/iconosquare.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -20,13 +18,11 @@ class IconosquareIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - html_title = self._html_search_regex( - r'<title>(.+?)</title>', + title = self._html_search_regex( + r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>', webpage, 'title') - title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title) uploader_id = self._html_search_regex( r'@([^ ]+)', title, 'uploader name', fatal=False) diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index 1f42c6d3a..3db668cd0 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -18,6 +18,7 @@ class IGNIE(InfoExtractor): _DESCRIPTION_RE = [ r'<span class="page-object-description">(.+?)</span>', r'id="my_show_video">.*?<p>(.*?)</p>', + r'<meta name="description" content="(.*?)"', ] _TESTS = [ @@ -55,13 +56,28 @@ class IGNIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch', + 'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7', + 'info_dict': { + 'id': '078fdd005f6d3c02f63d795faa1b984f', + 'ext': 'mp4', + 'title': 'Rewind Theater - Wild Trailer Gamescom 2014', + 'description': ( + 'Giant skeletons, bloody hunts, and captivating' + ' natural beauty take our breath away.' + ), + }, + }, ] def _find_video_id(self, webpage): res_id = [ + r'"video_id"\s*:\s*"(.*?)"', r'data-video-id="(.+?)"', r'<object id="vid_(.+?)"', r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', + r'class="hero-poster[^"]*?"[^>]*id="(.+?)"', ] return self._search_regex(res_id, webpage, 'video id') @@ -70,20 +86,22 @@ class IGNIE(InfoExtractor): name_or_id = mobj.group('name_or_id') page_type = mobj.group('type') webpage = self._download_webpage(url, name_or_id) - if page_type == 'articles': - video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url') - return self.url_result(video_url, ie='IGN') - elif page_type != 'video': + if page_type != 'video': multiple_urls = re.findall( - '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', + '<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', webpage) if multiple_urls: - return [self.url_result(u, ie='IGN') for u in multiple_urls] + entries = [self.url_result(u, ie='IGN') for u in multiple_urls] + return { + '_type': 'playlist', + 'id': name_or_id, + 'entries': entries, + } video_id = self._find_video_id(webpage) result = self._get_video_info(video_id) description = self._html_search_regex(self._DESCRIPTION_RE, - webpage, 'video description', flags=re.DOTALL) + webpage, 'video description', flags=re.DOTALL) result['description'] = description return result @@ -101,13 +119,13 @@ class IGNIE(InfoExtractor): class OneUPIE(IGNIE): - _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)' + _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html' IE_NAME = '1up.com' _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>' _TESTS = [{ - 'url': 'http://gamevideos.1up.com/video/id/34976', + 'url': 'http://gamevideos.1up.com/video/id/34976.html', 'md5': '68a54ce4ebc772e4b71e3123d413163d', 'info_dict': { 'id': '34976', diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 7cee505c0..f2c1c10f5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - get_element_by_attribute, ) @@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) - descr = get_element_by_attribute('itemprop', 'description', webpage) + descr = self._html_search_regex( + r'(?s)<span itemprop="description">(.*?)</span>', + webpage, 'description', fatal=False) available_formats = re.findall( r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage, flags=re.MULTILINE) @@ -63,11 +63,17 @@ class ImdbListIE(InfoExtractor): IE_NAME = 'imdb:list' IE_DESC = 'Internet Movie Database lists' _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') + _TEST = { + 'url': 'http://www.imdb.com/list/JFs9NWw6XI0', + 'info_dict': { + 'id': 'JFs9NWw6XI0', + 'title': 'March 23, 2012 Releases', + }, + 'playlist_count': 7, + } + def _real_extract(self, url): + list_id = self._match_id(url) webpage = self._download_webpage(url, list_id) entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb') diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index b5372bf7a..b020e2621 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -27,9 +27,9 @@ class InstagramIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"', - webpage, 'uploader id', fatal=False) + webpage, 'uploader id', fatal=False) desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description', - fatal=False) + fatal=False) return { 'id': video_id, @@ -46,6 +46,30 @@ class InstagramUserIE(InfoExtractor): _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' + _TEST = { + 'url': 'http://instagram.com/porsche', + 'info_dict': { + 'id': 'porsche', + 'title': 'porsche', + }, + 'playlist_mincount': 2, + 'playlist': [{ + 'info_dict': { + 'id': '614605558512799803_462752227', + 'ext': 'mp4', + 'title': '#Porsche Intelligent Performance.', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Porsche', + 'uploader_id': 'porsche', + 'timestamp': 1387486713, + 'upload_date': '20131219', + }, + }], + 'params': { + 'extract_flat': True, + 'skip_download': True, + } + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 4ddda2f1b..1e4799187 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -12,12 +14,13 @@ class InternetVideoArchiveIE(InfoExtractor): _VALID_URL = r'https?://video\.internetvideoarchive\.net/flash/players/.*?\?.*?publishedid.*?' _TEST = { - u'url': u'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247', - u'file': u'452693.mp4', - u'info_dict': { - u'title': u'SKYFALL', - u'description': u'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.', - u'duration': 153, + 'url': 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247', + 'info_dict': { + 'id': '452693', + 'ext': 'mp4', + 'title': 'SKYFALL', + 'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.', + 'duration': 149, }, } @@ -29,7 +32,7 @@ class InternetVideoArchiveIE(InfoExtractor): def _clean_query(query): NEEDED_ARGS = ['publishedid', 'customerid'] query_dic = compat_urlparse.parse_qs(query) - cleaned_dic = dict((k,v[0]) for (k,v) in query_dic.items() if k in NEEDED_ARGS) + cleaned_dic = dict((k, v[0]) for (k, v) in query_dic.items() if k in NEEDED_ARGS) # Other player ids return m3u8 urls cleaned_dic['playerid'] = '247' cleaned_dic['videokbrate'] = '100000' @@ -42,22 +45,26 @@ class InternetVideoArchiveIE(InfoExtractor): url = self._build_url(query) flashconfiguration = self._download_xml(url, video_id, - u'Downloading flash configuration') + 'Downloading flash configuration') file_url = flashconfiguration.find('file').text file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx') # Replace some of the parameters in the query to get the best quality # and http links (no m3u8 manifests) file_url = re.sub(r'(?<=\?)(.+)$', - lambda m: self._clean_query(m.group()), - file_url) + lambda m: self._clean_query(m.group()), + file_url) info = self._download_xml(file_url, video_id, - u'Downloading video info') + 'Downloading video info') item = info.find('channel/item') def _bp(p): - return xpath_with_ns(p, - {'media': 'http://search.yahoo.com/mrss/', - 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'}) + return xpath_with_ns( + p, + { + 'media': 'http://search.yahoo.com/mrss/', + 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats', + } + ) formats = [] for content in item.findall(_bp('media:group/media:content')): attr = content.attrib diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index d1defd363..4247d6391 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -54,7 +54,7 @@ class IPrimaIE(InfoExtractor): player_url = ( 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % - (floor(random()*1073741824), floor(random()*1073741824)) + (floor(random() * 1073741824), floor(random() * 1073741824)) ) req = compat_urllib_request.Request(player_url) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 4027deb70..f0fba1adb 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -43,7 +43,7 @@ class IviIE(InfoExtractor): 'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg', }, 'skip': 'Only works from Russia', - } + } ] # Sorted by quality @@ -102,7 +102,7 @@ class IviIE(InfoExtractor): compilation = result['compilation'] title = result['title'] - title = '%s - %s' % (compilation, title) if compilation is not None else title + title = '%s - %s' % (compilation, title) if compilation is not None else title previews = result['preview'] previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format'])) @@ -127,6 +127,21 @@ class IviCompilationIE(InfoExtractor): IE_DESC = 'ivi.ru compilations' IE_NAME = 'ivi:compilation' _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$' + _TESTS = [{ + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa', + 'info_dict': { + 'id': 'dvoe_iz_lartsa', + 'title': 'Двое из ларца (2006 - 2008)', + }, + 'playlist_mincount': 24, + }, { + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1', + 'info_dict': { + 'id': 'dvoe_iz_lartsa/season1', + 'title': 'Двое из ларца (2006 - 2008) 1 сезон', + }, + 'playlist_mincount': 12, + }] def _extract_entries(self, html, compilation_id): return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') @@ -137,17 +152,17 @@ class IviCompilationIE(InfoExtractor): compilation_id = mobj.group('compilationid') season_id = mobj.group('seasonid') - if season_id is not None: # Season link + if season_id is not None: # Season link season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) playlist_id = '%s/season%s' % (compilation_id, season_id) playlist_title = self._html_search_meta('title', season_page, 'title') entries = self._extract_entries(season_page, compilation_id) - else: # Compilation link + else: # Compilation link compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') playlist_id = compilation_id playlist_title = self._html_search_meta('title', compilation_page, 'title') seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page) - if len(seasons) == 0: # No seasons in this compilation + if len(seasons) == 0: # No seasons in this compilation entries = self._extract_entries(compilation_page, compilation_id) else: entries = [] @@ -157,4 +172,4 @@ class IviCompilationIE(InfoExtractor): compilation_id, 'Downloading season %s web page' % season_id) entries.extend(self._extract_entries(season_page, compilation_id)) - return self.playlist_result(entries, playlist_id, playlist_title)
\ No newline at end of file + return self.playlist_result(entries, playlist_id, playlist_title) diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py new file mode 100644 index 000000000..d16d483ee --- /dev/null +++ b/youtube_dl/extractor/izlesene.py @@ -0,0 +1,125 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + float_or_none, + get_element_by_id, + int_or_none, + parse_iso8601, + str_to_int, +) + + +class IzleseneIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:(?:www|m)\.)?izlesene\.com/ + (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+) + ''' + _TESTS = [ + { + 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', + 'md5': '4384f9f0ea65086734b881085ee05ac2', + 'info_dict': { + 'id': '7599694', + 'ext': 'mp4', + 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'description': 'md5:253753e2655dde93f59f74b572454f6d', + 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'pelikzzle', + 'timestamp': 1404302298, + 'upload_date': '20140702', + 'duration': 95.395, + 'age_limit': 0, + } + }, + { + 'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997', + 'md5': '97f09b6872bffa284cb7fa4f6910cb72', + 'info_dict': { + 'id': '17997', + 'ext': 'mp4', + 'title': 'Tarkan Dortmund 2006 Konseri', + 'description': 'Tarkan Dortmund 2006 Konseri', + 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'parlayankiz', + 'timestamp': 1163322193, + 'upload_date': '20061112', + 'duration': 253.666, + 'age_limit': 0, + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + url = 'http://www.izlesene.com/video/%s' % video_id + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') + + uploader = self._html_search_regex( + r"adduserUsername\s*=\s*'([^']+)';", + webpage, 'uploader', fatal=False, default='') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date', fatal=False)) + + duration = float_or_none(self._html_search_regex( + r'"videoduration"\s*:\s*"([^"]+)"', + webpage, 'duration', fatal=False), scale=1000) + + view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) + comment_count = self._html_search_regex( + r'comment_count\s*=\s*\'([^\']+)\';', + webpage, 'comment_count', fatal=False) + + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, 'age limit', fatal=False) + + content_url = self._html_search_meta( + 'contentURL', webpage, 'content URL', fatal=False) + ext = determine_ext(content_url, 'mp4') + + # Might be empty for some videos. + streams = self._html_search_regex( + r'"qualitylevel"\s*:\s*"([^"]+)"', + webpage, 'streams', fatal=False, default='') + + formats = [] + if streams: + for stream in streams.split('|'): + quality, url = re.search(r'\[(\w+)\](.+)', stream).groups() + formats.append({ + 'format_id': '%sp' % quality if quality else 'sd', + 'url': url, + 'ext': ext, + }) + else: + stream_url = self._search_regex( + r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL') + formats.append({ + 'format_id': 'sd', + 'url': stream_url, + 'ext': ext, + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader_id': uploader, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': int_or_none(view_count), + 'comment_count': int_or_none(comment_count), + 'age_limit': 18 if family_friendly == 'False' else 0, + 'formats': formats, + } diff --git a/youtube_dl/extractor/jadorecettepub.py b/youtube_dl/extractor/jadorecettepub.py index ace08769b..063e86de4 100644 --- a/youtube_dl/extractor/jadorecettepub.py +++ b/youtube_dl/extractor/jadorecettepub.py @@ -45,4 +45,3 @@ class JadoreCettePubIE(InfoExtractor): 'title': title, 'description': description, } - diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index 188165966..8094cc2e4 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -29,7 +29,7 @@ class JeuxVideoIE(InfoExtractor): xml_link = self._html_search_regex( r'<param name="flashvars" value="config=(.*?)" />', webpage, 'config URL') - + video_id = self._search_regex( r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml', xml_link, 'video ID') @@ -38,7 +38,7 @@ class JeuxVideoIE(InfoExtractor): xml_link, title, 'Downloading XML config') info_json = config.find('format.json').text info = json.loads(info_json)['versions'][0] - + video_url = 'http://video720.jeuxvideo.com/' + info['file'] return { diff --git a/youtube_dl/extractor/jove.py b/youtube_dl/extractor/jove.py new file mode 100644 index 000000000..cf73cd753 --- /dev/null +++ b/youtube_dl/extractor/jove.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unified_strdate +) + + +class JoveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)' + _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' + _TESTS = [ + { + 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', + 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', + 'info_dict': { + 'id': '2744', + 'ext': 'mp4', + 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', + 'description': 'md5:015dd4509649c0908bc27f049e0262c6', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20110523', + } + }, + { + 'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation', + 'md5': '914aeb356f416811d911996434811beb', + 'info_dict': { + 'id': '51796', + 'ext': 'mp4', + 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment', + 'description': 'md5:35ff029261900583970c4023b70f1dc9', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20140802', + } + }, + + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + chapters_id = self._html_search_regex( + r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') + + chapters_xml = self._download_xml( + self._CHAPTERS_URL.format(video_id=chapters_id), + video_id, note='Downloading chapters XML', + errnote='Failed to download chapters XML') + + video_url = chapters_xml.attrib.get('video') + if not video_url: + raise ExtractorError('Failed to get the video URL') + + title = self._html_search_meta('citation_title', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._html_search_regex( + r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>', + webpage, 'description', fatal=False) + publish_date = unified_strdate(self._html_search_meta( + 'citation_publication_date', webpage, 'publish date', fatal=False)) + comment_count = self._html_search_regex( + r'<meta name="num_comments" content="(\d+) Comments?"', + webpage, 'comment count', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': publish_date, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py index aad782578..122e2dd8c 100644 --- a/youtube_dl/extractor/jpopsukitv.py +++ b/youtube_dl/extractor/jpopsukitv.py @@ -1,8 +1,6 @@ # coding=utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( int_or_none, @@ -12,14 +10,14 @@ from ..utils import ( class JpopsukiIE(InfoExtractor): IE_NAME = 'jpopsuki.tv' - _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)' + _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P<id>\S+)' _TEST = { 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', 'md5': '88018c0c1a9b1387940e90ec9e7e198e', - 'file': '00be659d23b0b40508169cdee4545771.mp4', 'info_dict': { 'id': '00be659d23b0b40508169cdee4545771', + 'ext': 'mp4', 'title': 'ayumi hamasaki - evolution', 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', @@ -30,8 +28,7 @@ class JpopsukiIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) @@ -47,11 +44,9 @@ class JpopsukiIE(InfoExtractor): uploader_id = self._html_search_regex( r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', webpage, 'video uploader_id', fatal=False) - upload_date = self._html_search_regex( + upload_date = unified_strdate(self._html_search_regex( r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date', - fatal=False) - if upload_date is not None: - upload_date = unified_strdate(upload_date) + fatal=False)) view_count_str = self._html_search_regex( r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count', fatal=False) diff --git a/youtube_dl/extractor/jukebox.py b/youtube_dl/extractor/jukebox.py index 9b553b9fa..da8068efc 100644 --- a/youtube_dl/extractor/jukebox.py +++ b/youtube_dl/extractor/jukebox.py @@ -11,10 +11,9 @@ from ..utils import ( class JukeboxIE(InfoExtractor): - _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html' + _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<id>[a-z0-9\-]+)\.html' _TEST = { 'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html', - 'md5': '1574e9b4d6438446d5b7dbcdf2786276', 'info_dict': { 'id': 'r303r', 'ext': 'flv', @@ -24,8 +23,7 @@ class JukeboxIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) html = self._download_webpage(url, video_id) iframe_url = unescapeHTML(self._search_regex(r'<iframe .*src="([^"]*)"', html, 'iframe url')) @@ -38,7 +36,7 @@ class JukeboxIE(InfoExtractor): try: video_url = self._search_regex(r'"config":{"file":"(?P<video_url>http:[^"]+\?mdtk=[0-9]+)"', - iframe_html, 'video url') + iframe_html, 'video url') video_url = unescapeHTML(video_url).replace('\/', '/') except RegexNotFoundError: youtube_url = self._search_regex( @@ -49,9 +47,9 @@ class JukeboxIE(InfoExtractor): return self.url_result(youtube_url, ie='Youtube') title = self._html_search_regex(r'<h1 class="inline">([^<]+)</h1>', - html, 'title') + html, 'title') artist = self._html_search_regex(r'<span id="infos_article_artist">([^<]+)</span>', - html, 'artist') + html, 'artist') return { 'id': video_id, diff --git a/youtube_dl/extractor/justintv.py b/youtube_dl/extractor/justintv.py deleted file mode 100644 index 27017e89f..000000000 --- a/youtube_dl/extractor/justintv.py +++ /dev/null @@ -1,155 +0,0 @@ -from __future__ import unicode_literals - -import itertools -import json -import os -import re - -from .common import InfoExtractor -from ..utils import ( - compat_str, - ExtractorError, - formatSeconds, -) - - -class JustinTVIE(InfoExtractor): - """Information extractor for justin.tv and twitch.tv""" - # TODO: One broadcast may be split into multiple videos. The key - # 'broadcast_id' is the same for all parts, and 'broadcast_part' - # starts at 1 and increases. Can we treat all parts as one video? - - _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ - (?: - (?P<channelid>[^/]+)| - (?:(?:[^/]+)/b/(?P<videoid>[^/]+))| - (?:(?:[^/]+)/c/(?P<chapterid>[^/]+)) - ) - /?(?:\#.*)?$ - """ - _JUSTIN_PAGE_LIMIT = 100 - IE_NAME = 'justin.tv' - IE_DESC = 'justin.tv and twitch.tv' - _TEST = { - 'url': 'http://www.twitch.tv/thegamedevhub/b/296128360', - 'md5': 'ecaa8a790c22a40770901460af191c9a', - 'info_dict': { - 'id': '296128360', - 'ext': 'flv', - 'upload_date': '20110927', - 'uploader_id': 25114803, - 'uploader': 'thegamedevhub', - 'title': 'Beginner Series - Scripting With Python Pt.1' - } - } - - # Return count of items, list of *valid* items - def _parse_page(self, url, video_id, counter): - info_json = self._download_webpage( - url, video_id, - 'Downloading video info JSON on page %d' % counter, - 'Unable to download video info JSON %d' % counter) - - response = json.loads(info_json) - if type(response) != list: - error_text = response.get('error', 'unknown error') - raise ExtractorError('Justin.tv API: %s' % error_text) - info = [] - for clip in response: - video_url = clip['video_file_url'] - if video_url: - video_extension = os.path.splitext(video_url)[1][1:] - video_date = re.sub('-', '', clip['start_time'][:10]) - video_uploader_id = clip.get('user_id', clip.get('channel_id')) - video_id = clip['id'] - video_title = clip.get('title', video_id) - info.append({ - 'id': compat_str(video_id), - 'url': video_url, - 'title': video_title, - 'uploader': clip.get('channel_name', video_uploader_id), - 'uploader_id': video_uploader_id, - 'upload_date': video_date, - 'ext': video_extension, - }) - return (len(response), info) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - api_base = 'http://api.justin.tv' - paged = False - if mobj.group('channelid'): - paged = True - video_id = mobj.group('channelid') - api = api_base + '/channel/archives/%s.json' % video_id - elif mobj.group('chapterid'): - chapter_id = mobj.group('chapterid') - - webpage = self._download_webpage(url, chapter_id) - m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) - if not m: - raise ExtractorError('Cannot find archive of a chapter') - archive_id = m.group(1) - - api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id - doc = self._download_xml( - api, chapter_id, - note='Downloading chapter information', - errnote='Chapter information download failed') - for a in doc.findall('.//archive'): - if archive_id == a.find('./id').text: - break - else: - raise ExtractorError('Could not find chapter in chapter information') - - video_url = a.find('./video_file_url').text - video_ext = video_url.rpartition('.')[2] or 'flv' - - chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id - chapter_info = self._download_json( - chapter_api_url, 'c' + chapter_id, - note='Downloading chapter metadata', - errnote='Download of chapter metadata failed') - - bracket_start = int(doc.find('.//bracket_start').text) - bracket_end = int(doc.find('.//bracket_end').text) - - # TODO determine start (and probably fix up file) - # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 - #video_url += '?start=' + TODO:start_timestamp - # bracket_start is 13290, but we want 51670615 - self._downloader.report_warning('Chapter detected, but we can just download the whole file. ' - 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) - - info = { - 'id': 'c' + chapter_id, - 'url': video_url, - 'ext': video_ext, - 'title': chapter_info['title'], - 'thumbnail': chapter_info['preview'], - 'description': chapter_info['description'], - 'uploader': chapter_info['channel']['display_name'], - 'uploader_id': chapter_info['channel']['name'], - } - return info - else: - video_id = mobj.group('videoid') - api = api_base + '/broadcast/by_archive/%s.json' % video_id - - entries = [] - offset = 0 - limit = self._JUSTIN_PAGE_LIMIT - for counter in itertools.count(1): - page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) - page_count, page_info = self._parse_page( - page_url, video_id, counter) - entries.extend(page_info) - if not paged or page_count != limit: - break - offset += limit - return { - '_type': 'playlist', - 'id': video_id, - 'entries': entries, - } diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py index 23103b163..dbfe4cc03 100644 --- a/youtube_dl/extractor/kankan.py +++ b/youtube_dl/extractor/kankan.py @@ -10,7 +10,7 @@ _md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() class KankanIE(InfoExtractor): _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml' - + _TEST = { 'url': 'http://yinyue.kankan.com/vod/48/48863.shtml', 'file': '48863.flv', diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 772bb5671..408d00944 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -9,21 +9,30 @@ from ..utils import ( class KhanAcademyIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])' + _VALID_URL = r'^https?://(?:(?:www|api)\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])' IE_NAME = 'KhanAcademy' - _TEST = { + _TESTS = [{ 'url': 'http://www.khanacademy.org/video/one-time-pad', - 'file': 'one-time-pad.mp4', 'md5': '7021db7f2d47d4fff89b13177cb1e8f4', 'info_dict': { + 'id': 'one-time-pad', + 'ext': 'mp4', 'title': 'The one-time pad', 'description': 'The perfect cipher', 'duration': 176, 'uploader': 'Brit Cruise', 'upload_date': '20120411', } - } + }, { + 'url': 'https://www.khanacademy.org/math/applied-math/cryptography', + 'info_dict': { + 'id': 'cryptography', + 'title': 'Journey into cryptography', + 'description': 'How have humans protected their secret messages through history? What has changed today?', + }, + 'playlist_mincount': 3, + }] def _real_extract(self, url): m = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py index 56a76380c..7d4b57056 100644 --- a/youtube_dl/extractor/kickstarter.py +++ b/youtube_dl/extractor/kickstarter.py @@ -1,8 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -15,28 +13,25 @@ class KickStarterIE(InfoExtractor): 'id': '1404461844', 'ext': 'mp4', 'title': 'Intersection: The Story of Josh Grant by Kyle Cowling', - 'description': 'A unique motocross documentary that examines the ' - 'life and mind of one of sports most elite athletes: Josh Grant.', + 'description': ( + 'A unique motocross documentary that examines the ' + 'life and mind of one of sports most elite athletes: Josh Grant.' + ), }, }, { 'note': 'Embedded video (not using the native kickstarter video service)', 'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178', - 'playlist': [ - { - 'info_dict': { - 'id': '78704821', - 'ext': 'mp4', - 'uploader_id': 'pebble', - 'uploader': 'Pebble Technology', - 'title': 'Pebble iOS Notifications', - } - } - ], + 'info_dict': { + 'id': '78704821', + 'ext': 'mp4', + 'uploader_id': 'pebble', + 'uploader': 'Pebble Technology', + 'title': 'Pebble iOS Notifications', + } }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex( diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py index 5341ac773..41fd62009 100644 --- a/youtube_dl/extractor/kontrtube.py +++ b/youtube_dl/extractor/kontrtube.py @@ -34,7 +34,7 @@ class KontrTubeIE(InfoExtractor): video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL') thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False) title = self._html_search_regex( - r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage, 'video title') + r'<title>(.+?)</title>', webpage, 'video title') description = self._html_search_meta('description', webpage, 'video description') mobj = re.search( @@ -63,4 +63,4 @@ class KontrTubeIE(InfoExtractor): 'duration': duration, 'view_count': int_or_none(view_count), 'comment_count': int_or_none(comment_count), - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/ku6.py b/youtube_dl/extractor/ku6.py index 484239b19..a602980a1 100644 --- a/youtube_dl/extractor/ku6.py +++ b/youtube_dl/extractor/ku6.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -18,11 +16,11 @@ class Ku6IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title') + + title = self._html_search_regex( + r'<h1 title=.*>(.*?)</h1>', webpage, 'title') dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id jsonData = self._download_json(dataUrl, video_id) downloadUrl = jsonData['data']['f'] @@ -32,4 +30,3 @@ class Ku6IE(InfoExtractor): 'title': title, 'url': downloadUrl } - diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py new file mode 100644 index 000000000..2fd3b4699 --- /dev/null +++ b/youtube_dl/extractor/laola1tv.py @@ -0,0 +1,77 @@ +from __future__ import unicode_literals + +import random +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Laola1TvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html', + 'info_dict': { + 'id': '250019', + 'ext': 'mp4', + 'title': 'Bitburger Open Grand Prix Gold - Court 1', + 'categories': ['Badminton'], + 'uploader': 'BWF - Badminton World Federation', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + } + + _BROKEN = True # Not really - extractor works fine, but f4m downloader does not support live streams yet. + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + lang = mobj.group('lang') + portal = mobj.group('portal') + + webpage = self._download_webpage(url, video_id) + iframe_url = self._search_regex( + r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"', + webpage, 'iframe URL') + + iframe = self._download_webpage( + iframe_url, video_id, note='Downloading iframe') + flashvars_m = re.findall( + r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe) + flashvars = dict((m[0], m[1]) for m in flashvars_m) + + xml_url = ('http://www.laola1.tv/server/hd_video.php?' + + 'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % ( + video_id, portal, lang)) + hd_doc = self._download_xml(xml_url, video_id) + + title = hd_doc.find('.//video/title').text + flash_url = hd_doc.find('.//video/url').text + categories = hd_doc.find('.//video/meta_sports').text.split(',') + uploader = hd_doc.find('.//video/meta_organistation').text + + ident = random.randint(10000000, 99999999) + token_url = '%s&ident=%s&klub=0&unikey=0×tamp=%s&auth=%s' % ( + flash_url, ident, flashvars['timestamp'], flashvars['auth']) + + token_doc = self._download_xml( + token_url, video_id, note='Downloading token') + token_attrib = token_doc.find('.//token').attrib + if token_attrib.get('auth') == 'blocked': + raise ExtractorError('Token error: ' % token_attrib.get('comment')) + + video_url = '%s?hdnea=%s&hdcore=3.2.0' % ( + token_attrib['url'], token_attrib['auth']) + + return { + 'id': video_id, + 'is_live': True, + 'title': title, + 'url': video_url, + 'uploader': uploader, + 'categories': categories, + 'ext': 'mp4', + } diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 8d9491f23..1dfe7f77f 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -52,7 +52,7 @@ class LifeNewsIE(InfoExtractor): r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False) upload_date = self._html_search_regex( - r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False) + r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False) if upload_date is not None: upload_date = unified_strdate(upload_date) @@ -71,4 +71,4 @@ class LifeNewsIE(InfoExtractor): if len(videos) == 1: return make_entry(video_id, videos[0]) else: - return [make_entry(video_id, media, video_number+1) for video_number, media in enumerate(videos)]
\ No newline at end of file + return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)] diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index 8e50e8f79..b04be1e8c 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -19,8 +19,7 @@ class LiveLeakIE(InfoExtractor): 'uploader': 'ljfriel2', 'title': 'Most unlucky car accident' } - }, - { + }, { 'url': 'http://www.liveleak.com/view?i=f93_1390833151', 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf', 'info_dict': { @@ -30,8 +29,7 @@ class LiveLeakIE(InfoExtractor): 'uploader': 'ARD_Stinkt', 'title': 'German Television does first Edward Snowden Interview (ENGLISH)', } - }, - { + }, { 'url': 'http://www.liveleak.com/view?i=4f7_1392687779', 'md5': '42c6d97d54f1db107958760788c5f48f', 'info_dict': { diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index c0c2d9b09..03c4691c6 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -18,8 +18,8 @@ from ..utils import ( class LivestreamIE(InfoExtractor): IE_NAME = 'livestream' - _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' - _TEST = { + _VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])' + _TESTS = [{ 'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', 'md5': '53274c76ba7754fb0e8d072716f2292b', 'info_dict': { @@ -31,7 +31,16 @@ class LivestreamIE(InfoExtractor): 'view_count': int, 'thumbnail': 're:^http://.*\.jpg$' } - } + }, { + 'url': 'http://new.livestream.com/tedx/cityenglish', + 'info_dict': { + 'title': 'TEDCity2.0 (English)', + }, + 'playlist_mincount': 4, + }, { + 'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640', + 'only_matching': True, + }] def _parse_smil(self, video_id, smil_url): formats = [] @@ -111,23 +120,37 @@ class LivestreamIE(InfoExtractor): event_name = mobj.group('event_name') webpage = self._download_webpage(url, video_id or event_name) + og_video = self._og_search_video_url( + webpage, 'player url', fatal=False, default=None) + if og_video is not None: + query_str = compat_urllib_parse_urlparse(og_video).query + query = compat_urlparse.parse_qs(query_str) + if 'play_url' in query: + api_url = query['play_url'][0].replace('.smil', '') + info = json.loads(self._download_webpage( + api_url, video_id, 'Downloading video info')) + return self._extract_video_info(info) + + config_json = self._search_regex( + r'window.config = ({.*?});', webpage, 'window config') + info = json.loads(config_json)['event'] + + def is_relevant(vdata, vid): + result = vdata['type'] == 'video' + if video_id is not None: + result = result and compat_str(vdata['data']['id']) == vid + return result + + videos = [self._extract_video_info(video_data['data']) + for video_data in info['feed']['data'] + if is_relevant(video_data, video_id)] if video_id is None: # This is an event page: - config_json = self._search_regex( - r'window.config = ({.*?});', webpage, 'window config') - info = json.loads(config_json)['event'] - videos = [self._extract_video_info(video_data['data']) - for video_data in info['feed']['data'] - if video_data['type'] == 'video'] return self.playlist_result(videos, info['id'], info['full_name']) else: - og_video = self._og_search_video_url(webpage, 'player url') - query_str = compat_urllib_parse_urlparse(og_video).query - query = compat_urlparse.parse_qs(query_str) - api_url = query['play_url'][0].replace('.smil', '') - info = json.loads(self._download_webpage( - api_url, video_id, 'Downloading video info')) - return self._extract_video_info(info) + if not videos: + raise ExtractorError('Cannot find video %s' % video_id) + return videos[0] # The original version of Livestream uses a different system @@ -137,7 +160,7 @@ class LivestreamOriginalIE(InfoExtractor): (?P<user>[^/]+)/(?P<type>video|folder) (?:\?.*?Id=|/)(?P<id>.*?)(&|$) ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', 'info_dict': { 'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', @@ -148,7 +171,13 @@ class LivestreamOriginalIE(InfoExtractor): # rtmp 'skip_download': True, }, - } + }, { + 'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3', + 'info_dict': { + 'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3', + }, + 'playlist_mincount': 4, + }] def _extract_video(self, user, video_id): api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id) @@ -164,22 +193,27 @@ class LivestreamOriginalIE(InfoExtractor): 'id': video_id, 'title': item.find('title').text, 'url': 'rtmp://extondemand.livestream.com/ondemand', - 'play_path': 'mp4:trans/dv15/mogulus-{0}.mp4'.format(path), + 'play_path': 'trans/dv15/mogulus-{0}'.format(path), + 'player_url': 'http://static.livestream.com/chromelessPlayer/v21/playerapi.swf?hash=5uetk&v=0803&classid=D27CDB6E-AE6D-11cf-96B8-444553540000&jsEnabled=false&wmode=opaque', 'ext': 'flv', 'thumbnail': thumbnail_url, } def _extract_folder(self, url, folder_id): webpage = self._download_webpage(url, folder_id) - urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage)) + paths = orderedSet(re.findall( + r'''(?x)(?: + <li\s+class="folder">\s*<a\s+href="| + <a\s+href="(?=https?://livestre\.am/) + )([^"]+)"''', webpage)) return { '_type': 'playlist', 'id': folder_id, 'entries': [{ '_type': 'url', - 'url': video_url, - } for video_url in urls], + 'url': compat_urlparse.urljoin(url, p), + } for p in paths], } def _real_extract(self, url): diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py new file mode 100644 index 000000000..d72d470aa --- /dev/null +++ b/youtube_dl/extractor/lrt.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + js_to_json, + parse_duration, + remove_end, +) + + +class LRTIE(InfoExtractor): + IE_NAME = 'lrt.lt' + _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.lrt.lt/mediateka/irasas/54391/', + 'info_dict': { + 'id': '54391', + 'ext': 'mp4', + 'title': 'Septynios Kauno dienos', + 'description': 'md5:24d84534c7dc76581e59f5689462411a', + 'duration': 1783, + }, + 'params': { + 'skip_download': True, # HLS download + }, + + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = remove_end(self._og_search_title(webpage), ' - LRT') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + duration = parse_duration(self._search_regex( + r"'duration':\s*'([^']+)',", webpage, + 'duration', fatal=False, default=None)) + + formats = [] + for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage): + data = json.loads(js_to_json(js)) + if data['provider'] == 'rtmp': + formats.append({ + 'format_id': 'rtmp', + 'ext': determine_ext(data['file']), + 'url': data['streamer'], + 'play_path': 'mp4:%s' % data['file'], + 'preference': -1, + }) + else: + formats.extend( + self._extract_m3u8_formats(data['file'], video_id, 'mp4')) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + } diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 33f34f4e9..2160d6cb0 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -45,7 +45,7 @@ class LyndaIE(SubtitlesInfoExtractor): video_id = mobj.group(1) page = self._download_webpage('http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id, video_id, - 'Downloading video JSON') + 'Downloading video JSON') video_json = json.loads(page) if 'Status' in video_json: @@ -109,7 +109,7 @@ class LyndaIE(SubtitlesInfoExtractor): 'password': password, 'remember': 'false', 'stayPut': 'false' - } + } request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) login_page = self._download_webpage(request, None, 'Logging in as %s' % username) @@ -117,7 +117,7 @@ class LyndaIE(SubtitlesInfoExtractor): m = re.search(r'loginResultJson = \'(?P<json>[^\']+)\';', login_page) if m is not None: response = m.group('json') - response_json = json.loads(response) + response_json = json.loads(response) state = response_json['state'] if state == 'notlogged': @@ -187,7 +187,7 @@ class LyndaCourseIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) course_path = mobj.group('coursepath') course_id = mobj.group('courseid') - + page = self._download_webpage('http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id, course_id, 'Downloading course JSON') course_json = json.loads(page) @@ -221,4 +221,4 @@ class LyndaCourseIE(InfoExtractor): course_title = course_json['Title'] - return self.playlist_result(entries, course_id, course_title)
\ No newline at end of file + return self.playlist_result(entries, course_id, course_title) diff --git a/youtube_dl/extractor/m6.py b/youtube_dl/extractor/m6.py index 1a26b5d57..7e025831b 100644 --- a/youtube_dl/extractor/m6.py +++ b/youtube_dl/extractor/m6.py @@ -27,7 +27,7 @@ class M6IE(InfoExtractor): video_id = mobj.group('id') rss = self._download_xml('http://ws.m6.fr/v1/video/info/m6/bonus/%s' % video_id, video_id, - 'Downloading video RSS') + 'Downloading video RSS') title = rss.find('./channel/item/title').text description = rss.find('./channel/item/description').text @@ -53,4 +53,4 @@ class M6IE(InfoExtractor): 'duration': duration, 'view_count': view_count, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index 7460d81cd..54a14cb94 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -16,7 +16,7 @@ class MailRuIE(InfoExtractor): 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', 'md5': 'dea205f03120046894db4ebb6159879a', 'info_dict': { - 'id': '46301138', + 'id': '46301138_76', 'ext': 'mp4', 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', 'timestamp': 1393232740, @@ -30,7 +30,7 @@ class MailRuIE(InfoExtractor): 'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html', 'md5': '00a91a58c3402204dcced523777b475f', 'info_dict': { - 'id': '46843144', + 'id': '46843144_1263', 'ext': 'mp4', 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion', 'timestamp': 1397217632, @@ -54,33 +54,36 @@ class MailRuIE(InfoExtractor): author = video_data['author'] uploader = author['name'] - uploader_id = author['id'] + uploader_id = author.get('id') or author.get('email') + view_count = video_data.get('views_count') - movie = video_data['movie'] - content_id = str(movie['contentId']) - title = movie['title'] + meta_data = video_data['meta'] + content_id = '%s_%s' % ( + meta_data.get('accId', ''), meta_data['itemId']) + title = meta_data['title'] if title.endswith('.mp4'): title = title[:-4] - thumbnail = movie['poster'] - duration = movie['duration'] - - view_count = video_data['views_count'] + thumbnail = meta_data['poster'] + duration = meta_data['duration'] + timestamp = meta_data['timestamp'] formats = [ { 'url': video['url'], - 'format_id': video['name'], + 'format_id': video['key'], + 'height': int(video['key'].rstrip('p')) } for video in video_data['videos'] ] + self._sort_formats(formats) return { 'id': content_id, 'title': title, 'thumbnail': thumbnail, - 'timestamp': video_data['timestamp'], + 'timestamp': timestamp, 'uploader': uploader, 'uploader_id': uploader_id, 'duration': duration, 'view_count': view_count, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/malemotion.py b/youtube_dl/extractor/malemotion.py index 8c1966ab2..1abf6e4f8 100644 --- a/youtube_dl/extractor/malemotion.py +++ b/youtube_dl/extractor/malemotion.py @@ -7,6 +7,7 @@ from ..utils import ( compat_urllib_parse, ) + class MalemotionIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' _TEST = { diff --git a/youtube_dl/extractor/mdr.py b/youtube_dl/extractor/mdr.py index 1b8c4a32e..5fdd19027 100644 --- a/youtube_dl/extractor/mdr.py +++ b/youtube_dl/extractor/mdr.py @@ -7,7 +7,7 @@ from .common import InfoExtractor class MDRIE(InfoExtractor): _VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)' - + # No tests, MDR regularily deletes its videos _TEST = { 'url': 'http://www.mdr.de/fakt/video189002.html', diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 6436c05a3..858c1c0c3 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -9,6 +9,7 @@ from ..utils import ( compat_urllib_request, determine_ext, ExtractorError, + int_or_none, ) @@ -21,7 +22,7 @@ class MetacafeIE(InfoExtractor): # Youtube video { 'add_ie': ['Youtube'], - 'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/', + 'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/', 'info_dict': { 'id': '_aUehQsCQtM', 'ext': 'mp4', @@ -83,6 +84,21 @@ class MetacafeIE(InfoExtractor): 'skip_download': True, }, }, + # Movieclips.com video + { + 'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/', + 'info_dict': { + 'id': 'mv-Wy7ZU', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.', + 'uploader': 'movie_trailers', + 'duration': 176, + }, + 'params': { + 'skip_download': 'requires rtmpdump', + } + } ] def report_disclaimer(self): @@ -134,6 +150,7 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) + video_url = None mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse.unquote(mobj.group(1)) @@ -146,16 +163,17 @@ class MetacafeIE(InfoExtractor): else: gdaKey = mobj.group(1) video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: + if video_url is None: mobj = re.search(r'<video src="([^"]+)"', webpage) if mobj: video_url = mobj.group(1) video_ext = 'mp4' - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - raise ExtractorError('Unable to extract media URL') - vardict = compat_parse_qs(mobj.group(1)) + if video_url is None: + flashvars = self._search_regex( + r' name="flashvars" value="(.*?)"', webpage, 'flashvars', + default=None) + if flashvars: + vardict = compat_parse_qs(flashvars) if 'mediaData' not in vardict: raise ExtractorError('Unable to extract media URL') mobj = re.search( @@ -165,26 +183,68 @@ class MetacafeIE(InfoExtractor): mediaURL = mobj.group('mediaURL').replace('\\/', '/') video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) video_ext = determine_ext(video_url) - - video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title') + if video_url is None: + player_url = self._search_regex( + r"swfobject\.embedSWF\('([^']+)'", + webpage, 'config URL', default=None) + if player_url: + config_url = self._search_regex( + r'config=(.+)$', player_url, 'config URL') + config_doc = self._download_xml( + config_url, video_id, + note='Downloading video config') + smil_url = config_doc.find('.//properties').attrib['smil_file'] + smil_doc = self._download_xml( + smil_url, video_id, + note='Downloading SMIL document') + base_url = smil_doc.find('./head/meta').attrib['base'] + video_url = [] + for vn in smil_doc.findall('.//video'): + br = int(vn.attrib['system-bitrate']) + play_path = vn.attrib['src'] + video_url.append({ + 'format_id': 'smil-%d' % br, + 'url': base_url, + 'play_path': play_path, + 'page_url': url, + 'player_url': player_url, + 'ext': play_path.partition(':')[0], + }) + + if video_url is None: + raise ExtractorError('Unsupported video type') + + video_title = self._html_search_regex( + r'(?im)<title>(.*) - Video</title>', webpage, 'title') description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) video_uploader = self._html_search_regex( - r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', - webpage, 'uploader nickname', fatal=False) - - if re.search(r'"contentRating":"restricted"', webpage) is not None: - age_limit = 18 + r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', + webpage, 'uploader nickname', fatal=False) + duration = int_or_none( + self._html_search_meta('video:duration', webpage)) + + age_limit = ( + 18 + if re.search(r'"contentRating":"restricted"', webpage) + else 0) + + if isinstance(video_url, list): + formats = video_url else: - age_limit = 0 + formats = [{ + 'url': video_url, + 'ext': video_ext, + }] + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, 'description': description, 'uploader': video_uploader, 'title': video_title, - 'thumbnail':thumbnail, - 'ext': video_ext, + 'thumbnail': thumbnail, 'age_limit': age_limit, + 'formats': formats, + 'duration': duration, } diff --git a/youtube_dl/extractor/metacritic.py b/youtube_dl/extractor/metacritic.py index 07f072924..e30320569 100644 --- a/youtube_dl/extractor/metacritic.py +++ b/youtube_dl/extractor/metacritic.py @@ -28,7 +28,7 @@ class MetacriticIE(InfoExtractor): webpage = self._download_webpage(url, video_id) # The xml is not well formatted, there are raw '&' info = self._download_xml('http://www.metacritic.com/video_data?video=' + video_id, - video_id, 'Downloading info xml', transform_source=fix_xml_ampersands) + video_id, 'Downloading info xml', transform_source=fix_xml_ampersands) clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id) formats = [] @@ -44,7 +44,7 @@ class MetacriticIE(InfoExtractor): self._sort_formats(formats) description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>', - webpage, 'description', flags=re.DOTALL) + webpage, 'description', flags=re.DOTALL) return { 'id': video_id, diff --git a/youtube_dl/extractor/mgoon.py b/youtube_dl/extractor/mgoon.py new file mode 100644 index 000000000..94bc87b00 --- /dev/null +++ b/youtube_dl/extractor/mgoon.py @@ -0,0 +1,87 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + qualities, + unified_strdate, +) + + +class MgoonIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)? + (?:(:?m\.)?mgoon\.com/(?:ch/(?:.+)/v|play/view)| + video\.mgoon\.com)/(?P<id>[0-9]+)''' + _API_URL = 'http://mpos.mgoon.com/player/video?id={0:}' + _TESTS = [ + { + 'url': 'http://m.mgoon.com/ch/hi6618/v/5582148', + 'md5': 'dd46bb66ab35cf6d51cc812fd82da79d', + 'info_dict': { + 'id': '5582148', + 'uploader_id': 'hi6618', + 'duration': 240.419, + 'upload_date': '20131220', + 'ext': 'mp4', + 'title': 'md5:543aa4c27a4931d371c3f433e8cebebc', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + { + 'url': 'http://www.mgoon.com/play/view/5582148', + 'only_matching': True, + }, + { + 'url': 'http://video.mgoon.com/5582148', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + data = self._download_json(self._API_URL.format(video_id), video_id) + + if data.get('errorInfo', {}).get('code') != 'NONE': + raise ExtractorError('%s encountered an error: %s' % ( + self.IE_NAME, data['errorInfo']['message']), expected=True) + + v_info = data['videoInfo'] + title = v_info.get('v_title') + thumbnail = v_info.get('v_thumbnail') + duration = v_info.get('v_duration') + upload_date = unified_strdate(v_info.get('v_reg_date')) + uploader_id = data.get('userInfo', {}).get('u_alias') + if duration: + duration /= 1000.0 + + age_limit = None + if data.get('accessInfo', {}).get('code') == 'VIDEO_STATUS_ADULT': + age_limit = 18 + + formats = [] + get_quality = qualities(['360p', '480p', '720p', '1080p']) + for fmt in data['videoFiles']: + formats.append({ + 'format_id': fmt['label'], + 'quality': get_quality(fmt['label']), + 'url': fmt['url'], + 'ext': fmt['format'], + + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'duration': duration, + 'upload_date': upload_date, + 'uploader_id': uploader_id, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/minhateca.py b/youtube_dl/extractor/minhateca.py new file mode 100644 index 000000000..14934b7ec --- /dev/null +++ b/youtube_dl/extractor/minhateca.py @@ -0,0 +1,72 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + int_or_none, + parse_duration, + parse_filesize, +) + + +class MinhatecaIE(InfoExtractor): + _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.' + _TEST = { + 'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)', + 'info_dict': { + 'id': '125848331', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + 'thumbnail': 're:^https?://.*\.jpg$', + 'filesize_approx': 1530000, + 'duration': 9, + 'view_count': int, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + token = self._html_search_regex( + r'<input name="__RequestVerificationToken".*?value="([^"]+)"', + webpage, 'request token') + token_data = [ + ('fileId', video_id), + ('__RequestVerificationToken', token), + ] + req = compat_urllib_request.Request( + 'http://minhateca.com.br/action/License/Download', + data=compat_urllib_parse.urlencode(token_data)) + req.add_header('Content-Type', 'application/x-www-form-urlencoded') + data = self._download_json( + req, video_id, note='Downloading metadata') + + video_url = data['redirectUrl'] + title_str = self._html_search_regex( + r'<h1.*?>(.*?)</h1>', webpage, 'title') + title, _, ext = title_str.rpartition('.') + filesize_approx = parse_filesize(self._html_search_regex( + r'<p class="fileSize">(.*?)</p>', + webpage, 'file size approximation', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'(?s)<p class="fileLeng[ht][th]">.*?class="bold">(.*?)<', + webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'<p class="downloadsCounter">([0-9]+)</p>', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': ext, + 'filesize_approx': filesize_approx, + 'duration': duration, + 'view_count': view_count, + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/ministrygrid.py b/youtube_dl/extractor/ministrygrid.py new file mode 100644 index 000000000..949ad11db --- /dev/null +++ b/youtube_dl/extractor/ministrygrid.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + smuggle_url, +) + + +class MinistryGridIE(InfoExtractor): + _VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])' + + _TEST = { + 'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers', + 'md5': '844be0d2a1340422759c2a9101bab017', + 'info_dict': { + 'id': '3453494717001', + 'ext': 'mp4', + 'title': 'The Gospel by Numbers', + 'description': 'Coming soon from T4G 2014!', + 'uploader': 'LifeWay Christian Resources (MG)', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + portlets_json = self._search_regex( + r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list') + portlets = json.loads(portlets_json) + pl_id = self._search_regex( + r'<!--\s*p_l_id - ([0-9]+)<br>', webpage, 'p_l_id') + + for i, portlet in enumerate(portlets): + portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet) + portlet_code = self._download_webpage( + portlet_url, video_id, + note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)), + fatal=False) + video_iframe_url = self._search_regex( + r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe', + default=None) + if video_iframe_url: + surl = smuggle_url( + video_iframe_url, {'force_videoid': video_id}) + return { + '_type': 'url', + 'id': video_id, + 'url': surl, + } + + raise ExtractorError('Could not find video iframe in any portlets') diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py new file mode 100644 index 000000000..6691521e5 --- /dev/null +++ b/youtube_dl/extractor/mitele.py @@ -0,0 +1,69 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urlparse, + get_element_by_attribute, + parse_duration, + strip_jsonp, +) + + +class MiTeleIE(InfoExtractor): + IE_NAME = 'mitele.es' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + + _TEST = { + 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', + 'md5': '6a75fe9d0d3275bead0cb683c616fddb', + 'info_dict': { + 'id': '0fce117d', + 'ext': 'mp4', + 'title': 'Programa 144 - Tor, la web invisible', + 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', + 'display_id': 'programa-144', + 'duration': 2913, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + episode = mobj.group('episode') + webpage = self._download_webpage(url, episode) + embed_data_json = self._search_regex( + r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', + flags=re.DOTALL + ).replace('\'', '"') + embed_data = json.loads(embed_data_json) + + domain = embed_data['mediaUrl'] + if not domain.startswith('http'): + # only happens in telecinco.es videos + domain = 'http://' + domain + info_url = compat_urlparse.urljoin( + domain, + compat_urllib_parse.unquote(embed_data['flashvars']['host']) + ) + info_el = self._download_xml(info_url, episode).find('./video/info') + + video_link = info_el.find('videoUrl/link').text + token_query = compat_urllib_parse.urlencode({'id': video_link}) + token_info = self._download_json( + embed_data['flashvars']['ov_tk'] + '?' + token_query, + episode, + transform_source=strip_jsonp + ) + + return { + 'id': embed_data['videoId'], + 'display_id': episode, + 'title': info_el.find('title').text, + 'url': token_info['tokenizedUrl'], + 'description': get_element_by_attribute('class', 'text', webpage), + 'thumbnail': info_el.find('thumb').text, + 'duration': parse_duration(info_el.find('duration').text), + } diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 5f64e7bd0..55cc33a3e 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + HEADRequest, int_or_none, parse_iso8601, ) @@ -32,22 +33,22 @@ class MixcloudIE(InfoExtractor): }, } - def check_urls(self, url_list): - """Returns 1st active url from list""" - for url in url_list: + def _get_url(self, track_id, template_url): + server_count = 30 + for i in range(server_count): + url = template_url % i try: # We only want to know if the request succeed # don't download the whole file - self._request_webpage(url, None, False) + self._request_webpage( + HEADRequest(url), track_id, + 'Checking URL %d/%d ...' % (i + 1, server_count + 1)) return url except ExtractorError: - url = None + pass return None - def _get_url(self, template_url): - return self.check_urls(template_url % i for i in range(30)) - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) uploader = mobj.group(1) @@ -60,16 +61,16 @@ class MixcloudIE(InfoExtractor): r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url') song_url = preview_url.replace('/previews/', '/c/originals/') template_url = re.sub(r'(stream\d*)', 'stream%d', song_url) - final_song_url = self._get_url(template_url) + final_song_url = self._get_url(track_id, template_url) if final_song_url is None: self.to_screen('Trying with m4a extension') template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/') - final_song_url = self._get_url(template_url) + final_song_url = self._get_url(track_id, template_url) if final_song_url is None: raise ExtractorError('Unable to extract track url') PREFIX = ( - r'<div class="cloudcast-play-button-container"' + r'<span class="play-button[^"]*?"' r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+') title = self._html_search_regex( PREFIX + r'm-title="([^"]+)"', webpage, 'title') diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py index 37c72bc53..1a241aca7 100644 --- a/youtube_dl/extractor/mlb.py +++ b/youtube_dl/extractor/mlb.py @@ -6,12 +6,11 @@ from .common import InfoExtractor from ..utils import ( parse_duration, parse_iso8601, - find_xpath_attr, ) class MLBIE(InfoExtractor): - _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)' + _VALID_URL = r'https?://m(?:lb)?\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)' _TESTS = [ { 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', @@ -69,6 +68,18 @@ class MLBIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', }, }, + { + 'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb', + 'only_matching': True, + }, + { + 'url': 'http://mlb.mlb.com/shared/video/embed/embed.html?content_id=36599553', + 'only_matching': True, + }, + { + 'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553', + 'only_matching': True, + }, ] def _real_extract(self, url): @@ -84,8 +95,9 @@ class MLBIE(InfoExtractor): duration = parse_duration(detail.find('./duration').text) timestamp = parse_iso8601(detail.attrib['date'][:-5]) - thumbnail = find_xpath_attr( - detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text + thumbnails = [{ + 'url': thumbnail.text, + } for thumbnail in detail.findall('./thumbnailScenarios/thumbnailScenario')] formats = [] for media_url in detail.findall('./url'): @@ -112,5 +124,5 @@ class MLBIE(InfoExtractor): 'duration': duration, 'timestamp': timestamp, 'formats': formats, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, } diff --git a/youtube_dl/extractor/moevideo.py b/youtube_dl/extractor/moevideo.py new file mode 100644 index 000000000..2ff79b9b8 --- /dev/null +++ b/youtube_dl/extractor/moevideo.py @@ -0,0 +1,112 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + int_or_none, +) + + +class MoeVideoIE(InfoExtractor): + IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net' + _VALID_URL = r'''(?x) + https?://(?P<host>(?:www\.)? + (?:(?:moevideo|playreplay|videochart)\.net))/ + (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)''' + _API_URL = 'http://api.letitbit.net/' + _API_KEY = 'tVL0gjqo5' + _TESTS = [ + { + 'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29', + 'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a', + 'info_dict': { + 'id': '00297.0036103fe3d513ef27915216fd29', + 'ext': 'flv', + 'title': 'Sink cut out machine', + 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8', + 'thumbnail': 're:^https?://.*\.jpg$', + 'width': 540, + 'height': 360, + 'duration': 179, + 'filesize': 17822500, + } + }, + { + 'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a', + 'md5': '74f0a014d5b661f0f0e2361300d1620e', + 'info_dict': { + 'id': '77107.7f325710a627383d40540d8e991a', + 'ext': 'flv', + 'title': 'Operacion Condor.', + 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3', + 'thumbnail': 're:^https?://.*\.jpg$', + 'width': 480, + 'height': 296, + 'duration': 6027, + 'filesize': 588257923, + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage( + 'http://%s/video/%s' % (mobj.group('host'), video_id), + video_id, 'Downloading webpage') + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + + r = [ + self._API_KEY, + [ + 'preview/flv_link', + { + 'uid': video_id, + }, + ], + ] + r_json = json.dumps(r) + post = compat_urllib_parse.urlencode({'r': r_json}) + req = compat_urllib_request.Request(self._API_URL, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + response = self._download_json(req, video_id) + if response['status'] != 'OK': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, response['data']), + expected=True + ) + item = response['data'][0] + video_url = item['link'] + duration = int_or_none(item['length']) + width = int_or_none(item['width']) + height = int_or_none(item['height']) + filesize = int_or_none(item['convert_size']) + + formats = [{ + 'format_id': 'sd', + 'http_headers': {'Range': 'bytes=0-'}, # Required to download + 'url': video_url, + 'width': width, + 'height': height, + 'filesize': filesize, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index b9430b09b..d658647e6 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -8,15 +10,17 @@ from ..utils import ( compat_urllib_parse, ) + class MofosexIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' + _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' _TEST = { - u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', - u'file': u'5018.mp4', - u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a', - u'info_dict': { - u"title": u"Japanese Teen Music Video", - u"age_limit": 18, + 'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', + 'md5': '1b2eb47ac33cc75d4a80e3026b613c5a', + 'info_dict': { + 'id': '5018', + 'ext': 'mp4', + 'title': 'Japanese Teen Music Video', + 'age_limit': 18, } } @@ -29,8 +33,8 @@ class MofosexIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url')) + video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url')) path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py new file mode 100644 index 000000000..0ba435dc5 --- /dev/null +++ b/youtube_dl/extractor/mojvideo.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_duration, +) + + +class MojvideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)' + _TEST = { + 'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906', + 'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7', + 'info_dict': { + 'id': '3d1ed4497707730b2906', + 'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic', + 'ext': 'mp4', + 'title': 'V avtu pred mano rdečelaska - Alfi Nipič', + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 242, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + # XML is malformed + playerapi = self._download_webpage( + 'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id) + + if '<error>true</error>' in playerapi: + error_desc = self._html_search_regex( + r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True) + + title = self._html_search_regex( + r'<title>([^<]+)</title>', playerapi, 'title') + video_url = self._html_search_regex( + r'<file>([^<]+)</file>', playerapi, 'video URL') + thumbnail = self._html_search_regex( + r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False) + duration = parse_duration(self._html_search_regex( + r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + } diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py new file mode 100644 index 000000000..1c4f589cc --- /dev/null +++ b/youtube_dl/extractor/moniker.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import os.path +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) + + +class MonikerIE(InfoExtractor): + IE_DESC = 'allmyvideos.net and vidspot.net' + _VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)' + + _TESTS = [{ + 'url': 'http://allmyvideos.net/jih3nce3x6wn', + 'md5': '710883dee1bfc370ecf9fa6a89307c88', + 'info_dict': { + 'id': 'jih3nce3x6wn', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + }, + }, { + 'url': 'http://vidspot.net/l2ngsmhs8ci5', + 'md5': '710883dee1bfc370ecf9fa6a89307c88', + 'info_dict': { + 'id': 'l2ngsmhs8ci5', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + }, + }, { + 'url': 'https://www.vidspot.net/l2ngsmhs8ci5', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + orig_webpage = self._download_webpage(url, video_id) + fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) + data = dict(fields) + + post = compat_urllib_parse.urlencode(data) + headers = { + b'Content-Type': b'application/x-www-form-urlencoded', + } + req = compat_urllib_request.Request(url, post, headers) + webpage = self._download_webpage( + req, video_id, note='Downloading video page ...') + + title = os.path.splitext(data['fname'])[0] + + # Could be several links with different quality + links = re.findall(r'"file" : "?(.+?)",', webpage) + # Assume the links are ordered in quality + formats = [{ + 'url': l, + 'quality': i, + } for i, l in enumerate(links)] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index 7d21ea18f..34a4bec3a 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -49,7 +49,7 @@ class MooshareIE(InfoExtractor): page = self._download_webpage(url, video_id, 'Downloading page') if re.search(r'>Video Not Found or Deleted<', page) is not None: - raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + raise ExtractorError('Video %s does not exist' % video_id, expected=True) hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash') title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title') @@ -111,4 +111,4 @@ class MooshareIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 6229b2173..97d5da626 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -5,20 +5,20 @@ import re from .common import InfoExtractor from ..utils import ( - int_or_none, + str_to_int, unified_strdate, ) class MotherlessIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P<id>[A-Z0-9]+)' + _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)' _TESTS = [ { 'url': 'http://motherless.com/AC3FFE1', - 'md5': '5527fef81d2e529215dad3c2d744a7d9', + 'md5': '310f62e325a9fafe64f68c0bccb6e75f', 'info_dict': { 'id': 'AC3FFE1', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Fucked in the ass while playing PS3', 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'upload_date': '20100913', @@ -40,33 +40,51 @@ class MotherlessIE(InfoExtractor): 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } + }, + { + 'url': 'http://motherless.com/g/cosplay/633979F', + 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0', + 'info_dict': { + 'id': '633979F', + 'ext': 'mp4', + 'title': 'Turtlette', + 'categories': ['superheroine heroine superher'], + 'upload_date': '20140827', + 'uploader_id': 'shade0230', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, + } } ] - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + def _real_extract(self, url): + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') - - video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url') + title = self._html_search_regex( + r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + video_url = self._html_search_regex( + r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL') age_limit = self._rta_search(webpage) + view_count = str_to_int(self._html_search_regex( + r'<strong>Views</strong>\s+([^<]+)<', + webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'<strong>Favorited</strong>\s+([^<]+)<', + webpage, 'like count', fatal=False)) - view_count = self._html_search_regex(r'<strong>Views</strong>\s+([^<]+)<', webpage, 'view_count') - - upload_date = self._html_search_regex(r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload_date') + upload_date = self._html_search_regex( + r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date') if 'Ago' in upload_date: days = int(re.search(r'([0-9]+)', upload_date).group(1)) upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') else: upload_date = unified_strdate(upload_date) - like_count = self._html_search_regex(r'<strong>Favorited</strong>\s+([^<]+)<', webpage, 'like_count') - comment_count = webpage.count('class="media-comment-contents"') - uploader_id = self._html_search_regex(r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id') + uploader_id = self._html_search_regex( + r'"thumb-member-username">\s+<a href="/m/([^"]+)"', + webpage, 'uploader_id') categories = self._html_search_meta('keywords', webpage) if categories: @@ -79,8 +97,8 @@ class MotherlessIE(InfoExtractor): 'uploader_id': uploader_id, 'thumbnail': self._og_search_thumbnail(webpage), 'categories': categories, - 'view_count': int_or_none(view_count.replace(',', '')), - 'like_count': int_or_none(like_count.replace(',', '')), + 'view_count': view_count, + 'like_count': like_count, 'comment_count': comment_count, 'age_limit': age_limit, 'url': video_url, diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py new file mode 100644 index 000000000..456807dd1 --- /dev/null +++ b/youtube_dl/extractor/movieclips.py @@ -0,0 +1,78 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_str, + clean_html, +) + + +class MovieClipsIE(InfoExtractor): + _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?' + _TEST = { + 'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/', + 'info_dict': { + 'id': 'Wy7ZU', + 'display_id': 'my-week-with-marilyn-movie-do-you-love-me', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'md5:e86795bd332fe3cff461e7c8dc542acb', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + show_id = display_id or video_id + + config = self._download_xml( + 'http://config.movieclips.com/player/config/%s' % video_id, + show_id, 'Downloading player config') + + if config.find('./country-region').text == 'false': + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True) + + properties = config.find('./video/properties') + smil_file = properties.attrib['smil_file'] + + smil = self._download_xml(smil_file, show_id, 'Downloading SMIL') + base_url = smil.find('./head/meta').attrib['base'] + + formats = [] + for video in smil.findall('./body/switch/video'): + vbr = int(video.attrib['system-bitrate']) / 1000 + src = video.attrib['src'] + formats.append({ + 'url': base_url, + 'play_path': src, + 'ext': src.split(':')[0], + 'vbr': vbr, + 'format_id': '%dk' % vbr, + }) + + self._sort_formats(formats) + + title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title']) + description = clean_html(compat_str(properties.attrib['clip_description'])) + thumbnail = properties.attrib['image'] + categories = properties.attrib['clip_categories'].split(',') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + } diff --git a/youtube_dl/extractor/moviezine.py b/youtube_dl/extractor/moviezine.py index 43146180a..f130b75c4 100644 --- a/youtube_dl/extractor/moviezine.py +++ b/youtube_dl/extractor/moviezine.py @@ -27,7 +27,7 @@ class MoviezineIE(InfoExtractor): webpage = self._download_webpage(url, video_id) jsplayer = self._download_webpage('http://www.moviezine.se/api/player.js?video=%s' % video_id, video_id, 'Downloading js api player') - formats =[{ + formats = [{ 'format_id': 'sd', 'url': self._html_search_regex(r'file: "(.+?)",', jsplayer, 'file'), 'quality': 0, diff --git a/youtube_dl/extractor/movshare.py b/youtube_dl/extractor/movshare.py index 4191cf7a0..6101063f2 100644 --- a/youtube_dl/extractor/movshare.py +++ b/youtube_dl/extractor/movshare.py @@ -24,4 +24,4 @@ class MovShareIE(NovaMovIE): 'title': 'dissapeared image', 'description': 'optical illusion dissapeared image magic illusion', } - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/mpora.py b/youtube_dl/extractor/mpora.py index 387935d4d..88c9501cd 100644 --- a/youtube_dl/extractor/mpora.py +++ b/youtube_dl/extractor/mpora.py @@ -44,7 +44,7 @@ class MporaIE(InfoExtractor): r'_([0-9]+)\.[a-zA-Z0-9]+$', src['src'], False, default=None) vcodec = src['type'].partition('/')[2] - + formats.append({ 'format_id': encoding_id + '-' + vcodec, 'url': src['src'], diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 228b42d2b..b482d6d4d 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -33,7 +33,7 @@ class MTVServicesInfoExtractor(InfoExtractor): m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url) if not m: return rtmp_video_url - base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' + base = 'http://viacommtvstrmfs.fplive.net/' return base + m.group('finalid') def _get_feed_url(self, uri): @@ -53,23 +53,23 @@ class MTVServicesInfoExtractor(InfoExtractor): # Otherwise we get a webpage that would execute some javascript req.add_header('Youtubedl-user-agent', 'curl/7') webpage = self._download_webpage(req, mtvn_id, - 'Downloading mobile page') + 'Downloading mobile page') metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url')) req = HEADRequest(metrics_url) response = self._request_webpage(req, mtvn_id, 'Resolving url') url = response.geturl() # Transform the url to get the best quality: url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1) - return [{'url': url,'ext': 'mp4'}] + return [{'url': url, 'ext': 'mp4'}] def _extract_video_formats(self, mdoc, mtvn_id): if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None: if mtvn_id is not None and self._MOBILE_TEMPLATE is not None: self.to_screen('The normal version is not available from your ' - 'country, trying with the mobile version') + 'country, trying with the mobile version') return self._extract_mobile_video_formats(mtvn_id) raise ExtractorError('This video is not available from your country.', - expected=True) + expected=True) formats = [] for rendition in mdoc.findall('.//rendition'): @@ -98,7 +98,7 @@ class MTVServicesInfoExtractor(InfoExtractor): mediagen_url += '&acceptMethods=fms' mediagen_doc = self._download_xml(mediagen_url, video_id, - 'Downloading video urls') + 'Downloading video urls') description_node = itemdoc.find('description') if description_node is not None: @@ -126,7 +126,7 @@ class MTVServicesInfoExtractor(InfoExtractor): # This a short id that's used in the webpage urls mtvn_id = None mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category', - 'scheme', 'urn:mtvn:id') + 'scheme', 'urn:mtvn:id') if mtvn_id_node is not None: mtvn_id = mtvn_id_node.text @@ -145,7 +145,8 @@ class MTVServicesInfoExtractor(InfoExtractor): idoc = self._download_xml( feed_url + '?' + data, video_id, 'Downloading info', transform_source=fix_xml_ampersands) - return [self._get_video_info(item) for item in idoc.findall('.//item')] + return self.playlist_result( + [self._get_video_info(item) for item in idoc.findall('.//item')]) def _real_extract(self, url): title = url_basename(url) @@ -163,7 +164,7 @@ class MTVServicesInfoExtractor(InfoExtractor): if mgid is None or ':' not in mgid: mgid = self._search_regex( [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'], - webpage, u'mgid') + webpage, 'mgid') return self._get_videos_info(mgid) @@ -186,7 +187,8 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor): def _get_feed_url(self, uri): video_id = self._id_from_uri(uri) site_id = uri.replace(video_id, '') - config_url = 'http://media.mtvnservices.com/pmt/e1/players/{0}/config.xml'.format(site_id) + config_url = ('http://media.mtvnservices.com/pmt/e1/players/{0}/' + 'context4/context5/config.xml'.format(site_id)) config_doc = self._download_xml(config_url, video_id) feed_node = config_doc.find('.//feed') feed_url = feed_node.text.strip().split('?')[0] @@ -238,15 +240,15 @@ class MTVIE(MTVServicesInfoExtractor): uri = mobj.groupdict().get('mgid') if uri is None: webpage = self._download_webpage(url, video_id) - + # Some videos come from Vevo.com m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage, re.DOTALL) if m_vevo: - vevo_id = m_vevo.group(1); + vevo_id = m_vevo.group(1) self.to_screen('Vevo video detected: %s' % vevo_id) return self.url_result('vevo:%s' % vevo_id, ie='Vevo') - + uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri') return self._get_videos_info(uri) diff --git a/youtube_dl/extractor/muenchentv.py b/youtube_dl/extractor/muenchentv.py new file mode 100644 index 000000000..b4e8ad17e --- /dev/null +++ b/youtube_dl/extractor/muenchentv.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + js_to_json, +) + + +class MuenchenTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?muenchen\.tv/livestream' + IE_DESC = 'münchen.tv' + _TEST = { + 'url': 'http://www.muenchen.tv/livestream/', + 'info_dict': { + 'id': '5334', + 'display_id': 'live', + 'ext': 'mp4', + 'title': 're:^münchen.tv-Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'is_live': True, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + display_id = 'live' + webpage = self._download_webpage(url, display_id) + + title = self._live_title(self._og_search_title(webpage)) + + data_js = self._search_regex( + r'(?s)\nplaylist:\s*(\[.*?}\]),related:', + webpage, 'playlist configuration') + data_json = js_to_json(data_js) + data = json.loads(data_json)[0] + + video_id = data['mediaid'] + thumbnail = data.get('image') + + formats = [] + for format_num, s in enumerate(data['sources']): + ext = determine_ext(s['file'], None) + label_str = s.get('label') + if label_str is None: + label_str = '_%d' % format_num + + if ext is None: + format_id = label_str + else: + format_id = '%s-%s' % (ext, label_str) + + formats.append({ + 'url': s['file'], + 'tbr': int_or_none(s.get('label')), + 'ext': 'mp4', + 'format_id': format_id, + 'preference': -100 if '.smil' in s['file'] else 0, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'is_live': True, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/musicplayon.py b/youtube_dl/extractor/musicplayon.py index 42d7a82a5..50d92b50a 100644 --- a/youtube_dl/extractor/musicplayon.py +++ b/youtube_dl/extractor/musicplayon.py @@ -72,4 +72,4 @@ class MusicPlayOnIE(InfoExtractor): 'duration': int_or_none(duration), 'view_count': int_or_none(view_count), 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/musicvault.py b/youtube_dl/extractor/musicvault.py new file mode 100644 index 000000000..ebb1eb8e9 --- /dev/null +++ b/youtube_dl/extractor/musicvault.py @@ -0,0 +1,76 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, +) + + +class MusicVaultIE(InfoExtractor): + _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html', + 'md5': '2cdbb3ae75f7fb3519821507d2fb3c15', + 'info_dict': { + 'id': '1010863', + 'ext': 'mp4', + 'uploader_id': 'the-allman-brothers-band', + 'title': 'Straight from the Heart', + 'duration': 244, + 'uploader': 'The Allman Brothers Band', + 'thumbnail': 're:^https?://.*/thumbnail/.*', + 'upload_date': '19811216', + 'location': 'Capitol Theatre (Passaic, NJ)', + 'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id) + + thumbnail = self._search_regex( + r'<meta itemprop="thumbnail" content="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + data_div = self._search_regex( + r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields') + uploader = self._html_search_regex( + r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False) + title = self._html_search_regex( + r'<h2.*?>(.*?)</h2>', data_div, 'title') + upload_date = unified_strdate(self._html_search_regex( + r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False)) + location = self._html_search_regex( + r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False) + + duration = parse_duration(self._html_search_meta('duration', webpage)) + + VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http' + kaltura_id = self._search_regex( + r'<div id="video-detail-player" data-kaltura-id="([^"]+)"', + webpage, 'kaltura ID') + video_url = VIDEO_URL_TEMPLATE % { + 'entry_id': kaltura_id, + 'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'), + 'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'), + } + + return { + 'id': mobj.group('id'), + 'url': video_url, + 'ext': 'mp4', + 'display_id': display_id, + 'uploader_id': mobj.group('uploader_id'), + 'thumbnail': thumbnail, + 'description': self._html_search_meta('description', webpage), + 'upload_date': upload_date, + 'location': location, + 'title': title, + 'uploader': uploader, + 'duration': duration, + } diff --git a/youtube_dl/extractor/muzu.py b/youtube_dl/extractor/muzu.py index 1772b7f9a..1e9cf8de9 100644 --- a/youtube_dl/extractor/muzu.py +++ b/youtube_dl/extractor/muzu.py @@ -1,64 +1,65 @@ -import re -import json +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - determine_ext, ) class MuzuTVIE(InfoExtractor): _VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)' - IE_NAME = u'muzu.tv' + IE_NAME = 'muzu.tv' _TEST = { - u'url': u'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/', - u'file': u'1981454.mp4', - u'md5': u'98f8b2c7bc50578d6a0364fff2bfb000', - u'info_dict': { - u'title': u'Cat Walk (Original Mix)', - u'description': u'md5:90e868994de201b2570e4e5854e19420', - u'uploader': u'MarcAshken featuring SOS', + 'url': 'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/', + 'md5': '98f8b2c7bc50578d6a0364fff2bfb000', + 'info_dict': { + 'id': '1981454', + 'ext': 'mp4', + 'title': 'Cat Walk (Original Mix)', + 'description': 'md5:90e868994de201b2570e4e5854e19420', + 'uploader': 'MarcAshken featuring SOS', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - info_data = compat_urllib_parse.urlencode({'format': 'json', - 'url': url, - }) - video_info_page = self._download_webpage('http://www.muzu.tv/api/oembed/?%s' % info_data, - video_id, u'Downloading video info') - info = json.loads(video_info_page) + info_data = compat_urllib_parse.urlencode({ + 'format': 'json', + 'url': url, + }) + info = self._download_json( + 'http://www.muzu.tv/api/oembed/?%s' % info_data, + video_id, 'Downloading video info') - player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id, - video_id, u'Downloading player info') - video_info = json.loads(player_info_page)['videos'][0] - for quality in ['1080' , '720', '480', '360']: + player_info = self._download_json( + 'http://player.muzu.tv/player/playerInit?ai=%s' % video_id, + video_id, 'Downloading player info') + video_info = player_info['videos'][0] + for quality in ['1080', '720', '480', '360']: if video_info.get('v%s' % quality): break - data = compat_urllib_parse.urlencode({'ai': video_id, - # Even if each time you watch a video the hash changes, - # it seems to work for different videos, and it will work - # even if you use any non empty string as a hash - 'viewhash': 'VBNff6djeV4HV5TRPW5kOHub2k', - 'device': 'web', - 'qv': quality, - }) - video_url_page = self._download_webpage('http://player.muzu.tv/player/requestVideo?%s' % data, - video_id, u'Downloading video url') - video_url_info = json.loads(video_url_page) + data = compat_urllib_parse.urlencode({ + 'ai': video_id, + # Even if each time you watch a video the hash changes, + # it seems to work for different videos, and it will work + # even if you use any non empty string as a hash + 'viewhash': 'VBNff6djeV4HV5TRPW5kOHub2k', + 'device': 'web', + 'qv': quality, + }) + video_url_info = self._download_json( + 'http://player.muzu.tv/player/requestVideo?%s' % data, + video_id, 'Downloading video url') video_url = video_url_info['url'] - return {'id': video_id, - 'title': info['title'], - 'url': video_url, - 'ext': determine_ext(video_url), - 'thumbnail': info['thumbnail_url'], - 'description': info['description'], - 'uploader': info['author_name'], - } + return { + 'id': video_id, + 'title': info['title'], + 'url': video_url, + 'thumbnail': info['thumbnail_url'], + 'description': info['description'], + 'uploader': info['author_name'], + } diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py index c16939f54..83414a232 100644 --- a/youtube_dl/extractor/myspace.py +++ b/youtube_dl/extractor/myspace.py @@ -1,12 +1,14 @@ +# encoding: utf-8 from __future__ import unicode_literals import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, ) +from ..utils import ExtractorError class MySpaceIE(InfoExtractor): @@ -14,33 +16,58 @@ class MySpaceIE(InfoExtractor): _TESTS = [ { - 'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689', + 'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919', 'info_dict': { - 'id': '100008689', + 'id': '109594919', 'ext': 'flv', - 'title': 'Viva La Vida', - 'description': 'The official Viva La Vida video, directed by Hype Williams', - 'uploader': 'Coldplay', - 'uploader_id': 'coldplay', + 'title': 'Little Big Town', + 'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.', + 'uploader': 'Five Minutes to the Stage', + 'uploader_id': 'fiveminutestothestage', }, 'params': { # rtmp download 'skip_download': True, }, }, - # song + # songs { - 'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242', + 'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681', 'info_dict': { - 'id': '39008454', + 'id': '93388656', 'ext': 'flv', - 'title': 'Darkness In My Heart', - 'uploader_id': 'spiderbags', + 'title': 'Of weakened soul...', + 'uploader': 'Killsorrow', + 'uploader_id': 'killsorrow', }, 'params': { # rtmp download 'skip_download': True, }, + }, { + 'add_ie': ['Vevo'], + 'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041', + 'info_dict': { + 'id': 'USZM20600099', + 'ext': 'mp4', + 'title': 'Animal I Have Become', + 'uploader': 'Three Days Grace', + 'timestamp': int, + 'upload_date': '20060502', + }, + 'skip': 'VEVO is only available in some countries', + }, { + 'add_ie': ['Youtube'], + 'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426', + 'info_dict': { + 'id': 'ypWvQgnJrSU', + 'ext': 'mp4', + 'title': 'Starset - First Light', + 'description': 'md5:2d5db6c9d11d527683bcda818d332414', + 'uploader': 'Jacob Soren', + 'uploader_id': 'SorenPromotions', + 'upload_date': '20140725', + } }, ] @@ -48,22 +75,47 @@ class MySpaceIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) + player_url = self._search_regex( + r'playerSwf":"([^"?]*)', webpage, 'player URL') if mobj.group('mediatype').startswith('music/song'): # songs don't store any useful info in the 'context' variable + song_data = self._search_regex( + r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id, + webpage, 'song_data', default=None, group=0) + if song_data is None: + # some songs in an album are not playable + self.report_warning( + '%s: No downloadable song on this page' % video_id) + return + def search_data(name): - return self._search_regex(r'data-%s="(.*?)"' % name, webpage, - name) + return self._search_regex( + r'''data-%s=([\'"])(?P<data>.*?)\1''' % name, + song_data, name, default='', group='data') streamUrl = search_data('stream-url') + if not streamUrl: + vevo_id = search_data('vevo-id') + youtube_id = search_data('youtube-id') + if vevo_id: + self.to_screen('Vevo video detected: %s' % vevo_id) + return self.url_result('vevo:%s' % vevo_id, ie='Vevo') + elif youtube_id: + self.to_screen('Youtube video detected: %s' % youtube_id) + return self.url_result(youtube_id, ie='Youtube') + else: + raise ExtractorError( + 'Found song but don\'t know how to download it') info = { 'id': video_id, 'title': self._og_search_title(webpage), + 'uploader': search_data('artist-name'), 'uploader_id': search_data('artist-username'), 'thumbnail': self._og_search_thumbnail(webpage), } else: - context = json.loads(self._search_regex(r'context = ({.*?});', webpage, - u'context')) + context = json.loads(self._search_regex( + r'context = ({.*?});', webpage, 'context')) video = context['video'] streamUrl = video['streamUrl'] info = { @@ -79,6 +131,50 @@ class MySpaceIE(InfoExtractor): info.update({ 'url': rtmp_url, 'play_path': play_path, + 'player_url': player_url, 'ext': 'flv', }) return info + + +class MySpaceAlbumIE(InfoExtractor): + IE_NAME = 'MySpace:album' + _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)' + + _TESTS = [{ + 'url': 'https://myspace.com/starset2/music/album/transmissions-19455773', + 'info_dict': { + 'title': 'Transmissions', + 'id': '19455773', + }, + 'playlist_count': 14, + 'skip': 'this album is only available in some countries', + }, { + 'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029', + 'info_dict': { + 'title': 'The Demo', + 'id': '18596029', + }, + 'playlist_count': 5, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + display_id = mobj.group('title') + playlist_id + webpage = self._download_webpage(url, display_id) + tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage) + if not tracks_paths: + raise ExtractorError( + '%s: No songs found, try using proxy' % display_id, + expected=True) + entries = [ + self.url_result(t_path, ie=MySpaceIE.ie_key()) + for t_path in tracks_paths] + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': display_id, + 'title': self._og_search_title(webpage), + 'entries': entries, + } diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py index 4fa0575f8..51e540814 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -13,9 +13,10 @@ class MySpassIE(InfoExtractor): _VALID_URL = r'http://www\.myspass\.de/.*' _TEST = { 'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/', - 'file': '11741.mp4', 'md5': '0b49f4844a068f8b33f4b7c88405862b', 'info_dict': { + 'id': '11741', + 'ext': 'mp4', "description": "Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?", "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2", }, diff --git a/youtube_dl/extractor/myvideo.py b/youtube_dl/extractor/myvideo.py index ccb5959c4..5e754fcff 100644 --- a/youtube_dl/extractor/myvideo.py +++ b/youtube_dl/extractor/myvideo.py @@ -7,11 +7,12 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_ord, compat_urllib_parse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, ) @@ -32,7 +33,7 @@ class MyVideoIE(InfoExtractor): # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git # Released into the Public Domain by Tristan Fischer on 2013-05-19 # https://github.com/rg3/youtube-dl/pull/842 - def __rc4crypt(self,data, key): + def __rc4crypt(self, data, key): x = 0 box = list(range(256)) for i in list(range(256)): @@ -48,17 +49,17 @@ class MyVideoIE(InfoExtractor): out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256]) return out - def __md5(self,s): + def __md5(self, s): return hashlib.md5(s).hexdigest().encode() - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') GK = ( - b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt' - b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3' - b'TnpsbA0KTVRkbU1tSTRNdz09' + b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt' + b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3' + b'TnpsbA0KTVRkbU1tSTRNdz09' ) # Get video webpage @@ -71,7 +72,7 @@ class MyVideoIE(InfoExtractor): video_url = mobj.group(1) + '.flv' video_title = self._html_search_regex('<title>([^<]+)</title>', - webpage, 'title') + webpage, 'title') return { 'id': video_id, @@ -161,7 +162,7 @@ class MyVideoIE(InfoExtractor): video_swfobj = compat_urllib_parse.unquote(video_swfobj) video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>", - webpage, 'title') + webpage, 'title') return { 'id': video_id, @@ -172,4 +173,3 @@ class MyVideoIE(InfoExtractor): 'play_path': video_playpath, 'player_url': video_swfobj, } - diff --git a/youtube_dl/extractor/myvidster.py b/youtube_dl/extractor/myvidster.py new file mode 100644 index 000000000..a94ab8358 --- /dev/null +++ b/youtube_dl/extractor/myvidster.py @@ -0,0 +1,29 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class MyVidsterIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?myvidster\.com/video/(?P<id>\d+)/' + + _TEST = { + 'url': 'http://www.myvidster.com/video/32059805/Hot_chemistry_with_raw_love_making', + 'md5': '95296d0231c1363222c3441af62dc4ca', + 'info_dict': { + 'id': '3685814', + 'title': 'md5:7d8427d6d02c4fbcef50fe269980c749', + 'upload_date': '20141027', + 'uploader_id': 'utkualp', + 'ext': 'mp4', + 'age_limit': 18, + }, + 'add_ie': ['XHamster'], + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + return self.url_result(self._html_search_regex( + r'rel="videolink" href="(?P<real_url>.*)">', + webpage, 'real video url')) diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index c0231c197..fbe34defd 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + clean_html, ) @@ -29,12 +30,17 @@ class NaverIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"', - webpage) + webpage) if m_id is None: + m_error = re.search( + r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>', + webpage) + if m_error: + raise ExtractorError(clean_html(m_error.group('msg')), expected=True) raise ExtractorError('couldn\'t extract vid and key') vid = m_id.group(1) key = m_id.group(2) - query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,}) + query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key, }) query_urls = compat_urllib_parse.urlencode({ 'masterVid': vid, 'protocol': 'p2p', @@ -59,7 +65,7 @@ class NaverIE(InfoExtractor): if domain.startswith('rtmp'): f.update({ 'ext': 'flv', - 'rtmp_protocol': '1', # rtmpt + 'rtmp_protocol': '1', # rtmpt }) formats.append(f) self._sort_formats(formats) diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 633b42f72..862b706bf 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -1,39 +1,47 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import ( + remove_end, + parse_duration, +) class NBAIE(InfoExtractor): - _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$' - _TEST = { + _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$' + _TESTS = [{ 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', - 'md5': u'c0edcfc37607344e2ff8f13c378c88a4', + 'md5': 'c0edcfc37607344e2ff8f13c378c88a4', 'info_dict': { 'id': '0021200253-okc-bkn-recap.nba', 'ext': 'mp4', - 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'title': 'Thunder vs. Nets', + 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', + 'duration': 181, }, - } + }, { + 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' shortened_video_id = video_id.rpartition('/')[2] - title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '') + title = remove_end( + self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') - description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False) + description = self._og_search_description(webpage) + duration = parse_duration( + self._html_search_meta('duration', webpage, 'duration')) return { 'id': shortened_video_id, 'url': video_url, 'title': title, 'description': description, + 'duration': duration, } diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index d2e4acbad..bf5132721 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -12,24 +12,37 @@ from ..utils import ( class NBCIE(InfoExtractor): - _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)' - - _TEST = { - 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', - 'md5': '54d0fbc33e0b853a65d7b4de5c06d64e', - 'info_dict': { - 'id': 'u1RInQZRN7QJ', - 'ext': 'flv', - 'title': 'I Am a Firefighter', - 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', + _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)' + + _TESTS = [ + { + 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', + # md5 checksum is not stable + 'info_dict': { + 'id': 'bTmnLCvIbaaH', + 'ext': 'flv', + 'title': 'I Am a Firefighter', + 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', + }, + }, + { + 'url': 'http://www.nbc.com/the-tonight-show/episodes/176', + 'info_dict': { + 'id': 'XwU9KZkp98TH', + 'ext': 'flv', + 'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen', + 'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.', + }, + 'skip': 'Only works from US', }, - } + ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url') + theplatform_url = self._search_regex( + '(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"', + webpage, 'theplatform url').replace('_no_endcard', '') if theplatform_url.startswith('//'): theplatform_url = 'http:' + theplatform_url return self.url_result(theplatform_url) @@ -57,7 +70,7 @@ class NBCNewsIE(InfoExtractor): 'md5': 'b2421750c9f260783721d898f4c42063', 'info_dict': { 'id': 'I1wpAI_zmhsQ', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', }, @@ -97,6 +110,8 @@ class NBCNewsIE(InfoExtractor): ] for base_url in base_urls: + if not base_url: + continue playlist_url = base_url + '?form=MPXNBCNewsAPI' all_videos = self._download_json(playlist_url, title)['videos'] diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 94d5ba982..f49c66690 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -18,16 +18,16 @@ class NDRIE(InfoExtractor): _TESTS = [ { - 'url': 'http://www.ndr.de/fernsehen/media/dienordreportage325.html', - 'md5': '4a4eeafd17c3058b65f0c8f091355855', + 'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html', + 'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c', 'note': 'Video file', 'info_dict': { - 'id': '325', + 'id': '25866', 'ext': 'mp4', - 'title': 'Blaue Bohnen aus Blocken', - 'description': 'md5:190d71ba2ccddc805ed01547718963bc', - 'duration': 1715, - }, + 'title': 'Kartoffeltage in der Lewitz', + 'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8', + 'duration': 166, + } }, { 'url': 'http://www.ndr.de/info/audio51535.html', @@ -67,7 +67,7 @@ class NDRIE(InfoExtractor): thumbnail = None - video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page) + video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page) if video_url: thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page) if thumbnails: @@ -91,4 +91,4 @@ class NDRIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py index 2e72e8915..cd117b04e 100644 --- a/youtube_dl/extractor/newgrounds.py +++ b/youtube_dl/extractor/newgrounds.py @@ -23,12 +23,12 @@ class NewgroundsIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) music_id = mobj.group('id') webpage = self._download_webpage(url, music_id) - + title = self._html_search_regex( r',"name":"([^"]+)",', webpage, 'music title') uploader = self._html_search_regex( r',"artist":"([^"]+)",', webpage, 'music uploader') - + music_url_json_string = self._html_search_regex( r'({"url":"[^"]+"),', webpage, 'music url') + '}' music_url_json = json.loads(music_url_json_string) diff --git a/youtube_dl/extractor/newstube.py b/youtube_dl/extractor/newstube.py index 551bd4d7a..85fcad06b 100644 --- a/youtube_dl/extractor/newstube.py +++ b/youtube_dl/extractor/newstube.py @@ -89,4 +89,4 @@ class NewstubeIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/nfb.py b/youtube_dl/extractor/nfb.py index ba7b77a46..7ce1d481d 100644 --- a/youtube_dl/extractor/nfb.py +++ b/youtube_dl/extractor/nfb.py @@ -38,12 +38,12 @@ class NFBIE(InfoExtractor): page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page') uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"', - page, 'director id', fatal=False) + page, 'director id', fatal=False) uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>', - page, 'director name', fatal=False) + page, 'director name', fatal=False) request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id, - compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii')) + compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii')) request.add_header('Content-Type', 'application/x-www-form-urlencoded') request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf') @@ -93,4 +93,4 @@ class NFBIE(InfoExtractor): 'uploader': uploader, 'uploader_id': uploader_id, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/nfl.py b/youtube_dl/extractor/nfl.py new file mode 100644 index 000000000..cc7c921c3 --- /dev/null +++ b/youtube_dl/extractor/nfl.py @@ -0,0 +1,144 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse_urlparse, + int_or_none, + remove_end, +) + + +class NFLIE(InfoExtractor): + IE_NAME = 'nfl.com' + _VALID_URL = r'''(?x)https?:// + (?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/ + (?:.+?/)* + (?P<id>(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))''' + _TESTS = [ + { + 'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights', + 'md5': '394ef771ddcd1354f665b471d78ec4c6', + 'info_dict': { + 'id': '0ap3000000398478', + 'ext': 'mp4', + 'title': 'Week 3: Redskins vs. Eagles highlights', + 'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478', + 'upload_date': '20140921', + 'timestamp': 1411337580, + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + { + 'url': 'http://prod.www.steelers.clubs.nfl.com/video-and-audio/videos/LIVE_Post_Game_vs_Browns/9d72f26a-9e2b-4718-84d3-09fb4046c266', + 'md5': 'cf85bdb4bc49f6e9d3816d130c78279c', + 'info_dict': { + 'id': '9d72f26a-9e2b-4718-84d3-09fb4046c266', + 'ext': 'mp4', + 'title': 'LIVE: Post Game vs. Browns', + 'description': 'md5:6a97f7e5ebeb4c0e69a418a89e0636e8', + 'upload_date': '20131229', + 'timestamp': 1388354455, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + ] + + @staticmethod + def prepend_host(host, url): + if not url.startswith('http'): + if not url.startswith('/'): + url = '/%s' % url + url = 'http://{0:}{1:}'.format(host, url) + return url + + @staticmethod + def format_from_stream(stream, protocol, host, path_prefix='', + preference=0, note=None): + url = '{protocol:}://{host:}/{prefix:}{path:}'.format( + protocol=protocol, + host=host, + prefix=path_prefix, + path=stream.get('path'), + ) + return { + 'url': url, + 'vbr': int_or_none(stream.get('rate', 0), 1000), + 'preference': preference, + 'format_note': note, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, host = mobj.group('id'), mobj.group('host') + + webpage = self._download_webpage(url, video_id) + + config_url = NFLIE.prepend_host(host, self._search_regex( + r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL')) + config = self._download_json(config_url, video_id, + note='Downloading player config') + url_template = NFLIE.prepend_host( + host, '{contentURLTemplate:}'.format(**config)) + video_data = self._download_json( + url_template.format(id=video_id), video_id) + + formats = [] + cdn_data = video_data.get('cdnData', {}) + streams = cdn_data.get('bitrateInfo', []) + if cdn_data.get('format') == 'EXTERNAL_HTTP_STREAM': + parts = compat_urllib_parse_urlparse(cdn_data.get('uri')) + protocol, host = parts.scheme, parts.netloc + for stream in streams: + formats.append( + NFLIE.format_from_stream(stream, protocol, host)) + else: + cdns = config.get('cdns') + if not cdns: + raise ExtractorError('Failed to get CDN data', expected=True) + + for name, cdn in cdns.items(): + # LimeLight streams don't seem to work + if cdn.get('name') == 'LIMELIGHT': + continue + + protocol = cdn.get('protocol') + host = remove_end(cdn.get('host', ''), '/') + if not (protocol and host): + continue + + prefix = cdn.get('pathprefix', '') + if prefix and not prefix.endswith('/'): + prefix = '%s/' % prefix + + preference = 0 + if protocol == 'rtmp': + preference = -2 + elif 'prog' in name.lower(): + preference = 1 + + for stream in streams: + formats.append( + NFLIE.format_from_stream(stream, protocol, host, + prefix, preference, name)) + + self._sort_formats(formats) + + thumbnail = None + for q in ('xl', 'l', 'm', 's', 'xs'): + thumbnail = video_data.get('imagePaths', {}).get(q) + if thumbnail: + break + + return { + 'id': video_id, + 'title': video_data.get('headline'), + 'formats': formats, + 'description': video_data.get('caption'), + 'duration': video_data.get('duration'), + 'thumbnail': thumbnail, + 'timestamp': int_or_none(video_data.get('posted'), 1000), + } diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 2edd806a3..b2f40344f 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -1,11 +1,16 @@ +from __future__ import unicode_literals + import re import json +import os from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, compat_urllib_parse, - determine_ext, + compat_urllib_parse_urlparse +) +from ..utils import ( unified_strdate, ) @@ -20,21 +25,26 @@ class NHLBaseInfoExtractor(InfoExtractor): self.report_extraction(video_id) initial_video_url = info['publishPoint'] - data = compat_urllib_parse.urlencode({ - 'type': 'fvod', - 'path': initial_video_url.replace('.mp4', '_sd.mp4'), - }) - path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data - path_doc = self._download_xml(path_url, video_id, - u'Downloading final video url') - video_url = path_doc.find('path').text + if info['formats'] == '1': + parsed_url = compat_urllib_parse_urlparse(initial_video_url) + filename, ext = os.path.splitext(parsed_url.path) + path = '%s_sd%s' % (filename, ext) + data = compat_urllib_parse.urlencode({ + 'type': 'fvod', + 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:]) + }) + path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data + path_doc = self._download_xml( + path_url, video_id, 'Downloading final video url') + video_url = path_doc.find('path').text + else: + video_url = initial_video_url join = compat_urlparse.urljoin return { 'id': video_id, 'title': info['name'], 'url': video_url, - 'ext': determine_ext(video_url), 'description': info['description'], 'duration': int(info['duration']), 'thumbnail': join(join(video_url, '/u/'), info['bigImage']), @@ -43,41 +53,68 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): - IE_NAME = u'nhl.com' - _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)' - - _TEST = { - u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', - u'file': u'453614.mp4', - u'info_dict': { - u'title': u'Quick clip: Weise 4-3 goal vs Flames', - u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.', - u'duration': 18, - u'upload_date': u'20131006', + IE_NAME = 'nhl.com' + _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9a-z-]+)' + + _TESTS = [{ + 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', + 'md5': 'db704a4ea09e8d3988c85e36cc892d09', + 'info_dict': { + 'id': '453614', + 'ext': 'mp4', + 'title': 'Quick clip: Weise 4-3 goal vs Flames', + 'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.', + 'duration': 18, + 'upload_date': '20131006', }, - } + }, { + 'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h', + 'md5': 'd22e82bc592f52d37d24b03531ee9696', + 'info_dict': { + 'id': '2014020024-628-h', + 'ext': 'mp4', + 'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)', + 'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014', + 'duration': 0, + 'upload_date': '20141011', + }, + }, { + 'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802', + 'md5': 'c78fc64ea01777e426cfc202b746c825', + 'info_dict': { + 'id': '58665', + 'ext': 'flv', + 'title': 'Classic Game In Six - April 22, 1979', + 'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.', + 'duration': 400, + 'upload_date': '20100129' + }, + }, { + 'url': 'http://video.flames.nhl.com/videocenter/console?id=630616', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id - info_json = self._download_webpage(json_url, video_id, - u'Downloading info json') - info_json = self._fix_json(info_json) - info = json.loads(info_json)[0] - return self._extract_video(info) + data = self._download_json( + json_url, video_id, transform_source=self._fix_json) + return self._extract_video(data[0]) class NHLVideocenterIE(NHLBaseInfoExtractor): - IE_NAME = u'nhl.com:videocenter' - IE_DESC = u'NHL videocenter category' - _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?' - - @classmethod - def suitable(cls, url): - if NHLIE.suitable(url): - return False - return super(NHLVideocenterIE, cls).suitable(url) + IE_NAME = 'nhl.com:videocenter' + IE_DESC = 'NHL videocenter category' + _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' + _TEST = { + 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999', + 'info_dict': { + 'id': '999', + 'title': 'Highlights', + }, + 'playlist_count': 12, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -86,10 +123,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): cat_id = self._search_regex( [r'var defaultCatId = "(.+?)";', r'{statusIndex:0,index:0,.*?id:(.*?),'], - webpage, u'category id') + webpage, 'category id') playlist_title = self._html_search_regex( r'tab0"[^>]*?>(.*?)</td>', - webpage, u'playlist title', flags=re.DOTALL).lower().capitalize() + webpage, 'playlist title', flags=re.DOTALL).lower().capitalize() data = compat_urllib_parse.urlencode({ 'cid': cat_id, @@ -103,10 +140,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): response = self._download_webpage(request_url, playlist_title) response = self._fix_json(response) if not response.strip(): - self._downloader.report_warning(u'Got an empty reponse, trying ' - u'adding the "newvideos" parameter') + self._downloader.report_warning('Got an empty reponse, trying ' + 'adding the "newvideos" parameter') response = self._download_webpage(request_url + '&newvideos=true', - playlist_title) + playlist_title) response = self._fix_json(response) videos = json.loads(response) @@ -114,5 +151,5 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): '_type': 'playlist', 'title': playlist_title, 'id': cat_id, - 'entries': [self._extract_video(i) for i in videos], + 'entries': [self._extract_video(v) for v in videos], } diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index c0c139b5d..1d9c1a096 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor from ..utils import ( @@ -11,6 +12,7 @@ from ..utils import ( unified_strdate, parse_duration, int_or_none, + ExtractorError, ) @@ -39,18 +41,17 @@ class NiconicoIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)' _NETRC_MACHINE = 'niconico' - # Determine whether the downloader uses authentication to download video - _AUTHENTICATE = False + # Determine whether the downloader used authentication to download video + _AUTHENTICATED = False def _real_initialize(self): - if self._downloader.params.get('username', None) is not None: - self._AUTHENTICATE = True - - if self._AUTHENTICATE: - self._login() + self._login() def _login(self): (username, password) = self._get_login_info() + # No authentication to be performed + if not username: + return True # Log in login_form_strs = { @@ -68,6 +69,8 @@ class NiconicoIE(InfoExtractor): if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None: self._downloader.report_warning('unable to log in: bad username or password') return False + # Successful login + self._AUTHENTICATED = True return True def _real_extract(self, url): @@ -82,7 +85,7 @@ class NiconicoIE(InfoExtractor): 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, note='Downloading video info page') - if self._AUTHENTICATE: + if self._AUTHENTICATED: # Get flv info flv_info_webpage = self._download_webpage( 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, @@ -106,6 +109,9 @@ class NiconicoIE(InfoExtractor): flv_info_request, video_id, note='Downloading flv info', errnote='Unable to download flv info') + if 'deleted=' in flv_info_webpage: + raise ExtractorError('The video has been deleted.', + expected=True) video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] # Start extracting information @@ -145,3 +151,37 @@ class NiconicoIE(InfoExtractor): 'duration': duration, 'webpage_url': webpage_url, } + + +class NiconicoPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)' + + _TEST = { + 'url': 'http://www.nicovideo.jp/mylist/27411728', + 'info_dict': { + 'id': '27411728', + 'title': 'AKB48のオールナイトニッポン', + }, + 'playlist_mincount': 225, + } + + def _real_extract(self, url): + list_id = self._match_id(url) + webpage = self._download_webpage(url, list_id) + + entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);', + webpage, 'entries') + entries = json.loads(entries_json) + entries = [{ + '_type': 'url', + 'ie_key': NiconicoIE.ie_key(), + 'url': ('http://www.nicovideo.jp/watch/%s' % + entry['item_data']['video_id']), + } for entry in entries] + + return { + '_type': 'playlist', + 'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'), + 'id': list_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py index 33daa0dec..16a02ad79 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -27,8 +27,7 @@ class NineGagIE(InfoExtractor): "thumbnail": "re:^https?://", }, 'add_ie': ['Youtube'] - }, - { + }, { 'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar', 'info_dict': { 'id': 'KklwM', diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index da203538d..7d2ff7b9a 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -2,10 +2,15 @@ from __future__ import unicode_literals import re +import time +import hashlib from .common import InfoExtractor from ..utils import ( + compat_urllib_request, + compat_urllib_parse, ExtractorError, + clean_html, unified_strdate, compat_str, ) @@ -13,6 +18,10 @@ from ..utils import ( class NocoIE(InfoExtractor): _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)' + _LOGIN_URL = 'http://noco.tv/do.php' + _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s' + _SUB_LANG_TEMPLATE = '&sub_lang=%s' + _NETRC_MACHINE = 'noco' _TEST = { 'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/', @@ -30,54 +39,111 @@ class NocoIE(InfoExtractor): 'skip': 'Requires noco account', } + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'a': 'login', + 'cookie': '1', + 'username': username, + 'password': password, + } + request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8') + + login = self._download_json(request, None, 'Logging in as %s' % username) + + if 'erreur' in login: + raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) + + def _call_api(self, path, video_id, note, sub_lang=None): + ts = compat_str(int(time.time() * 1000)) + tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest() + url = self._API_URL_TEMPLATE % (path, ts, tk) + if sub_lang: + url += self._SUB_LANG_TEMPLATE % sub_lang + + resp = self._download_json(url, video_id, note) + + if isinstance(resp, dict) and resp.get('error'): + self._raise_error(resp['error'], resp['description']) + + return resp + + def _raise_error(self, error, description): + raise ExtractorError( + '%s returned error: %s - %s' % (self.IE_NAME, error, description), + expected=True) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - medias = self._download_json( - 'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON') + medias = self._call_api( + 'shows/%s/medias' % video_id, + video_id, 'Downloading video JSON') - formats = [] + qualities = self._call_api( + 'qualities', + video_id, 'Downloading qualities JSON') - for fmt in medias['fr']['video_list']['default']['quality_list']: - format_id = fmt['quality_key'] + formats = [] - file = self._download_json( - 'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id), - video_id, 'Downloading %s video JSON' % format_id) - - file_url = file['file'] - if not file_url: - continue - - if file_url == 'forbidden': - raise ExtractorError( - '%s returned error: %s - %s' % ( - self.IE_NAME, file['popmessage']['title'], file['popmessage']['message']), - expected=True) - - formats.append({ - 'url': file_url, - 'format_id': format_id, - 'width': fmt['res_width'], - 'height': fmt['res_lines'], - 'abr': fmt['audiobitrate'], - 'vbr': fmt['videobitrate'], - 'filesize': fmt['filesize'], - 'format_note': fmt['quality_name'], - 'preference': fmt['priority'], - }) + for lang, lang_dict in medias['fr']['video_list'].items(): + for format_id, fmt in lang_dict['quality_list'].items(): + format_id_extended = '%s-%s' % (lang, format_id) if lang != 'none' else format_id + + video = self._call_api( + 'shows/%s/video/%s/fr' % (video_id, format_id.lower()), + video_id, 'Downloading %s video JSON' % format_id_extended, + lang if lang != 'none' else None) + + file_url = video['file'] + if not file_url: + continue + + if file_url in ['forbidden', 'not found']: + popmessage = video['popmessage'] + self._raise_error(popmessage['title'], popmessage['message']) + + formats.append({ + 'url': file_url, + 'format_id': format_id_extended, + 'width': fmt['res_width'], + 'height': fmt['res_lines'], + 'abr': fmt['audiobitrate'], + 'vbr': fmt['videobitrate'], + 'filesize': fmt['filesize'], + 'format_note': qualities[format_id]['quality_name'], + 'preference': qualities[format_id]['priority'], + }) self._sort_formats(formats) - show = self._download_json( - 'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0] + show = self._call_api( + 'shows/by_id/%s' % video_id, + video_id, 'Downloading show JSON')[0] - upload_date = unified_strdate(show['indexed']) + upload_date = unified_strdate(show['online_date_start_utc']) uploader = show['partner_name'] uploader_id = show['partner_key'] duration = show['duration_ms'] / 1000.0 - thumbnail = show['screenshot'] + + thumbnails = [] + for thumbnail_key, thumbnail_url in show.items(): + m = re.search(r'^screenshot_(?P<width>\d+)x(?P<height>\d+)$', thumbnail_key) + if not m: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) episode = show.get('show_TT') or show.get('show_OT') family = show.get('family_TT') or show.get('family_OT') @@ -97,10 +163,10 @@ class NocoIE(InfoExtractor): 'id': video_id, 'title': title, 'description': description, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, 'upload_date': upload_date, 'uploader': uploader, 'uploader_id': uploader_id, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py index 25e71a56e..3d35b11ac 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -31,9 +31,9 @@ class NormalbootsIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>', - webpage, 'uploader') + webpage, 'uploader') raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', - webpage, 'date') + webpage, 'date') video_upload_date = unified_strdate(raw_upload_date) player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url') diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py new file mode 100644 index 000000000..f3be8f552 --- /dev/null +++ b/youtube_dl/extractor/nosvideo.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + urlencode_postdata, + xpath_text, + xpath_with_ns, +) + +_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'}) + + +class NosVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \ + '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?' + _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml' + _FILE_DELETED_REGEX = r'<b>File Not Found</b>' + _TEST = { + 'url': 'http://nosvideo.com/?v=mu8fle7g7rpq', + 'md5': '6124ed47130d8be3eacae635b071e6b6', + 'info_dict': { + 'id': 'mu8fle7g7rpq', + 'ext': 'mp4', + 'title': 'big_buck_bunny_480p_surround-fix.avi.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + fields = { + 'id': video_id, + 'op': 'download1', + 'method_free': 'Continue to Video', + } + req = compat_urllib_request.Request(url, urlencode_postdata(fields)) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage(req, video_id, + 'Downloading download page') + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID') + playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id) + playlist = self._download_xml(playlist_url, video_id) + + track = playlist.find(_x('.//xspf:track')) + if track is None: + raise ExtractorError( + 'XML playlist is missing the \'track\' element', + expected=True) + title = xpath_text(track, _x('./xspf:title'), 'title') + url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True) + thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail') + if title is not None: + title = title.strip() + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 2e7ab1e4f..38d05e466 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -66,4 +66,4 @@ class NovaMovIE(InfoExtractor): 'url': video_url, 'title': title, 'description': description - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index 1c5e9401f..6b2f3f55a 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,3 +1,4 @@ +# encoding: utf-8 from __future__ import unicode_literals import re @@ -8,19 +9,34 @@ from ..utils import ExtractorError class NownessIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' - - _TEST = { - 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'md5': '068bc0202558c2e391924cb8cc470676', - 'info_dict': { - 'id': '2520295746001', - 'ext': 'mp4', - 'description': 'Candor: The Art of Gesticulation', - 'uploader': 'Nowness', - 'title': 'Candor: The Art of Gesticulation', - } - } + _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' + + _TESTS = [ + { + 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', + 'md5': '068bc0202558c2e391924cb8cc470676', + 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', + 'title': 'Candor: The Art of Gesticulation', + 'description': 'Candor: The Art of Gesticulation', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + { + 'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr', + 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', + 'info_dict': { + 'id': '3716354522001', + 'ext': 'mp4', + 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index bfba18418..ecb38de2d 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -25,4 +25,4 @@ class NowVideoIE(NovaMovIE): 'title': 'youtubedl test video _BaW_jenozKc.mp4', 'description': 'Description', } - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 12e85a716..ce31694a5 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -5,6 +5,10 @@ import re from .common import InfoExtractor from ..utils import ( unified_strdate, + parse_duration, + qualities, + strip_jsonp, + url_basename, ) @@ -12,51 +16,124 @@ class NPOIE(InfoExtractor): IE_NAME = 'npo.nl' _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)' - _TEST = { - 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', - 'md5': '4b3f9c429157ec4775f2c9cb7b911016', - 'info_dict': { - 'id': 'VPWON_1220719', - 'ext': 'mp4', - 'title': 'Nieuwsuur', - 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', - 'upload_date': '20140622', + _TESTS = [ + { + 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', + 'md5': '4b3f9c429157ec4775f2c9cb7b911016', + 'info_dict': { + 'id': 'VPWON_1220719', + 'ext': 'm4v', + 'title': 'Nieuwsuur', + 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', + 'upload_date': '20140622', + }, }, - } + { + 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800', + 'md5': 'da50a5787dbfc1603c4ad80f31c5120b', + 'info_dict': { + 'id': 'VARA_101191800', + 'ext': 'm4v', + 'title': 'De Mega Mike & Mega Thomas show', + 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', + 'upload_date': '20090227', + 'duration': 2400, + }, + }, + { + 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', + 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', + 'info_dict': { + 'id': 'VPWON_1169289', + 'ext': 'm4v', + 'title': 'Tegenlicht', + 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', + 'upload_date': '20130225', + 'duration': 3000, + }, + } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + return self._get_info(video_id) + def _get_info(self, video_id): metadata = self._download_json( 'http://e.omroep.nl/metadata/aflevering/%s' % video_id, video_id, # We have to remove the javascript callback - transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//.*$', r'\1', j) + transform_source=strip_jsonp, ) token_page = self._download_webpage( 'http://ida.omroep.nl/npoplayer/i.js', video_id, note='Downloading token' ) - token = self._search_regex(r'npoplayer.token = "(.+?)"', token_page, 'token') - streams_info = self._download_json( - 'http://ida.omroep.nl/odi/?prid=%s&puboptions=h264_std&adaptive=yes&token=%s' % (video_id, token), - video_id - ) + token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token') - stream_info = self._download_json( - streams_info['streams'][0] + '&type=json', - video_id, - 'Downloading stream info' - ) + formats = [] + quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) + for format_id in metadata['pubopties']: + format_info = self._download_json( + 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token), + video_id, 'Downloading %s JSON' % format_id) + if format_info.get('error_code', 0) or format_info.get('errorcode', 0): + continue + streams = format_info.get('streams') + if streams: + video_info = self._download_json( + streams[0] + '&type=json', + video_id, 'Downloading %s stream JSON' % format_id) + else: + video_info = format_info + video_url = video_info.get('url') + if not video_url: + continue + if format_id == 'adaptive': + formats.extend(self._extract_m3u8_formats(video_url, video_id)) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'quality': quality(format_id), + }) + self._sort_formats(formats) return { 'id': video_id, 'title': metadata['titel'], - 'ext': 'mp4', - 'url': stream_info['url'], 'description': metadata['info'], - 'thumbnail': metadata['images'][-1]['url'], - 'upload_date': unified_strdate(metadata['gidsdatum']), + 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], + 'upload_date': unified_strdate(metadata.get('gidsdatum')), + 'duration': parse_duration(metadata.get('tijdsduur')), + 'formats': formats, } + + +class TegenlichtVproIE(NPOIE): + IE_NAME = 'tegenlicht.vpro.nl' + _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?' + + _TESTS = [ + { + 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html', + 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', + 'info_dict': { + 'id': 'VPWON_1169289', + 'ext': 'm4v', + 'title': 'Tegenlicht', + 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', + 'upload_date': '20130225', + }, + }, + ] + + def _real_extract(self, url): + name = url_basename(url) + webpage = self._download_webpage(url, name) + urn = self._html_search_meta('mediaurn', webpage) + info_page = self._download_json( + 'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name) + return self._get_info(info_page['mid']) diff --git a/youtube_dl/extractor/ntv.py b/youtube_dl/extractor/ntv.py index ed60314ec..ee740cd9c 100644 --- a/youtube_dl/extractor/ntv.py +++ b/youtube_dl/extractor/ntv.py @@ -130,7 +130,7 @@ class NTVIE(InfoExtractor): 'rtmp_conn': 'B:1', 'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128', 'page_url': 'http://www.ntv.ru', - 'flash_ver': 'LNX 11,2,202,341', + 'flash_version': 'LNX 11,2,202,341', 'rtmp_live': True, 'ext': 'flv', 'filesize': int(size.text), @@ -145,4 +145,4 @@ class NTVIE(InfoExtractor): 'duration': duration, 'view_count': view_count, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 280328b78..449c8a6a3 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -38,7 +38,7 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( request, video_id, 'Downloading %s page' % format_id) video_url = self._html_search_regex( - r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False) + r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False) if not video_url: continue formats.append({ @@ -49,21 +49,26 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') title = self._html_search_regex( - r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip() - thumbnail = self._html_search_regex( - r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', - webpage, 'thumbnail URL', fatal=False) + [r'<span title="([^"]+)">', + r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( - r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False)) + r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_regex( - r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False)) + r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) return { 'id': video_id, 'title': title, - 'thumbnail': 'http://m.nuvid.com%s' % thumbnail, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, 'duration': duration, 'upload_date': upload_date, 'age_limit': 18, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 7bf105d38..56e1cad3b 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -74,4 +74,4 @@ class NYTimesIE(InfoExtractor): 'duration': duration, 'formats': formats, 'thumbnails': thumbnails, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py deleted file mode 100644 index 38971ab4d..000000000 --- a/youtube_dl/extractor/oe1.py +++ /dev/null @@ -1,40 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import calendar -import datetime -import re - -from .common import InfoExtractor - -# audios on oe1.orf.at are only available for 7 days, so we can't -# add tests. - - -class OE1IE(InfoExtractor): - IE_DESC = 'oe1.orf.at' - _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') - - data = self._download_json( - 'http://oe1.orf.at/programm/%s/konsole' % show_id, - show_id - ) - - timestamp = datetime.datetime.strptime('%s %s' % ( - data['item']['day_label'], - data['item']['time'] - ), '%d.%m.%Y %H:%M') - unix_timestamp = calendar.timegm(timestamp.utctimetuple()) - - return { - 'id': show_id, - 'title': data['item']['title'], - 'url': data['item']['url_stream'], - 'ext': 'mp3', - 'description': data['item'].get('info'), - 'timestamp': unix_timestamp - } diff --git a/youtube_dl/extractor/oktoberfesttv.py b/youtube_dl/extractor/oktoberfesttv.py new file mode 100644 index 000000000..4a41c0542 --- /dev/null +++ b/youtube_dl/extractor/oktoberfesttv.py @@ -0,0 +1,47 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class OktoberfestTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)' + + _TEST = { + 'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt', + 'info_dict': { + 'id': 'hb-zelt', + 'ext': 'mp4', + 'title': 're:^Live-Kamera: Hofbräuzelt [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'thumbnail': 're:^https?://.*\.jpg$', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._live_title(self._html_search_regex( + r'<h1><strong>.*?</strong>(.*?)</h1>', webpage, 'title')) + + clip = self._search_regex( + r"clip:\s*\{\s*url:\s*'([^']+)'", webpage, 'clip') + ncurl = self._search_regex( + r"netConnectionUrl:\s*'([^']+)'", webpage, 'rtmp base') + video_url = ncurl + clip + thumbnail = self._search_regex( + r"canvas:\s*\{\s*backgroundImage:\s*'url\(([^)]+)\)'", webpage, + 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'ext': 'mp4', + 'is_live': True, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 13f12824c..f17a52858 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -3,23 +3,38 @@ import re import json from .common import InfoExtractor -from ..utils import unescapeHTML +from ..utils import ( + unescapeHTML, + ExtractorError, +) class OoyalaIE(InfoExtractor): _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' - _TEST = { - # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video - 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', - 'info_dict': { - 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'ext': 'mp4', - 'title': 'Explaining Data Recovery from Hard Drives and SSDs', - 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + _TESTS = [ + { + # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video + 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', + 'info_dict': { + 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'ext': 'mp4', + 'title': 'Explaining Data Recovery from Hard Drives and SSDs', + 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + }, + }, { + # Only available for ipad + 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'md5': '4b9754921fddb68106e48c142e2a01e6', + 'info_dict': { + 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'ext': 'mp4', + 'title': 'Simulation Overview - Levels of Simulation', + 'description': '', + }, }, - } + ] @staticmethod def _url_for_embed_code(embed_code): @@ -28,7 +43,7 @@ class OoyalaIE(InfoExtractor): @classmethod def _build_url_result(cls, embed_code): return cls.url_result(cls._url_for_embed_code(embed_code), - ie=cls.ie_key()) + ie=cls.ie_key()) def _extract_result(self, info, more_info): return { @@ -47,13 +62,30 @@ class OoyalaIE(InfoExtractor): player = self._download_webpage(player_url, embedCode) mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', player, 'mobile player url') - mobile_player = self._download_webpage(mobile_url, embedCode) - videos_info = self._search_regex( - r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', - mobile_player, 'info').replace('\\"','"') - videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"') + # Looks like some videos are only available for particular devices + # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0 + # is only available for ipad) + # Working around with fetching URLs for all the devices found starting with 'unknown' + # until we succeed or eventually fail for each device. + devices = re.findall(r'device\s*=\s*"([^"]+)";', player) + devices.remove('unknown') + devices.insert(0, 'unknown') + for device in devices: + mobile_player = self._download_webpage( + '%s&device=%s' % (mobile_url, device), embedCode, + 'Downloading mobile player JS for %s device' % device) + videos_info = self._search_regex( + r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', + mobile_player, 'info', fatal=False, default=None) + if videos_info: + break + if not videos_info: + raise ExtractorError('Unable to extract info') + videos_info = videos_info.replace('\\"', '"') + videos_more_info = self._search_regex( + r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"') videos_info = json.loads(videos_info) - videos_more_info =json.loads(videos_more_info) + videos_more_info = json.loads(videos_more_info) if videos_more_info.get('lineup'): videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] @@ -65,4 +97,3 @@ class OoyalaIE(InfoExtractor): } else: return self._extract_result(videos_info[0], videos_more_info) - diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 03421d1d5..572a234ad 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals import json import re +import calendar +import datetime from .common import InfoExtractor from ..utils import ( @@ -12,7 +14,9 @@ from ..utils import ( ) -class ORFIE(InfoExtractor): +class ORFTVthekIE(InfoExtractor): + IE_NAME = 'orf:tvthek' + IE_DESC = 'ORF TVthek' _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)' _TEST = { @@ -105,3 +109,73 @@ class ORFIE(InfoExtractor): 'entries': entries, 'id': playlist_id, } + + +# Audios on ORF radio are only available for 7 days, so we can't add tests. + + +class ORFOE1IE(InfoExtractor): + IE_NAME = 'orf:oe1' + IE_DESC = 'Radio Österreich 1' + _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('id') + + data = self._download_json( + 'http://oe1.orf.at/programm/%s/konsole' % show_id, + show_id + ) + + timestamp = datetime.datetime.strptime('%s %s' % ( + data['item']['day_label'], + data['item']['time'] + ), '%d.%m.%Y %H:%M') + unix_timestamp = calendar.timegm(timestamp.utctimetuple()) + + return { + 'id': show_id, + 'title': data['item']['title'], + 'url': data['item']['url_stream'], + 'ext': 'mp3', + 'description': data['item'].get('info'), + 'timestamp': unix_timestamp + } + + +class ORFFM4IE(InfoExtractor): + IE_DESC = 'orf:fm4' + IE_DESC = 'radio FM4' + _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_date = mobj.group('date') + show_id = mobj.group('show') + + data = self._download_json( + 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), + show_id + ) + + def extract_entry_dict(info, title, subtitle): + return { + 'id': info['loopStreamId'].replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'], + 'title': title, + 'description': subtitle, + 'duration': (info['end'] - info['start']) / 1000, + 'timestamp': info['start'] / 1000, + 'ext': 'mp3' + } + + entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + + return { + '_type': 'playlist', + 'id': show_id, + 'title': data['title'], + 'description': data['subtitle'], + 'entries': entries + } diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py new file mode 100644 index 000000000..5429592a7 --- /dev/null +++ b/youtube_dl/extractor/patreon.py @@ -0,0 +1,100 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, +) + + +class PatreonIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(.+)' + _TESTS = [ + { + 'url': 'http://www.patreon.com/creation?hid=743933', + 'md5': 'e25505eec1053a6e6813b8ed369875cc', + 'info_dict': { + 'id': '743933', + 'ext': 'mp3', + 'title': 'Episode 166: David Smalley of Dogma Debate', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + ] + + # Currently Patreon exposes download URL via hidden CSS, so login is not + # needed. Keeping this commented for when this inevitably changes. + ''' + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'redirectUrl': 'http://www.patreon.com/', + 'email': username, + 'password': password, + } + + request = compat_urllib_request.Request( + 'https://www.patreon.com/processLogin', + compat_urllib_parse.urlencode(login_form).encode('utf-8') + ) + login_page = self._download_webpage(request, None, note='Logging in as %s' % username) + + if re.search(r'onLoginFailed', login_page): + raise ExtractorError('Unable to login, incorrect username and/or password', expected=True) + + def _real_initialize(self): + self._login() + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage).strip() + + attach_fn = self._html_search_regex( + r'<div class="attach"><a target="_blank" href="([^"]+)">', + webpage, 'attachment URL', default=None) + if attach_fn is not None: + video_url = 'http://www.patreon.com' + attach_fn + thumbnail = self._og_search_thumbnail(webpage) + uploader = self._html_search_regex( + r'<strong>(.*?)</strong> is creating', webpage, 'uploader') + else: + playlist_js = self._search_regex( + r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])', + webpage, 'playlist JSON') + playlist_json = js_to_json(playlist_js) + playlist = json.loads(playlist_json) + data = playlist[0] + video_url = self._proto_relative_url(data['mp3']) + thumbnail = self._proto_relative_url(data.get('cover')) + uploader = data.get('artist') + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'title': title, + 'uploader': uploader, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 64cded707..6118ed5c2 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + unified_strdate, US_RATINGS, ) @@ -11,36 +12,115 @@ from ..utils import ( class PBSIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?: - # Direct video URL - video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? | - # Article with embedded player - (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) | + # Direct video URL + video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? | + # Article with embedded player (or direct video) + (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ ) ''' - _TEST = { - 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', - 'md5': 'ce1888486f0908d555a8093cac9a7362', - 'info_dict': { - 'id': '2365006249', - 'ext': 'mp4', - 'title': 'A More Perfect Union', - 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', - 'duration': 3190, + _TESTS = [ + { + 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', + 'md5': 'ce1888486f0908d555a8093cac9a7362', + 'info_dict': { + 'id': '2365006249', + 'ext': 'mp4', + 'title': 'A More Perfect Union', + 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', + 'duration': 3190, + }, + }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/', + 'md5': '143c98aa54a346738a3d78f54c925321', + 'info_dict': { + 'id': '2365297690', + 'ext': 'mp4', + 'title': 'Losing Iraq', + 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e', + 'duration': 5050, + }, + }, + { + 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', + 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', + 'info_dict': { + 'id': '2201174722', + 'ext': 'mp4', + 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', + 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', + 'duration': 801, + }, + }, + { + 'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/', + 'md5': 'c62859342be2a0358d6c9eb306595978', + 'info_dict': { + 'id': '2365297708', + 'ext': 'mp4', + 'description': 'md5:68d87ef760660eb564455eb30ca464fe', + 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full', + 'duration': 6559, + 'thumbnail': 're:^https?://.*\.jpg$', + } }, - } + { + 'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html', + 'md5': '908f3e5473a693b266b84e25e1cf9703', + 'info_dict': { + 'id': '2365160389', + 'display_id': 'killer-typhoon', + 'ext': 'mp4', + 'description': 'md5:c741d14e979fc53228c575894094f157', + 'title': 'Killer Typhoon', + 'duration': 3172, + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20140122', + } + }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/', + 'info_dict': { + 'id': 'united-states-of-secrets', + }, + 'playlist_count': 2, + } + ] - def _real_extract(self, url): + def _extract_webpage(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') display_id = presumptive_id if presumptive_id: webpage = self._download_webpage(url, display_id) + + upload_date = unified_strdate(self._search_regex( + r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"', + webpage, 'upload date', default=None)) + + # tabbed frontline videos + tabbed_videos = re.findall( + r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage) + if tabbed_videos: + return tabbed_videos, presumptive_id, upload_date + + MEDIA_ID_REGEXES = [ + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed + r'class="coveplayerid">([^<]+)<', # coveplayer + r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer + ] + + media_id = self._search_regex( + MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) + if media_id: + return media_id, presumptive_id, upload_date + url = self._search_regex( - r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', + r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', webpage, 'player URL') mobj = re.match(self._VALID_URL, url) @@ -57,6 +137,17 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id + return video_id, display_id, None + + def _real_extract(self, url): + video_id, display_id, upload_date = self._extract_webpage(url) + + if isinstance(video_id, list): + entries = [self.url_result( + 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id) + for vid_id in video_id] + return self.playlist_result(entries, display_id) + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) @@ -67,6 +158,7 @@ class PBSIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'title': info['title'], 'url': info['alternate_encoding']['url'], 'ext': 'mp4', @@ -74,4 +166,5 @@ class PBSIE(InfoExtractor): 'thumbnail': info.get('image_url'), 'duration': info.get('duration'), 'age_limit': age_limit, + 'upload_date': upload_date, } diff --git a/youtube_dl/extractor/phoenix.py b/youtube_dl/extractor/phoenix.py new file mode 100644 index 000000000..a20672c0c --- /dev/null +++ b/youtube_dl/extractor/phoenix.py @@ -0,0 +1,31 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from .zdf import extract_from_xml_url + + +class PhoenixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.phoenix.de/content/884301', + 'md5': 'ed249f045256150c92e72dbb70eadec6', + 'info_dict': { + 'id': '884301', + 'ext': 'mp4', + 'title': 'Michael Krons mit Hans-Werner Sinn', + 'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr', + 'upload_date': '20141025', + 'uploader': 'Im Dialog', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + internal_id = self._search_regex( + r'<div class="phx_vod" id="phx_vod_([0-9]+)"', + webpage, 'internal video ID') + + api_url = 'http://www.phoenix.de/php/zdfplayer-v1.3/data/beitragsDetails.php?ak=web&id=%s' % internal_id + return extract_from_xml_url(self, video_id, api_url) diff --git a/youtube_dl/extractor/photobucket.py b/youtube_dl/extractor/photobucket.py index 8aa69c46e..b4389e0b6 100644 --- a/youtube_dl/extractor/photobucket.py +++ b/youtube_dl/extractor/photobucket.py @@ -31,7 +31,7 @@ class PhotobucketIE(InfoExtractor): # Extract URL, uploader, and title from webpage self.report_extraction(video_id) info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);', - webpage, 'info json') + webpage, 'info json') info = json.loads(info_json) url = compat_urllib_parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url')) return { diff --git a/youtube_dl/extractor/planetaplay.py b/youtube_dl/extractor/planetaplay.py new file mode 100644 index 000000000..596c621d7 --- /dev/null +++ b/youtube_dl/extractor/planetaplay.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class PlanetaPlayIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?planetaplay\.com/\?sng=(?P<id>[0-9]+)' + _API_URL = 'http://planetaplay.com/action/playlist/?sng={0:}' + _THUMBNAIL_URL = 'http://planetaplay.com/img/thumb/{thumb:}' + _TEST = { + 'url': 'http://planetaplay.com/?sng=3586', + 'md5': '9d569dceb7251a4e01355d5aea60f9db', + 'info_dict': { + 'id': '3586', + 'ext': 'flv', + 'title': 'md5:e829428ee28b1deed00de90de49d1da1', + } + } + + _SONG_FORMATS = { + 'lq': (0, 'http://www.planetaplay.com/videoplayback/{med_hash:}'), + 'hq': (1, 'http://www.planetaplay.com/videoplayback/hi/{med_hash:}'), + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + response = self._download_json( + self._API_URL.format(video_id), video_id)['response'] + try: + data = response.get('data')[0] + except IndexError: + raise ExtractorError( + '%s: failed to get the playlist' % self.IE_NAME, expected=True) + + title = '{song_artists:} - {sng_name:}'.format(**data) + thumbnail = self._THUMBNAIL_URL.format(**data) + + formats = [] + for format_id, (quality, url_template) in self._SONG_FORMATS.items(): + formats.append({ + 'format_id': format_id, + 'url': url_template.format(**data), + 'quality': quality, + 'ext': 'flv', + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py new file mode 100644 index 000000000..17880471d --- /dev/null +++ b/youtube_dl/extractor/played.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import os.path + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, +) + + +class PlayedIE(InfoExtractor): + IE_NAME = 'played.to' + _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)' + + _TEST = { + 'url': 'http://played.to/j2f2sfiiukgt', + 'md5': 'c2bd75a368e82980e7257bf500c00637', + 'info_dict': { + 'id': 'j2f2sfiiukgt', + 'ext': 'flv', + 'title': 'youtube-dl_test_video.mp4', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + orig_webpage = self._download_webpage(url, video_id) + + m_error = re.search( + r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage) + if m_error: + raise ExtractorError(m_error.group('msg'), expected=True) + + fields = re.findall( + r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage) + data = dict(fields) + + self._sleep(2, video_id) + + post = compat_urllib_parse.urlencode(data) + headers = { + b'Content-Type': b'application/x-www-form-urlencoded', + } + req = compat_urllib_request.Request(url, post, headers) + webpage = self._download_webpage( + req, video_id, note='Downloading video page ...') + + title = os.path.splitext(data['fname'])[0] + + video_url = self._search_regex( + r'file: "?(.+?)",', webpage, 'video URL') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + } diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py new file mode 100644 index 000000000..ebc046804 --- /dev/null +++ b/youtube_dl/extractor/playfm.py @@ -0,0 +1,86 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + ExtractorError, + float_or_none, + int_or_none, + str_to_int, +) + + +class PlayFMIE(InfoExtractor): + IE_NAME = 'play.fm' + _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])' + + _TEST = { + 'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220', + 'md5': 'c505f8307825a245d0c7ad1850001f22', + 'info_dict': { + 'id': '137220', + 'ext': 'mp3', + 'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12', + 'uploader': 'Sven Tasnadi', + 'uploader_id': 'sventasnadi', + 'duration': 5627.428, + 'upload_date': '20140712', + 'view_count': int, + 'comment_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + upload_date = mobj.group('upload_date') + + rec_data = compat_urllib_parse.urlencode({'rec_id': video_id}) + req = compat_urllib_request.Request( + 'http://www.play.fm/flexRead/recording', data=rec_data) + req.add_header('Content-Type', 'application/x-www-form-urlencoded') + rec_doc = self._download_xml(req, video_id) + + error_node = rec_doc.find('./error') + if error_node is not None: + raise ExtractorError('An error occured: %s (code %s)' % ( + error_node.text, rec_doc.find('./status').text)) + + recording = rec_doc.find('./recording') + title = recording.find('./title').text + view_count = str_to_int(recording.find('./stats/playcount').text) + comment_count = str_to_int(recording.find('./stats/comments').text) + duration = float_or_none(recording.find('./duration').text, scale=1000) + thumbnail = recording.find('./image').text + + artist = recording.find('./artists/artist') + uploader = artist.find('./name').text + uploader_id = artist.find('./slug').text + + video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % ( + 'http:', recording.find('./url').text, + recording.find('./_class').text, recording.find('./file_id').text, + rec_doc.find('./uuid').text, video_id, + rec_doc.find('./jingle/file_id').text, + 'http%3A%2F%2Fwww.play.fm%2Fplayer', + ) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'filesize': int_or_none(recording.find('./size').text), + 'title': title, + 'upload_date': upload_date, + 'view_count': view_count, + 'comment_count': comment_count, + 'duration': duration, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + } diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py index b1322f13f..cd3905acb 100644 --- a/youtube_dl/extractor/playvid.py +++ b/youtube_dl/extractor/playvid.py @@ -4,6 +4,8 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, + clean_html, compat_urllib_parse, ) @@ -28,6 +30,11 @@ class PlayvidIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + m_error = re.search( + r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage) + if m_error: + raise ExtractorError(clean_html(m_error.group('msg')), expected=True) + video_title = None duration = None video_thumbnail = None diff --git a/youtube_dl/extractor/podomatic.py b/youtube_dl/extractor/podomatic.py index ffafd2380..f20946a2b 100644 --- a/youtube_dl/extractor/podomatic.py +++ b/youtube_dl/extractor/podomatic.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import int_or_none + class PodomaticIE(InfoExtractor): IE_NAME = 'podomatic' _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)' diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 718fe9aba..954dfccb7 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -4,19 +4,26 @@ import re import json from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + js_to_json, + qualities, +) class PornHdIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)' + _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?' _TEST = { 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'md5': '956b8ca569f7f4d8ec563e2c41598441', 'info_dict': { 'id': '1962', + 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', 'title': 'Sierra loves doing laundry', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', + 'thumbnail': 're:^https?://.*\.jpg', + 'view_count': int, 'age_limit': 18, } } @@ -24,54 +31,36 @@ class PornHdIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + display_id = mobj.group('display_id') - webpage = self._download_webpage(url, video_id) - - title = self._og_search_title(webpage) - TITLE_SUFFIX = ' porn HD Video | PornHD.com ' - if title.endswith(TITLE_SUFFIX): - title = title[:-len(TITLE_SUFFIX)] + webpage = self._download_webpage(url, display_id or video_id) + title = self._html_search_regex( + r'<title>(.+) porn HD.+?</title>', webpage, 'title') description = self._html_search_regex( r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) view_count = int_or_none(self._html_search_regex( - r'(\d+) views </span>', webpage, 'view count', fatal=False)) - - formats = [ - { - 'url': format_url, - 'ext': format.lower(), - 'format_id': '%s-%s' % (format.lower(), quality.lower()), - 'quality': 1 if quality.lower() == 'high' else 0, - } for format, quality, format_url in re.findall( - r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage) - ] - - mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage) - if mobj: - flashvars = json.loads(mobj.group('flashvars')) - formats.extend([ - { - 'url': flashvars['hashlink'].replace('?noProxy=1', ''), - 'ext': 'flv', - 'format_id': 'flv-low', - 'quality': 0, - }, - { - 'url': flashvars['hd'].replace('?noProxy=1', ''), - 'ext': 'flv', - 'format_id': 'flv-high', - 'quality': 1, - } - ]) - thumbnail = flashvars['urlWallpaper'] - else: - thumbnail = self._og_search_thumbnail(webpage) + r'(\d+) views\s*</span>', webpage, 'view count', fatal=False)) + thumbnail = self._search_regex( + r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False) + quality = qualities(['sd', 'hd']) + sources = json.loads(js_to_json(self._search_regex( + r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}\);", webpage, 'sources'))) + formats = [] + for container, s in sources.items(): + for qname, video_url in s.items(): + formats.append({ + 'url': video_url, + 'container': container, + 'format_id': '%s-%s' % (container, qname), + 'quality': quality(qname), + }) self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 4118ee956..2ca15b717 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -16,13 +16,14 @@ from ..aes import ( class PornHubIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))' + _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)' _TEST = { 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', - 'file': '648719015.mp4', 'md5': '882f488fa1f0026f023f33576004a2ed', 'info_dict': { - "uploader": "BABES-COM", + 'id': '648719015', + 'ext': 'mp4', + "uploader": "Babes", "title": "Seductive Indian beauty strips down and fingers her pink pussy", "age_limit": 18 } @@ -35,9 +36,7 @@ class PornHubIE(InfoExtractor): return count def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') @@ -45,7 +44,7 @@ class PornHubIE(InfoExtractor): video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'(?s)From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<', + r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<', webpage, 'uploader', fatal=False) thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False) if thumbnail: @@ -57,7 +56,7 @@ class PornHubIE(InfoExtractor): comment_count = self._extract_count( r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment') - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) + video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) if webpage.find('"encrypted":true') != -1: password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password')) video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py index 35dc5a9ff..5253aa3d3 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -9,15 +11,16 @@ from ..utils import ( class PornotubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' _TEST = { - u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', - u'file': u'1689755.flv', - u'md5': u'374dd6dcedd24234453b295209aa69b6', - u'info_dict': { - u"upload_date": u"20090708", - u"title": u"Marilyn-Monroe-Bathing", - u"age_limit": 18 + 'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', + 'md5': '374dd6dcedd24234453b295209aa69b6', + 'info_dict': { + 'id': '1689755', + 'ext': 'flv', + 'upload_date': '20090708', + 'title': 'Marilyn-Monroe-Bathing', + 'age_limit': 18 } } @@ -32,22 +35,22 @@ class PornotubeIE(InfoExtractor): # Get the video URL VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') + video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') video_url = compat_urllib_parse.unquote(video_url) - #Get the uploaded date + # Get the uploaded date VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) - if upload_date: upload_date = unified_strdate(upload_date) + upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) + if upload_date: + upload_date = unified_strdate(upload_date) age_limit = self._rta_search(webpage) - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'age_limit': age_limit} - - return [info] + return { + 'id': video_id, + 'url': video_url, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/pornoxo.py b/youtube_dl/extractor/pornoxo.py new file mode 100644 index 000000000..202f58673 --- /dev/null +++ b/youtube_dl/extractor/pornoxo.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + str_to_int, +) + + +class PornoXOIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html' + _TEST = { + 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html', + 'md5': '582f28ecbaa9e6e24cb90f50f524ce87', + 'info_dict': { + 'id': '7564', + 'ext': 'flv', + 'title': 'Striptease From Sexy Secretary!', + 'description': 'Striptease From Sexy Secretary!', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title') + + description = self._html_search_regex( + r'<meta name="description" content="([^"]+)\s*featuring', + webpage, 'description', fatal=False) + + thumbnail = self._html_search_regex( + r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) + + view_count = str_to_int(self._html_search_regex( + r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False)) + + categories_str = self._html_search_regex( + r'<meta name="description" content=".*featuring\s*([^"]+)"', + webpage, 'categories', fatal=False) + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py new file mode 100644 index 000000000..7fcde086c --- /dev/null +++ b/youtube_dl/extractor/promptfile.py @@ -0,0 +1,65 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class PromptFileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' + _TEST = { + 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', + 'md5': 'd1451b6302da7215485837aaea882c4c', + 'info_dict': { + 'id': 'D21B4746E9-F01462F0FF', + 'ext': 'mp4', + 'title': 'Birds.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + fields = dict(re.findall(r'''(?x)type="hidden"\s+ + name="(.+?)"\s+ + value="(.*?)" + ''', webpage)) + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL') + title = self._html_search_regex( + r'<span.+title="([^"]+)">', webpage, 'title') + thumbnail = self._html_search_regex( + r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"', + webpage, 'thumbnail', fatal=False, flags=re.DOTALL) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': determine_ext(title), + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index da64a1a7b..1262793c8 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -85,7 +85,7 @@ class ProSiebenSat1IE(InfoExtractor): 'ext': 'mp4', 'title': 'Im Interview: Kai Wiesinger', 'description': 'md5:e4e5370652ec63b95023e914190b4eb9', - 'upload_date': '20140225', + 'upload_date': '20140203', 'duration': 522.56, }, 'params': { @@ -100,7 +100,7 @@ class ProSiebenSat1IE(InfoExtractor): 'ext': 'mp4', 'title': 'Jagd auf Fertigkost im Elsthal - Teil 2', 'description': 'md5:2669cde3febe9bce13904f701e774eb6', - 'upload_date': '20140225', + 'upload_date': '20141014', 'duration': 2410.44, }, 'params': { @@ -144,8 +144,7 @@ class ProSiebenSat1IE(InfoExtractor): 'id': '2156342', 'ext': 'mp4', 'title': 'Kurztrips zum Valentinstag', - 'description': 'md5:8ba6301e70351ae0bedf8da00f7ba528', - 'upload_date': '20130206', + 'description': 'Romantischer Kurztrip zum Valentinstag? Wir verraten, was sich hier wirklich lohnt.', 'duration': 307.24, }, 'params': { @@ -153,12 +152,22 @@ class ProSiebenSat1IE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.prosieben.de/tv/joko-gegen-klaas/videos/playlists/episode-8-ganze-folge-playlist', + 'info_dict': { + 'id': '439664', + 'title': 'Episode 8 - Ganze Folge - Playlist', + 'description': 'md5:63b8963e71f481782aeea877658dec84', + }, + 'playlist_count': 2, + }, ] _CLIPID_REGEXES = [ r'"clip_id"\s*:\s+"(\d+)"', r'clipid: "(\d+)"', r'clip[iI]d=(\d+)', + r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)", ] _TITLE_REGEXES = [ r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', @@ -179,14 +188,20 @@ class ProSiebenSat1IE(InfoExtractor): r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>', r'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>', ] + _PAGE_TYPE_REGEXES = [ + r'<meta name="page_type" content="([^"]+)">', + r"'itemType'\s*:\s*'([^']*)'", + ] + _PLAYLIST_ID_REGEXES = [ + r'content[iI]d=(\d+)', + r"'itemId'\s*:\s*'([^']*)'", + ] + _PLAYLIST_CLIP_REGEXES = [ + r'(?s)data-qvt=.+?<a href="([^"]+)"', + ] - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage(url, video_id, 'Downloading page') - - clip_id = self._html_search_regex(self._CLIPID_REGEXES, page, 'clip id') + def _extract_clip(self, url, webpage): + clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id') access_token = 'testclient' client_name = 'kolibri-1.2.5' @@ -235,12 +250,12 @@ class ProSiebenSat1IE(InfoExtractor): urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON') - title = self._html_search_regex(self._TITLE_REGEXES, page, 'title') - description = self._html_search_regex(self._DESCRIPTION_REGEXES, page, 'description', fatal=False) - thumbnail = self._og_search_thumbnail(page) + title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title') + description = self._html_search_regex(self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) upload_date = unified_strdate(self._html_search_regex( - self._UPLOAD_DATE_REGEXES, page, 'upload date', fatal=False)) + self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None)) formats = [] @@ -249,7 +264,7 @@ class ProSiebenSat1IE(InfoExtractor): urls_sources = urls_sources.values() def fix_bitrate(bitrate): - return bitrate / 1000 if bitrate % 1000 == 0 else bitrate + return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate for source in urls_sources: protocol = source['protocol'] @@ -283,4 +298,32 @@ class ProSiebenSat1IE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } + + def _extract_playlist(self, url, webpage): + playlist_id = self._html_search_regex( + self._PLAYLIST_ID_REGEXES, webpage, 'playlist id') + for regex in self._PLAYLIST_CLIP_REGEXES: + playlist_clips = re.findall(regex, webpage) + if playlist_clips: + title = self._html_search_regex( + self._TITLE_REGEXES, webpage, 'title') + description = self._html_search_regex( + self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False) + entries = [ + self.url_result( + re.match('(.+?//.+?)/', url).group(1) + clip_path, + 'ProSiebenSat1') + for clip_path in playlist_clips] + return self.playlist_result(entries, playlist_id, title, description) + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + page_type = self._search_regex( + self._PAGE_TYPE_REGEXES, webpage, + 'page type', default='clip').lower() + if page_type == 'clip': + return self._extract_clip(url, webpage) + elif page_type == 'playlist': + return self._extract_playlist(url, webpage) diff --git a/youtube_dl/extractor/quickvid.py b/youtube_dl/extractor/quickvid.py new file mode 100644 index 000000000..3bc78060d --- /dev/null +++ b/youtube_dl/extractor/quickvid.py @@ -0,0 +1,51 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + determine_ext, + int_or_none, +) + + +class QuickVidIE(InfoExtractor): + _VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P<id>[a-zA-Z_0-9-]+)' + _TEST = { + 'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx', + 'md5': 'c0c72dd473f260c06c808a05d19acdc5', + 'info_dict': { + 'id': 'sUQT3RCG8dx', + 'ext': 'mp4', + 'title': 'Nick Offerman\'s Summer Reading Recap', + 'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$', + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title') + view_count = int_or_none(self._html_search_regex( + r'(?s)<div id="views">(.*?)</div>', + webpage, 'view count', fatal=False)) + video_code = self._search_regex( + r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code') + formats = [ + { + 'url': compat_urlparse.urljoin(url, src), + 'format_id': determine_ext(src, None), + } for src in re.findall('<source\s+src="([^"]+)"', video_code) + ] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': self._og_search_thumbnail(webpage), + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/radiode.py b/youtube_dl/extractor/radiode.py new file mode 100644 index 000000000..f95bc9454 --- /dev/null +++ b/youtube_dl/extractor/radiode.py @@ -0,0 +1,55 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor + + +class RadioDeIE(InfoExtractor): + IE_NAME = 'radio.de' + _VALID_URL = r'https?://(?P<id>.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)' + _TEST = { + 'url': 'http://ndr2.radio.de/', + 'md5': '3b4cdd011bc59174596b6145cda474a4', + 'info_dict': { + 'id': 'ndr2', + 'ext': 'mp3', + 'title': 're:^NDR 2 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:591c49c702db1a33751625ebfb67f273', + 'thumbnail': 're:^https?://.*\.png', + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + radio_id = self._match_id(url) + + webpage = self._download_webpage(url, radio_id) + + broadcast = json.loads(self._search_regex( + r'_getBroadcast\s*=\s*function\(\s*\)\s*{\s*return\s+({.+?})\s*;\s*}', + webpage, 'broadcast')) + + title = self._live_title(broadcast['name']) + description = broadcast.get('description') or broadcast.get('shortDescription') + thumbnail = broadcast.get('picture4Url') or broadcast.get('picture4TransUrl') + + formats = [{ + 'url': stream['streamUrl'], + 'ext': stream['streamContentFormat'].lower(), + 'acodec': stream['streamContentFormat'], + 'abr': stream['bitRate'], + 'asr': stream['sampleRate'] + } for stream in broadcast['streamUrls']] + self._sort_formats(formats) + + return { + 'id': radio_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'is_live': True, + 'formats': formats, + } diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index ba3dd707f..2d39ecfe4 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -119,4 +119,4 @@ class RaiIE(SubtitlesInfoExtractor): if captions.endswith(STL_EXT): captions = captions[:-len(STL_EXT)] + SRT_EXT subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions) - return subtitles
\ No newline at end of file + return subtitles diff --git a/youtube_dl/extractor/rbmaradio.py b/youtube_dl/extractor/rbmaradio.py index 2c53ed2e1..0f8f3ebde 100644 --- a/youtube_dl/extractor/rbmaradio.py +++ b/youtube_dl/extractor/rbmaradio.py @@ -33,7 +33,7 @@ class RBMARadioIE(InfoExtractor): webpage = self._download_webpage(url, video_id) json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$', - webpage, 'json data', flags=re.MULTILINE) + webpage, 'json data', flags=re.MULTILINE) try: data = json.loads(json_data) diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index d1e12dd8d..846b76c81 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -9,32 +7,23 @@ class RedTubeIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)' _TEST = { 'url': 'http://www.redtube.com/66418', - 'file': '66418.mp4', - # md5 varies from time to time, as in - # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295 - #'md5': u'7b8c22b5e7098a3e1c09709df1126d2d', 'info_dict': { + 'id': '66418', + 'ext': 'mp4', "title": "Sucked on a toilet", "age_limit": 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - video_extension = 'mp4' + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - video_url = self._html_search_regex( - r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL') - + r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL') video_title = self._html_search_regex( r'<h1 class="videoTitle[^"]*">(.+?)</h1>', - webpage, u'title') - + webpage, 'title') video_thumbnail = self._og_search_thumbnail(webpage) # No self-labeling, but they describe themselves as @@ -44,7 +33,7 @@ class RedTubeIE(InfoExtractor): return { 'id': video_id, 'url': video_url, - 'ext': video_extension, + 'ext': 'mp4', 'title': video_title, 'thumbnail': video_thumbnail, 'age_limit': age_limit, diff --git a/youtube_dl/extractor/reverbnation.py b/youtube_dl/extractor/reverbnation.py index 49cf427a1..ec7e7df7b 100644 --- a/youtube_dl/extractor/reverbnation.py +++ b/youtube_dl/extractor/reverbnation.py @@ -1,23 +1,23 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import strip_jsonp +from ..utils import str_or_none class ReverbNationIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$' _TESTS = [{ 'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa', - 'file': '16965047.mp3', 'md5': '3da12ebca28c67c111a7f8b262d3f7a7', 'info_dict': { + "id": "16965047", + "ext": "mp3", "title": "MONA LISA", "uploader": "ALKILADOS", - "uploader_id": 216429, - "thumbnail": "//gp1.wac.edgecastcdn.net/802892/production_public/Photo/13761700/image/1366002176_AVATAR_MONA_LISA.jpg" + "uploader_id": "216429", + "thumbnail": "re:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$" }, }] @@ -26,10 +26,8 @@ class ReverbNationIE(InfoExtractor): song_id = mobj.group('id') api_res = self._download_json( - 'https://api.reverbnation.com/song/%s?callback=api_response_5&_=%d' - % (song_id, int(time.time() * 1000)), + 'https://api.reverbnation.com/song/%s' % song_id, song_id, - transform_source=strip_jsonp, note='Downloading information of song %s' % song_id ) @@ -38,8 +36,9 @@ class ReverbNationIE(InfoExtractor): 'title': api_res.get('name'), 'url': api_res.get('url'), 'uploader': api_res.get('artist', {}).get('name'), - 'uploader_id': api_res.get('artist', {}).get('id'), - 'thumbnail': api_res.get('image', api_res.get('thumbnail')), + 'uploader_id': str_or_none(api_res.get('artist', {}).get('id')), + 'thumbnail': self._proto_relative_url( + api_res.get('image', api_res.get('thumbnail'))), 'ext': 'mp3', 'vcodec': 'none', } diff --git a/youtube_dl/extractor/ringtv.py b/youtube_dl/extractor/ringtv.py index 9fbdb9fcb..59dc137cc 100644 --- a/youtube_dl/extractor/ringtv.py +++ b/youtube_dl/extractor/ringtv.py @@ -41,4 +41,3 @@ class RingTVIE(InfoExtractor): 'thumbnail': thumbnail_url, 'description': description, } - diff --git a/youtube_dl/extractor/ro220.py b/youtube_dl/extractor/ro220.py index a6ad59465..962b524e9 100644 --- a/youtube_dl/extractor/ro220.py +++ b/youtube_dl/extractor/ro220.py @@ -1,43 +1,43 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - clean_html, - compat_parse_qs, -) +from ..compat import compat_urllib_parse_unquote class Ro220IE(InfoExtractor): IE_NAME = '220.ro' - _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)' + _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<id>[^/]+)' _TEST = { - "url": "http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/", - 'file': 'LYV6doKo7f.mp4', + 'url': 'http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/', 'md5': '03af18b73a07b4088753930db7a34add', 'info_dict': { - "title": "Luati-le Banii sez 4 ep 1", - "description": "re:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$", + 'id': 'LYV6doKo7f', + 'ext': 'mp4', + 'title': 'Luati-le Banii sez 4 ep 1', + 'description': 're:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - flashVars_str = self._search_regex( - r'<param name="flashVars" value="([^"]+)"', - webpage, 'flashVars') - flashVars = compat_parse_qs(flashVars_str) + url = compat_urllib_parse_unquote(self._search_regex( + r'(?s)clip\s*:\s*{.*?url\s*:\s*\'([^\']+)\'', webpage, 'url')) + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': 'mp4', + }] return { - '_type': 'video', 'id': video_id, - 'ext': 'mp4', - 'url': flashVars['videoURL'][0], - 'title': flashVars['title'][0], - 'description': clean_html(flashVars['desc'][0]), - 'thumbnail': flashVars['preview'][0], + 'formats': formats, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py new file mode 100644 index 000000000..d029b0ec5 --- /dev/null +++ b/youtube_dl/extractor/rtlnl.py @@ -0,0 +1,71 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class RtlXlIE(InfoExtractor): + IE_NAME = 'rtlxl.nl' + _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' + + _TEST = { + 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', + 'md5': 'cc16baa36a6c169391f0764fa6b16654', + 'info_dict': { + 'id': '6e4203a6-0a5e-3596-8424-c599a59e0677', + 'ext': 'mp4', + 'title': 'RTL Nieuws - Laat', + 'description': 'md5:6b61f66510c8889923b11f2778c72dc5', + 'timestamp': 1408051800, + 'upload_date': '20140814', + 'duration': 576.880, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + uuid = mobj.group('uuid') + + info = self._download_json( + 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid, + uuid) + + material = info['material'][0] + episode_info = info['episodes'][0] + + progname = info['abstracts'][0]['name'] + subtitle = material['title'] or info['episodes'][0]['name'] + + # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118) + videopath = material['videopath'].replace('.f4m', '.m3u8') + m3u8_url = 'http://manifest.us.rtl.nl' + videopath + + formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4') + + video_urlpart = videopath.split('/flash/')[1][:-5] + PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4' + + formats.extend([ + { + 'url': PG_URL_TEMPLATE % ('a2m', video_urlpart), + 'format_id': 'pg-sd', + }, + { + 'url': PG_URL_TEMPLATE % ('a3m', video_urlpart), + 'format_id': 'pg-hd', + 'quality': 0, + } + ]) + + self._sort_formats(formats) + + return { + 'id': uuid, + 'title': '%s - %s' % (progname, subtitle), + 'formats': formats, + 'timestamp': material['original_date'], + 'description': episode_info['synopsis'], + 'duration': parse_duration(material.get('duration')), + } diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index a45884b25..285c3c4be 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -81,7 +81,7 @@ class RTLnowIE(InfoExtractor): 'id': '99205', 'ext': 'flv', 'title': 'Medicopter 117 - Angst!', - 'description': 'md5:895b1df01639b5f61a04fc305a5cb94d', + 'description': 're:^Im Therapiezentrum \'Sonnalm\' kommen durch eine Unachtsamkeit die für die B.handlung mit Phobikern gehaltenen Voglespinnen frei\. Eine Ausreißerin', 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg', 'upload_date': '20080928', 'duration': 2691, @@ -122,7 +122,7 @@ class RTLnowIE(InfoExtractor): playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML') videoinfo = playerdata.find('./playlist/videoinfo') - + formats = [] for filename in videoinfo.findall('filename'): mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text) @@ -153,4 +153,4 @@ class RTLnowIE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index e8199b114..dc59a5e5c 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -15,7 +15,7 @@ from ..utils import ( class RTSIE(InfoExtractor): IE_DESC = 'RTS.ch' - _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html' + _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))' _TESTS = [ { @@ -23,6 +23,7 @@ class RTSIE(InfoExtractor): 'md5': '753b877968ad8afaeddccc374d4256a5', 'info_dict': { 'id': '3449373', + 'display_id': 'les-enfants-terribles', 'ext': 'mp4', 'duration': 1488, 'title': 'Les Enfants Terribles', @@ -30,7 +31,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Divers', 'upload_date': '19680921', 'timestamp': -40280400, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -38,6 +40,7 @@ class RTSIE(InfoExtractor): 'md5': 'c148457a27bdc9e5b1ffe081a7a8337b', 'info_dict': { 'id': '5624067', + 'display_id': 'entre-ciel-et-mer', 'ext': 'mp4', 'duration': 3720, 'title': 'Les yeux dans les cieux - Mon homard au Canada', @@ -45,7 +48,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Passe-moi les jumelles', 'upload_date': '20140404', 'timestamp': 1396635300, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -53,6 +57,7 @@ class RTSIE(InfoExtractor): 'md5': 'b4326fecd3eb64a458ba73c73e91299d', 'info_dict': { 'id': '5745975', + 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski', 'ext': 'mp4', 'duration': 48, 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski', @@ -60,7 +65,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Hockey', 'upload_date': '20140403', 'timestamp': 1396556882, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, 'skip': 'Blocked outside Switzerland', }, @@ -69,6 +75,7 @@ class RTSIE(InfoExtractor): 'md5': '9bb06503773c07ce83d3cbd793cebb91', 'info_dict': { 'id': '5745356', + 'display_id': 'londres-cachee-par-un-epais-smog', 'ext': 'mp4', 'duration': 33, 'title': 'Londres cachée par un épais smog', @@ -76,7 +83,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Le Journal en continu', 'upload_date': '20140403', 'timestamp': 1396537322, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -84,6 +92,7 @@ class RTSIE(InfoExtractor): 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae', 'info_dict': { 'id': '5706148', + 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014', 'ext': 'mp3', 'duration': 123, 'title': '"Urban Hippie", de Damien Krisl', @@ -92,22 +101,44 @@ class RTSIE(InfoExtractor): 'timestamp': 1396551600, }, }, + { + 'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260', + 'md5': '968777c8779e5aa2434be96c54e19743', + 'info_dict': { + 'id': '6348260', + 'display_id': 'le-19h30', + 'ext': 'mp4', + 'duration': 1796, + 'title': 'Le 19h30', + 'description': '', + 'uploader': 'Le 19h30', + 'upload_date': '20141201', + 'timestamp': 1417458600, + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, + }, + }, + { + 'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280', + 'only_matching': True, + } ] def _real_extract(self, url): m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = m.group('id') or m.group('id_new') + display_id = m.group('display_id') or m.group('display_id_new') def download_json(internal_id): return self._download_json( 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id, - video_id) + display_id) all_info = download_json(video_id) # video_id extracted out of URL is not always a real id if 'video' not in all_info and 'audio' not in all_info: - page = self._download_webpage(url, video_id) + page = self._download_webpage(url, display_id) internal_id = self._html_search_regex( r'<(?:video|audio) data-id="([0-9]+)"', page, 'internal video id') @@ -143,6 +174,7 @@ class RTSIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'formats': formats, 'title': info['title'], 'description': info.get('intro'), diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index c2228b2f0..0ce22d60c 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -1,21 +1,65 @@ # encoding: utf-8 from __future__ import unicode_literals -import re import base64 +import re +import time from .common import InfoExtractor from ..utils import ( struct_unpack, + remove_end, ) +def _decrypt_url(png): + encrypted_data = base64.b64decode(png) + text_index = encrypted_data.find(b'tEXt') + text_chunk = encrypted_data[text_index - 4:] + length = struct_unpack('!I', text_chunk[:4])[0] + # Use bytearray to get integers when iterating in both python 2.x and 3.x + data = bytearray(text_chunk[8:8 + length]) + data = [chr(b) for b in data if b != 0] + hash_index = data.index('#') + alphabet_data = data[:hash_index] + url_data = data[hash_index + 1:] + + alphabet = [] + e = 0 + d = 0 + for l in alphabet_data: + if d == 0: + alphabet.append(l) + d = e = (e + 1) % 4 + else: + d -= 1 + url = '' + f = 0 + e = 3 + b = 1 + for letter in url_data: + if f == 0: + l = int(letter) * 10 + f = 1 + else: + if e == 0: + l += int(letter) + url += alphabet[l] + e = (b + 3) % 4 + f = 0 + b += 1 + else: + e -= 1 + + return url + + class RTVEALaCartaIE(InfoExtractor): IE_NAME = 'rtve.es:alacarta' IE_DESC = 'RTVE a la carta' _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43', 'info_dict': { @@ -23,48 +67,15 @@ class RTVEALaCartaIE(InfoExtractor): 'ext': 'mp4', 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', }, - } - - def _decrypt_url(self, png): - encrypted_data = base64.b64decode(png) - text_index = encrypted_data.find(b'tEXt') - text_chunk = encrypted_data[text_index-4:] - length = struct_unpack('!I', text_chunk[:4])[0] - # Use bytearray to get integers when iterating in both python 2.x and 3.x - data = bytearray(text_chunk[8:8+length]) - data = [chr(b) for b in data if b != 0] - hash_index = data.index('#') - alphabet_data = data[:hash_index] - url_data = data[hash_index+1:] - - alphabet = [] - e = 0 - d = 0 - for l in alphabet_data: - if d == 0: - alphabet.append(l) - d = e = (e + 1) % 4 - else: - d -= 1 - url = '' - f = 0 - e = 3 - b = 1 - for letter in url_data: - if f == 0: - l = int(letter)*10 - f = 1 - else: - if e == 0: - l += int(letter) - url += alphabet[l] - e = (b + 3) % 4 - f = 0 - b += 1 - else: - e -= 1 - - return url + }, { + 'note': 'Live stream', + 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/', + 'info_dict': { + 'id': '1694255', + 'ext': 'flv', + 'title': 'TODO', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -74,11 +85,57 @@ class RTVEALaCartaIE(InfoExtractor): video_id)['page']['items'][0] png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id png = self._download_webpage(png_url, video_id, 'Downloading url information') - video_url = self._decrypt_url(png) + video_url = _decrypt_url(png) return { 'id': video_id, 'title': info['title'], 'url': video_url, - 'thumbnail': info['image'], + 'thumbnail': info.get('image'), + 'page_url': url, + } + + +class RTVELiveIE(InfoExtractor): + IE_NAME = 'rtve.es:live' + IE_DESC = 'RTVE.es live streams' + _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)' + + _TESTS = [{ + 'url': 'http://www.rtve.es/noticias/directo-la-1/', + 'info_dict': { + 'id': 'directo-la-1', + 'ext': 'flv', + 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$', + }, + 'params': { + 'skip_download': 'live stream', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + start_time = time.gmtime() + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_url = self._search_regex( + r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL') + title = remove_end(self._og_search_title(webpage), ' en directo') + title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time) + + vidplayer_id = self._search_regex( + r' id="vidplayer([0-9]+)"', webpage, 'internal video ID') + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id + png = self._download_webpage(png_url, video_id, 'Downloading url information') + video_url = _decrypt_url(png) + + return { + 'id': video_id, + 'ext': 'flv', + 'title': title, + 'url': video_url, + 'app': 'rtve-live-live?ovpfv=2.1.2', + 'player_url': player_url, + 'rtmp_live': True, } diff --git a/youtube_dl/extractor/ruhd.py b/youtube_dl/extractor/ruhd.py index 55b58e5e6..0e470e73f 100644 --- a/youtube_dl/extractor/ruhd.py +++ b/youtube_dl/extractor/ruhd.py @@ -1,8 +1,6 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -21,19 +19,20 @@ class RUHDIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = self._html_search_regex( r'<param name="src" value="([^"]+)"', webpage, 'video url') title = self._html_search_regex( - r'<title>([^<]+) RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title') + r'<title>([^<]+) RUHD.ru - Видео Высокого качества №1 в России!</title>', + webpage, 'title') description = self._html_search_regex( - r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False) + r'(?s)<div id="longdesc">(.+?)<span id="showlink">', + webpage, 'description', fatal=False) thumbnail = self._html_search_regex( - r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False) + r'<param name="previewImage" value="([^"]+)"', + webpage, 'thumbnail', fatal=False) if thumbnail: thumbnail = 'http://www.ruhd.ru' + thumbnail diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 357edbbda..6941d96fb 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -53,6 +53,7 @@ class RutubeIE(InfoExtractor): m3u8_url = options['video_balancer'].get('m3u8') if m3u8_url is None: raise ExtractorError('Couldn\'t find m3u8 manifest url') + formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') return { 'id': video['id'], @@ -60,8 +61,7 @@ class RutubeIE(InfoExtractor): 'description': video['description'], 'duration': video['duration'], 'view_count': video['hits'], - 'url': m3u8_url, - 'ext': 'mp4', + 'formats': formats, 'thumbnail': video['thumbnail_url'], 'uploader': author.get('name'), 'uploader_id': compat_str(author['id']) if author else None, @@ -74,6 +74,13 @@ class RutubeChannelIE(InfoExtractor): IE_NAME = 'rutube:channel' IE_DESC = 'Rutube channels' _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://rutube.ru/tags/video/1800/', + 'info_dict': { + 'id': '1800', + }, + 'playlist_mincount': 68, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json' @@ -101,6 +108,7 @@ class RutubeMovieIE(RutubeChannelIE): IE_NAME = 'rutube:movie' IE_DESC = 'Rutube movies' _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)' + _TESTS = [] _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json' _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' @@ -119,5 +127,12 @@ class RutubePersonIE(RutubeChannelIE): IE_NAME = 'rutube:person' IE_DESC = 'Rutube person videos' _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://rutube.ru/video/person/313878/', + 'info_dict': { + 'id': '313878', + }, + 'playlist_mincount': 37, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py index 6c5f5a680..a73e6f331 100644 --- a/youtube_dl/extractor/rutv.py +++ b/youtube_dl/extractor/rutv.py @@ -100,7 +100,7 @@ class RUTVIE(InfoExtractor): return mobj.group('url') mobj = re.search( - r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>http://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)', + r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)', webpage) if mobj: return mobj.group('url') @@ -191,4 +191,4 @@ class RUTVIE(InfoExtractor): 'view_count': view_count, 'duration': duration, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py new file mode 100644 index 000000000..b8775c2f9 --- /dev/null +++ b/youtube_dl/extractor/sbs.py @@ -0,0 +1,59 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import json +import re +from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) + + +class SBSIE(InfoExtractor): + IE_DESC = 'sbs.com.au' + _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)' + + _TESTS = [{ + # Original URL is handled by the generic IE which finds the iframe: + # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation + 'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed', + 'md5': '3150cf278965eeabb5b4cea1c963fe0a', + 'info_dict': { + 'id': '320403011771', + 'ext': 'mp4', + 'title': 'Dingo Conservation', + 'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction', + 'thumbnail': 're:http://.*\.jpg', + }, + 'add_ies': ['generic'], + }, { + 'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + release_urls_json = js_to_json(self._search_regex( + r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', + webpage, '')) + release_urls = json.loads(release_urls_json) + theplatform_url = ( + release_urls.get('progressive') or release_urls.get('standard')) + + title = remove_end(self._og_search_title(webpage), ' (The Feed)') + description = self._html_search_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': theplatform_url, + + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py index 55a481cc0..3bf93c870 100644 --- a/youtube_dl/extractor/scivee.py +++ b/youtube_dl/extractor/scivee.py @@ -53,4 +53,4 @@ class SciVeeIE(InfoExtractor): 'description': description, 'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index 306869e6a..c145f6fc7 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -96,7 +96,7 @@ class ScreencastIE(InfoExtractor): if title is None: title = self._html_search_regex( [r'<b>Title:</b> ([^<]*)</div>', - r'class="tabSeperator">></span><span class="tabText">(.*?)<'], + r'class="tabSeperator">></span><span class="tabText">(.*?)<'], webpage, 'title') thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage, default=None) diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py new file mode 100644 index 000000000..6c9fdb7c1 --- /dev/null +++ b/youtube_dl/extractor/screenwavemedia.py @@ -0,0 +1,178 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class ScreenwaveMediaIE(InfoExtractor): + _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)' + + _TESTS = [{ + 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + playerdata = self._download_webpage(url, video_id, 'Downloading player webpage') + + vidtitle = self._search_regex( + r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/') + vidurl = self._search_regex( + r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/') + + videolist_url = None + + mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata) + if mobj: + videoserver = mobj.group('videoserver') + mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata) + vidid = mobj.group('vidid') if mobj else video_id + videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid) + else: + mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata) + if mobj: + videolist_url = mobj.group('smil') + + if videolist_url: + videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') + formats = [] + baseurl = vidurl[:vidurl.rfind('/') + 1] + for video in videolist.findall('.//video'): + src = video.get('src') + if not src: + continue + file_ = src.partition(':')[-1] + width = int_or_none(video.get('width')) + height = int_or_none(video.get('height')) + bitrate = int_or_none(video.get('system-bitrate'), scale=1000) + format = { + 'url': baseurl + file_, + 'format_id': src.rpartition('.')[0].rpartition('_')[-1], + } + if width or height: + format.update({ + 'tbr': bitrate, + 'width': width, + 'height': height, + }) + else: + format.update({ + 'abr': bitrate, + 'vcodec': 'none', + }) + formats.append(format) + else: + formats = [{ + 'url': vidurl, + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': vidtitle, + 'formats': formats, + } + + +class CinemassacreIE(InfoExtractor): + _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' + _TESTS = [ + { + 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', + 'md5': 'fde81fbafaee331785f58cd6c0d46190', + 'info_dict': { + 'id': 'Cinemassacre-19911', + 'ext': 'mp4', + 'upload_date': '20121110', + 'title': '“Angry Video Game Nerd: The Movie” – Trailer', + 'description': 'md5:fb87405fcb42a331742a0dce2708560b', + }, + }, + { + 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', + 'md5': 'd72f10cd39eac4215048f62ab477a511', + 'info_dict': { + 'id': 'Cinemassacre-521be8ef82b16', + 'ext': 'mp4', + 'upload_date': '20131002', + 'title': 'The Mummy’s Hand (1940)', + }, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') + + webpage = self._download_webpage(url, display_id) + + playerdata_url = self._search_regex( + r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + webpage, 'player data URL') + video_title = self._html_search_regex( + r'<title>(?P<title>.+?)\|', webpage, 'title') + video_description = self._html_search_regex( + r'<div class="entry-content">(?P<description>.+?)</div>', + webpage, 'description', flags=re.DOTALL, fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + 'url': playerdata_url, + } + + +class TeamFourIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?' + _TEST = { + 'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/', + 'info_dict': { + 'id': 'TeamFourStar-5292a02f20bfa', + 'ext': 'mp4', + 'upload_date': '20130401', + 'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar', + 'title': 'A Moment With TFS Episode 4', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + playerdata_url = self._search_regex( + r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + webpage, 'player data URL') + + video_title = self._html_search_regex( + r'<div class="heroheadingtitle">(?P<title>.+?)</div>', + webpage, 'title') + video_date = unified_strdate(self._html_search_regex( + r'<div class="heroheadingdate">(?P<date>.+?)</div>', + webpage, 'date', fatal=False)) + video_description = self._html_search_regex( + r'(?s)<div class="postcontent">(?P<description>.+?)</div>', + webpage, 'description', fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + 'url': playerdata_url, + } diff --git a/youtube_dl/extractor/servingsys.py b/youtube_dl/extractor/servingsys.py index 1dc551d5c..16dc3736b 100644 --- a/youtube_dl/extractor/servingsys.py +++ b/youtube_dl/extractor/servingsys.py @@ -67,5 +67,3 @@ class ServingSysIE(InfoExtractor): 'title': title, 'entries': entries, } - -
\ No newline at end of file diff --git a/youtube_dl/extractor/sexu.py b/youtube_dl/extractor/sexu.py new file mode 100644 index 000000000..6365a8779 --- /dev/null +++ b/youtube_dl/extractor/sexu.py @@ -0,0 +1,61 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class SexuIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://sexu.com/961791/', + 'md5': 'ff615aca9691053c94f8f10d96cd7884', + 'info_dict': { + 'id': '961791', + 'ext': 'mp4', + 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b', + 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + quality_arr = self._search_regex( + r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string') + formats = [{ + 'url': fmt[0].replace('\\', ''), + 'format_id': fmt[1], + 'height': int(fmt[1][:3]), + } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)] + self._sort_formats(formats) + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title') + + description = self._html_search_meta( + 'description', webpage, 'description') + + thumbnail = self._html_search_regex( + r'image:\s*"([^"]+)"', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_meta( + 'keywords', webpage, 'categories') + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py new file mode 100644 index 000000000..c833fc8ee --- /dev/null +++ b/youtube_dl/extractor/sexykarma.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + parse_duration, + int_or_none, +) + + +class SexyKarmaIE(InfoExtractor): + IE_DESC = 'Sexy Karma and Watch Indian Porn' + _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html' + _TESTS = [{ + 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html', + 'md5': 'b9798e7d1ef1765116a8f516c8091dbd', + 'info_dict': { + 'id': 'yHI70cOyIHt', + 'display_id': 'taking-a-quick-pee', + 'ext': 'mp4', + 'title': 'Taking a quick pee.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'wildginger7', + 'upload_date': '20141007', + 'duration': 22, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }, { + 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html', + 'md5': 'dd216c68d29b49b12842b9babe762a5d', + 'info_dict': { + 'id': '8Id6EZPbuHf', + 'display_id': 'pot-pixie-tribute', + 'ext': 'mp4', + 'title': 'pot_pixie tribute', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'banffite', + 'upload_date': '20141013', + 'duration': 16, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }, { + 'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html', + 'md5': '9afb80675550406ed9a63ac2819ef69d', + 'info_dict': { + 'id': 'dW2mtctxJfs', + 'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number', + 'ext': 'mp4', + 'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'Don', + 'upload_date': '20140213', + 'duration': 83, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._html_search_regex( + r"url: escape\('([^']+)'\)", webpage, 'url') + + title = self._html_search_regex( + r'<h2 class="he2"><span>(.*?)</span>', + webpage, 'title') + thumbnail = self._html_search_regex( + r'<span id="container"><img\s+src="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + uploader = self._html_search_regex( + r'class="aupa">\s*(.*?)</a>', + webpage, 'uploader') + upload_date = unified_strdate(self._html_search_regex( + r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False)) + + duration = parse_duration(self._search_regex( + r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>', + webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._search_regex( + r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>', + webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._search_regex( + r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>', + webpage, 'comment count', fatal=False)) + + categories = re.findall( + r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>', + webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + 'categories': categories, + } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 8607482be..fdc31603a 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -17,11 +17,11 @@ class SharedIE(InfoExtractor): _TEST = { 'url': 'http://shared.sx/0060718775', - 'md5': '53e1c58fc3e777ae1dfe9e57ba2f9c72', + 'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'info_dict': { 'id': '0060718775', 'ext': 'mp4', - 'title': 'Big Buck Bunny Trailer', + 'title': 'Bmp4', }, } @@ -54,4 +54,4 @@ class SharedIE(InfoExtractor): 'filesize': filesize, 'title': title, 'thumbnail': thumbnail, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/sharesix.py b/youtube_dl/extractor/sharesix.py new file mode 100644 index 000000000..7531e8325 --- /dev/null +++ b/youtube_dl/extractor/sharesix.py @@ -0,0 +1,91 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + parse_duration, +) + + +class ShareSixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)' + _TESTS = [ + { + 'url': 'http://sharesix.com/f/OXjQ7Y6', + 'md5': '9e8e95d8823942815a7d7c773110cc93', + 'info_dict': { + 'id': 'OXjQ7Y6', + 'ext': 'mp4', + 'title': 'big_buck_bunny_480p_surround-fix.avi', + 'duration': 596, + 'width': 854, + 'height': 480, + }, + }, + { + 'url': 'http://sharesix.com/lfrwoxp35zdd', + 'md5': 'dd19f1435b7cec2d7912c64beeee8185', + 'info_dict': { + 'id': 'lfrwoxp35zdd', + 'ext': 'flv', + 'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv', + 'duration': 65, + 'width': 1280, + 'height': 720, + }, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + fields = { + 'method_free': 'Free' + } + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage(req, video_id, + 'Downloading video page') + + video_url = self._search_regex( + r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL') + title = self._html_search_regex( + r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title') + duration = parse_duration( + self._search_regex( + r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>', + webpage, + 'duration', + fatal=False + ) + ) + + m = re.search( + r'''(?xs)<dt>Width\sx\sHeight</dt>.+? + <dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''', + webpage + ) + width = height = None + if m: + width, height = int(m.group('width')), int(m.group('height')) + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'width': width, + 'height': height, + }] + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index 2909ef18b..5eadbb7ea 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -46,7 +46,7 @@ class SinaIE(InfoExtractor): def _extract_video(self, video_id): data = compat_urllib_parse.urlencode({'vid': video_id}) url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data, - video_id, 'Downloading video url') + video_id, 'Downloading video url') image_page = self._download_webpage( 'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data, video_id, 'Downloading thumbnail info') diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py index 53c3c9220..5864b9936 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -39,7 +39,7 @@ class SlideshareIE(InfoExtractor): ext = info['jsplayer']['video_extension'] video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext) description = self._html_search_regex( - r'<p\s+(?:style="[^"]*"\s+)?class="description.*?"[^>]*>(.*?)</p>', webpage, + r'<p\s+(?:style="[^"]*"\s+)?class=".*?description.*?"[^>]*>(.*?)</p>', webpage, 'description', fatal=False) return { diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py index e6e7d0865..3df71304d 100644 --- a/youtube_dl/extractor/slutload.py +++ b/youtube_dl/extractor/slutload.py @@ -26,7 +26,7 @@ class SlutloadIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>', - webpage, 'title').strip() + webpage, 'title').strip() video_url = self._html_search_regex( r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"', diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 13e7e71cb..646af3cc9 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -1,7 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import os.path import re import json import hashlib @@ -12,15 +11,15 @@ from ..utils import ( compat_urllib_parse, compat_urllib_request, ExtractorError, - url_basename, int_or_none, + unified_strdate, ) class SmotriIE(InfoExtractor): IE_DESC = 'Smotri.com' IE_NAME = 'smotri' - _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})' + _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})' _NETRC_MACHINE = 'smotri' _TESTS = [ @@ -35,7 +34,6 @@ class SmotriIE(InfoExtractor): 'uploader': 'rbc2008', 'uploader_id': 'rbc08', 'upload_date': '20131118', - 'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения', 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg', }, }, @@ -50,7 +48,6 @@ class SmotriIE(InfoExtractor): 'uploader': 'Support Photofile@photofile', 'uploader_id': 'support-photofile', 'upload_date': '20070704', - 'description': 'test, видео test', 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg', }, }, @@ -66,7 +63,6 @@ class SmotriIE(InfoExtractor): 'uploader_id': 'timoxa40', 'upload_date': '20100404', 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg', - 'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', }, 'params': { 'videopassword': 'qwerty', @@ -85,7 +81,6 @@ class SmotriIE(InfoExtractor): 'upload_date': '20101001', 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg', 'age_limit': 18, - 'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ', }, 'params': { 'videopassword': '333' @@ -102,17 +97,11 @@ class SmotriIE(InfoExtractor): 'uploader': 'HannahL', 'uploader_id': 'lisaha95', 'upload_date': '20090331', - 'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother', 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg', }, }, ] - _SUCCESS = 0 - _PASSWORD_NOT_VERIFIED = 1 - _PASSWORD_DETECTED = 2 - _VIDEO_NOT_FOUND = 3 - @classmethod def _extract_url(cls, webpage): mobj = re.search( @@ -137,44 +126,44 @@ class SmotriIE(InfoExtractor): return self._html_search_meta(name, html, display_name) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - real_video_id = mobj.group('realvideoid') + video_id = self._match_id(url) + + video_form = { + 'ticket': video_id, + 'video_url': '1', + 'frame_url': '1', + 'devid': 'LoadupFlashPlayer', + 'getvideoinfo': '1', + } + + request = compat_urllib_request.Request( + 'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') - # Download video JSON data - video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id - video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON') - video_json = json.loads(video_json_page) + video = self._download_json(request, video_id, 'Downloading video JSON') - status = video_json['status'] - if status == self._VIDEO_NOT_FOUND: + if video.get('_moderate_no') or not video.get('moderated'): + raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True) + + if video.get('error'): raise ExtractorError('Video %s does not exist' % video_id, expected=True) - elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with - # video-password set - video_password = self._downloader.params.get('videopassword', None) - if not video_password: - raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) - video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest() - video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)') - video_json = json.loads(video_json_page) - status = video_json['status'] - if status == self._PASSWORD_NOT_VERIFIED: - raise ExtractorError('Video password is invalid', expected=True) - - if status != self._SUCCESS: - raise ExtractorError('Unexpected status value %s' % status) - - # Extract the URL of the video - video_url = video_json['file_data'] + + video_url = video.get('_vidURL') or video.get('_vidURL_mp4') + title = video['title'] + thumbnail = video['_imgURL'] + upload_date = unified_strdate(video['added']) + uploader = video['userNick'] + uploader_id = video['userLogin'] + duration = int_or_none(video['duration']) # Video JSON does not provide enough meta data # We will extract some from the video web page instead - video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id - video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page') + webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id + webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page') # Warning if video is unavailable warning = self._html_search_regex( - r'<div class="videoUnModer">(.*?)</div>', video_page, + r'<div class="videoUnModer">(.*?)</div>', webpage, 'warning message', default=None) if warning is not None: self._downloader.report_warning( @@ -182,84 +171,32 @@ class SmotriIE(InfoExtractor): (video_id, warning)) # Adult content - if re.search('EroConfirmText">', video_page) is not None: + if re.search('EroConfirmText">', webpage) is not None: self.report_age_confirmation() confirm_string = self._html_search_regex( r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id, - video_page, 'confirm string') - confirm_url = video_page_url + '&confirm=%s' % confirm_string - video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)') + webpage, 'confirm string') + confirm_url = webpage_url + '&confirm=%s' % confirm_string + webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)') adult_content = True else: adult_content = False - # Extract the rest of meta data - video_title = self._search_meta('name', video_page, 'title') - if not video_title: - video_title = os.path.splitext(url_basename(video_url))[0] - - video_description = self._search_meta('description', video_page) - END_TEXT = ' на сайте Smotri.com' - if video_description and video_description.endswith(END_TEXT): - video_description = video_description[:-len(END_TEXT)] - START_TEXT = 'Смотреть онлайн ролик ' - if video_description and video_description.startswith(START_TEXT): - video_description = video_description[len(START_TEXT):] - video_thumbnail = self._search_meta('thumbnail', video_page) - - upload_date_str = self._search_meta('uploadDate', video_page, 'upload date') - if upload_date_str: - upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str) - video_upload_date = ( - ( - upload_date_m.group('year') + - upload_date_m.group('month') + - upload_date_m.group('day') - ) - if upload_date_m else None - ) - else: - video_upload_date = None - - duration_str = self._search_meta('duration', video_page) - if duration_str: - duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str) - video_duration = ( - ( - (int(duration_m.group('hours')) * 60 * 60) + - (int(duration_m.group('minutes')) * 60) + - int(duration_m.group('seconds')) - ) - if duration_m else None - ) - else: - video_duration = None - - video_uploader = self._html_search_regex( - '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>', - video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL) - - video_uploader_id = self._html_search_regex( - '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">', - video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL) - - video_view_count = self._html_search_regex( + view_count = self._html_search_regex( 'Общее количество просмотров.*?<span class="Number">(\\d+)</span>', - video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL) + webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL) return { 'id': video_id, 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'uploader': video_uploader, - 'upload_date': video_upload_date, - 'uploader_id': video_uploader_id, - 'duration': video_duration, - 'view_count': int_or_none(video_view_count), + 'title': title, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + 'uploader_id': uploader_id, + 'duration': duration, + 'view_count': int_or_none(view_count), 'age_limit': 18 if adult_content else 0, - 'video_page_url': video_page_url } @@ -267,7 +204,15 @@ class SmotriCommunityIE(InfoExtractor): IE_DESC = 'Smotri.com community videos' IE_NAME = 'smotri:community' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)' - + _TEST = { + 'url': 'http://smotri.com/community/video/kommuna', + 'info_dict': { + 'id': 'kommuna', + 'title': 'КПРФ', + }, + 'playlist_mincount': 4, + } + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) community_id = mobj.group('communityid') @@ -289,6 +234,14 @@ class SmotriUserIE(InfoExtractor): IE_DESC = 'Smotri.com user videos' IE_NAME = 'smotri:user' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)' + _TESTS = [{ + 'url': 'http://smotri.com/user/inspector', + 'info_dict': { + 'id': 'inspector', + 'title': 'Inspector', + }, + 'playlist_mincount': 9, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -321,15 +274,18 @@ class SmotriBroadcastIE(InfoExtractor): broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page') if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None: - raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True) + raise ExtractorError( + 'Broadcast %s does not exist' % broadcast_id, expected=True) # Adult content if re.search('EroConfirmText">', broadcast_page) is not None: (username, password) = self._get_login_info() if username is None: - raise ExtractorError('Erotic broadcasts allowed only for registered users, ' - 'use --username and --password options to provide account credentials.', expected=True) + raise ExtractorError( + 'Erotic broadcasts allowed only for registered users, ' + 'use --username and --password options to provide account credentials.', + expected=True) login_form = { 'login-hint53': '1', @@ -338,9 +294,11 @@ class SmotriBroadcastIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form)) + request = compat_urllib_request.Request( + broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age') + broadcast_page = self._download_webpage( + request, broadcast_id, 'Logging in and confirming age') if re.search('>Неверный логин или пароль<', broadcast_page) is not None: raise ExtractorError('Unable to log in: bad username or password', expected=True) @@ -350,7 +308,7 @@ class SmotriBroadcastIE(InfoExtractor): adult_content = False ticket = self._html_search_regex( - 'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);', + r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)", broadcast_page, 'broadcast ticket') url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket @@ -359,26 +317,31 @@ class SmotriBroadcastIE(InfoExtractor): if broadcast_password: url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest() - broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON') + broadcast_json_page = self._download_webpage( + url, broadcast_id, 'Downloading broadcast JSON') try: broadcast_json = json.loads(broadcast_json_page) protected_broadcast = broadcast_json['_pass_protected'] == 1 if protected_broadcast and not broadcast_password: - raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True) + raise ExtractorError( + 'This broadcast is protected by a password, use the --video-password option', + expected=True) broadcast_offline = broadcast_json['is_play'] == 0 if broadcast_offline: raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True) rtmp_url = broadcast_json['_server'] - if not rtmp_url.startswith('rtmp://'): + mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url) + if not mobj: raise ExtractorError('Unexpected broadcast rtmp URL') broadcast_playpath = broadcast_json['_streamName'] + broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL']) broadcast_thumbnail = broadcast_json['_imgURL'] - broadcast_title = broadcast_json['title'] + broadcast_title = self._live_title(broadcast_json['title']) broadcast_description = broadcast_json['description'] broadcaster_nick = broadcast_json['nick'] broadcaster_login = broadcast_json['login'] @@ -399,6 +362,9 @@ class SmotriBroadcastIE(InfoExtractor): 'age_limit': 18 if adult_content else 0, 'ext': 'flv', 'play_path': broadcast_playpath, + 'player_url': 'http://pics.smotri.com/broadcast_play.swf', + 'app': broadcast_app, 'rtmp_live': True, - 'rtmp_conn': rtmp_conn + 'rtmp_conn': rtmp_conn, + 'is_live': True, } diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py index dc9f80550..c663e56d4 100644 --- a/youtube_dl/extractor/sockshare.py +++ b/youtube_dl/extractor/sockshare.py @@ -61,7 +61,10 @@ class SockshareIE(InfoExtractor): r'<a href="([^"]*)".+class="download_file_link"', webpage, 'file url') video_url = "http://www.sockshare.com" + video_url - title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title') + title = self._html_search_regex(( + r'<h1>(.+)<strong>', + r'var name = "([^"]+)";'), + webpage, 'title', default=None) thumbnail = self._html_search_regex( r'<img\s+src="([^"]*)".+?name="bg"', webpage, 'thumbnail') diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index bebcafb62..07f514a46 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -1,4 +1,5 @@ # encoding: utf-8 +from __future__ import unicode_literals import json import re @@ -11,13 +12,14 @@ class SohuIE(InfoExtractor): _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?' _TEST = { - u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super', - u'file': u'382479172.mp4', - u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7', - u'info_dict': { - u'title': u'MV：Far East Movement《The Illest》', + 'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super', + 'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7', + 'info_dict': { + 'id': '382479172', + 'ext': 'mp4', + 'title': 'MV：Far East Movement《The Illest》', }, - u'skip': u'Only available from China', + 'skip': 'Only available from China', } def _real_extract(self, url): @@ -26,11 +28,11 @@ class SohuIE(InfoExtractor): if mytv: base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' else: - base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' + base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' data_url = base_data_url + str(vid_id) data_json = self._download_webpage( data_url, video_id, - note=u'Downloading JSON data for ' + str(vid_id)) + note='Downloading JSON data for ' + str(vid_id)) return json.loads(data_json) mobj = re.match(self._VALID_URL, url) @@ -39,11 +41,11 @@ class SohuIE(InfoExtractor): webpage = self._download_webpage(url, video_id) raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>', - webpage, u'video title') + webpage, 'video title') title = raw_title.partition('-')[0].strip() vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage, - u'video path') + 'video path') data = _fetch_data(vid, mytv) QUALITIES = ('ori', 'super', 'high', 'nor') @@ -51,7 +53,7 @@ class SohuIE(InfoExtractor): for q in QUALITIES if data['data'][q + 'Vid'] != 0] if not vid_ids: - raise ExtractorError(u'No formats available for this video') + raise ExtractorError('No formats available for this video') # For now, we just pick the highest available quality vid_id = vid_ids[-1] @@ -69,7 +71,7 @@ class SohuIE(InfoExtractor): (allot, prot, clipsURL[i], su[i])) part_str = self._download_webpage( part_url, video_id, - note=u'Downloading part %d of %d' % (i+1, part_count)) + note='Downloading part %d of %d' % (i + 1, part_count)) part_info = part_str.split('|') video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 097d0e418..ab9483d2d 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -28,9 +28,11 @@ class SoundcloudIE(InfoExtractor): _VALID_URL = r'''(?x)^(?:https?://)? (?:(?:(?:www\.|m\.)?soundcloud\.com/ (?P<uploader>[\w\d-]+)/ - (?!sets/)(?P<title>[\w\d-]+)/? + (?!sets/|likes/?(?:$|[?#])) + (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) - |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)) + |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) + (?:/?\?secret_token=(?P<secret_token>[^&]+))?) |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' @@ -38,14 +40,15 @@ class SoundcloudIE(InfoExtractor): _TESTS = [ { 'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy', - 'file': '62986583.mp3', 'md5': 'ebef0a451b909710ed1d7787dddbf0d7', 'info_dict': { - "upload_date": "20121011", - "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", - "uploader": "E.T. ExTerrestrial Music", - "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1", - "duration": 143, + 'id': '62986583', + 'ext': 'mp3', + 'upload_date': '20121011', + 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', + 'uploader': 'E.T. ExTerrestrial Music', + 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', + 'duration': 143, } }, # not streamable song @@ -79,6 +82,20 @@ class SoundcloudIE(InfoExtractor): 'duration': 9, }, }, + # private link (alt format) + { + 'url': 'https://api.soundcloud.com/tracks/123998367?secret_token=s-8Pjrp', + 'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604', + 'info_dict': { + 'id': '123998367', + 'ext': 'mp3', + 'title': 'Youtube - Dl Test Video \'\' Ä↭', + 'uploader': 'jaimeMF', + 'description': 'test chars: \"\'/\\ä↭', + 'upload_date': '20131209', + 'duration': 9, + }, + }, # downloadable song { 'url': 'https://soundcloud.com/oddsamples/bus-brakes', @@ -87,7 +104,7 @@ class SoundcloudIE(InfoExtractor): 'id': '128590877', 'ext': 'mp3', 'title': 'Bus Brakes', - 'description': 'md5:0170be75dd395c96025d210d261c784e', + 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', 'upload_date': '20140109', 'duration': 17, @@ -124,6 +141,7 @@ class SoundcloudIE(InfoExtractor): 'description': info['description'], 'thumbnail': thumbnail, 'duration': int_or_none(info.get('duration'), 1000), + 'webpage_url': info.get('permalink_url'), } formats = [] if info.get('downloadable', False): @@ -141,7 +159,7 @@ class SoundcloudIE(InfoExtractor): # We have to retrieve the url streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?' - 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) + 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) format_dict = self._download_json( streams_url, track_id, 'Downloading track url') @@ -196,6 +214,9 @@ class SoundcloudIE(InfoExtractor): if track_id is not None: info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID full_title = track_id + token = mobj.group('secret_token') + if token: + info_json_url += "&secret_token=" + token elif mobj.group('player'): query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) return self.url_result(query['url'][0]) @@ -203,14 +224,14 @@ class SoundcloudIE(InfoExtractor): # extract uploader (which is in the url) uploader = mobj.group('uploader') # extract simple title (uploader + slug of song title) - slug_title = mobj.group('title') + slug_title = mobj.group('title') token = mobj.group('token') full_title = resolve_title = '%s/%s' % (uploader, slug_title) if token: resolve_title += '/%s' % token - + self.report_resolve(full_title) - + url = 'http://soundcloud.com/%s' % resolve_title info_json_url = self._resolv_url(url) info = self._download_json(info_json_url, full_title, 'Downloading info JSON') @@ -219,25 +240,33 @@ class SoundcloudIE(InfoExtractor): class SoundcloudSetIE(SoundcloudIE): - _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' + _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?' IE_NAME = 'soundcloud:set' - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep', + 'info_dict': { + 'title': 'The Royal Concept EP', + }, + 'playlist_mincount': 6, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) # extract uploader (which is in the url) - uploader = mobj.group(1) + uploader = mobj.group('uploader') # extract simple title (uploader + slug of song title) - slug_title = mobj.group(2) + slug_title = mobj.group('slug_title') full_title = '%s/sets/%s' % (uploader, slug_title) + url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) + + token = mobj.group('token') + if token: + full_title += '/' + token + url += '/' + token self.report_resolve(full_title) - url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) resolv_url = self._resolv_url(url) info = self._download_json(resolv_url, full_title) @@ -246,20 +275,32 @@ class SoundcloudSetIE(SoundcloudIE): self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message'])) return - self.report_extraction(full_title) - return {'_type': 'playlist', - 'entries': [self._extract_info_dict(track) for track in info['tracks']], - 'id': info['id'], - 'title': info['title'], - } + return { + '_type': 'playlist', + 'entries': [self._extract_info_dict(track, secret_token=token) for track in info['tracks']], + 'id': info['id'], + 'title': info['title'], + } class SoundcloudUserIE(SoundcloudIE): _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$' IE_NAME = 'soundcloud:user' - - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'https://soundcloud.com/the-concept-band', + 'info_dict': { + 'id': '9615865', + 'title': 'The Royal Concept', + }, + 'playlist_mincount': 12 + }, { + 'url': 'https://soundcloud.com/the-concept-band/likes', + 'info_dict': { + 'id': '9615865', + 'title': 'The Royal Concept', + }, + 'playlist_mincount': 1, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -299,25 +340,38 @@ class SoundcloudUserIE(SoundcloudIE): class SoundcloudPlaylistIE(SoundcloudIE): - _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)' + _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' IE_NAME = 'soundcloud:playlist' - - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'http://api.soundcloud.com/playlists/4110309', + 'info_dict': { + 'id': '4110309', + 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', + 'description': 're:.*?TILT Brass - Bowery Poetry Club', + }, + 'playlist_count': 6, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) playlist_id = mobj.group('id') base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id) - data = compat_urllib_parse.urlencode({ + data_dict = { 'client_id': self._CLIENT_ID, - }) + } + token = mobj.group('token') + + if token: + data_dict['secret_token'] = token + + data = compat_urllib_parse.urlencode(data_dict) data = self._download_json( base_url + data, playlist_id, 'Downloading playlist') entries = [ - self._extract_info_dict(t, quiet=True) for t in data['tracks']] + self._extract_info_dict(t, quiet=True, secret_token=token) + for t in data['tracks']] return { '_type': 'playlist', diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py index d34aefeaa..c2d0d36a6 100644 --- a/youtube_dl/extractor/space.py +++ b/youtube_dl/extractor/space.py @@ -33,5 +33,6 @@ class SpaceIE(InfoExtractor): # Other videos works fine with the info from the object brightcove_url = BrightcoveIE._extract_brightcove_url(webpage) if brightcove_url is None: - raise ExtractorError(u'The webpage does not contain a video', expected=True) + raise ExtractorError( + 'The webpage does not contain a video', expected=True) return self.url_result(brightcove_url, BrightcoveIE.ie_key()) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 2007a0013..94602e89e 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -9,7 +9,6 @@ from ..utils import ( compat_urllib_parse, unified_strdate, str_to_int, - int_or_none, ) from ..aes import aes_decrypt_text @@ -40,31 +39,42 @@ class SpankwireIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title') + title = self._html_search_regex( + r'<h1>([^<]+)', webpage, 'title') description = self._html_search_regex( - r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False) + r'<div\s+id="descriptionContent">([^<]+)<', + webpage, 'description', fatal=False) thumbnail = self._html_search_regex( - r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False) + r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']', + webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( - r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False) + r'by:\s*<a [^>]*>(.+?)</a>', + webpage, 'uploader', fatal=False) uploader_id = self._html_search_regex( - r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False) - upload_date = self._html_search_regex(r'</a> on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - - view_count = self._html_search_regex( - r'<div id="viewsCounter"><span>([^<]+)</span> views</div>', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = int_or_none(self._html_search_regex( - r'<span id="spCommentCount">\s*(\d+)</span> Comments</div>', webpage, 'comment count', fatal=False)) + r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', + webpage, 'uploader id', fatal=False) + upload_date = unified_strdate(self._html_search_regex( + r'</a> on (.+?) at \d+:\d+', + webpage, 'upload date', fatal=False)) - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage))) + view_count = str_to_int(self._html_search_regex( + r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>', + webpage, 'comment count', fatal=False)) + + video_urls = list(map( + compat_urllib_parse.unquote, + re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage))) if webpage.find('flashvars\.encrypted = "true"') != -1: - password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ') - video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) + password = self._html_search_regex( + r'flashvars\.video_title = "([^"]+)', + webpage, 'password').replace('+', ' ') + video_urls = list(map( + lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), + video_urls)) formats = [] for video_url in video_urls: diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 340a38440..1e55a9ffb 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -4,10 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse +from .spiegeltv import SpiegeltvIE class SpiegelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' + _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed)?(?:\.html)?(?:#.*)?$' _TESTS = [{ 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', 'md5': '2c2754212136f35fb4b19767d242f66e', @@ -29,25 +31,27 @@ class SpiegelIE(InfoExtractor): 'duration': 983, }, }, { - 'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html', - 'md5': '54f58ba0e752e3c07bc2a26222dd0acf', + 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html', + 'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51', 'info_dict': { - 'id': '1502367', + 'id': '1519126', 'ext': 'mp4', - 'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern', - 'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91', - 'duration': 42, - }, + 'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.', + 'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"', + } }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') + video_id = self._match_id(url) + webpage, handle = self._download_webpage_handle(url, video_id) - webpage = self._download_webpage(url, video_id) + # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html + if SpiegeltvIE.suitable(handle.geturl()): + return self.url_result(handle.geturl(), 'Spiegeltv') - title = self._html_search_regex( - r'<div class="module-title">(.*?)</div>', webpage, 'title') + title = re.sub(r'\s+', ' ', self._html_search_regex( + r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>', + webpage, 'title')) description = self._html_search_meta('description', webpage, 'description') base_url = self._search_regex( @@ -82,3 +86,48 @@ class SpiegelIE(InfoExtractor): 'duration': duration, 'formats': formats, } + + +class SpiegelArticleIE(InfoExtractor): + _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html' + IE_NAME = 'Spiegel:Article' + IE_DESC = 'Articles on spiegel.de' + _TESTS = [{ + 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', + 'info_dict': { + 'id': '1516455', + 'ext': 'mp4', + 'title': 'Faszination Badminton: Nennt es bloß nicht Federball', + 'description': 're:^Patrick Kämnitz gehört.{100,}', + }, + }, { + 'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html', + 'info_dict': { + + }, + 'playlist_count': 6, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # Single video on top of the page + video_link = self._search_regex( + r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage, + 'video page URL', default=None) + if video_link: + video_url = compat_urlparse.urljoin( + self.http_scheme() + '//spiegel.de/', video_link) + return self.url_result(video_url) + + # Multiple embedded videos + embeds = re.findall( + r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"', + webpage) + entries = [ + self.url_result(compat_urlparse.urljoin( + self.http_scheme() + '//spiegel.de/', embed_path)) + for embed_path in embeds + ] + return self.playlist_result(entries) diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py index 7f388aced..98cf92d89 100644 --- a/youtube_dl/extractor/spiegeltv.py +++ b/youtube_dl/extractor/spiegeltv.py @@ -1,13 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals -import re from .common import InfoExtractor +from ..utils import float_or_none class SpiegeltvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/(?:#/)?filme/(?P<id>[\-a-z0-9]+)' + _TESTS = [{ 'url': 'http://www.spiegel.tv/filme/flug-mh370/', 'info_dict': { 'id': 'flug-mh370', @@ -20,12 +20,15 @@ class SpiegeltvIE(InfoExtractor): # rtmp download 'skip_download': True, } - } + }, { + 'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + if '/#/' in url: + url = url.replace('/#/', '/') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title') @@ -61,12 +64,8 @@ class SpiegeltvIE(InfoExtractor): }) description = media_json['subtitle'] - duration = media_json['duration_in_ms'] / 1000. - - if is_wide: - format = '16x9' - else: - format = '4x3' + duration = float_or_none(media_json.get('duration_in_ms'), scale=1000) + format = '16x9' if is_wide else '4x3' url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v' @@ -78,4 +77,4 @@ class SpiegeltvIE(InfoExtractor): 'description': description, 'duration': duration, 'thumbnails': thumbnails - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/sport5.py b/youtube_dl/extractor/sport5.py new file mode 100644 index 000000000..dfe50ed45 --- /dev/null +++ b/youtube_dl/extractor/sport5.py @@ -0,0 +1,92 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Sport5IE(InfoExtractor): + _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1', + 'info_dict': { + 'id': 's5-Y59xx1-GUh2', + 'ext': 'mp4', + 'title': 'ולנסיה-קורדובה 0:3', + 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה', + 'duration': 228, + 'categories': list, + }, + 'skip': 'Blocked outside of Israel', + }, { + 'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE', + 'info_dict': { + 'id': 's5-SiXxx1-hKh2', + 'ext': 'mp4', + 'title': 'GOALS_CELTIC_270914.mp4', + 'description': '', + 'duration': 87, + 'categories': list, + }, + 'skip': 'Blocked outside of Israel', + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + media_id = mobj.group('id') + + webpage = self._download_webpage(url, media_id) + + video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id') + + metadata = self._download_xml( + 'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id, + video_id) + + error = metadata.find('./Error') + if error is not None: + raise ExtractorError( + '%s returned error: %s - %s' % ( + self.IE_NAME, + error.find('./Name').text, + error.find('./Description').text), + expected=True) + + title = metadata.find('./Title').text + description = metadata.find('./Description').text + duration = int(metadata.find('./Duration').text) + + posters_el = metadata.find('./PosterLinks') + thumbnails = [{ + 'url': thumbnail.text, + 'width': int(thumbnail.get('width')), + 'height': int(thumbnail.get('height')), + } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else [] + + categories_el = metadata.find('./Categories') + categories = [ + cat.get('name') for cat in categories_el.findall('./Category') + ] if categories_el is not None else [] + + formats = [{ + 'url': fmt.text, + 'ext': 'mp4', + 'vbr': int(fmt.get('bitrate')), + 'width': int(fmt.get('width')), + 'height': int(fmt.get('height')), + } for fmt in metadata.findall('./PlaybackLinks/FileURL')] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnails': thumbnails, + 'duration': duration, + 'categories': categories, + 'formats': formats, + } diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py new file mode 100644 index 000000000..becdf658f --- /dev/null +++ b/youtube_dl/extractor/sportbox.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, +) + + +class SportBoxIE(InfoExtractor): + _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)' + _TESTS = [ + { + 'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '80822', + 'ext': 'mp4', + 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', + 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1411896237, + 'upload_date': '20140928', + 'duration': 4846, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4', + 'only_matching': True, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'src="/vdl/player/media/(\d+)"', webpage, 'video id') + + player = self._download_webpage( + 'http://news.sportbox.ru/vdl/player/media/%s' % video_id, + display_id, 'Downloading player webpage') + + hls = self._search_regex( + r"var\s+original_hls_file\s*=\s*'([^']+)'", player, 'hls file') + + formats = self._extract_m3u8_formats(hls, display_id, 'mp4') + + title = self._html_search_regex( + r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title') + description = self._html_search_regex( + r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + timestamp = parse_iso8601(self._search_regex( + r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py new file mode 100644 index 000000000..057ef5251 --- /dev/null +++ b/youtube_dl/extractor/sportdeutschland.py @@ -0,0 +1,95 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + parse_iso8601, +) + + +class SportDeutschlandIE(InfoExtractor): + _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])' + _TESTS = [{ + 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'info_dict': { + 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'ext': 'mp4', + 'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', + 'categories': ['Badminton'], + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV', + 'timestamp': int, + 'upload_date': 're:^201408[23][0-9]$', + }, + 'params': { + 'skip_download': 'Live stream', + }, + }, { + 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', + 'info_dict': { + 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', + 'ext': 'mp4', + 'upload_date': '20140825', + 'description': 'md5:60a20536b57cee7d9a4ec005e8687504', + 'timestamp': 1408976060, + 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee', + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, + 'categories': ['Li-Ning Badminton WM 2014'], + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + sport_id = mobj.group('sport') + + api_url = 'http://splink.tv/api/permalinks/%s/%s' % ( + sport_id, video_id) + req = compat_urllib_request.Request(api_url, headers={ + 'Accept': 'application/vnd.vidibus.v2.html+json', + 'Referer': url, + }) + data = self._download_json(req, video_id) + + categories = list(data.get('section', {}).get('tags', {}).values()) + asset = data['asset'] + + formats = [] + smil_url = asset['video'] + if '.smil' in smil_url: + m3u8_url = smil_url.replace('.smil', '.m3u8') + formats.extend( + self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')) + + smil_doc = self._download_xml( + smil_url, video_id, note='Downloading SMIL metadata') + base_url = smil_doc.find('./head/meta').attrib['base'] + formats.extend([{ + 'format_id': 'rmtp', + 'url': base_url, + 'play_path': n.attrib['src'], + 'ext': 'flv', + 'preference': -100, + 'format_note': 'Seems to fail at example stream', + } for n in smil_doc.findall('./body/video')]) + else: + formats.append({'url': smil_url}) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'formats': formats, + 'title': asset['title'], + 'thumbnail': asset.get('image'), + 'description': asset.get('teaser'), + 'categories': categories, + 'view_count': asset.get('views'), + 'rtmp_live': asset.get('live'), + 'timestamp': parse_iso8601(asset.get('date')), + } diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py new file mode 100644 index 000000000..666a7dcc8 --- /dev/null +++ b/youtube_dl/extractor/srmediathek.py @@ -0,0 +1,43 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import js_to_json + + +class SRMediathekIE(InfoExtractor): + IE_DESC = 'Süddeutscher Rundfunk' + _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)' + + _TEST = { + 'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455', + 'info_dict': { + 'id': '28455', + 'ext': 'mp4', + 'title': 'sportarena (26.10.2014)', + 'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + murls = json.loads(js_to_json(self._search_regex( + r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs'))) + formats = [{'url': murl} for murl in murls] + self._sort_formats(formats) + + title = json.loads(js_to_json(self._search_regex( + r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/stanfordoc.py b/youtube_dl/extractor/stanfordoc.py index 44c52c718..4a3d8bb8f 100644 --- a/youtube_dl/extractor/stanfordoc.py +++ b/youtube_dl/extractor/stanfordoc.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -9,24 +11,23 @@ from ..utils import ( class StanfordOpenClassroomIE(InfoExtractor): - IE_NAME = u'stanfordoc' - IE_DESC = u'Stanford Open ClassRoom' - _VALID_URL = r'^(?:https?://)?openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' + IE_NAME = 'stanfordoc' + IE_DESC = 'Stanford Open ClassRoom' + _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' _TEST = { - u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100', - u'file': u'PracticalUnix_intro-environment.mp4', - u'md5': u'544a9468546059d4e80d76265b0443b8', - u'info_dict': { - u"title": u"Intro Environment" + 'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100', + 'md5': '544a9468546059d4e80d76265b0443b8', + 'info_dict': { + 'id': 'PracticalUnix_intro-environment', + 'ext': 'mp4', + 'title': 'Intro Environment', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - if mobj.group('course') and mobj.group('video'): # A specific video + if mobj.group('course') and mobj.group('video'): # A specific video course = mobj.group('course') video = mobj.group('video') info = { @@ -35,7 +36,6 @@ class StanfordOpenClassroomIE(InfoExtractor): 'upload_date': None, } - self.report_extraction(info['id']) baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' xmlUrl = baseUrl + video + '.xml' mdoc = self._download_xml(xmlUrl, info['id']) @@ -43,63 +43,49 @@ class StanfordOpenClassroomIE(InfoExtractor): info['title'] = mdoc.findall('./title')[0].text info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text except IndexError: - raise ExtractorError(u'Invalid metadata XML file') - info['ext'] = info['url'].rpartition('.')[2] - return [info] - elif mobj.group('course'): # A course page + raise ExtractorError('Invalid metadata XML file') + return info + elif mobj.group('course'): # A course page course = mobj.group('course') info = { 'id': course, - 'type': 'playlist', + '_type': 'playlist', 'uploader': None, 'upload_date': None, } - coursepage = self._download_webpage(url, info['id'], - note='Downloading course info page', - errnote='Unable to download course info page') + coursepage = self._download_webpage( + url, info['id'], + note='Downloading course info page', + errnote='Unable to download course info page') - info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id']) + info['title'] = self._html_search_regex( + r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id']) - info['description'] = self._html_search_regex('<description>([^<]+)</description>', - coursepage, u'description', fatal=False) + info['description'] = self._html_search_regex( + r'(?s)<description>([^<]+)</description>', + coursepage, 'description', fatal=False) links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) - info['list'] = [ - { - 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), - } - for vpage in links] - results = [] - for entry in info['list']: - assert entry['type'] == 'reference' - results += self.extract(entry['url']) - return results - else: # Root page + info['entries'] = [self.url_result( + 'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l) + ) for l in links] + return info + else: # Root page info = { 'id': 'Stanford OpenClassroom', - 'type': 'playlist', + '_type': 'playlist', 'uploader': None, 'upload_date': None, } + info['title'] = info['id'] rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' rootpage = self._download_webpage(rootURL, info['id'], - errnote=u'Unable to download course info page') - - info['title'] = info['id'] + errnote='Unable to download course info page') links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) - info['list'] = [ - { - 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), - } - for cpage in links] - - results = [] - for entry in info['list']: - assert entry['type'] == 'reference' - results += self.extract(entry['url']) - return results + info['entries'] = [self.url_result( + 'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l) + ) for l in links] + return info diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 172def221..c1178f26d 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -13,7 +13,7 @@ from ..utils import ( class StreamcloudIE(InfoExtractor): IE_NAME = 'streamcloud.eu' - _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html' + _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?' _TEST = { 'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', @@ -27,8 +27,8 @@ class StreamcloudIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + url = 'http://streamcloud.eu/%s' % video_id orig_webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py index db33745c1..59a51268d 100644 --- a/youtube_dl/extractor/subtitles.py +++ b/youtube_dl/extractor/subtitles.py @@ -1,7 +1,8 @@ +from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_str, ExtractorError, ) @@ -17,10 +18,10 @@ class SubtitlesInfoExtractor(InfoExtractor): sub_lang_list = self._get_available_subtitles(video_id, webpage) auto_captions_list = self._get_available_automatic_caption(video_id, webpage) sub_lang = ",".join(list(sub_lang_list.keys())) - self.to_screen(u'%s: Available subtitles for video: %s' % + self.to_screen('%s: Available subtitles for video: %s' % (video_id, sub_lang)) auto_lang = ",".join(auto_captions_list.keys()) - self.to_screen(u'%s: Available automatic captions for video: %s' % + self.to_screen('%s: Available automatic captions for video: %s' % (video_id, auto_lang)) def extract_subtitles(self, video_id, webpage): @@ -50,8 +51,8 @@ class SubtitlesInfoExtractor(InfoExtractor): sub_lang_list = {} for sub_lang in requested_langs: - if not sub_lang in available_subs_list: - self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) + if sub_lang not in available_subs_list: + self._downloader.report_warning('no closed captions found in the specified language "%s"' % sub_lang) continue sub_lang_list[sub_lang] = available_subs_list[sub_lang] @@ -70,10 +71,10 @@ class SubtitlesInfoExtractor(InfoExtractor): try: sub = self._download_subtitle_url(sub_lang, url) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) + self._downloader.report_warning('unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) return if not sub: - self._downloader.report_warning(u'Did not fetch video subtitles') + self._downloader.report_warning('Did not fetch video subtitles') return return sub @@ -94,5 +95,5 @@ class SubtitlesInfoExtractor(InfoExtractor): Must be redefined by the subclasses that support automatic captions, otherwise it will return {} """ - self._downloader.report_warning(u'Automatic Captions not supported by this server') + self._downloader.report_warning('Automatic Captions not supported by this server') return {} diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py new file mode 100644 index 000000000..263f09b46 --- /dev/null +++ b/youtube_dl/extractor/sunporno.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, + qualities, + determine_ext, +) + + +class SunPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.sunporno.com/videos/807778/', + 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', + 'info_dict': { + 'id': '807778', + 'ext': 'flv', + 'title': 'md5:0a400058e8105d39e35c35e7c5184164', + 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 302, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) + + duration = parse_duration(self._search_regex( + r'Duration:\s*(\d+:\d+)\s*<', webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'class="views">\s*(\d+)\s*<', webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) + + formats = [] + quality = qualities(['mp4', 'flv']) + for video_url in re.findall(r'<source src="([^"]+)"', webpage): + video_ext = determine_ext(video_url) + formats.append({ + 'url': video_url, + 'format_id': video_ext, + 'quality': quality(video_ext), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py index 5d9d70367..58073eefe 100644 --- a/youtube_dl/extractor/swrmediathek.py +++ b/youtube_dl/extractor/swrmediathek.py @@ -52,20 +52,6 @@ class SWRMediathekIE(InfoExtractor): 'uploader': 'SWR 2', 'uploader_id': '284670', } - }, { - 'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6', - 'md5': '881531487d0633080a8cc88d31ef896f', - 'info_dict': { - 'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6', - 'ext': 'mp4', - 'title': 'Familienspaß am Bodensee', - 'description': 'md5:0b591225a32cfde7be1629ed49fe4315', - 'thumbnail': 're:http://.*\.jpg', - 'duration': 1784, - 'upload_date': '20140727', - 'uploader': 'SWR Fernsehen BW', - 'uploader_id': '281130', - } }] def _real_extract(self, url): @@ -94,7 +80,7 @@ class SWRMediathekIE(InfoExtractor): if media_type == 'Video': fmt.update({ - 'format_note': ['144p', '288p', '544p'][quality-1], + 'format_note': ['144p', '288p', '544p', '720p'][quality - 1], 'vcodec': codec, }) elif media_type == 'Audio': @@ -115,4 +101,4 @@ class SWRMediathekIE(InfoExtractor): 'uploader': attr['channel_title'], 'uploader_id': attr['channel_idkey'], 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/syfy.py b/youtube_dl/extractor/syfy.py index f76b6e2b2..5ca079f88 100644 --- a/youtube_dl/extractor/syfy.py +++ b/youtube_dl/extractor/syfy.py @@ -10,7 +10,6 @@ class SyfyIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458', - 'md5': 'e07de1d52c7278adbb9b9b1c93a66849', 'info_dict': { 'id': 'NmqMrGnXvmO1', 'ext': 'flv', diff --git a/youtube_dl/extractor/sztvhu.py b/youtube_dl/extractor/sztvhu.py index c9359fafb..aa5964acb 100644 --- a/youtube_dl/extractor/sztvhu.py +++ b/youtube_dl/extractor/sztvhu.py @@ -1,27 +1,24 @@ # -*- coding: utf-8 -*- - -import re +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext class SztvHuIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)' + _VALID_URL = r'http://(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)' _TEST = { - u'url': u'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909', - u'file': u'20130909.mp4', - u'md5': u'a6df607b11fb07d0e9f2ad94613375cb', - u'info_dict': { - u"title": u"Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren", - u"description": u'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...', + 'url': 'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909', + 'md5': 'a6df607b11fb07d0e9f2ad94613375cb', + 'info_dict': { + 'id': '20130909', + 'ext': 'mp4', + 'title': 'Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren', + 'description': 'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...', }, - u'skip': u'Service temporarily disabled as of 2013-11-20' } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_file = self._search_regex( r'file: "...:(.*?)",', webpage, 'video file') @@ -39,7 +36,6 @@ class SztvHuIE(InfoExtractor): 'id': video_id, 'url': video_url, 'title': title, - 'ext': determine_ext(video_url), 'description': description, 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py index b87047451..bfe07b024 100644 --- a/youtube_dl/extractor/tagesschau.py +++ b/youtube_dl/extractor/tagesschau.py @@ -4,10 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import parse_filesize class TagesschauIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html' + _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/ts|video/video)(?P<id>-?[0-9]+)\.html' _TESTS = [{ 'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html', @@ -19,6 +20,16 @@ class TagesschauIE(InfoExtractor): 'description': 'md5:69da3c61275b426426d711bde96463ab', 'thumbnail': 're:^http:.*\.jpg$', }, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html', + 'md5': '3c54c1f6243d279b706bde660ceec633', + 'info_dict': { + 'id': '5727', + 'ext': 'mp4', + 'description': 'md5:695c01bfd98b7e313c501386327aea59', + 'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr', + 'thumbnail': 're:^http:.*\.jpg$', + } }] _FORMATS = { @@ -28,42 +39,82 @@ class TagesschauIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - if video_id.startswith('-'): - display_id = video_id.strip('-') - else: - display_id = video_id - + video_id = self._match_id(url) + display_id = video_id.lstrip('-') webpage = self._download_webpage(url, display_id) - playerpage = self._download_webpage( - 'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id, - display_id, 'Downloading player page') - - medias = re.findall( - r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"', - playerpage) + player_url = self._html_search_meta( + 'twitter:player', webpage, 'player URL', default=None) + if player_url: + playerpage = self._download_webpage( + player_url, display_id, 'Downloading player page') - formats = [] - for url, ext, res in medias: - f = { - 'format_id': res + '_' + ext, - 'url': url, - 'ext': ext, - } - f.update(self._FORMATS.get(res, {})) - formats.append(f) + medias = re.findall( + r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"', + playerpage) + formats = [] + for url, ext, res in medias: + f = { + 'format_id': res + '_' + ext, + 'url': url, + 'ext': ext, + } + f.update(self._FORMATS.get(res, {})) + formats.append(f) + thumbnail_fn = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1] + title = self._og_search_title(webpage).strip() + description = self._og_search_description(webpage).strip() + else: + download_text = self._search_regex( + r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>', + webpage, 'download links') + links = re.finditer( + r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>', + download_text) + formats = [] + for l in links: + format_id = self._search_regex( + r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID') + format = { + 'format_id': format_id, + 'url': l.group('url'), + 'format_name': l.group('name'), + } + m = re.match( + r'''(?x) + Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10; + (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10; + (?P<vbr>[0-9]+)kbps&\#10; + Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10; + Größe:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''', + l.group('title')) + if m: + format.update({ + 'format_note': m.group('audio_desc'), + 'vcodec': m.group('vcodec'), + 'width': int(m.group('width')), + 'height': int(m.group('height')), + 'abr': int(m.group('abr')), + 'vbr': int(m.group('vbr')), + 'filesize_approx': parse_filesize(m.group('filesize_approx')), + }) + formats.append(format) + thumbnail_fn = self._search_regex( + r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"', + webpage, 'thumbnail', fatal=False) + description = self._html_search_regex( + r'(?s)<p class="teasertext">(.*?)</p>', + webpage, 'description', fatal=False) + title = self._html_search_regex( + r'<span class="headline".*?>(.*?)</span>', webpage, 'title') self._sort_formats(formats) - - thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1] + thumbnail = 'http://www.tagesschau.de' + thumbnail_fn return { 'id': display_id, - 'title': self._og_search_title(webpage).strip(), - 'thumbnail': 'http://www.tagesschau.de' + thumbnail, + 'title': title, + 'thumbnail': thumbnail, 'formats': formats, - 'description': self._og_search_description(webpage).strip(), + 'description': description, } diff --git a/youtube_dl/extractor/tapely.py b/youtube_dl/extractor/tapely.py new file mode 100644 index 000000000..283e11350 --- /dev/null +++ b/youtube_dl/extractor/tapely.py @@ -0,0 +1,105 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + clean_html, + compat_urllib_request, + float_or_none, + parse_iso8601, +) + + +class TapelyIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tape\.ly/(?P<id>[A-Za-z0-9\-_]+)(?:/(?P<songnr>\d+))?' + _API_URL = 'http://tape.ly/showtape?id={0:}' + _S3_SONG_URL = 'http://mytape.s3.amazonaws.com/{0:}' + _SOUNDCLOUD_SONG_URL = 'http://api.soundcloud.com{0:}' + _TESTS = [ + { + 'url': 'http://tape.ly/my-grief-as-told-by-water', + 'info_dict': { + 'id': 23952, + 'title': 'my grief as told by water', + 'thumbnail': 're:^https?://.*\.png$', + 'uploader_id': 16484, + 'timestamp': 1411848286, + 'description': 'For Robin and Ponkers, whom the tides of life have taken out to sea.', + }, + 'playlist_count': 13, + }, + { + 'url': 'http://tape.ly/my-grief-as-told-by-water/1', + 'md5': '79031f459fdec6530663b854cbc5715c', + 'info_dict': { + 'id': 258464, + 'title': 'Dreaming Awake (My Brightest Diamond)', + 'ext': 'm4a', + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + playlist_url = self._API_URL.format(display_id) + request = compat_urllib_request.Request(playlist_url) + request.add_header('X-Requested-With', 'XMLHttpRequest') + request.add_header('Accept', 'application/json') + request.add_header('Referer', url) + + playlist = self._download_json(request, display_id) + + tape = playlist['tape'] + + entries = [] + for s in tape['songs']: + song = s['song'] + entry = { + 'id': song['id'], + 'duration': float_or_none(song.get('songduration'), 1000), + 'title': song['title'], + } + if song['source'] == 'S3': + entry.update({ + 'url': self._S3_SONG_URL.format(song['filename']), + }) + entries.append(entry) + elif song['source'] == 'YT': + self.to_screen('YouTube video detected') + yt_id = song['filename'].replace('/youtube/', '') + entry.update(self.url_result(yt_id, 'Youtube', video_id=yt_id)) + entries.append(entry) + elif song['source'] == 'SC': + self.to_screen('SoundCloud song detected') + sc_url = self._SOUNDCLOUD_SONG_URL.format(song['filename']) + entry.update(self.url_result(sc_url, 'Soundcloud')) + entries.append(entry) + else: + self.report_warning('Unknown song source: %s' % song['source']) + + if mobj.group('songnr'): + songnr = int(mobj.group('songnr')) - 1 + try: + return entries[songnr] + except IndexError: + raise ExtractorError( + 'No song with index: %s' % mobj.group('songnr'), + expected=True) + + return { + '_type': 'playlist', + 'id': tape['id'], + 'display_id': display_id, + 'title': tape['name'], + 'entries': entries, + 'thumbnail': tape.get('image_url'), + 'description': clean_html(tape.get('subtext')), + 'like_count': tape.get('likescount'), + 'uploader_id': tape.get('user_id'), + 'timestamp': parse_iso8601(tape.get('published_at')), + } diff --git a/youtube_dl/extractor/tass.py b/youtube_dl/extractor/tass.py new file mode 100644 index 000000000..c4ef70778 --- /dev/null +++ b/youtube_dl/extractor/tass.py @@ -0,0 +1,62 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + qualities, +) + + +class TassIE(InfoExtractor): + _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://tass.ru/obschestvo/1586870', + 'md5': '3b4cdd011bc59174596b6145cda474a4', + 'info_dict': { + 'id': '1586870', + 'ext': 'mp4', + 'title': 'Посетителям московского зоопарка показали красную панду', + 'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://itar-tass.com/obschestvo/1600009', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + sources = json.loads(js_to_json(self._search_regex( + r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources'))) + + quality = qualities(['sd', 'hd']) + + formats = [] + for source in sources: + video_url = source.get('file') + if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'): + continue + label = source.get('label') + formats.append({ + 'url': video_url, + 'format_id': label, + 'quality': quality(label), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + } diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 46d727d1d..6c3445d79 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -106,6 +106,13 @@ class TeacherTubeUserIE(InfoExtractor): \s* <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)" ''' + _TEST = { + 'url': 'http://www.teachertube.com/user/profile/rbhagwati2', + 'info_dict': { + 'id': 'rbhagwati2' + }, + 'playlist_mincount': 179, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -114,7 +121,7 @@ class TeacherTubeUserIE(InfoExtractor): urls = [] webpage = self._download_webpage(url, user_id) urls.extend(re.findall(self._MEDIA_RE, webpage)) - + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1] for p in pages: more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index f8dd7e955..5fa67eb8d 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -8,24 +8,23 @@ from .common import InfoExtractor class TeamcocoIE(InfoExtractor): _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)' _TESTS = [ - { - 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', - 'file': '80187.mp4', - 'md5': '3f7746aa0dc86de18df7539903d399ea', - 'info_dict': { - 'title': 'Conan Becomes A Mary Kay Beauty Consultant', - 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.' + { + 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', + 'file': '80187.mp4', + 'md5': '3f7746aa0dc86de18df7539903d399ea', + 'info_dict': { + 'title': 'Conan Becomes A Mary Kay Beauty Consultant', + 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.' + } + }, { + 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush', + 'file': '19705.mp4', + 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a', + 'info_dict': { + "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.", + "title": "Louis C.K. Interview Pt. 1 11/3/11" + } } - }, - { - 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush', - 'file': '19705.mp4', - 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a', - 'info_dict': { - "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.", - "title": "Louis C.K. Interview Pt. 1 11/3/11" - } - } ] def _real_extract(self, url): @@ -33,11 +32,11 @@ class TeamcocoIE(InfoExtractor): display_id = mobj.group('display_id') webpage = self._download_webpage(url, display_id) - + video_id = mobj.group("video_id") if not video_id: video_id = self._html_search_regex( - r'<article class="video" data-id="(\d+?)"', + r'data-node-id="(\d+?)"', webpage, 'video id') data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id diff --git a/youtube_dl/extractor/techtalks.py b/youtube_dl/extractor/techtalks.py index a55f236cb..16e945d8e 100644 --- a/youtube_dl/extractor/techtalks.py +++ b/youtube_dl/extractor/techtalks.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -11,24 +13,30 @@ class TechTalksIE(InfoExtractor): _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/' _TEST = { - u'url': u'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/', - u'playlist': [ + 'url': 'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/', + 'info_dict': { + 'id': '57758', + 'title': 'Learning Topic Models --- Going beyond SVD', + }, + 'playlist': [ { - u'file': u'57758.flv', - u'info_dict': { - u'title': u'Learning Topic Models --- Going beyond SVD', + 'info_dict': { + 'id': '57758', + 'ext': 'flv', + 'title': 'Learning Topic Models --- Going beyond SVD', }, }, { - u'file': u'57758-slides.flv', - u'info_dict': { - u'title': u'Learning Topic Models --- Going beyond SVD', + 'info_dict': { + 'id': '57758-slides', + 'ext': 'flv', + 'title': 'Learning Topic Models --- Going beyond SVD', }, }, ], - u'params': { + 'params': { # rtmp download - u'skip_download': True, + 'skip_download': True, }, } @@ -36,30 +44,36 @@ class TechTalksIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) talk_id = mobj.group('id') webpage = self._download_webpage(url, talk_id) - rtmp_url = self._search_regex(r'netConnectionUrl: \'(.*?)\'', webpage, - u'rtmp url') - play_path = self._search_regex(r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"', - webpage, u'presenter play path') + rtmp_url = self._search_regex( + r'netConnectionUrl: \'(.*?)\'', webpage, 'rtmp url') + play_path = self._search_regex( + r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"', + webpage, 'presenter play path') title = clean_html(get_element_by_attribute('class', 'title', webpage)) video_info = { - 'id': talk_id, - 'title': title, - 'url': rtmp_url, - 'play_path': play_path, - 'ext': 'flv', - } + 'id': talk_id, + 'title': title, + 'url': rtmp_url, + 'play_path': play_path, + 'ext': 'flv', + } m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage) if m_slides is None: return video_info else: - return [ - video_info, - # The slides video - { - 'id': talk_id + '-slides', - 'title': title, - 'url': rtmp_url, - 'play_path': m_slides.group(1), - 'ext': 'flv', - }, - ] + return { + '_type': 'playlist', + 'id': talk_id, + 'title': title, + 'entries': [ + video_info, + # The slides video + { + 'id': talk_id + '-slides', + 'title': title, + 'url': rtmp_url, + 'play_path': m_slides.group(1), + 'ext': 'flv', + }, + ], + } diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index bce32a873..72160503c 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -33,11 +33,12 @@ class TEDIE(SubtitlesInfoExtractor): 'ext': 'mp4', 'title': 'The illusion of consciousness', 'description': ('Philosopher Dan Dennett makes a compelling ' - 'argument that not only don\'t we understand our own ' - 'consciousness, but that half the time our brains are ' - 'actively fooling us.'), + 'argument that not only don\'t we understand our own ' + 'consciousness, but that half the time our brains are ' + 'actively fooling us.'), 'uploader': 'Dan Dennett', 'width': 854, + 'duration': 1308, } }, { 'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms', @@ -51,13 +52,36 @@ class TEDIE(SubtitlesInfoExtractor): } }, { 'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best', - 'md5': '49144e345a899b8cb34d315f3b9cfeeb', 'info_dict': { 'id': '1972', 'ext': 'mp4', 'title': 'Be passionate. Be courageous. Be your best.', 'uploader': 'Gabby Giffords and Mark Kelly', 'description': 'md5:5174aed4d0f16021b704120360f72b92', + 'duration': 1128, + }, + }, { + 'url': 'http://www.ted.com/playlists/who_are_the_hackers', + 'info_dict': { + 'id': '10', + 'title': 'Who are the hackers?', + }, + 'playlist_mincount': 6, + }, { + # contains a youtube video + 'url': 'https://www.ted.com/talks/douglas_adams_parrots_the_universe_and_everything', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': '_ZG8HBuDjgc', + 'ext': 'mp4', + 'title': 'Douglas Adams: Parrots the Universe and Everything', + 'description': 'md5:01ad1e199c49ac640cb1196c0e9016af', + 'uploader': 'University of California Television (UCTV)', + 'uploader_id': 'UCtelevision', + 'upload_date': '20080522', + }, + 'params': { + 'skip_download': True, }, }] @@ -69,7 +93,7 @@ class TEDIE(SubtitlesInfoExtractor): def _extract_info(self, webpage): info_json = self._search_regex(r'q\("\w+.init",({.+})\)</script>', - webpage, 'info json') + webpage, 'info json') return json.loads(info_json) def _real_extract(self, url): @@ -89,7 +113,7 @@ class TEDIE(SubtitlesInfoExtractor): '''Returns the videos of the playlist''' webpage = self._download_webpage(url, name, - 'Downloading playlist webpage') + 'Downloading playlist webpage') info = self._extract_info(webpage) playlist_info = info['playlist'] @@ -108,6 +132,13 @@ class TEDIE(SubtitlesInfoExtractor): talk_info = self._extract_info(webpage)['talks'][0] + if talk_info.get('external') is not None: + self.to_screen('Found video from %s' % talk_info['external']['service']) + return { + '_type': 'url', + 'url': talk_info['external']['uri'], + } + formats = [{ 'url': format_url, 'format_id': format_id, @@ -143,12 +174,13 @@ class TEDIE(SubtitlesInfoExtractor): thumbnail = 'http://' + thumbnail return { 'id': video_id, - 'title': talk_info['title'], + 'title': talk_info['title'].strip(), 'uploader': talk_info['speaker'], 'thumbnail': thumbnail, 'description': self._og_search_description(webpage), 'subtitles': video_subtitles, 'formats': formats, + 'duration': talk_info.get('duration'), } def _get_available_subtitles(self, video_id, talk_info): @@ -167,8 +199,9 @@ class TEDIE(SubtitlesInfoExtractor): webpage = self._download_webpage(url, name) config_json = self._html_search_regex( - r"data-config='([^']+)", webpage, 'config') - config = json.loads(config_json) + r'"pages\.jwplayer"\s*,\s*({.+?})\s*\)\s*</script>', + webpage, 'config') + config = json.loads(config_json)['config'] video_url = config['video']['url'] thumbnail = config.get('image', {}).get('url') diff --git a/youtube_dl/extractor/telebruxelles.py b/youtube_dl/extractor/telebruxelles.py new file mode 100644 index 000000000..a3d05f97d --- /dev/null +++ b/youtube_dl/extractor/telebruxelles.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TeleBruxellesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)' + _TESTS = [{ + 'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/', + 'md5': '59439e568c9ee42fb77588b2096b214f', + 'info_dict': { + 'id': '11942', + 'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus', + 'ext': 'flv', + 'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition', + 'description': 're:Les auditions des ministres se poursuivent*' + }, + 'params': { + 'skip_download': 'requires rtmpdump' + }, + }, { + 'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/', + 'md5': '181d3fbdcf20b909309e5aef5c6c6047', + 'info_dict': { + 'id': '10091', + 'display_id': 'basket-brussels-bat-mons-80-74', + 'ext': 'flv', + 'title': 'Basket : le Brussels bat Mons 80-74', + 'description': 're:^Ils l\u2019on fait ! En basket, le B*', + }, + 'params': { + 'skip_download': 'requires rtmpdump' + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + article_id = self._html_search_regex( + r"<article id=\"post-(\d+)\"", webpage, 'article ID') + title = self._html_search_regex( + r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title') + description = self._og_search_description(webpage) + + rtmp_url = self._html_search_regex( + r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"", + webpage, 'RTMP url') + rtmp_url = rtmp_url.replace("\" + \"", "") + + return { + 'id': article_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'url': rtmp_url, + 'ext': 'flv', + 'rtmp_live': True # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed + } diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py new file mode 100644 index 000000000..2a2fff5e1 --- /dev/null +++ b/youtube_dl/extractor/telecinco.py @@ -0,0 +1,19 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .mitele import MiTeleIE + + +class TelecincoIE(MiTeleIE): + IE_NAME = 'telecinco.es' + _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<episode>.*?)\.html' + + _TEST = { + 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html', + 'info_dict': { + 'id': 'MDSVID20141015_0058', + 'ext': 'mp4', + 'title': 'Con Martín Berasategui, hacer un bacalao al ...', + 'duration': 662, + }, + } diff --git a/youtube_dl/extractor/telemb.py b/youtube_dl/extractor/telemb.py new file mode 100644 index 000000000..1bbd0e7bd --- /dev/null +++ b/youtube_dl/extractor/telemb.py @@ -0,0 +1,78 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import remove_start + + +class TeleMBIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html' + _TESTS = [ + { + 'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html', + 'md5': 'f45ea69878516ba039835794e0f8f783', + 'info_dict': { + 'id': '13466', + 'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-', + 'ext': 'mp4', + 'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages', + 'description': 'md5:bc5225f47b17c309761c856ad4776265', + 'thumbnail': 're:^http://.*\.(?:jpg|png)$', + } + }, + { + # non-ASCII characters in download URL + 'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html', + 'md5': '6e9682736e5ccd4eab7f21e855350733', + 'info_dict': { + 'id': '13514', + 'display_id': 'les-reportages-havre-incendie-mortel', + 'ext': 'mp4', + 'title': 'Havré - Incendie mortel - Les reportages', + 'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a', + 'thumbnail': 're:^http://.*\.(?:jpg|png)$', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + formats = [] + for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage): + fmt = { + 'url': video_url, + 'format_id': video_url.split(':')[0] + } + rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url) + if rtmp: + fmt.update({ + 'play_path': rtmp.group('playpath'), + 'app': rtmp.group('app'), + 'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf', + 'page_url': 'http://www.telemb.be', + 'preference': -1, + }) + formats.append(fmt) + self._sort_formats(formats) + + title = remove_start(self._og_search_title(webpage), 'TéléMB : ') + description = self._html_search_regex( + r'<meta property="og:description" content="(.+?)" />', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index fdae17b1b..6e61cc9e2 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -30,7 +30,7 @@ class TF1IE(InfoExtractor): embed_url = self._html_search_regex( r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed player page') + 'Downloading embed player page') wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') wat_info = self._download_json( 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) diff --git a/youtube_dl/extractor/theonion.py b/youtube_dl/extractor/theonion.py new file mode 100644 index 000000000..b65d8e03f --- /dev/null +++ b/youtube_dl/extractor/theonion.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class TheOnionIE(InfoExtractor): + _VALID_URL = r'(?x)https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<article_id>[0-9]+)/?' + _TEST = { + 'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/', + 'md5': '19eaa9a39cf9b9804d982e654dc791ee', + 'info_dict': { + 'id': '2133', + 'ext': 'mp4', + 'title': 'Man Wearing M&M Jacket Apparently Made In God\'s Image', + 'description': 'md5:cc12448686b5600baae9261d3e180910', + 'thumbnail': 're:^https?://.*\.jpg\?\d+$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + article_id = mobj.group('article_id') + + webpage = self._download_webpage(url, article_id) + + video_id = self._search_regex( + r'"videoId":\s(\d+),', webpage, 'video ID') + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage) + if not sources: + raise ExtractorError( + 'No sources found for video %s' % video_id, expected=True) + + formats = [] + for src, type_ in sources: + if type_ == 'video/mp4': + formats.append({ + 'format_id': 'mp4_sd', + 'preference': 1, + 'url': src, + }) + elif type_ == 'video/webm': + formats.append({ + 'format_id': 'webm_sd', + 'preference': 0, + 'url': src, + }) + elif type_ == 'application/x-mpegURL': + formats.extend( + self._extract_m3u8_formats(src, video_id, preference=-1)) + else: + self.report_warning( + 'Encountered unexpected format: %s' % type_) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index b6b2dba9c..e2653d62d 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -5,6 +5,8 @@ import json from .common import InfoExtractor from ..utils import ( + compat_str, + determine_ext, ExtractorError, xpath_with_ns, ) @@ -34,9 +36,20 @@ class ThePlatformIE(InfoExtractor): }, } - def _get_info(self, video_id, smil_url): - meta = self._download_xml(smil_url, video_id) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + if mobj.group('config'): + config_url = url + '&form=json' + config_url = config_url.replace('swf/', 'config/') + config_url = config_url.replace('onsite/', 'onsite/config/') + config = self._download_json(config_url, video_id, 'Downloading config') + smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m' + else: + smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' + 'format=smil&mbr=true'.format(video_id)) + meta = self._download_xml(smil_url, video_id) try: error_msg = next( n.attrib['abstract'] @@ -55,36 +68,48 @@ class ThePlatformIE(InfoExtractor): body = meta.find(_x('smil:body')) f4m_node = body.find(_x('smil:seq//smil:video')) - if f4m_node is not None: + if f4m_node is not None and '.f4m' in f4m_node.attrib['src']: f4m_url = f4m_node.attrib['src'] if 'manifest.f4m?' not in f4m_url: f4m_url += '?' # the parameters are from syfy.com, other sites may use others, # they also work for nbc.com f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3' - formats = [{ - 'ext': 'flv', - 'url': f4m_url, - }] + formats = self._extract_f4m_formats(f4m_url, video_id) else: - base_url = head.find(_x('smil:meta')).attrib['base'] - switch = body.find(_x('smil:switch')) formats = [] - for f in switch.findall(_x('smil:video')): - attr = f.attrib - width = int(attr['width']) - height = int(attr['height']) - vbr = int(attr['system-bitrate']) // 1000 - format_id = '%dx%d_%dk' % (width, height, vbr) - formats.append({ - 'format_id': format_id, - 'url': base_url, - 'play_path': 'mp4:' + attr['src'], - 'ext': 'flv', - 'width': width, - 'height': height, - 'vbr': vbr, - }) + switch = body.find(_x('smil:switch')) + if switch is not None: + base_url = head.find(_x('smil:meta')).attrib['base'] + for f in switch.findall(_x('smil:video')): + attr = f.attrib + width = int(attr['width']) + height = int(attr['height']) + vbr = int(attr['system-bitrate']) // 1000 + format_id = '%dx%d_%dk' % (width, height, vbr) + formats.append({ + 'format_id': format_id, + 'url': base_url, + 'play_path': 'mp4:' + attr['src'], + 'ext': 'flv', + 'width': width, + 'height': height, + 'vbr': vbr, + }) + else: + switch = body.find(_x('smil:seq//smil:switch')) + for f in switch.findall(_x('smil:video')): + attr = f.attrib + vbr = int(attr['system-bitrate']) // 1000 + ext = determine_ext(attr['src']) + if ext == 'once': + ext = 'mp4' + formats.append({ + 'format_id': compat_str(vbr), + 'url': attr['src'], + 'vbr': vbr, + 'ext': ext, + }) self._sort_formats(formats) return { @@ -93,19 +118,5 @@ class ThePlatformIE(InfoExtractor): 'formats': formats, 'description': info['description'], 'thumbnail': info['defaultThumbnailUrl'], - 'duration': info['duration']//1000, + 'duration': info['duration'] // 1000, } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - if mobj.group('config'): - config_url = url+ '&form=json' - config_url = config_url.replace('swf/', 'config/') - config_url = config_url.replace('onsite/', 'onsite/config/') - config = self._download_json(config_url, video_id, 'Downloading config') - smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m' - else: - smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' - 'format=smil&mbr=true'.format(video_id)) - return self._get_info(video_id, smil_url) diff --git a/youtube_dl/extractor/thesixtyone.py b/youtube_dl/extractor/thesixtyone.py new file mode 100644 index 000000000..a77c6a2fc --- /dev/null +++ b/youtube_dl/extractor/thesixtyone.py @@ -0,0 +1,100 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class TheSixtyOneIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)?thesixtyone\.com/ + (?:.*?/)* + (?: + s| + song/comments/list| + song + )/(?P<id>[A-Za-z0-9]+)/?$''' + _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}' + _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}.thesixtyone.com/thesixtyone_production/audio/{0:}_stream' + _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop' + _TESTS = [ + { + 'url': 'http://www.thesixtyone.com/s/SrE3zD7s1jt/', + 'md5': '821cc43b0530d3222e3e2b70bb4622ea', + 'info_dict': { + 'id': 'SrE3zD7s1jt', + 'ext': 'mp3', + 'title': 'CASIO - Unicorn War Mixtape', + 'thumbnail': 're:^https?://.*_desktop$', + 'upload_date': '20071217', + 'duration': 3208, + } + }, + { + 'url': 'http://www.thesixtyone.com/song/comments/list/SrE3zD7s1jt', + 'only_matching': True, + }, + { + 'url': 'http://www.thesixtyone.com/s/ULoiyjuJWli#/s/SrE3zD7s1jt/', + 'only_matching': True, + }, + { + 'url': 'http://www.thesixtyone.com/#/s/SrE3zD7s1jt/', + 'only_matching': True, + }, + { + 'url': 'http://www.thesixtyone.com/song/SrE3zD7s1jt/', + 'only_matching': True, + }, + ] + + _DECODE_MAP = { + "x": "a", + "m": "b", + "w": "c", + "q": "d", + "n": "e", + "p": "f", + "a": "0", + "h": "1", + "e": "2", + "u": "3", + "s": "4", + "i": "5", + "o": "6", + "y": "7", + "r": "8", + "c": "9" + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + song_id = mobj.group('id') + + webpage = self._download_webpage( + self._SONG_URL_TEMPLATE.format(song_id), song_id) + + song_data = json.loads(self._search_regex( + r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data')) + keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']] + url = self._SONG_FILE_URL_TEMPLATE.format( + "".join(reversed(keys)), **song_data) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': 'mp3', + }] + + return { + 'id': song_id, + 'title': '{artist:} - {name:}'.format(**song_data), + 'formats': formats, + 'comment_count': song_data.get('comments_count'), + 'duration': song_data.get('play_time'), + 'like_count': song_data.get('score'), + 'thumbnail': self._THUMBNAIL_URL_TEMPLATE.format(**song_data), + 'upload_date': unified_strdate(song_data.get('publish_date')), + } diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py index bfb9d2fc9..7f323c938 100644 --- a/youtube_dl/extractor/thisav.py +++ b/youtube_dl/extractor/thisav.py @@ -1,4 +1,4 @@ -#coding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re @@ -36,12 +36,12 @@ class ThisAVIE(InfoExtractor): r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>', webpage, 'uploader id', fatal=False) ext = determine_ext(video_url) - + return { - 'id': video_id, - 'url': video_url, - 'uploader': uploader, + 'id': video_id, + 'url': video_url, + 'uploader': uploader, 'uploader_id': uploader_id, - 'title': title, - 'ext': ext, + 'title': title, + 'ext': ext, } diff --git a/youtube_dl/extractor/thvideo.py b/youtube_dl/extractor/thvideo.py new file mode 100644 index 000000000..496f15d80 --- /dev/null +++ b/youtube_dl/extractor/thvideo.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate +) + + +class THVideoIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://thvideo.tv/v/th1987/', + 'md5': 'fa107b1f73817e325e9433505a70db50', + 'info_dict': { + 'id': '1987', + 'ext': 'mp4', + 'title': '【动画】秘封活动记录 ～ The Sealed Esoteric History.分镜稿预览', + 'display_id': 'th1987', + 'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg', + 'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 ～ The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...', + 'upload_date': '20140722' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + # extract download link from mobile player page + webpage_player = self._download_webpage( + 'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id), + video_id, note='Downloading video source page') + video_url = self._html_search_regex( + r'<source src="(.*?)" type', webpage_player, 'video url') + + # extract video info from main page + webpage = self._download_webpage( + 'http://thvideo.tv/v/th%s' % (video_id), video_id) + title = self._og_search_title(webpage) + display_id = 'th%s' % video_id + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + upload_date = unified_strdate(self._html_search_regex( + r'span itemprop="datePublished" content="(.*?)">', webpage, + 'upload date', fatal=False)) + + return { + 'id': video_id, + 'ext': 'mp4', + 'url': video_url, + 'title': title, + 'display_id': display_id, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': upload_date + } + + +class THVideoPlaylistIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://thvideo.tv/mylist2', + 'info_dict': { + 'id': '2', + 'title': '幻想万華鏡', + }, + 'playlist_mincount': 23, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + list_title = self._html_search_regex( + r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title', + fatal=False) + + entries = [ + self.url_result('http://thvideo.tv/v/th' + id, 'THVideo') + for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)] + + return self.playlist_result(entries, playlist_id, list_title) diff --git a/youtube_dl/extractor/tinypic.py b/youtube_dl/extractor/tinypic.py index a4aa25f66..4fe89dbe5 100644 --- a/youtube_dl/extractor/tinypic.py +++ b/youtube_dl/extractor/tinypic.py @@ -26,9 +26,9 @@ class TinyPicIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id, 'Downloading page') - + mobj = re.search(r'(?m)fo\.addVariable\("file",\s"(?P<fileid>[\da-z]+)"\);\n' - '\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage) + '\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage) if mobj is None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) @@ -47,4 +47,4 @@ class TinyPicIE(InfoExtractor): 'url': video_url, 'thumbnail': thumbnail, 'title': title - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py index d848ee186..66d159e99 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -36,9 +36,10 @@ class TlcDeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Breaking Amish: Die Welt da draußen', 'uploader': 'Discovery Networks - Germany', - 'description': 'Vier Amische und eine Mennonitin wagen in New York' + 'description': ( + 'Vier Amische und eine Mennonitin wagen in New York' ' den Sprung in ein komplett anderes Leben. Begleitet sie auf' - ' ihrem spannenden Weg.', + ' ihrem spannenden Weg.'), }, } diff --git a/youtube_dl/extractor/tmz.py b/youtube_dl/extractor/tmz.py new file mode 100644 index 000000000..827aa08a4 --- /dev/null +++ b/youtube_dl/extractor/tmz.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TMZIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/]+)/?' + _TEST = { + 'url': 'http://www.tmz.com/videos/0_okj015ty/', + 'md5': '791204e3bf790b1426cb2db0706184c0', + 'info_dict': { + 'id': '0_okj015ty', + 'url': 'http://tmz.vo.llnwd.net/o28/2014-03/13/0_okj015ty_0_rt8ro3si_2.mp4', + 'ext': 'mp4', + 'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!', + 'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie??? Or is she just showing off her amazing boobs?', + 'thumbnail': 'http://cdnbakmi.kaltura.com/p/591531/sp/59153100/thumbnail/entry_id/0_okj015ty/version/100002/acv/182/width/640', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + return { + 'id': video_id, + 'url': self._html_search_meta('VideoURL', webpage, fatal=True), + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._html_search_meta('ThumbURL', webpage), + } diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py new file mode 100644 index 000000000..0ecd695f8 --- /dev/null +++ b/youtube_dl/extractor/tnaflix.py @@ -0,0 +1,84 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + fix_xml_ampersands, +) + + +class TNAFlixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)' + + _TITLE_REGEX = None + _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' + + _TEST = { + 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', + 'md5': 'ecf3498417d09216374fc5907f9c6ec0', + 'info_dict': { + 'id': '553878', + 'display_id': 'Carmella-Decesare-striptease', + 'ext': 'mp4', + 'title': 'Carmella Decesare - striptease', + 'description': '', + 'thumbnail': 're:https?://.*\.jpg$', + 'duration': 91, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage) + description = self._html_search_regex( + self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='') + + age_limit = self._rta_search(webpage) + + duration = self._html_search_meta('duration', webpage, 'duration', default=None) + if duration: + duration = parse_duration(duration[1:]) + + cfg_url = self._html_search_regex( + self._CONFIG_REGEX, webpage, 'flashvars.config') + + cfg_xml = self._download_xml( + cfg_url, display_id, note='Downloading metadata', + transform_source=fix_xml_ampersands) + + thumbnail = cfg_xml.find('./startThumb').text + + formats = [] + for item in cfg_xml.findall('./quality/item'): + video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text) + format_id = item.find('res').text + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/toypics.py b/youtube_dl/extractor/toypics.py index 0f389bd93..2756f56d3 100644 --- a/youtube_dl/extractor/toypics.py +++ b/youtube_dl/extractor/toypics.py @@ -42,6 +42,13 @@ class ToypicsIE(InfoExtractor): class ToypicsUserIE(InfoExtractor): IE_DESC = 'Toypics user profile' _VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])' + _TEST = { + 'url': 'http://videos.toypics.net/Mikey', + 'info_dict': { + 'id': 'Mikey', + }, + 'playlist_mincount': 19, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/traileraddict.py b/youtube_dl/extractor/traileraddict.py index 11407428b..1c53a3fd0 100644 --- a/youtube_dl/extractor/traileraddict.py +++ b/youtube_dl/extractor/traileraddict.py @@ -25,7 +25,7 @@ class TrailerAddictIE(InfoExtractor): webpage = self._download_webpage(url, name) title = self._search_regex(r'<title>(.+?)</title>', - webpage, 'video title').replace(' - Trailer Addict','') + webpage, 'video title').replace(' - Trailer Addict', '') view_count_str = self._search_regex( r'<span class="views_n">([0-9,.]+)</span>', webpage, 'view count', fatal=False) @@ -43,12 +43,12 @@ class TrailerAddictIE(InfoExtractor): fvar = "fvar" info_url = "http://www.traileraddict.com/%s.php?tid=%s" % (fvar, str(video_id)) - info_webpage = self._download_webpage(info_url, video_id , "Downloading the info webpage") + info_webpage = self._download_webpage(info_url, video_id, "Downloading the info webpage") final_url = self._search_regex(r'&fileurl=(.+)', - info_webpage, 'Download url').replace('%3F','?') + info_webpage, 'Download url').replace('%3F', '?') thumbnail_url = self._search_regex(r'&image=(.+?)&', - info_webpage, 'thumbnail url') + info_webpage, 'thumbnail url') description = self._html_search_regex( r'(?s)<div class="synopsis">.*?<div class="movie_label_info"[^>]*>(.*?)</div>', diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py index d64aaa41f..220a05b7b 100644 --- a/youtube_dl/extractor/trilulilu.py +++ b/youtube_dl/extractor/trilulilu.py @@ -1,28 +1,28 @@ +from __future__ import unicode_literals + import json -import re from .common import InfoExtractor class TriluliluIE(InfoExtractor): - _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/video-[^/]+/(?P<id>[^/]+)' _TEST = { - u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1", - u'file': u"big-buck-bunny-1.mp4", - u'info_dict': { - u"title": u"Big Buck Bunny", - u"description": u":) pentru copilul din noi", + 'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1', + 'info_dict': { + 'id': 'big-buck-bunny-1', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'description': ':) pentru copilul din noi', }, # Server ignores Range headers (--test) - u"params": { - u"skip_download": True + 'params': { + 'skip_download': True } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._og_search_title(webpage) @@ -30,20 +30,20 @@ class TriluliluIE(InfoExtractor): description = self._og_search_description(webpage) log_str = self._search_regex( - r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info') + r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, 'log info') log = json.loads(log_str) - format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/' - u'video-formats2' % log) + format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/' + 'video-formats2' % log) format_doc = self._download_xml( format_url, video_id, - note=u'Downloading formats', - errnote=u'Error while downloading formats') - + note='Downloading formats', + errnote='Error while downloading formats') + video_url_template = ( - u'http://fs%(server)s.trilulilu.ro/stream.php?type=video' - u'&source=site&hash=%(hash)s&username=%(userid)s&' - u'key=ministhebest&format=%%s&sig=&exp=' % + 'http://fs%(server)s.trilulilu.ro/stream.php?type=video' + '&source=site&hash=%(hash)s&username=%(userid)s&' + 'key=ministhebest&format=%%s&sig=&exp=' % log) formats = [ { @@ -63,4 +63,3 @@ class TriluliluIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, } - diff --git a/youtube_dl/extractor/trutube.py b/youtube_dl/extractor/trutube.py index 57f956683..e7b79243a 100644 --- a/youtube_dl/extractor/trutube.py +++ b/youtube_dl/extractor/trutube.py @@ -1,13 +1,12 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import xpath_text class TruTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-', 'md5': 'c5b6e301b0a2040b074746cbeaa26ca1', 'info_dict': { @@ -16,29 +15,26 @@ class TruTubeIE(InfoExtractor): 'title': 'Ramses II - Proven To Be A Red Headed Caucasoid', 'thumbnail': 're:^http:.*\.jpg$', } - } + }, { + 'url': 'https://trutube.tv/nuevo/player/embed.php?v=14880', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_title = self._og_search_title(webpage).strip() - thumbnail = self._search_regex( - r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False) + config = self._download_xml( + 'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id, + video_id, transform_source=lambda s: s.strip()) - all_formats = re.finditer( - r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage) - formats = [{ - 'format_id': m.group('key'), - 'quality': -i, - 'url': m.group('url'), - } for i, m in enumerate(all_formats)] - self._sort_formats(formats) + # filehd is always 404 + video_url = xpath_text(config, './file', 'video URL', fatal=True) + title = xpath_text(config, './title', 'title').strip() + thumbnail = xpath_text(config, './image', ' thumbnail') return { 'id': video_id, - 'title': video_title, - 'formats': formats, + 'url': video_url, + 'title': title, 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 08a48c05a..64a1e9030 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -14,27 +14,35 @@ from ..aes import aes_decrypt_text class Tube8IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)' - _TEST = { - 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', - 'md5': '44bf12b98313827dd52d35b8706a4ea0', - 'info_dict': { - 'id': '229795', - 'ext': 'mp4', - 'description': 'hot teen Kasia grinding', - 'uploader': 'unknown', - 'title': 'Kasia music video', - 'age_limit': 18, - } - } + _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', + 'md5': '44bf12b98313827dd52d35b8706a4ea0', + 'info_dict': { + 'id': '229795', + 'display_id': 'kasia-music-video', + 'ext': 'mp4', + 'description': 'hot teen Kasia grinding', + 'uploader': 'unknown', + 'title': 'Kasia music video', + 'age_limit': 18, + } + }, + { + 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + display_id = mobj.group('display_id') req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + webpage = self._download_webpage(req, display_id) flashvars = json.loads(self._html_search_regex( r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars')) @@ -70,6 +78,7 @@ class Tube8IE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'url': video_url, 'title': title, 'description': description, diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 7a3891b89..161e47624 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -1,5 +1,7 @@ # coding: utf-8 +from __future__ import unicode_literals + import re import json @@ -9,30 +11,37 @@ from .common import InfoExtractor class TudouIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' _TESTS = [{ - u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', - u'file': u'159448201.f4v', - u'md5': u'140a49ed444bd22f93330985d8475fcb', - u'info_dict': { - u"title": u"卡马乔国足开大脚长传冲吊集锦" + 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', + 'md5': '140a49ed444bd22f93330985d8475fcb', + 'info_dict': { + 'id': '159448201', + 'ext': 'f4v', + 'title': '卡马乔国足开大脚长传冲吊集锦', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, { + 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/', + 'info_dict': { + 'id': '117049447', + 'ext': 'f4v', + 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', + 'thumbnail': 're:^https?://.*\.jpg$', } - }, - { - u'url': u'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', - u'file': u'todo.mp4', - u'md5': u'todo.mp4', - u'info_dict': { - u'title': u'todo.mp4', + }, { + 'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', + 'info_dict': { + 'title': 'todo.mp4', }, - u'add_ie': [u'Youku'], - u'skip': u'Only works from China' + 'add_ie': ['Youku'], + 'skip': 'Only works from China' }] - def _url_for_id(self, id, quality = None): - info_url = "http://v2.tudou.com/f?id="+str(id) + def _url_for_id(self, id, quality=None): + info_url = "http://v2.tudou.com/f?id=" + str(id) if quality: info_url += '&hd' + quality webpage = self._download_webpage(info_url, id, "Opening the info webpage") - final_url = self._html_search_regex('>(.+?)</f>',webpage, 'video url') + final_url = self._html_search_regex('>(.+?)</f>', webpage, 'video url') return final_url def _real_extract(self, url): @@ -44,35 +53,38 @@ class TudouIE(InfoExtractor): if m and m.group(1): return { '_type': 'url', - 'url': u'youku:' + m.group(1), + 'url': 'youku:' + m.group(1), 'ie_key': 'Youku' } title = self._search_regex( - r",kw:\s*['\"](.+?)[\"']", webpage, u'title') + r",kw:\s*['\"](.+?)[\"']", webpage, 'title') thumbnail_url = self._search_regex( - r",pic:\s*[\"'](.+?)[\"']", webpage, u'thumbnail URL', fatal=False) + r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segments = json.loads(segs_json) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher - quality = sorted(segments.keys())[-1] + # Also, filter non-number qualities (see issue #3643). + quality = sorted(filter(lambda k: k.isdigit(), segments.keys()), + key=lambda k: int(k))[-1] parts = segments[quality] result = [] len_parts = len(parts) if len_parts > 1: - self.to_screen(u'%s: found %s parts' % (video_id, len_parts)) + self.to_screen('%s: found %s parts' % (video_id, len_parts)) for part in parts: part_id = part['k'] final_url = self._url_for_id(part_id, quality) ext = (final_url.split('?')[0]).split('.')[-1] - part_info = {'id': part_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - } + part_info = { + 'id': '%s' % part_id, + 'url': final_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + } result.append(part_info) return result diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index 2882c1809..2a1ae5a71 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,13 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class TumblrIE(InfoExtractor): - _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)' + _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])' _TESTS = [{ 'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', 'md5': '479bb068e5b16462f5176a6828829767', @@ -18,7 +15,7 @@ class TumblrIE(InfoExtractor): 'id': '54196191430', 'ext': 'mp4', 'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...', - 'description': 'md5:dfac39636969fe6bf1caa2d50405f069', + 'description': 'md5:37db8211e40b50c7c44e95da14f630b7', 'thumbnail': 're:http://.*\.jpg', } }, { @@ -27,7 +24,7 @@ class TumblrIE(InfoExtractor): 'info_dict': { 'id': '90208453769', 'ext': 'mp4', - 'title': '5SOS STRUM ;)', + 'title': '5SOS STRUM ;]', 'description': 'md5:dba62ac8639482759c8eb10ce474586a', 'thumbnail': 're:http://.*\.jpg', } @@ -41,28 +38,24 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage = self._download_webpage(url, video_id) - re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id) - video = re.search(re_video, webpage) - if video is None: - raise ExtractorError('Unable to extract video') - video_url = video.group('video_url') - ext = video.group('ext') - - video_thumbnail = self._search_regex( - r'posters.*?\[\\x22(.*?)\\x22', - webpage, 'thumbnail', fatal=False) # We pick the first poster - if video_thumbnail: - video_thumbnail = video_thumbnail.replace('\\\\/', '/') + iframe_url = self._search_regex( + r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'', + webpage, 'iframe url') + iframe = self._download_webpage(iframe_url, video_id) + video_url = self._search_regex(r'<source src="([^"]+)"', + iframe, 'video url') # The only place where you can get a title, it's not complete, # but searching in other places doesn't work for all videos - video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>', - webpage, 'title', flags=re.DOTALL) + video_title = self._html_search_regex( + r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>', + webpage, 'title') - return [{'id': video_id, - 'url': video_url, - 'title': video_title, - 'description': self._html_search_meta('description', webpage), - 'thumbnail': video_thumbnail, - 'ext': ext - }] + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': video_title, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/tunein.py b/youtube_dl/extractor/tunein.py new file mode 100644 index 000000000..4ce5aeeba --- /dev/null +++ b/youtube_dl/extractor/tunein.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class TuneInIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)? + (?: + tunein\.com/ + (?: + radio/.*?-s| + station/.*?StationId\= + )(?P<id>[0-9]+) + |tun\.in/(?P<redirect_id>[A-Za-z0-9]+) + ) + ''' + _API_URL_TEMPLATE = 'http://tunein.com/tuner/tune/?stationId={0:}&tuneType=Station' + + _INFO_DICT = { + 'id': '34682', + 'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2', + 'ext': 'AAC', + 'thumbnail': 're:^https?://.*\.png$', + 'location': 'Tacoma, WA', + } + _TESTS = [ + { + 'url': 'http://tunein.com/radio/Jazz24-885-s34682/', + 'info_dict': _INFO_DICT, + 'params': { + 'skip_download': True, # live stream + }, + }, + { # test redirection + 'url': 'http://tun.in/ser7s', + 'info_dict': _INFO_DICT, + 'params': { + 'skip_download': True, # live stream + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + redirect_id = mobj.group('redirect_id') + if redirect_id: + # The server doesn't support HEAD requests + urlh = self._request_webpage( + url, redirect_id, note='Downloading redirect page') + url = urlh.geturl() + self.to_screen('Following redirect: %s' % url) + mobj = re.match(self._VALID_URL, url) + station_id = mobj.group('id') + + station_info = self._download_json( + self._API_URL_TEMPLATE.format(station_id), + station_id, note='Downloading station JSON') + + title = station_info['Title'] + thumbnail = station_info.get('Logo') + location = station_info.get('Location') + streams_url = station_info.get('StreamUrl') + if not streams_url: + raise ExtractorError('No downloadable streams found', + expected=True) + stream_data = self._download_webpage( + streams_url, station_id, note='Downloading stream data') + streams = json.loads(self._search_regex( + r'\((.*)\);', stream_data, 'stream info'))['Streams'] + + is_live = None + formats = [] + for stream in streams: + if stream.get('Type') == 'Live': + is_live = True + formats.append({ + 'abr': stream.get('Bandwidth'), + 'ext': stream.get('MediaType'), + 'acodec': stream.get('MediaType'), + 'vcodec': 'none', + 'url': stream.get('Url'), + # Sometimes streams with the highest quality do not exist + 'preference': stream.get('Reliability'), + }) + self._sort_formats(formats) + + return { + 'id': station_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'location': location, + 'is_live': is_live, + } diff --git a/youtube_dl/extractor/turbo.py b/youtube_dl/extractor/turbo.py new file mode 100644 index 000000000..29703a8a9 --- /dev/null +++ b/youtube_dl/extractor/turbo.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, + qualities, + xpath_text, +) + + +class TurboIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?turbo\.fr/videos-voiture/(?P<id>[0-9]+)-' + _API_URL = 'http://www.turbo.fr/api/tv/xml.php?player_generique=player_generique&id={0:}' + _TEST = { + 'url': 'http://www.turbo.fr/videos-voiture/454443-turbo-du-07-09-2014-renault-twingo-3-bentley-continental-gt-speed-ces-guide-achat-dacia.html', + 'md5': '33f4b91099b36b5d5a91f84b5bcba600', + 'info_dict': { + 'id': '454443', + 'ext': 'mp4', + 'duration': 3715, + 'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ', + 'description': 'Retrouvez dans cette rubrique toutes les vidéos de l\'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + playlist = self._download_xml(self._API_URL.format(video_id), video_id) + item = playlist.find('./channel/item') + if item is None: + raise ExtractorError('Playlist item was not found', expected=True) + + title = xpath_text(item, './title', 'title') + duration = int_or_none(xpath_text(item, './durate', 'duration')) + thumbnail = xpath_text(item, './visuel_clip', 'thumbnail') + description = self._og_search_description(webpage) + + formats = [] + get_quality = qualities(['3g', 'sd', 'hq']) + for child in item: + m = re.search(r'url_video_(?P<quality>.+)', child.tag) + if m: + quality = m.group('quality') + formats.append({ + 'format_id': quality, + 'url': child.text, + 'quality': get_quality(quality), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'thumbnail': thumbnail, + 'description': description, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index 0921cc5f8..ba65996dc 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -1,84 +1,84 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - unified_strdate, - clean_html, - int_or_none, + float_or_none, + parse_age_limit, ) class TvigleIE(InfoExtractor): IE_NAME = 'tvigle' IE_DESC = 'Интернет-телевидение Tvigle.ru' - _VALID_URL = r'http://(?:www\.)?tvigle\.ru/category/.+?[\?&]v(?:ideo)?=(?P<id>\d+)' + _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<id>[^/]+)/$' _TESTS = [ { - 'url': 'http://www.tvigle.ru/category/cinema/1608/?video=503081', - 'md5': '09afba4616666249f087efc6dcf83cb3', + 'url': 'http://www.tvigle.ru/video/sokrat/', + 'md5': '36514aed3657d4f70b4b2cef8eb520cd', 'info_dict': { - 'id': '503081', + 'id': '1848932', + 'display_id': 'sokrat', 'ext': 'flv', - 'title': 'Брат 2 ', - 'description': 'md5:f5a42970f50648cee3d7ad740f3ae769', - 'upload_date': '20110919', + 'title': 'Сократ', + 'description': 'md5:a05bd01be310074d5833efc6743be95e', + 'duration': 6586, + 'age_limit': 0, }, }, { - 'url': 'http://www.tvigle.ru/category/men/vysotskiy_vospominaniya02/?flt=196&v=676433', - 'md5': 'e7efe5350dd5011d0de6550b53c3ba7b', + 'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/', + 'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574', 'info_dict': { - 'id': '676433', - 'ext': 'flv', + 'id': '5142516', + 'ext': 'mp4', 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком', 'description': 'md5:027f7dc872948f14c96d19b4178428a4', - 'upload_date': '20121218', + 'duration': 186.080, + 'age_limit': 0, }, }, ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + display_id = self._match_id(url) - video_data = self._download_xml( - 'http://www.tvigle.ru/xml/single.php?obj=%s' % video_id, video_id, 'Downloading video XML') + webpage = self._download_webpage(url, display_id) - video = video_data.find('./video') + video_id = self._html_search_regex( + r'<li class="video-preview current_playing" id="(\d+)">', webpage, 'video id') - title = video.get('name') - description = video.get('anons') - if description: - description = clean_html(description) - thumbnail = video_data.get('img') - upload_date = unified_strdate(video.get('date')) - like_count = int_or_none(video.get('vtp')) + video_data = self._download_json( + 'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id) - formats = [] - for num, (format_id, format_note) in enumerate([['low_file', 'SQ'], ['file', 'HQ'], ['hd', 'HD 720']]): - video_url = video.get(format_id) - if not video_url: - continue - formats.append({ - 'url': video_url, - 'format_id': format_id, - 'format_note': format_note, - 'quality': num, - }) + item = video_data['playlist']['items'][0] + title = item['title'] + description = item['description'] + thumbnail = item['thumbnail'] + duration = float_or_none(item.get('durationMilliseconds'), 1000) + age_limit = parse_age_limit(item.get('ageRestrictions')) + + formats = [] + for vcodec, fmts in item['videos'].items(): + for quality, video_url in fmts.items(): + formats.append({ + 'url': video_url, + 'format_id': '%s-%s' % (vcodec, quality), + 'vcodec': vcodec, + 'height': int(quality[:-1]), + 'filesize': item['video_files_size'][vcodec][quality], + }) self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'like_count': like_count, - 'age_limit': 18, + 'duration': duration, + 'age_limit': age_limit, 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index bfed9dd04..a64580005 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,40 +1,35 @@ -import json -import re +from __future__ import unicode_literals from .common import InfoExtractor class TvpIE(InfoExtractor): - IE_NAME = u'tvp.pl' + IE_NAME = 'tvp.pl' _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)' _TEST = { - u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', - u'md5': u'148408967a6a468953c0a75cbdaf0d7a', - u'file': u'12878238.wmv', - u'info_dict': { - u'title': u'31.10.2013 - Odcinek 2', - u'description': u'31.10.2013 - Odcinek 2', + 'url': 'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', + 'md5': '148408967a6a468953c0a75cbdaf0d7a', + 'info_dict': { + 'id': '12878238', + 'ext': 'wmv', + 'title': '31.10.2013 - Odcinek 2', + 'description': '31.10.2013 - Odcinek 2', }, - u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' + 'skip': 'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id - json_params = self._download_webpage( - json_url, video_id, u"Downloading video metadata") - - params = json.loads(json_params) - self.report_extraction(video_id) + params = self._download_json( + json_url, video_id, "Downloading video metadata") video_url = params['video_url'] - title = self._og_search_title(webpage, fatal=True) return { 'id': video_id, - 'title': title, + 'title': self._og_search_title(webpage), 'ext': 'wmv', 'url': video_url, 'description': self._og_search_description(webpage), diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index a56a7ab5f..9a53a3c74 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -4,15 +4,29 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - ExtractorError, parse_iso8601, qualities, ) class TVPlayIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)' + IE_DESC = 'TV3Play and related services' + _VALID_URL = r'''(?x)http://(?:www\.)? + (?:tvplay\.lv/parraides| + tv3play\.lt/programos| + tv3play\.ee/sisu| + tv3play\.se/program| + tv6play\.se/program| + tv8play\.se/program| + tv10play\.se/program| + tv3play\.no/programmer| + viasat4play\.no/programmer| + tv6play\.no/programmer| + tv3play\.dk/programmer| + )/[^/]+/(?P<id>\d+) + ''' _TESTS = [ { 'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true', @@ -30,18 +44,145 @@ class TVPlayIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.tv3play.lt/programos/moterys-meluoja-geriau/409229?autostart=true', + 'info_dict': { + 'id': '409229', + 'ext': 'flv', + 'title': 'Moterys meluoja geriau', + 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e', + 'duration': 1330, + 'timestamp': 1403769181, + 'upload_date': '20140626', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true', + 'info_dict': { + 'id': '238551', + 'ext': 'flv', + 'title': 'Kodu keset linna 398537', + 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701', + 'duration': 1257, + 'timestamp': 1292449761, + 'upload_date': '20101215', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true', + 'info_dict': { + 'id': '395385', + 'ext': 'flv', + 'title': 'Husräddarna S02E07', + 'description': 'md5:f210c6c89f42d4fc39faa551be813777', + 'duration': 2574, + 'timestamp': 1400596321, + 'upload_date': '20140520', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true', + 'info_dict': { + 'id': '266636', + 'ext': 'flv', + 'title': 'Den sista dokusåpan S01E08', + 'description': 'md5:295be39c872520221b933830f660b110', + 'duration': 1492, + 'timestamp': 1330522854, + 'upload_date': '20120229', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true', + 'info_dict': { + 'id': '282756', + 'ext': 'flv', + 'title': 'Antikjakten S01E10', + 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8', + 'duration': 2646, + 'timestamp': 1348575868, + 'upload_date': '20120925', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true', + 'info_dict': { + 'id': '230898', + 'ext': 'flv', + 'title': 'Anna Anka søker assistent - Ep. 8', + 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474', + 'duration': 2656, + 'timestamp': 1277720005, + 'upload_date': '20100628', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true', + 'info_dict': { + 'id': '21873', + 'ext': 'flv', + 'title': 'Budbringerne program 10', + 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d', + 'duration': 1297, + 'timestamp': 1254205102, + 'upload_date': '20090929', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true', + 'info_dict': { + 'id': '361883', + 'ext': 'flv', + 'title': 'Hotelinspektør Alex Polizzi - Ep. 10', + 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81', + 'duration': 2594, + 'timestamp': 1393236292, + 'upload_date': '20140224', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) video = self._download_json( 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON') if video['is_geo_blocked']: - raise ExtractorError( - 'This content is not available in your country due to copyright reasons', expected=True) + self.report_warning( + 'This content might not be available in your country due to copyright reasons') streams = self._download_json( 'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON') @@ -49,7 +190,7 @@ class TVPlayIE(InfoExtractor): quality = qualities(['hls', 'medium', 'high']) formats = [] for format_id, video_url in streams['streams'].items(): - if not video_url: + if not video_url or not isinstance(video_url, compat_str): continue fmt = { 'format_id': format_id, @@ -65,6 +206,10 @@ class TVPlayIE(InfoExtractor): 'app': m.group('app'), 'play_path': m.group('playpath'), }) + elif video_url.endswith('.f4m'): + formats.extend(self._extract_f4m_formats( + video_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id)) + continue else: fmt.update({ 'url': video_url, diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py new file mode 100644 index 000000000..67e8bfea0 --- /dev/null +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -0,0 +1,109 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + int_or_none, +) + + +class TwentyFourVideoIE(InfoExtractor): + IE_NAME = '24video' + _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)' + + _TESTS = [ + { + 'url': 'http://www.24video.net/video/view/1044982', + 'md5': '48dd7646775690a80447a8dca6a2df76', + 'info_dict': { + 'id': '1044982', + 'ext': 'mp4', + 'title': 'Эротика каменного века', + 'description': 'Как смотрели порно в каменном веке.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'SUPERTELO', + 'duration': 31, + 'timestamp': 1275937857, + 'upload_date': '20100607', + 'age_limit': 18, + 'like_count': int, + 'dislike_count': int, + }, + }, + { + 'url': 'http://www.24video.net/player/new24_play.swf?id=1044982', + 'only_matching': True, + } + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'http://www.24video.net/video/view/%s' % video_id, video_id) + + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'<span itemprop="description">([^<]+)</span>', webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + duration = int_or_none(self._og_search_property( + 'duration', webpage, 'duration', fatal=False)) + timestamp = parse_iso8601(self._search_regex( + r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">', + webpage, 'upload date')) + + uploader = self._html_search_regex( + r'Загрузил\s*<a href="/jsecUser/movies/[^"]+" class="link">([^<]+)</a>', + webpage, 'uploader', fatal=False) + + view_count = int_or_none(self._html_search_regex( + r'<span class="video-views">(\d+) просмотр', + webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'<div class="comments-title" id="comments-count">(\d+) комментари', + webpage, 'comment count', fatal=False)) + + formats = [] + + pc_video = self._download_xml( + 'http://www.24video.net/video/xml/%s?mode=play' % video_id, + video_id, 'Downloading PC video URL').find('.//video') + + formats.append({ + 'url': pc_video.attrib['url'], + 'format_id': 'pc', + 'quality': 1, + }) + + like_count = int_or_none(pc_video.get('ratingPlus')) + dislike_count = int_or_none(pc_video.get('ratingMinus')) + age_limit = 18 if pc_video.get('adult') == 'true' else 0 + + mobile_video = self._download_xml( + 'http://www.24video.net/video/xml/%s' % video_id, + video_id, 'Downloading mobile video URL').find('.//video') + + formats.append({ + 'url': mobile_video.attrib['url'], + 'format_id': 'mobile', + 'quality': 0, + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'duration': duration, + 'timestamp': timestamp, + 'view_count': view_count, + 'comment_count': comment_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py new file mode 100644 index 000000000..397d167e8 --- /dev/null +++ b/youtube_dl/extractor/twitch.py @@ -0,0 +1,229 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + ExtractorError, + parse_iso8601, +) + + +class TwitchIE(InfoExtractor): + # TODO: One broadcast may be split into multiple videos. The key + # 'broadcast_id' is the same for all parts, and 'broadcast_part' + # starts at 1 and increases. Can we treat all parts as one video? + _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?twitch\.tv/ + (?: + (?P<channelid>[^/]+)| + (?:(?:[^/]+)/b/(?P<videoid>[^/]+))| + (?:(?:[^/]+)/c/(?P<chapterid>[^/]+)) + ) + /?(?:\#.*)?$ + """ + _PAGE_LIMIT = 100 + _API_BASE = 'https://api.twitch.tv' + _LOGIN_URL = 'https://secure.twitch.tv/user/login' + _TESTS = [{ + 'url': 'http://www.twitch.tv/riotgames/b/577357806', + 'info_dict': { + 'id': 'a577357806', + 'title': 'Worlds Semifinals - Star Horn Royal Club vs. OMG', + }, + 'playlist_mincount': 12, + }, { + 'url': 'http://www.twitch.tv/acracingleague/c/5285812', + 'info_dict': { + 'id': 'c5285812', + 'title': 'ACRL Off Season - Sports Cars @ Nordschleife', + }, + 'playlist_mincount': 3, + }, { + 'url': 'http://www.twitch.tv/vanillatv', + 'info_dict': { + 'id': 'vanillatv', + 'title': 'VanillaTV', + }, + 'playlist_mincount': 412, + }] + + def _handle_error(self, response): + if not isinstance(response, dict): + return + error = response.get('error') + if error: + raise ExtractorError( + '%s returned error: %s - %s' % (self.IE_NAME, error, response.get('message')), + expected=True) + + def _download_json(self, url, video_id, note='Downloading JSON metadata'): + response = super(TwitchIE, self)._download_json(url, video_id, note) + self._handle_error(response) + return response + + def _extract_media(self, item, item_id): + ITEMS = { + 'a': 'video', + 'c': 'chapter', + } + info = self._extract_info(self._download_json( + '%s/kraken/videos/%s%s' % (self._API_BASE, item, item_id), item_id, + 'Downloading %s info JSON' % ITEMS[item])) + response = self._download_json( + '%s/api/videos/%s%s' % (self._API_BASE, item, item_id), item_id, + 'Downloading %s playlist JSON' % ITEMS[item]) + entries = [] + chunks = response['chunks'] + qualities = list(chunks.keys()) + for num, fragment in enumerate(zip(*chunks.values()), start=1): + formats = [] + for fmt_num, fragment_fmt in enumerate(fragment): + format_id = qualities[fmt_num] + fmt = { + 'url': fragment_fmt['url'], + 'format_id': format_id, + 'quality': 1 if format_id == 'live' else 0, + } + m = re.search(r'^(?P<height>\d+)[Pp]', format_id) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) + entry = dict(info) + entry['id'] = '%s_%d' % (entry['id'], num) + entry['title'] = '%s part %d' % (entry['title'], num) + entry['formats'] = formats + entries.append(entry) + return self.playlist_result(entries, info['id'], info['title']) + + def _extract_info(self, info): + return { + 'id': info['_id'], + 'title': info['title'], + 'description': info['description'], + 'duration': info['length'], + 'thumbnail': info['preview'], + 'uploader': info['channel']['display_name'], + 'uploader_id': info['channel']['name'], + 'timestamp': parse_iso8601(info['recorded_at']), + 'view_count': info['views'], + } + + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + authenticity_token = self._search_regex( + r'<input name="authenticity_token" type="hidden" value="([^"]+)"', + login_page, 'authenticity token') + + login_form = { + 'utf8': '✓'.encode('utf-8'), + 'authenticity_token': authenticity_token, + 'redirect_on_login': '', + 'embed_form': 'false', + 'mp_source_action': '', + 'follow': '', + 'user[login]': username, + 'user[password]': password, + } + + request = compat_urllib_request.Request( + self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) + request.add_header('Referer', self._LOGIN_URL) + response = self._download_webpage( + request, None, 'Logging in as %s' % username) + + m = re.search( + r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response) + if m: + raise ExtractorError( + 'Unable to login: %s' % m.group('msg').strip(), expected=True) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj.group('chapterid'): + return self._extract_media('c', mobj.group('chapterid')) + + """ + webpage = self._download_webpage(url, chapter_id) + m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) + if not m: + raise ExtractorError('Cannot find archive of a chapter') + archive_id = m.group(1) + + api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id + doc = self._download_xml( + api, chapter_id, + note='Downloading chapter information', + errnote='Chapter information download failed') + for a in doc.findall('.//archive'): + if archive_id == a.find('./id').text: + break + else: + raise ExtractorError('Could not find chapter in chapter information') + + video_url = a.find('./video_file_url').text + video_ext = video_url.rpartition('.')[2] or 'flv' + + chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id + chapter_info = self._download_json( + chapter_api_url, 'c' + chapter_id, + note='Downloading chapter metadata', + errnote='Download of chapter metadata failed') + + bracket_start = int(doc.find('.//bracket_start').text) + bracket_end = int(doc.find('.//bracket_end').text) + + # TODO determine start (and probably fix up file) + # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 + #video_url += '?start=' + TODO:start_timestamp + # bracket_start is 13290, but we want 51670615 + self._downloader.report_warning('Chapter detected, but we can just download the whole file. ' + 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) + + info = { + 'id': 'c' + chapter_id, + 'url': video_url, + 'ext': video_ext, + 'title': chapter_info['title'], + 'thumbnail': chapter_info['preview'], + 'description': chapter_info['description'], + 'uploader': chapter_info['channel']['display_name'], + 'uploader_id': chapter_info['channel']['name'], + } + return info + """ + elif mobj.group('videoid'): + return self._extract_media('a', mobj.group('videoid')) + elif mobj.group('channelid'): + channel_id = mobj.group('channelid') + info = self._download_json( + '%s/kraken/channels/%s' % (self._API_BASE, channel_id), + channel_id, 'Downloading channel info JSON') + channel_name = info.get('display_name') or info.get('name') + entries = [] + offset = 0 + limit = self._PAGE_LIMIT + for counter in itertools.count(1): + response = self._download_json( + '%s/kraken/channels/%s/videos/?offset=%d&limit=%d' + % (self._API_BASE, channel_id, offset, limit), + channel_id, 'Downloading channel videos JSON page %d' % counter) + videos = response['videos'] + if not videos: + break + entries.extend([self.url_result(video['url'], 'Twitch') for video in videos]) + offset += limit + return self.playlist_result(entries, channel_id, channel_name) diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py new file mode 100644 index 000000000..0182d67ec --- /dev/null +++ b/youtube_dl/extractor/ubu.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class UbuIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html' + _TEST = { + 'url': 'http://ubu.com/film/her_noise.html', + 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9', + 'info_dict': { + 'id': 'her_noise', + 'ext': 'mp4', + 'title': 'Her Noise - The Making Of (2007)', + 'duration': 3600, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title') + + duration = int_or_none(self._html_search_regex( + r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None)) + if duration: + duration *= 60 + + formats = [] + + FORMAT_REGEXES = [ + ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"], + ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'] + ] + + for format_id, format_regex in FORMAT_REGEXES: + m = re.search(format_regex, webpage) + if m: + formats.append({ + 'url': m.group(1), + 'format_id': format_id, + }) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 054f42725..5271611ac 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -40,8 +40,24 @@ class UdemyIE(InfoExtractor): error_str += ' - %s' % error_data.get('formErrors') raise ExtractorError(error_str, expected=True) - def _download_json(self, url, video_id, note='Downloading JSON metadata'): - response = super(UdemyIE, self)._download_json(url, video_id, note) + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'): + headers = { + 'X-Udemy-Snail-Case': 'true', + 'X-Requested-With': 'XMLHttpRequest', + } + for cookie in self._downloader.cookiejar: + if cookie.name == 'client_id': + headers['X-Udemy-Client-Id'] = cookie.value + elif cookie.name == 'access_token': + headers['X-Udemy-Bearer-Token'] = cookie.value + + if isinstance(url_or_request, compat_urllib_request.Request): + for header, value in headers.items(): + url_or_request.add_header(header, value) + else: + url_or_request = compat_urllib_request.Request(url_or_request, headers=headers) + + response = super(UdemyIE, self)._download_json(url_or_request, video_id, note) self._handle_error(response) return response @@ -62,7 +78,9 @@ class UdemyIE(InfoExtractor): if login_popup == '<div class="run-command close-popup redirect" data-url="https://www.udemy.com/"></div>': return - csrf = self._html_search_regex(r'<input type="hidden" name="csrf" value="(.+?)"', login_popup, 'csrf token') + csrf = self._html_search_regex( + r'<input type="hidden" name="csrf" value="(.+?)"', + login_popup, 'csrf token') login_form = { 'email': username, @@ -71,42 +89,49 @@ class UdemyIE(InfoExtractor): 'displayType': 'json', 'isSubmitted': '1', } - request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) - response = self._download_json(request, None, 'Logging in as %s' % username) + request = compat_urllib_request.Request( + self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) + response = self._download_json( + request, None, 'Logging in as %s' % username) if 'returnUrl' not in response: raise ExtractorError('Unable to log in') def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - lecture_id = mobj.group('id') + lecture_id = self._match_id(url) lecture = self._download_json( - 'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id, lecture_id, 'Downloading lecture JSON') + 'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id, + lecture_id, 'Downloading lecture JSON') - if lecture['assetType'] != 'Video': - raise ExtractorError('Lecture %s is not a video' % lecture_id, expected=True) + asset_type = lecture.get('assetType') or lecture.get('asset_type') + if asset_type != 'Video': + raise ExtractorError( + 'Lecture %s is not a video' % lecture_id, expected=True) asset = lecture['asset'] - stream_url = asset['streamUrl'] + stream_url = asset.get('streamUrl') or asset.get('stream_url') mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url) if mobj: return self.url_result(mobj.group(1), 'Youtube') video_id = asset['id'] - thumbnail = asset['thumbnailUrl'] + thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url') duration = asset['data']['duration'] - download_url = asset['downloadUrl'] + download_url = asset.get('downloadUrl') or asset.get('download_url') + + video = download_url.get('Video') or download_url.get('video') + video_480p = download_url.get('Video480p') or download_url.get('video_480p') formats = [ { - 'url': download_url['Video480p'][0], + 'url': video_480p[0], 'format_id': '360p', }, { - 'url': download_url['Video'][0], + 'url': video[0], 'format_id': '720p', }, ] @@ -140,25 +165,29 @@ class UdemyCourseIE(UdemyIE): course_path = mobj.group('coursepath') response = self._download_json( - 'https://www.udemy.com/api-1.1/courses/%s' % course_path, course_path, 'Downloading course JSON') + 'https://www.udemy.com/api-1.1/courses/%s' % course_path, + course_path, 'Downloading course JSON') course_id = int(response['id']) course_title = response['title'] webpage = self._download_webpage( - 'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id, course_id, 'Enrolling in the course') + 'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id, + course_id, 'Enrolling in the course') if self._SUCCESSFULLY_ENROLLED in webpage: self.to_screen('%s: Successfully enrolled in' % course_id) elif self._ALREADY_ENROLLED in webpage: self.to_screen('%s: Already enrolled in' % course_id) - response = self._download_json('https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id, + response = self._download_json( + 'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id, course_id, 'Downloading course curriculum') entries = [ - self.url_result('https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), 'Udemy') - for asset in response if asset.get('assetType') == 'Video' + self.url_result( + 'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), 'Udemy') + for asset in response if asset.get('assetType') or asset.get('asset_type') == 'Video' ] - return self.playlist_result(entries, course_id, course_title)
\ No newline at end of file + return self.playlist_result(entries, course_id, course_title) diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py index 474610eec..f70978299 100644 --- a/youtube_dl/extractor/unistra.py +++ b/youtube_dl/extractor/unistra.py @@ -1,32 +1,66 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import qualities + class UnistraIE(InfoExtractor): - _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)' - - _TEST = { - u'url': u'http://utv.unistra.fr/video.php?id_video=154', - u'file': u'154.mp4', - u'md5': u'736f605cfdc96724d55bb543ab3ced24', - u'info_dict': { - u'title': u'M!ss Yella', - u'description': u'md5:104892c71bd48e55d70b902736b81bbf', + _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)' + + _TESTS = [ + { + 'url': 'http://utv.unistra.fr/video.php?id_video=154', + 'md5': '736f605cfdc96724d55bb543ab3ced24', + 'info_dict': { + 'id': '154', + 'ext': 'mp4', + 'title': 'M!ss Yella', + 'description': 'md5:104892c71bd48e55d70b902736b81bbf', + }, }, - } + { + 'url': 'http://utv.unistra.fr/index.php?id_video=437', + 'md5': '1ddddd6cccaae76f622ce29b8779636d', + 'info_dict': { + 'id': '437', + 'ext': 'mp4', + 'title': 'Prix Louise Weiss 2014', + 'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a', + }, + } + ] def _real_extract(self, url): - id = re.match(self._VALID_URL, url).group(1) - webpage = self._download_webpage(url, id) - file = re.search(r'file: "(.*?)",', webpage).group(1) - title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title') + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') - video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file + webpage = self._download_webpage(url, video_id) - return {'id': id, - 'title': title, - 'ext': 'mp4', - 'url': video_url, - 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL), - 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'), - } + files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage)) + + quality = qualities(['SD', 'HD']) + formats = [] + for file_path in files: + format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD' + formats.append({ + 'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path, + 'format_id': format_id, + 'quality': quality(format_id) + }) + + title = self._html_search_regex( + r'<title>UTV - (.*?)</', webpage, 'title') + description = self._html_search_regex( + r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL) + thumbnail = self._search_regex( + r'image: "(.*?)"', webpage, 'thumbnail') + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats + } diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 488b10df9..53dc3a496 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -1,12 +1,10 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( compat_urlparse, - get_meta_content, ) @@ -47,13 +45,13 @@ class UstreamIE(InfoExtractor): self.report_extraction(video_id) video_title = self._html_search_regex(r'data-title="(?P<title>.+)"', - webpage, 'title') + webpage, 'title') uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', - webpage, 'uploader', fatal=False, flags=re.DOTALL) + webpage, 'uploader', fatal=False, flags=re.DOTALL) thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"', - webpage, 'thumbnail', fatal=False) + webpage, 'thumbnail', fatal=False) return { 'id': video_id, @@ -68,21 +66,36 @@ class UstreamIE(InfoExtractor): class UstreamChannelIE(InfoExtractor): _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' IE_NAME = 'ustream:channel' + _TEST = { + 'url': 'http://www.ustream.tv/channel/channeljapan', + 'info_dict': { + 'id': '10874166', + }, + 'playlist_mincount': 17, + } def _real_extract(self, url): m = re.match(self._VALID_URL, url) - slug = m.group('slug') - webpage = self._download_webpage(url, slug) - channel_id = get_meta_content('ustream:channel_id', webpage) + display_id = m.group('slug') + webpage = self._download_webpage(url, display_id) + channel_id = self._html_search_meta('ustream:channel_id', webpage) BASE = 'http://www.ustream.tv' next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id video_ids = [] while next_url: - reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id)) + reply = self._download_json( + compat_urlparse.urljoin(BASE, next_url), display_id, + note='Downloading video information (next: %d)' % (len(video_ids) + 1)) video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data'])) next_url = reply['nextUrl'] - urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids] - url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls] - return self.playlist_result(url_entries, channel_id) + entries = [ + self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream') + for vid in video_ids] + return { + '_type': 'playlist', + 'id': channel_id, + 'display_id': display_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index df115d251..455b6d9da 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -19,7 +19,7 @@ class Vbox7IE(InfoExtractor): 'md5': '99f65c0c9ef9b682b97313e052734c3f', 'info_dict': { 'id': '249bb972c2', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Смях! Чудо - чист за секунди - Скрита камера', }, } @@ -30,13 +30,13 @@ class Vbox7IE(InfoExtractor): redirect_page, urlh = self._download_webpage_handle(url, video_id) new_location = self._search_regex(r'window\.location = \'(.*)\';', - redirect_page, 'redirect location') + redirect_page, 'redirect location') redirect_url = urlh.geturl() + new_location webpage = self._download_webpage(redirect_url, video_id, - 'Downloading redirect page') + 'Downloading redirect page') title = self._html_search_regex(r'<title>(.*)</title>', - webpage, 'title').split('/')[0].strip() + webpage, 'title').split('/')[0].strip() info_url = "http://vbox7.com/play/magare.do" data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id}) @@ -50,7 +50,6 @@ class Vbox7IE(InfoExtractor): return { 'id': video_id, 'url': final_url, - 'ext': 'flv', 'title': title, 'thumbnail': thumbnail_url, } diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index b1c854a64..94647d1c8 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -16,8 +16,9 @@ class VeeHDIE(InfoExtractor): _TEST = { 'url': 'http://veehd.com/video/4686958', - 'file': '4686958.mp4', 'info_dict': { + 'id': '4686958', + 'ext': 'mp4', 'title': 'Time Lapse View from Space ( ISS)', 'uploader_id': 'spotted', 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7', @@ -47,11 +48,11 @@ class VeeHDIE(InfoExtractor): video_url = compat_urlparse.unquote(config['clip']['url']) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>', - webpage, 'uploader') + webpage, 'uploader') thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"', - webpage, 'thumbnail') + webpage, 'thumbnail') description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul', - webpage, 'description', flags=re.DOTALL) + webpage, 'description', flags=re.DOTALL) return { '_type': 'video', diff --git a/youtube_dl/extractor/vesti.py b/youtube_dl/extractor/vesti.py index 27f9acb67..a0c59a2e0 100644 --- a/youtube_dl/extractor/vesti.py +++ b/youtube_dl/extractor/vesti.py @@ -112,10 +112,10 @@ class VestiIE(InfoExtractor): if mobj: video_id = mobj.group('id') page = self._download_webpage('http://www.vesti.ru/only_video.html?vid=%s' % video_id, video_id, - 'Downloading video page') + 'Downloading video page') rutv_url = RUTVIE._extract_url(page) if rutv_url: return self.url_result(rutv_url, 'RUTV') - raise ExtractorError('No video found', expected=True)
\ No newline at end of file + raise ExtractorError('No video found', expected=True) diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index d2ffd1b6b..c912c3cbe 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -5,7 +5,7 @@ import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( - compat_HTTPError, + compat_urllib_request, ExtractorError, ) @@ -13,7 +13,7 @@ from ..utils import ( class VevoIE(InfoExtractor): """ Accepts urls from vevo.com or in the format 'vevo:{id}' - (currently used by MTVIE) + (currently used by MTVIE and MySpaceIE) """ _VALID_URL = r'''(?x) (?:https?://www\.vevo\.com/watch/(?:[^/]+/(?:[^/]+/)?)?| @@ -24,7 +24,7 @@ class VevoIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280', - "md5": "06bea460acb744eab74a9d7dcb4bfd61", + "md5": "95ee28ee45e70130e3ab02b0f579ae23", 'info_dict': { 'id': 'GB1101300280', 'ext': 'mp4', @@ -40,7 +40,7 @@ class VevoIE(InfoExtractor): }, { 'note': 'v3 SMIL format', 'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923', - 'md5': '893ec0e0d4426a1d96c01de8f2bdff58', + 'md5': 'f6ab09b034f8c22969020b042e5ac7fc', 'info_dict': { 'id': 'USUV71302923', 'ext': 'mp4', @@ -69,6 +69,21 @@ class VevoIE(InfoExtractor): }] _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/' + def _real_initialize(self): + req = compat_urllib_request.Request( + 'http://www.vevo.com/auth', data=b'') + webpage = self._download_webpage( + req, None, + note='Retrieving oauth token', + errnote='Unable to retrieve oauth token', + fatal=False) + if webpage is False: + self._oauth_token = None + else: + self._oauth_token = self._search_regex( + r'access_token":\s*"([^"]+)"', + webpage, 'access token', fatal=False) + def _formats_from_json(self, video_info): last_version = {'version': -1} for version in video_info['videoVersions']: @@ -129,6 +144,26 @@ class VevoIE(InfoExtractor): }) return formats + def _download_api_formats(self, video_id): + if not self._oauth_token: + self._downloader.report_warning( + 'No oauth token available, skipping API HLS download') + return [] + + api_url = 'https://apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( + video_id, self._oauth_token) + api_data = self._download_json( + api_url, video_id, + note='Downloading HLS formats', + errnote='Failed to download HLS format list', fatal=False) + if api_data is None: + return [] + + m3u8_url = api_data[0]['url'] + return self._extract_m3u8_formats( + m3u8_url, video_id, entry_protocol='m3u8_native', ext='mp4', + preference=0) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') @@ -152,30 +187,8 @@ class VevoIE(InfoExtractor): else: age_limit = None - # Download SMIL - smil_blocks = sorted(( - f for f in video_info['videoVersions'] - if f['sourceType'] == 13), - key=lambda f: f['version']) - - smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % ( - self._SMIL_BASE_URL, video_id, video_id.lower()) - if smil_blocks: - smil_url_m = self._search_regex( - r'url="([^"]+)"', smil_blocks[-1]['data'], 'SMIL URL', - fatal=False) - if smil_url_m is not None: - smil_url = smil_url_m - - try: - smil_xml = self._download_webpage(smil_url, video_id, - 'Downloading SMIL info') - formats.extend(self._formats_from_smil(smil_xml)) - except ExtractorError as ee: - if not isinstance(ee.cause, compat_HTTPError): - raise - self._downloader.report_warning( - 'Cannot download SMIL information, falling back to JSON ..') + # Download via HLS API + formats.extend(self._download_api_formats(video_id)) self._sort_formats(formats) timestamp_ms = int(self._search_regex( diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py new file mode 100644 index 000000000..2f111bf7e --- /dev/null +++ b/youtube_dl/extractor/vgtv.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import float_or_none + + +class VGTVIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)' + _TESTS = [ + { + # streamType: vod + 'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu', + 'md5': 'b8be7a234cebb840c0d512c78013e02f', + 'info_dict': { + 'id': '84196', + 'ext': 'mp4', + 'title': 'Hevnen er søt: Episode 10 - Abu', + 'description': 'md5:e25e4badb5f544b04341e14abdc72234', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 648.000, + 'timestamp': 1404626400, + 'upload_date': '20140706', + 'view_count': int, + }, + }, + { + # streamType: wasLive + 'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen', + 'info_dict': { + 'id': '100764', + 'ext': 'flv', + 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen', + 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 9103.0, + 'timestamp': 1410113864, + 'upload_date': '20140907', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + { + # streamType: live + 'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen', + 'info_dict': { + 'id': '100015', + 'ext': 'flv', + 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!', + 'description': 'md5:9a60cc23fa349f761628924e56eeec2d', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 0, + 'timestamp': 1407423348, + 'upload_date': '20140807', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + data = self._download_json( + 'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id, + video_id, 'Downloading media JSON') + + streams = data['streamUrls'] + + formats = [] + + hls_url = streams.get('hls') + if hls_url: + formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4')) + + hds_url = streams.get('hds') + if hds_url: + formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id)) + + mp4_url = streams.get('mp4') + if mp4_url: + _url = hls_url or hds_url + MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1]) + for mp4_format in _url.split(','): + m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format) + if not m: + continue + width = int(m.group('width')) + height = int(m.group('height')) + vbr = int(m.group('vbr')) + formats.append({ + 'url': MP4_URL_TEMPLATE % mp4_format, + 'format_id': 'mp4-%s' % vbr, + 'width': width, + 'height': height, + 'vbr': vbr, + 'preference': 1, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': data['title'], + 'description': data['description'], + 'thumbnail': data['images']['main'] + '?t[]=900x506q80', + 'timestamp': data['published'], + 'duration': float_or_none(data['duration'], 1000), + 'view_count': data['displays'], + 'formats': formats, + } diff --git a/youtube_dl/extractor/vh1.py b/youtube_dl/extractor/vh1.py index 2f77e3898..6be3774b7 100644 --- a/youtube_dl/extractor/vh1.py +++ b/youtube_dl/extractor/vh1.py @@ -121,4 +121,7 @@ class VH1IE(MTVIE): idoc = self._download_xml( doc_url, video_id, 'Downloading info', transform_source=fix_xml_ampersands) - return [self._get_video_info(item) for item in idoc.findall('.//item')] + return self.playlist_result( + [self._get_video_info(item) for item in idoc.findall('.//item')], + playlist_id=video_id, + ) diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py new file mode 100644 index 000000000..71f520fb5 --- /dev/null +++ b/youtube_dl/extractor/vice.py @@ -0,0 +1,37 @@ +from __future__ import unicode_literals +import re + +from .common import InfoExtractor +from .ooyala import OoyalaIE +from ..utils import ExtractorError + + +class ViceIE(InfoExtractor): + _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)' + + _TEST = { + 'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1', + 'info_dict': { + 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', + 'ext': 'mp4', + 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + }, + 'params': { + # Requires ffmpeg (m3u8 manifest) + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + webpage = self._download_webpage(url, name) + try: + embed_code = self._search_regex( + r'embedCode=([^&\'"]+)', webpage, + 'ooyala embed code') + ooyala_url = OoyalaIE._url_for_embed_code(embed_code) + print(ooyala_url) + except ExtractorError: + raise ExtractorError('The page doesn\'t contain a video', expected=True) + return self.url_result(ooyala_url, ie='Ooyala') diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 9328ef4a2..0faa729c6 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -1,55 +1,85 @@ -import json -import re +from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, +) class ViddlerIE(InfoExtractor): - _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler\.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)' + _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)' _TEST = { - u"url": u"http://www.viddler.com/v/43903784", - u'file': u'43903784.mp4', - u'md5': u'fbbaedf7813e514eb7ca30410f439ac9', - u'info_dict': { - u"title": u"Video Made Easy", - u"uploader": u"viddler", - u"duration": 100.89, + "url": "http://www.viddler.com/v/43903784", + 'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4', + 'info_dict': { + 'id': '43903784', + 'ext': 'mp4', + "title": "Video Made Easy", + 'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ', + "uploader": "viddler", + 'timestamp': 1335371429, + 'upload_date': '20120425', + "duration": 100.89, + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, + 'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'], } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - embed_url = mobj.group('domain') + u'/embed/' + video_id - webpage = self._download_webpage(embed_url, video_id) - - video_sources_code = self._search_regex( - r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs') - video_sources = json.loads(video_sources_code.replace("'", '"')) - - formats = [{ - 'url': video_url, - 'format': format_id, - } for video_url, format_id in video_sources.items()] - - title = self._html_search_regex( - r"title\s*:\s*'([^']*)'", webpage, u'title') - uploader = self._html_search_regex( - r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False) - duration_s = self._html_search_regex( - r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False) - duration = float(duration_s) if duration_s else None - thumbnail = self._html_search_regex( - r"thumbnail\s*:\s*'([^']*)'", - webpage, u'thumbnail', fatal=False) + video_id = self._match_id(url) + + json_url = ( + 'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' % + video_id) + data = self._download_json(json_url, video_id)['video'] + + formats = [] + for filed in data['files']: + if filed.get('status', 'ready') != 'ready': + continue + f = { + 'format_id': filed['profile_id'], + 'format_note': filed['profile_name'], + 'url': self._proto_relative_url(filed['url']), + 'width': int_or_none(filed.get('width')), + 'height': int_or_none(filed.get('height')), + 'filesize': int_or_none(filed.get('size')), + 'ext': filed.get('ext'), + 'source_preference': -1, + } + formats.append(f) + + if filed.get('cdn_url'): + f = f.copy() + f['url'] = self._proto_relative_url(filed['cdn_url']) + f['format_id'] = filed['profile_id'] + '-cdn' + f['source_preference'] = 1 + formats.append(f) + + if filed.get('html5_video_source'): + f = f.copy() + f['url'] = self._proto_relative_url( + filed['html5_video_source']) + f['format_id'] = filed['profile_id'] + '-html5' + f['source_preference'] = 0 + formats.append(f) + self._sort_formats(formats) + + categories = [ + t.get('text') for t in data.get('tags', []) if 'text' in t] return { '_type': 'video', 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'duration': duration, + 'title': data['title'], 'formats': formats, + 'description': data.get('description'), + 'timestamp': int_or_none(data.get('upload_time')), + 'thumbnail': self._proto_relative_url(data.get('thumbnail_url')), + 'uploader': data.get('author'), + 'duration': float_or_none(data.get('length')), + 'view_count': int_or_none(data.get('view_count')), + 'categories': categories, } diff --git a/youtube_dl/extractor/videobam.py b/youtube_dl/extractor/videobam.py index fed95ef71..0eb3d9414 100644 --- a/youtube_dl/extractor/videobam.py +++ b/youtube_dl/extractor/videobam.py @@ -78,4 +78,4 @@ class VideoBamIE(InfoExtractor): 'view_count': view_count, 'formats': formats, 'age_limit': 18, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py index f75169041..94f9e9be9 100644 --- a/youtube_dl/extractor/videofyme.py +++ b/youtube_dl/extractor/videofyme.py @@ -1,46 +1,50 @@ -import re +from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( find_xpath_attr, - determine_ext, + int_or_none, ) + class VideofyMeIE(InfoExtractor): - _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)' - IE_NAME = u'videofy.me' + _VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)' + IE_NAME = 'videofy.me' _TEST = { - u'url': u'http://www.videofy.me/thisisvideofyme/1100701', - u'file': u'1100701.mp4', - u'md5': u'c77d700bdc16ae2e9f3c26019bd96143', - u'info_dict': { - u'title': u'This is VideofyMe', - u'description': None, - u'uploader': u'VideofyMe', - u'uploader_id': u'thisisvideofyme', + 'url': 'http://www.videofy.me/thisisvideofyme/1100701', + 'md5': 'c77d700bdc16ae2e9f3c26019bd96143', + 'info_dict': { + 'id': '1100701', + 'ext': 'mp4', + 'title': 'This is VideofyMe', + 'description': None, + 'uploader': 'VideofyMe', + 'uploader_id': 'thisisvideofyme', + 'view_count': int, }, - + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id, - video_id) + video_id) video = config.find('video') sources = video.find('sources') - url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) - for key in ['on', 'av', 'off']] if node is not None) + url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) + for key in ['on', 'av', 'off']] if node is not None) video_url = url_node.find('url').text + view_count = int_or_none(self._search_regex( + r'([0-9]+)', video.find('views').text, 'view count', fatal=False)) - return {'id': video_id, - 'title': video.find('title').text, - 'url': video_url, - 'ext': determine_ext(video_url), - 'thumbnail': video.find('thumb').text, - 'description': video.find('description').text, - 'uploader': config.find('blog/name').text, - 'uploader_id': video.find('identifier').text, - 'view_count': re.search(r'\d+', video.find('views').text).group(), - } + return { + 'id': video_id, + 'title': video.find('title').text, + 'url': video_url, + 'thumbnail': video.find('thumb').text, + 'description': video.find('description').text, + 'uploader': config.find('blog/name').text, + 'uploader_id': video.find('identifier').text, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py new file mode 100644 index 000000000..29c4e0101 --- /dev/null +++ b/youtube_dl/extractor/videomega.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + remove_start, +) + + +class VideoMegaIE(InfoExtractor): + _VALID_URL = r'''(?x)https?:// + (?:www\.)?videomega\.tv/ + (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+) + ''' + _TEST = { + 'url': 'http://videomega.tv/?ref=GKeGPVedBe', + 'md5': '240fb5bcf9199961f48eb17839b084d6', + 'info_dict': { + 'id': 'GKeGPVedBe', + 'ext': 'mp4', + 'title': 'XXL - All Sports United', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) + webpage = self._download_webpage(url, video_id) + + escaped_data = self._search_regex( + r'unescape\("([^"]+)"\)', webpage, 'escaped data') + playlist = compat_urllib_parse.unquote(escaped_data) + + thumbnail = self._search_regex( + r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False) + url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') + title = remove_start(self._html_search_regex( + r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ') + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/videopremium.py b/youtube_dl/extractor/videopremium.py index 65463c733..3176e3b9d 100644 --- a/youtube_dl/extractor/videopremium.py +++ b/youtube_dl/extractor/videopremium.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import random @@ -5,23 +7,22 @@ from .common import InfoExtractor class VideoPremiumIE(InfoExtractor): - _VALID_URL = r'(?:https?://)?(?:www\.)?videopremium\.(?:tv|me)/(?P<id>\w+)(?:/.*)?' + _VALID_URL = r'https?://(?:www\.)?videopremium\.(?:tv|me)/(?P<id>\w+)(?:/.*)?' _TEST = { - u'url': u'http://videopremium.tv/4w7oadjsf156', - u'file': u'4w7oadjsf156.f4v', - u'info_dict': { - u"title": u"youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4" + 'url': 'http://videopremium.tv/4w7oadjsf156', + 'info_dict': { + 'id': '4w7oadjsf156', + 'ext': 'f4v', + 'title': 'youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4' }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'Test file has been deleted.', + 'skip': 'Test file has been deleted.', } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') + video_id = self._match_id(url) webpage_url = 'http://videopremium.tv/' + video_id webpage = self._download_webpage(webpage_url, video_id) @@ -29,17 +30,17 @@ class VideoPremiumIE(InfoExtractor): # Download again, we need a cookie webpage = self._download_webpage( webpage_url, video_id, - note=u'Downloading webpage again (with cookie)') + note='Downloading webpage again (with cookie)') video_title = self._html_search_regex( - r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, u'video title') + r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, 'video title') return { - 'id': video_id, - 'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16), - 'play_path': "mp4:%s.f4v" % video_id, - 'page_url': "http://videopremium.tv/" + video_id, - 'player_url': "http://videopremium.tv/uplayer/uppod.swf", - 'ext': 'f4v', - 'title': video_title, + 'id': video_id, + 'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16), + 'play_path': "mp4:%s.f4v" % video_id, + 'page_url': "http://videopremium.tv/" + video_id, + 'player_url': "http://videopremium.tv/uplayer/uppod.swf", + 'ext': 'f4v', + 'title': video_title, } diff --git a/youtube_dl/extractor/videott.py b/youtube_dl/extractor/videott.py index a647807d0..1f938838c 100644 --- a/youtube_dl/extractor/videott.py +++ b/youtube_dl/extractor/videott.py @@ -58,4 +58,4 @@ class VideoTtIE(InfoExtractor): 'like_count': int_or_none(video['liked']), 'dislike_count': int_or_none(video['disliked']), 'formats': formats, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/videoweed.py b/youtube_dl/extractor/videoweed.py index 4a08ddd43..ca2e50935 100644 --- a/youtube_dl/extractor/videoweed.py +++ b/youtube_dl/extractor/videoweed.py @@ -23,4 +23,4 @@ class VideoWeedIE(NovaMovIE): 'title': 'optical illusion dissapeared image magic illusion', 'description': '' }, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py new file mode 100644 index 000000000..5c89824c1 --- /dev/null +++ b/youtube_dl/extractor/vidme.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, + str_to_int, +) + + +class VidmeIE(InfoExtractor): + _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)' + _TEST = { + 'url': 'https://vid.me/QNB', + 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', + 'info_dict': { + 'id': 'QNB', + 'ext': 'mp4', + 'title': 'Fishing for piranha - the easy way', + 'description': 'source: https://www.facebook.com/photo.php?v=312276045600871', + 'duration': 119.92, + 'timestamp': 1406313244, + 'upload_date': '20140725', + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex(r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage, default='') + thumbnail = self._og_search_thumbnail(webpage) + timestamp = int_or_none(self._og_search_property('updated_time', webpage, fatal=False)) + width = int_or_none(self._og_search_property('video:width', webpage, fatal=False)) + height = int_or_none(self._og_search_property('video:height', webpage, fatal=False)) + duration = float_or_none(self._html_search_regex( + r'data-duration="([^"]+)"', webpage, 'duration', fatal=False)) + view_count = str_to_int(self._html_search_regex( + r'<span class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">', + webpage, 'comment count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'width': width, + 'height': height, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py new file mode 100644 index 000000000..08a5a7b8d --- /dev/null +++ b/youtube_dl/extractor/vidzi.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class VidziIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)' + _TEST = { + 'url': 'http://vidzi.tv/cghql9yq6emu.html', + 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', + 'info_dict': { + 'id': 'cghql9yq6emu', + 'ext': 'mp4', + 'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + video_url = self._html_search_regex( + r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url') + title = self._html_search_regex( + r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index a3c6e83b0..06b0bed41 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -7,18 +7,20 @@ import itertools from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( +from ..compat import ( compat_HTTPError, compat_urllib_parse, compat_urllib_request, - clean_html, - get_element_by_attribute, + compat_urlparse, +) +from ..utils import ( ExtractorError, + InAdvancePagedList, + int_or_none, RegexNotFoundError, std_headers, unsmuggle_url, urlencode_postdata, - int_or_none, ) @@ -54,9 +56,10 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # _VALID_URL matches Vimeo URLs _VALID_URL = r'''(?x) - (?P<proto>(?:https?:)?//)? + https?:// (?:(?:www|(?P<player>player))\.)? vimeo(?P<pro>pro)?\.com/ + (?!channels/[^/?#]+/?(?:$|[?#])|album/) (?:.*?/)? (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? (?:videos?/)? @@ -88,6 +91,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader_id': 'openstreetmapus', 'uploader': 'OpenStreetMap US', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', + 'description': 'md5:380943ec71b89736ff4bf27183233d09', 'duration': 1595, }, }, @@ -102,6 +106,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader': 'The BLN & Business of Software', 'uploader_id': 'theblnbusinessofsoftware', 'duration': 3610, + 'description': None, }, }, { @@ -116,12 +121,28 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader_id': 'user18948128', 'uploader': 'Jaime Marquínez Ferrándiz', 'duration': 10, + 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.', }, 'params': { 'videopassword': 'youtube-dl', }, }, { + 'url': 'http://vimeo.com/channels/keypeele/75629013', + 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', + 'note': 'Video is freely available via original URL ' + 'and protected with password when accessed via http://vimeo.com/75629013', + 'info_dict': { + 'id': '75629013', + 'ext': 'mp4', + 'title': 'Key & Peele: Terrorist Interrogation', + 'description': 'md5:8678b246399b070816b12313e8b4eb5c', + 'uploader_id': 'atencio', + 'uploader': 'Peter Atencio', + 'duration': 187, + }, + }, + { 'url': 'http://vimeo.com/76979871', 'md5': '3363dd6ffebe3784d56f4132317fd446', 'note': 'Video with subtitles', @@ -136,17 +157,20 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'duration': 62, } }, + { + # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ + 'url': 'https://player.vimeo.com/video/98044508', + 'note': 'The js code contains assignments to the same variable as the config', + 'info_dict': { + 'id': '98044508', + 'ext': 'mp4', + 'title': 'Pier Solar OUYA Official Trailer', + 'uploader': 'Tulio Gonçalves', + 'uploader_id': 'user28849593', + }, + }, ] - @classmethod - def suitable(cls, url): - if VimeoChannelIE.suitable(url): - # Otherwise channel urls like http://vimeo.com/channels/31259 would - # match - return False - else: - return super(VimeoIE, cls).suitable(url) - def _verify_video_password(self, url, video_id, webpage): password = self._downloader.params.get('videopassword', None) if password is None: @@ -190,14 +214,15 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if data is not None: headers = headers.copy() headers.update(data) + if 'Referer' not in headers: + headers['Referer'] = url # Extract ID from URL mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + orig_url = url if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id - else: - url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) @@ -231,11 +256,11 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # We try to find out to which variable is assigned the config dic m_variable_name = re.search('(\w)\.video\.id', webpage) if m_variable_name is not None: - config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1)) + config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) else: config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] config = self._search_regex(config_re, webpage, 'info section', - flags=re.DOTALL) + flags=re.DOTALL) config = json.loads(config) except Exception as e: if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): @@ -263,21 +288,26 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if video_thumbnail is None: video_thumbs = config["video"].get("thumbs") if video_thumbs and isinstance(video_thumbs, dict): - _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1] + _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description - video_description = None - try: - video_description = get_element_by_attribute("class", "description_wrapper", webpage) - if video_description: - video_description = clean_html(video_description) - except AssertionError as err: - # On some pages like (http://player.vimeo.com/video/54469442) the - # html tags are not closed, python 2.6 cannot handle it - if err.args[0] == 'we should not get here!': - pass - else: - raise + + video_description = self._html_search_regex( + r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', + webpage, 'description', default=None) + if not video_description: + video_description = self._html_search_meta( + 'description', webpage, default=None) + if not video_description and mobj.group('pro'): + orig_webpage = self._download_webpage( + orig_url, video_id, + note='Downloading webpage for description', + fatal=False) + if orig_webpage: + video_description = self._html_search_meta( + 'description', orig_webpage, default=None) + if not video_description and not mobj.group('player'): + self._downloader.report_warning('Cannot find video description') # Extract video duration video_duration = int_or_none(config["video"].get("duration")) @@ -365,9 +395,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): class VimeoChannelIE(InfoExtractor): IE_NAME = 'vimeo:channel' - _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)/?(\?.*)?$' + _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' + _TESTS = [{ + 'url': 'http://vimeo.com/channels/tributes', + 'info_dict': { + 'title': 'Vimeo Tributes', + }, + 'playlist_mincount': 25, + }] def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) @@ -401,14 +438,15 @@ class VimeoChannelIE(InfoExtractor): class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)' + _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' - - @classmethod - def suitable(cls, url): - if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url): - return False - return super(VimeoUserIE, cls).suitable(url) + _TESTS = [{ + 'url': 'http://vimeo.com/nkistudio/videos', + 'info_dict': { + 'title': 'Nki', + }, + 'playlist_mincount': 66, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -418,8 +456,15 @@ class VimeoUserIE(VimeoChannelIE): class VimeoAlbumIE(VimeoChannelIE): IE_NAME = 'vimeo:album' - _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)' + _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' + _TESTS = [{ + 'url': 'http://vimeo.com/album/2632481', + 'info_dict': { + 'title': 'Staff Favorites: November 2013', + }, + 'playlist_mincount': 13, + }] def _page_url(self, base_url, pagenum): return '%s/page:%d/' % (base_url, pagenum) @@ -433,6 +478,13 @@ class VimeoAlbumIE(VimeoChannelIE): class VimeoGroupsIE(VimeoAlbumIE): IE_NAME = 'vimeo:group' _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)' + _TESTS = [{ + 'url': 'http://vimeo.com/groups/rolexawards', + 'info_dict': { + 'title': 'Rolex Awards for Enterprise', + }, + 'playlist_mincount': 73, + }] def _extract_list_title(self, webpage): return self._og_search_title(webpage) @@ -446,8 +498,8 @@ class VimeoGroupsIE(VimeoAlbumIE): class VimeoReviewIE(InfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)' - _TEST = { + _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' + _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'file': '75524534.mp4', 'md5': 'c507a72f780cacc12b2248bb4006d253', @@ -455,7 +507,19 @@ class VimeoReviewIE(InfoExtractor): 'title': "DICK HARDWICK 'Comedian'", 'uploader': 'Richard Hardwick', } - } + }, { + 'note': 'video player needs Referer', + 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053', + 'md5': '6295fdab8f4bf6a002d058b2c6dce276', + 'info_dict': { + 'id': '91613211', + 'ext': 'mp4', + 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', + 'uploader': 'DevWeek Events', + 'duration': 2773, + 'thumbnail': 're:^https?://.*\.jpg$', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -470,6 +534,10 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater' _LOGIN_REQUIRED = True _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<' + _TESTS = [{ + 'url': 'http://vimeo.com/home/watchlater', + 'only_matching': True, + }] def _real_initialize(self): self._login() @@ -484,3 +552,58 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): def _real_extract(self, url): return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater') + + +class VimeoLikesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' + IE_NAME = 'vimeo:likes' + IE_DESC = 'Vimeo user likes' + _TEST = { + 'url': 'https://vimeo.com/user755559/likes/', + 'playlist_mincount': 293, + "info_dict": { + "description": "See all the videos urza likes", + "title": 'Videos urza likes', + }, + } + + def _real_extract(self, url): + user_id = self._match_id(url) + webpage = self._download_webpage(url, user_id) + page_count = self._int( + self._search_regex( + r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> + .*?</a></li>\s*<li\s+class="pagination_next"> + ''', webpage, 'page count'), + 'page count', fatal=True) + PAGE_SIZE = 12 + title = self._html_search_regex( + r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) + description = self._html_search_meta('description', webpage) + + def _get_page(idx): + page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % ( + self.http_scheme(), user_id, idx + 1) + webpage = self._download_webpage( + page_url, user_id, + note='Downloading page %d/%d' % (idx + 1, page_count)) + video_list = self._search_regex( + r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', + webpage, 'video content') + paths = re.findall( + r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) + for path in paths: + yield { + '_type': 'url', + 'url': compat_urlparse.urljoin(page_url, path), + } + + pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) + + return { + '_type': 'playlist', + 'id': 'user%s_likes' % user_id, + 'title': title, + 'description': description, + 'entries': pl, + } diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 076c87119..0b58fe0fe 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -17,6 +17,7 @@ class VineIE(InfoExtractor): 'id': 'b9KOOWX7HUx', 'ext': 'mp4', 'title': 'Chicken.', + 'alt_title': 'Vine by Jack Dorsey', 'description': 'Chicken.', 'upload_date': '20130519', 'uploader': 'Jack Dorsey', @@ -25,30 +26,26 @@ class VineIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id) data = json.loads(self._html_search_regex( r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data')) - formats = [ - { - 'url': data['videoLowURL'], - 'ext': 'mp4', - 'format_id': 'low', - }, - { - 'url': data['videoUrl'], - 'ext': 'mp4', - 'format_id': 'standard', - } - ] + formats = [{ + 'url': data['videoLowURL'], + 'ext': 'mp4', + 'format_id': 'low', + }, { + 'url': data['videoUrl'], + 'ext': 'mp4', + 'format_id': 'standard', + }] return { 'id': video_id, 'title': self._og_search_title(webpage), + 'alt_title': self._og_search_description(webpage), 'description': data['description'], 'thumbnail': data['thumbnailUrl'], 'upload_date': unified_strdate(data['created']), @@ -63,22 +60,36 @@ class VineIE(InfoExtractor): class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' - _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$' + _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$' _VINE_BASE_URL = "https://vine.co/" + _TESTS = [ + { + 'url': 'https://vine.co/Visa', + 'info_dict': { + 'id': 'Visa', + }, + 'playlist_mincount': 46, + }, + { + 'url': 'https://vine.co/u/941705360593584128', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user = mobj.group('user') + u = mobj.group('u') - profile_url = "%sapi/users/profiles/vanity/%s" % ( - self._VINE_BASE_URL, user) + profile_url = "%sapi/users/profiles/%s%s" % ( + self._VINE_BASE_URL, 'vanity/' if not u else '', user) profile_data = self._download_json( profile_url, user, note='Downloading user profile data') user_id = profile_data['data']['userId'] timeline_data = [] for pagenum in itertools.count(1): - timeline_url = "%sapi/timelines/users/%s?page=%s" % ( + timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % ( self._VINE_BASE_URL, user_id, pagenum) timeline_page = self._download_json( timeline_url, user, note='Downloading page %d' % pagenum) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 918bd1098..ca6b0d5b3 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -11,12 +11,13 @@ from ..utils import ( compat_urllib_parse, compat_str, unescapeHTML, -) + unified_strdate, + orderedSet) class VKIE(InfoExtractor): IE_NAME = 'vk.com' - _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' + _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))' _NETRC_MACHINE = 'vk' _TESTS = [ @@ -29,17 +30,19 @@ class VKIE(InfoExtractor): 'title': 'ProtivoGunz - Хуёвая песня', 'uploader': 're:Noize MC.*', 'duration': 195, + 'upload_date': '20120212', }, }, { - 'url': 'http://vk.com/video4643923_163339118', - 'md5': 'f79bccb5cd182b1f43502ca5685b2b36', + 'url': 'http://vk.com/video205387401_165548505', + 'md5': '6c0aeb2e90396ba97035b9cbde548700', 'info_dict': { - 'id': '163339118', + 'id': '165548505', 'ext': 'mp4', - 'uploader': 'Elya Iskhakova', - 'title': 'Dream Theater - Hollow Years Live at Budokan 720*', - 'duration': 558, + 'uploader': 'Tom Cruise', + 'title': 'No name', + 'duration': 9, + 'upload_date': '20130721' } }, { @@ -52,9 +55,12 @@ class VKIE(InfoExtractor): 'uploader': 'Vladimir Gavrin', 'title': 'Lin Dan', 'duration': 101, + 'upload_date': '20120730', } }, { + # VIDEO NOW REMOVED + # please update if you find a video whose URL follows the same pattern 'url': 'http://vk.com/video-8871596_164049491', 'md5': 'a590bcaf3d543576c9bd162812387666', 'note': 'Only available for registered users', @@ -64,18 +70,7 @@ class VKIE(InfoExtractor): 'uploader': 'Триллеры', 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]', 'duration': 8352, - }, - 'skip': 'Requires vk account credentials', - }, - { - 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', - 'md5': 'd82c22e449f036282d1d3f7f4d276869', - 'info_dict': { - 'id': '166094326', - 'ext': 'mp4', - 'uploader': 'Киномания - лучшее из мира кино', - 'title': 'Запах женщины (1992)', - 'duration': 9392, + 'upload_date': '20121218' }, 'skip': 'Requires vk account credentials', }, @@ -88,6 +83,7 @@ class VKIE(InfoExtractor): 'uploader': 'Киномания - лучшее из мира кино', 'title': ' ', 'duration': 7291, + 'upload_date': '20140328', }, 'skip': 'Requires vk account credentials', }, @@ -100,9 +96,15 @@ class VKIE(InfoExtractor): 'ext': 'mp4', 'title': 'Книга Илая', 'duration': 6771, + 'upload_date': '20140626', }, 'skip': 'Only works from Russia', }, + { + # removed video, just testing that we match the pattern + 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', + 'only_matching': True, + }, ] def _login(self): @@ -119,7 +121,7 @@ class VKIE(InfoExtractor): } request = compat_urllib_request.Request('https://login.vk.com/?act=login', - compat_urllib_parse.urlencode(login_form).encode('utf-8')) + compat_urllib_parse.urlencode(login_form).encode('utf-8')) login_page = self._download_webpage(request, None, note='Logging in as %s' % username) if re.search(r'onLoginFailed', login_page): @@ -138,9 +140,21 @@ class VKIE(InfoExtractor): info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id info_page = self._download_webpage(info_url, video_id) - if re.search(r'<!>Please log in or <', info_page): - raise ExtractorError('This video is only available for registered users, ' - 'use --username and --password options to provide account credentials.', expected=True) + ERRORS = { + r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': + 'Video %s has been removed from public access due to rightholder complaint.', + + r'<!>Please log in or <': + 'Video %s is only available for registered users, ' + 'use --username and --password options to provide account credentials.', + + r'<!>Unknown error': + 'Video %s does not exist.' + } + + for error_re, error_msg in ERRORS.items(): + if re.search(error_re, info_page): + raise ExtractorError(error_msg % video_id, expected=True) m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page) if m_yt is not None: @@ -159,6 +173,13 @@ class VKIE(InfoExtractor): data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars') data = json.loads(data_json) + # Extract upload date + upload_date = None + mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page) + if mobj is not None: + mobj.group(1) + ' ' + mobj.group(2) + upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2)) + formats = [{ 'format_id': k, 'url': v, @@ -173,5 +194,28 @@ class VKIE(InfoExtractor): 'title': unescapeHTML(data['md_title']), 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), - 'duration': data.get('duration') + 'duration': data.get('duration'), + 'upload_date': upload_date, } + + +class VKUserVideosIE(InfoExtractor): + IE_NAME = 'vk.com:user-videos' + IE_DESC = 'vk.com:All of a user\'s videos' + _VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?' + _TEMPLATE_URL = 'https://vk.com/videos' + _TEST = { + 'url': 'http://vk.com/videos205387401', + 'playlist_mincount': 4, + } + + def _real_extract(self, url): + page_id = self._match_id(url) + page = self._download_webpage(url, page_id) + video_ids = orderedSet( + m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page)) + url_entries = [ + self.url_result( + 'http://vk.com/video' + video_id, 'VK', video_id=video_id) + for video_id in video_ids] + return self.playlist_result(url_entries, page_id) diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index 6d3b78749..affef6507 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -44,7 +44,7 @@ class VodlockerIE(InfoExtractor): req, video_id, 'Downloading video page') title = self._search_regex( - r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title') + r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title') thumbnail = self._search_regex( r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail') url = self._search_regex( diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py new file mode 100644 index 000000000..2d23effcc --- /dev/null +++ b/youtube_dl/extractor/vporn.py @@ -0,0 +1,125 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class VpornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/', + 'md5': 'facf37c1b86546fa0208058546842c55', + 'info_dict': { + 'id': '497944', + 'display_id': 'violet-on-her-th-birthday', + 'ext': 'mp4', + 'title': 'Violet on her 19th birthday', + 'description': 'Violet dances in front of the camera which is sure to get you horny.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'kileyGrope', + 'categories': ['Masturbation', 'Teen'], + 'duration': 393, + 'age_limit': 18, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + } + }, + { + 'url': 'http://www.vporn.com/female/hana-shower/523564/', + 'md5': 'ced35a4656198a1664cf2cda1575a25f', + 'info_dict': { + 'id': '523564', + 'display_id': 'hana-shower', + 'ext': 'mp4', + 'title': 'Hana Shower', + 'description': 'Hana showers at the bathroom.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'Hmmmmm', + 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'], + 'duration': 588, + 'age_limit': 18, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() + description = self._html_search_regex( + r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) + if thumbnail: + thumbnail = 'http://www.vporn.com' + thumbnail + + uploader = self._html_search_regex( + r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>', + webpage, 'uploader', fatal=False) + + categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage) + + duration = parse_duration(self._search_regex( + r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False)) + + formats = [] + + for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage): + video_url = video[1] + fmt = { + 'url': video_url, + 'format_id': video[0], + } + m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url) + if m: + fmt.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + 'vbr': int(m.group('vbr')), + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'age_limit': 18, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vrt.py b/youtube_dl/extractor/vrt.py new file mode 100644 index 000000000..bbd3bbf7b --- /dev/null +++ b/youtube_dl/extractor/vrt.py @@ -0,0 +1,95 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import float_or_none + + +class VRTIE(InfoExtractor): + _VALID_URL = r'https?://(?:deredactie|sporza|cobra)\.be/cm/(?:[^/]+/)+(?P<id>[^/]+)/*' + _TESTS = [ + # deredactie.be + { + 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL', + 'md5': '4cebde1eb60a53782d4f3992cbd46ec8', + 'info_dict': { + 'id': '2129880', + 'ext': 'flv', + 'title': 'Het journaal L - 25/10/14', + 'description': None, + 'timestamp': 1414271750.949, + 'upload_date': '20141025', + 'duration': 929, + } + }, + # sporza.be + { + 'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time', + 'md5': '11f53088da9bf8e7cfc42456697953ff', + 'info_dict': { + 'id': '2124639', + 'ext': 'flv', + 'title': 'Bekijk Extra Time van 20 oktober', + 'description': 'md5:83ac5415a4f1816c6a93f8138aef2426', + 'timestamp': 1413835980.560, + 'upload_date': '20141020', + 'duration': 3238, + } + }, + # cobra.be + { + 'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari', + 'md5': '78a2b060a5083c4f055449a72477409d', + 'info_dict': { + 'id': '2126050', + 'ext': 'flv', + 'title': 'Bret Easton Ellis in Café Corsari', + 'description': 'md5:f699986e823f32fd6036c1855a724ee9', + 'timestamp': 1413967500.494, + 'upload_date': '20141022', + 'duration': 661, + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._search_regex( + r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False) + + formats = [] + mobj = re.search( + r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"', + webpage) + if mobj: + formats.extend(self._extract_m3u8_formats( + '%s/%s' % (mobj.group('server'), mobj.group('path')), + video_id, 'mp4')) + mobj = re.search(r'data-video-src="(?P<src>[^"]+)"', webpage) + if mobj: + formats.extend(self._extract_f4m_formats( + '%s/manifest.f4m' % mobj.group('src'), video_id)) + self._sort_formats(formats) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage, default=None) + thumbnail = self._og_search_thumbnail(webpage) + timestamp = float_or_none(self._search_regex( + r'data-video-sitestat-pubdate="(\d+)"', webpage, 'timestamp', fatal=False), 1000) + duration = float_or_none(self._search_regex( + r'data-video-duration="(\d+)"', webpage, 'duration', fatal=False), 1000) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index f1b9e9a19..1b2f731e9 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -1,10 +1,13 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, + ExtractorError, +) class VubeIE(InfoExtractor): @@ -14,6 +17,24 @@ class VubeIE(InfoExtractor): _TESTS = [ { + 'url': 'http://vube.com/trending/William+Wei/Y8NUZ69Tf7?t=s', + 'md5': 'e7aabe1f8f1aa826b9e4735e1f9cee42', + 'info_dict': { + 'id': 'Y8NUZ69Tf7', + 'ext': 'mp4', + 'title': 'Best Drummer Ever [HD]', + 'description': 'md5:2d63c4b277b85c2277761c2cf7337d71', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'William', + 'timestamp': 1406876915, + 'upload_date': '20140801', + 'duration': 258.051, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'], + }, + }, { 'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon', 'md5': 'db7aba89d4603dadd627e9d1973946fe', 'info_dict': { @@ -29,7 +50,9 @@ class VubeIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, - } + 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'], + }, + 'skip': 'Removed due to DMCA', }, { 'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1', @@ -47,7 +70,9 @@ class VubeIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, - } + 'categories': ['seraina', 'jessica', 'krewella', 'alive'], + }, + 'skip': 'Removed due to DMCA', }, { 'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s', 'md5': '0584fc13b50f887127d9d1007589d27f', @@ -56,14 +81,17 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Frozen - Let It Go Cover by Siren Gene', 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.', - 'uploader': 'Siren Gene', - 'uploader_id': 'Siren', 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$', + 'uploader': 'Siren', + 'timestamp': 1395448018, + 'upload_date': '20140322', 'duration': 221.788, 'like_count': int, 'dislike_count': int, 'comment_count': int, - } + 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'], + }, + 'skip': 'Removed due to DMCA', } ] @@ -71,47 +99,45 @@ class VubeIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - data_json = self._search_regex( - r'(?s)window\["(?:tapiVideoData|vubeOriginalVideoData)"\]\s*=\s*(\{.*?\n});\n', - webpage, 'video data' - ) - data = json.loads(data_json) - video = ( - data.get('video') or - data) - assert isinstance(video, dict) + video = self._download_json( + 'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON') public_id = video['public_id'] - formats = [ - { - 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id), - 'height': int(fmt['height']), - 'abr': int(fmt['audio_bitrate']), - 'vbr': int(fmt['video_bitrate']), - 'format_id': fmt['media_resolution_id'] - } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed' - ] + formats = [] + + for media in video['media'].get('video', []) + video['media'].get('audio', []): + if media['transcoding_status'] != 'processed': + continue + fmt = { + 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id), + 'abr': int(media['audio_bitrate']), + 'format_id': compat_str(media['media_resolution_id']), + } + vbr = int(media['video_bitrate']) + if vbr: + fmt.update({ + 'vbr': vbr, + 'height': int(media['height']), + }) + formats.append(fmt) self._sort_formats(formats) + if not formats and video.get('vst') == 'dmca': + raise ExtractorError( + 'This video has been removed in response to a complaint received under the US Digital Millennium Copyright Act.', + expected=True) + title = video['title'] description = video.get('description') - thumbnail = self._proto_relative_url( - video.get('thumbnail') or video.get('thumbnail_src'), - scheme='http:') - uploader = data.get('user', {}).get('channel', {}).get('name') or video.get('user_alias') - uploader_id = data.get('user', {}).get('name') + thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:') + uploader = video.get('user_alias') or video.get('channel') timestamp = int_or_none(video.get('upload_time')) duration = video['duration'] view_count = video.get('raw_view_count') - like_count = video.get('rlikes') - if like_count is None: - like_count = video.get('total_likes') - dislike_count = video.get('rhates') - if dislike_count is None: - dislike_count = video.get('total_hates') + like_count = video.get('total_likes') + dislike_count = video.get('total_hates') comments = video.get('comments') comment_count = None @@ -124,6 +150,8 @@ class VubeIE(InfoExtractor): else: comment_count = len(comments) + categories = [tag['text'] for tag in video['tags']] + return { 'id': video_id, 'formats': formats, @@ -131,11 +159,11 @@ class VubeIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'uploader_id': uploader_id, 'timestamp': timestamp, 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, + 'categories': categories, } diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py index fb0600f1a..ec3c010ad 100644 --- a/youtube_dl/extractor/vuclip.py +++ b/youtube_dl/extractor/vuclip.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse_urlparse, + ExtractorError, parse_duration, qualities, ) @@ -14,13 +15,12 @@ class VuClipIE(InfoExtractor): _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)' _TEST = { - 'url': 'http://m.vuclip.com/w?cid=843902317&fid=63532&z=1007&nvar&frm=index.html&bu=4757321434', - 'md5': '92ac9d1ccefec4f0bb474661ab144fcf', + 'url': 'http://m.vuclip.com/w?cid=922692425&fid=70295&z=1010&nvar&frm=index.html', 'info_dict': { - 'id': '843902317', + 'id': '922692425', 'ext': '3gp', - 'title': 'Movie Trailer: Noah', - 'duration': 139, + 'title': 'The Toy Soldiers - Hollywood Movie Trailer', + 'duration': 180, } } @@ -37,16 +37,32 @@ class VuClipIE(InfoExtractor): webpage = self._download_webpage( adfree_url, video_id, note='Download post-ad page') + error_msg = self._html_search_regex( + r'<p class="message">(.*?)</p>', webpage, 'error message', + default=None) + if error_msg: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error_msg), expected=True) + + # These clowns alternate between two page types links_code = self._search_regex( - r'(?s)<div class="social align_c".*?>(.*?)<hr\s*/?>', webpage, - 'links') + r'''(?xs) + (?: + <img\s+src="/im/play.gif".*?>| + <!--\ player\ end\ -->\s*</div><!--\ thumb\ end--> + ) + (.*?) + (?: + <a\s+href="fblike|<div\s+class="social"> + ) + ''', webpage, 'links') title = self._html_search_regex( r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip() quality_order = qualities(['Reg', 'Hi']) formats = [] for url, q in re.findall( - r'<a href="(?P<url>[^"]+)".*?>(?P<q>[^<]+)</a>', links_code): + r'<a\s+href="(?P<url>[^"]+)".*?>(?:<button[^>]*>)?(?P<q>[^<]+)(?:</button>)?</a>', links_code): format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q formats.append({ 'format_id': format_id, @@ -56,7 +72,7 @@ class VuClipIE(InfoExtractor): self._sort_formats(formats) duration = parse_duration(self._search_regex( - r'\(([0-9:]+)\)</span></h1>', webpage, 'duration', fatal=False)) + r'\(([0-9:]+)\)</span>', webpage, 'duration', fatal=False)) return { 'id': video_id, diff --git a/youtube_dl/extractor/walla.py b/youtube_dl/extractor/walla.py new file mode 100644 index 000000000..672bda7a7 --- /dev/null +++ b/youtube_dl/extractor/walla.py @@ -0,0 +1,89 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .subtitles import SubtitlesInfoExtractor +from ..utils import ( + xpath_text, + int_or_none, +) + + +class WallaIE(SubtitlesInfoExtractor): + _VALID_URL = r'http://vod\.walla\.co\.il/[^/]+/(?P<id>\d+)/(?P<display_id>.+)' + _TEST = { + 'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one', + 'info_dict': { + 'id': '2642630', + 'display_id': 'one-direction-all-for-one', + 'ext': 'flv', + 'title': 'וואן דיירקשן: ההיסטריה', + 'description': 'md5:de9e2512a92442574cdb0913c49bc4d8', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 3600, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + _SUBTITLE_LANGS = { + 'עברית': 'heb', + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + video = self._download_xml( + 'http://video2.walla.co.il/?w=null/null/%s/@@/video/flv_pl' % video_id, + display_id) + + item = video.find('./items/item') + + title = xpath_text(item, './title', 'title') + description = xpath_text(item, './synopsis', 'description') + thumbnail = xpath_text(item, './preview_pic', 'thumbnail') + duration = int_or_none(xpath_text(item, './duration', 'duration')) + + subtitles = {} + for subtitle in item.findall('./subtitles/subtitle'): + lang = xpath_text(subtitle, './title') + subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = xpath_text(subtitle, './src') + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self.extract_subtitles(video_id, subtitles) + + formats = [] + for quality in item.findall('./qualities/quality'): + format_id = xpath_text(quality, './title') + fmt = { + 'url': 'rtmp://wafla.walla.co.il/vod', + 'play_path': xpath_text(quality, './src'), + 'player_url': 'http://isc.walla.co.il/w9/swf/video_swf/vod/WallaMediaPlayerAvod.swf', + 'page_url': url, + 'ext': 'flv', + 'format_id': xpath_text(quality, './title'), + } + m = re.search(r'^(?P<height>\d+)[Pp]', format_id) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/washingtonpost.py b/youtube_dl/extractor/washingtonpost.py index cb8f0887d..88bbbb219 100644 --- a/youtube_dl/extractor/washingtonpost.py +++ b/youtube_dl/extractor/washingtonpost.py @@ -13,6 +13,9 @@ class WashingtonPostIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _TEST = { 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', + 'info_dict': { + 'title': 'Sinkhole of bureaucracy', + }, 'playlist': [{ 'md5': 'c3f4b4922ffa259243f68e928db2db8c', 'info_dict': { diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index a584e0896..bf9e40bad 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -2,29 +2,47 @@ from __future__ import unicode_literals import re +import hashlib from .common import InfoExtractor from ..utils import ( + ExtractorError, unified_strdate, ) class WatIE(InfoExtractor): - _VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html' + _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html' IE_NAME = 'wat.tv' - _TEST = { - 'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', - 'info_dict': { - 'id': '10631273', - 'ext': 'mp4', - 'title': 'World War Z - Philadelphia VOST', - 'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', + _TESTS = [ + { + 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', + 'md5': 'ce70e9223945ed26a8056d413ca55dc9', + 'info_dict': { + 'id': '11713067', + 'display_id': 'soupe-figues-l-orange-aux-epices', + 'ext': 'mp4', + 'title': 'Soupe de figues à l\'orange et aux épices', + 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.', + 'upload_date': '20140819', + 'duration': 120, + }, }, - 'params': { - # Sometimes wat serves the whole file with the --test option - 'skip_download': True, + { + 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', + 'md5': 'fbc84e4378165278e743956d9c1bf16b', + 'info_dict': { + 'id': '11713075', + 'display_id': 'gregory-lemarchal-voix-ange', + 'ext': 'mp4', + 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)', + 'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3', + 'upload_date': '20140816', + 'duration': 2910, + }, + 'skip': "Ce contenu n'est pas disponible pour l'instant.", }, - } + ] def download_video_info(self, real_id): # 'contentv4' is used in the website, but it also returns the related @@ -36,13 +54,25 @@ class WatIE(InfoExtractor): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] mobj = re.match(self._VALID_URL, url) - short_id = mobj.group('shortID') - webpage = self._download_webpage(url, short_id) + short_id = mobj.group('short_id') + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id or short_id) real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') video_info = self.download_video_info(real_id) + + error_desc = video_info.get('error_desc') + if error_desc: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error_desc), expected=True) + + geo_list = video_info.get('geoList') + country = geo_list[0] if geo_list else '' + chapters = video_info['chapters'] first_chapter = chapters[0] + files = video_info['files'] + first_file = files[0] if real_id_for_chapter(first_chapter) != real_id: self.to_screen('Multipart video detected') @@ -61,12 +91,47 @@ class WatIE(InfoExtractor): upload_date = unified_strdate(first_chapter['date_diffusion']) # Otherwise we can continue and extract just one part, we have to use # the short id for getting the video url + + formats = [{ + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'format_id': 'Mobile', + }] + + fmts = [('SD', 'web')] + if first_file.get('hasHD'): + fmts.append(('HD', 'webhd')) + + def compute_token(param): + timestamp = '%08x' % int(self._download_webpage( + 'http://www.wat.tv/servertime', real_id, + 'Downloading server time').split('|')[0]) + magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564' + return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp) + + for fmt in fmts: + webid = '/%s/%s' % (fmt[1], real_id) + video_url = self._download_webpage( + 'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country), + real_id, + 'Downloding %s video URL' % fmt[0], + 'Failed to download %s video URL' % fmt[0], + False) + if not video_url: + continue + formats.append({ + 'url': video_url, + 'ext': 'mp4', + 'format_id': fmt[0], + }) + return { 'id': real_id, - 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'display_id': display_id, 'title': first_chapter['title'], 'thumbnail': first_chapter['preview'], 'description': first_chapter['description'], 'view_count': video_info['views'], 'upload_date': upload_date, + 'duration': first_file['duration'], + 'formats': formats, } diff --git a/youtube_dl/extractor/wayofthemaster.py b/youtube_dl/extractor/wayofthemaster.py new file mode 100644 index 000000000..af7bb8b49 --- /dev/null +++ b/youtube_dl/extractor/wayofthemaster.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class WayOfTheMasterIE(InfoExtractor): + _VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])' + + _TEST = { + 'url': 'http://www.wayofthemaster.com/hbks.shtml', + 'md5': '5316b57487ada8480606a93cb3d18d24', + 'info_dict': { + 'id': 'hbks', + 'ext': 'mp4', + 'title': 'Intelligent Design vs. Evolution', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex( + r'<img src="images/title_[^"]+".*?alt="([^"]+)"', + webpage, 'title', default=None) + if title is None: + title = self._html_search_regex( + r'<title>(.*?)</title>', webpage, 'page title') + + url_base = self._search_regex( + r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"', + webpage, 'URL base') + formats = [{ + 'format_id': 'low', + 'quality': 1, + 'url': url_base + '_low.mp4', + }, { + 'format_id': 'high', + 'quality': 2, + 'url': url_base + '_high.mp4', + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 54d37da61..93a6e6454 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -224,4 +224,4 @@ class WDRMausIE(InfoExtractor): 'upload_date': upload_date, } -# TODO test _1
\ No newline at end of file +# TODO test _1 diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py index b24297a40..20bb039d3 100644 --- a/youtube_dl/extractor/weibo.py +++ b/youtube_dl/extractor/weibo.py @@ -41,7 +41,7 @@ class WeiboIE(InfoExtractor): videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u) player_url = videos_urls[-1] m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html', - player_url) + player_url) if m_sina is not None: self.to_screen('Sina video detected') sina_id = m_sina.group(1) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index c27dda944..d6dec25ca 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -37,7 +37,7 @@ class WimpIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL') + r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL') if YoutubeIE.suitable(video_url): self.to_screen('Found YouTube video') return { diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index e6bfa9e14..748443f81 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,13 +1,14 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor +from ..utils import ExtractorError, compat_urllib_request class WistiaIE(InfoExtractor): _VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)' + _API_URL = 'http://fast.wistia.com/embed/medias/{0:}.json' _TEST = { 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt', @@ -24,11 +25,13 @@ class WistiaIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - data_json = self._html_search_regex( - r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data') - - data = json.loads(data_json) + request = compat_urllib_request.Request(self._API_URL.format(video_id)) + request.add_header('Referer', url) # Some videos require this. + data_json = self._download_json(request, video_id) + if data_json.get('error'): + raise ExtractorError('Error while getting the playlist', + expected=True) + data = data_json['media'] formats = [] thumbnails = [] diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index 4e89acd81..d5c26a032 100644 --- a/youtube_dl/extractor/worldstarhiphop.py +++ b/youtube_dl/extractor/worldstarhiphop.py @@ -13,37 +13,35 @@ class WorldStarHipHopIE(InfoExtractor): "info_dict": { "id": "wshh6a7q1ny0G34ZwuIO", "ext": "mp4", - "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" + "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" } } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - webpage_src = self._download_webpage(url, video_id) - - m_vevo_id = re.search(r'videoId=(.*?)&?', - webpage_src) + m_vevo_id = re.search(r'videoId=(.*?)&?', webpage) if m_vevo_id is not None: return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') video_url = self._search_regex( - r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL') + r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL') if 'youtube' in video_url: return self.url_result(video_url, ie='Youtube') video_title = self._html_search_regex( - r"<title>(.*)</title>", webpage_src, 'title') + r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>', + webpage, 'title') # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. thumbnail = self._html_search_regex( - r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail', + r'rel="image_src" href="(.*)" />', webpage, 'thumbnail', fatal=False) if not thumbnail: - _title = r"""candytitles.*>(.*)</span>""" - mobj = re.search(_title, webpage_src) + _title = r'candytitles.*>(.*)</span>' + mobj = re.search(_title, webpage) if mobj is not None: video_title = mobj.group(1) @@ -53,4 +51,3 @@ class WorldStarHipHopIE(InfoExtractor): 'title': video_title, 'thumbnail': thumbnail, } - diff --git a/youtube_dl/extractor/wrzuta.py b/youtube_dl/extractor/wrzuta.py index 34dd6d952..c42764921 100644 --- a/youtube_dl/extractor/wrzuta.py +++ b/youtube_dl/extractor/wrzuta.py @@ -27,15 +27,15 @@ class WrzutaIE(InfoExtractor): 'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd', }, }, { - 'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad', - 'md5': '1e546a18e1c22ac6e9adce17b8961ff5', + 'url': 'http://jolka85.wrzuta.pl/audio/063jOPX5ue2/liber_natalia_szroeder_-_teraz_ty', + 'md5': 'bc78077859bea7bcfe4295d7d7fc9025', 'info_dict': { - 'id': '9oXJqdcndqv', + 'id': '063jOPX5ue2', 'ext': 'ogg', - 'title': 'David Guetta & Showtek ft. Vassy - Bad', - 'duration': 270, - 'uploader_id': 'w729', - 'description': 'md5:4628f01c666bbaaecefa83476cfa794a', + 'title': 'Liber & Natalia Szroeder - Teraz Ty', + 'duration': 203, + 'uploader_id': 'jolka85', + 'description': 'md5:2d2b6340f9188c8c4cd891580e481096', }, }] @@ -49,16 +49,17 @@ class WrzutaIE(InfoExtractor): quality = qualities(['SD', 'MQ', 'HQ', 'HD']) - audio_table = {'flv': 'mp3', 'webm': 'ogg'} + audio_table = {'flv': 'mp3', 'webm': 'ogg', '???': 'mp3'} embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id) formats = [] for media in embedpage['url']: + fmt = media['type'].split('@')[0] if typ == 'audio': - ext = audio_table[media['type'].split('@')[0]] + ext = audio_table.get(fmt, fmt) else: - ext = media['type'].split('@')[0] + ext = fmt formats.append({ 'format_id': '%s_%s' % (ext, media['quality'].lower()), diff --git a/youtube_dl/extractor/xbef.py b/youtube_dl/extractor/xbef.py index 71bd7c463..1b4e88365 100644 --- a/youtube_dl/extractor/xbef.py +++ b/youtube_dl/extractor/xbef.py @@ -47,4 +47,3 @@ class XBefIE(InfoExtractor): 'thumbnail': thumbnail, 'age_limit': 18, } - diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py new file mode 100644 index 000000000..a9aa72e73 --- /dev/null +++ b/youtube_dl/extractor/xboxclips.py @@ -0,0 +1,57 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + float_or_none, + int_or_none, +) + + +class XboxClipsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' + _TEST = { + 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', + 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', + 'info_dict': { + 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', + 'ext': 'mp4', + 'title': 'Iabdulelah playing Upload Studio', + 'filesize_approx': 28101836.8, + 'timestamp': 1407388500, + 'upload_date': '20140807', + 'duration': 56, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'>Link: <a href="([^"]+)">', webpage, 'video URL') + title = self._html_search_regex( + r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title') + timestamp = parse_iso8601(self._html_search_regex( + r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False)) + filesize = float_or_none(self._html_search_regex( + r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024) + duration = int_or_none(self._html_search_regex( + r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'>Views: (\d+)<', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'timestamp': timestamp, + 'filesize_approx': filesize, + 'duration': duration, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 5374495f9..6b37bcbc9 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -14,11 +14,10 @@ from ..utils import ( class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" - _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' + _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' _TESTS = [ { 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', - 'md5': '8281348b8d3c53d39fffb377d24eac4e', 'info_dict': { 'id': '1509445', 'ext': 'mp4', @@ -31,7 +30,6 @@ class XHamsterIE(InfoExtractor): }, { 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', - 'md5': '4cbd8d56708ecb4fb4124c23e4acb81a', 'info_dict': { 'id': '2221348', 'ext': 'mp4', @@ -44,7 +42,7 @@ class XHamsterIE(InfoExtractor): } ] - def _real_extract(self,url): + def _real_extract(self, url): def extract_video_url(webpage): mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage) if mp4 is None: @@ -69,17 +67,17 @@ class XHamsterIE(InfoExtractor): description = mobj.group(1) if mobj else None upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'', - webpage, 'upload date', fatal=False) + webpage, 'upload date', fatal=False) if upload_date: upload_date = unified_strdate(upload_date) uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)', - webpage, 'uploader id', default='anonymous') + webpage, 'uploader id', default='anonymous') thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>', - webpage, 'duration', fatal=False)) + webpage, 'duration', fatal=False)) view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False) if view_count: diff --git a/youtube_dl/extractor/xminus.py b/youtube_dl/extractor/xminus.py new file mode 100644 index 000000000..8c6241aed --- /dev/null +++ b/youtube_dl/extractor/xminus.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_chr, + compat_ord, +) +from ..utils import ( + int_or_none, + parse_filesize, +) + + +class XMinusIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html', + 'md5': '401a15f2d2dcf6d592cb95528d72a2a8', + 'info_dict': { + 'id': '4542', + 'ext': 'mp3', + 'title': 'Леонид Агутин-Песенка шофера', + 'duration': 156, + 'tbr': 320, + 'filesize_approx': 5900000, + 'view_count': int, + 'description': 'md5:03238c5b663810bc79cf42ef3c03e371', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + artist = self._html_search_regex( + r'minus_track\.artist="(.+?)"', webpage, 'artist') + title = artist + '-' + self._html_search_regex( + r'minus_track\.title="(.+?)"', webpage, 'title') + duration = int_or_none(self._html_search_regex( + r'minus_track\.dur_sec=\'([0-9]*?)\'', + webpage, 'duration', fatal=False)) + filesize_approx = parse_filesize(self._html_search_regex( + r'<div class="filesize[^"]*"></div>\s*([0-9.]+\s*[a-zA-Z][bB])', + webpage, 'approximate filesize', fatal=False)) + tbr = int_or_none(self._html_search_regex( + r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps', + webpage, 'bitrate', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'<div class="quality.*?► ([0-9]+)', + webpage, 'view count', fatal=False)) + description = self._html_search_regex( + r'(?s)<div id="song_texts">(.*?)</div><br', + webpage, 'song lyrics', fatal=False) + if description: + description = re.sub(' *\r *', '\n', description) + + enc_token = self._html_search_regex( + r'minus_track\.tkn="(.+?)"', webpage, 'enc_token') + token = ''.join( + c if pos == 3 else compat_chr(compat_ord(c) - 1) + for pos, c in enumerate(reversed(enc_token))) + video_url = 'http://x-minus.org/dwlf/%s/%s.mp3' % (video_id, token) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'duration': duration, + 'filesize_approx': filesize_approx, + 'tbr': tbr, + 'view_count': view_count, + 'description': description, + } diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py index 7a73b2430..53ed7ef5a 100644 --- a/youtube_dl/extractor/xnxx.py +++ b/youtube_dl/extractor/xnxx.py @@ -30,14 +30,14 @@ class XNXXIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex(r'flv_url=(.*?)&', - webpage, 'video URL') + webpage, 'video URL') video_url = compat_urllib_parse.unquote(video_url) video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM', - webpage, 'title') + webpage, 'title') video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&', - webpage, 'thumbnail', fatal=False) + webpage, 'thumbnail', fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index b293e2665..38448e7c0 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -20,7 +20,7 @@ class XTubeIE(InfoExtractor): 'id': 'kVTUy_G222_', 'ext': 'mp4', 'title': 'strange erotica', - 'description': 'surreal gay themed erotica...almost an ET kind of thing', + 'description': 'http://www.xtube.com an ET kind of thing', 'uploader': 'greenshowers', 'duration': 450, 'age_limit': 18, @@ -77,9 +77,17 @@ class XTubeIE(InfoExtractor): 'age_limit': 18, } + class XTubeUserIE(InfoExtractor): IE_DESC = 'XTube user profile' _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])' + _TEST = { + 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers', + 'info_dict': { + 'id': 'greenshowers', + }, + 'playlist_mincount': 155, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -89,7 +97,7 @@ class XTubeUserIE(InfoExtractor): url, username, note='Retrieving profile page') video_count = int(self._search_regex( - r'<strong>%s\'s Videos \(([0-9]+)\)</strong>'%username, profile_page, + r'<strong>%s\'s Videos \(([0-9]+)\)</strong>' % username, profile_page, 'video count')) PAGE_SIZE = 25 diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index d84be2562..0fdb12243 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import itertools @@ -6,6 +7,7 @@ import re from .common import InfoExtractor, SearchInfoExtractor from ..utils import ( + ExtractorError, compat_urllib_parse, compat_urlparse, clean_html, @@ -15,7 +17,7 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html' + _VALID_URL = r'(?P<url>(?P<host>https?://(?:[a-zA-Z]{2}\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?P<display_id>.+?)-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -25,6 +27,7 @@ class YahooIE(InfoExtractor): 'ext': 'mp4', 'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith', + 'duration': 6863, }, }, { @@ -34,25 +37,107 @@ class YahooIE(InfoExtractor): 'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9', 'ext': 'mp4', 'title': 'Codefellas - The Cougar Lies with Spanish Moss', - 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', + 'description': 'md5:66b627ab0a282b26352136ca96ce73c1', + 'duration': 151, }, }, { - 'url': 'https://movies.yahoo.com/video/world-loves-spider-man-190819223.html', - 'md5': '410b7104aa9893b765bc22787a22f3d9', + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '60e8ac193d8fb71997caa8fce54c6460', 'info_dict': { - 'id': '516ed8e2-2c4f-339f-a211-7a8b49d30845', + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', 'ext': 'mp4', - 'title': 'The World Loves Spider-Man', - 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + 'duration': 170, } + }, + { + 'url': 'https://tw.screen.yahoo.com/taipei-opinion-poll/選情站報-街頭民調-台北市篇-102823042.html', + 'md5': '92a7fdd8a08783c68a174d7aa067dde8', + 'info_dict': { + 'id': '7a23b569-7bea-36cb-85b9-bd5301a0a1fb', + 'ext': 'mp4', + 'title': '選情站報 街頭民調 台北市篇', + 'description': '選情站報 街頭民調 台北市篇', + 'duration': 429, + } + }, + { + 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', + 'md5': '0b51660361f0e27c9789e7037ef76f4b', + 'info_dict': { + 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', + 'ext': 'mp4', + 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', + 'description': 'md5:f66c890e1490f4910a9953c941dee944', + 'duration': 97, + } + }, + { + 'url': 'https://ca.sports.yahoo.com/video/program-makes-hockey-more-affordable-013127711.html', + 'md5': '57e06440778b1828a6079d2f744212c4', + 'info_dict': { + 'id': 'c9fa2a36-0d4d-3937-b8f6-cc0fb1881e73', + 'ext': 'mp4', + 'title': 'Program that makes hockey more affordable not offered in Manitoba', + 'description': 'md5:c54a609f4c078d92b74ffb9bf1f496f4', + 'duration': 121, + } + }, { + 'url': 'https://ca.finance.yahoo.com/news/20-most-valuable-brands-world-112600775.html', + 'md5': '3e401e4eed6325aa29d9b96125fd5b4f', + 'info_dict': { + 'id': 'c1b4c09c-8ed8-3b65-8b05-169c55358a83', + 'ext': 'mp4', + 'title': "Apple Is The World's Most Valuable Brand", + 'description': 'md5:73eabc1a11c6f59752593b2ceefa1262', + 'duration': 21, + } + }, { + 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + 'md5': '67010fdf3a08d290e060a4dd96baa07b', + 'info_dict': { + 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', + 'ext': 'mp4', + 'title': 'China Moses Is Crazy About the Blues', + 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', + 'duration': 128, + } + }, { + 'url': 'https://in.lifestyle.yahoo.com/video/connect-dots-dark-side-virgo-090247395.html', + 'md5': 'd9a083ccf1379127bf25699d67e4791b', + 'info_dict': { + 'id': '52aeeaa3-b3d1-30d8-9ef8-5d0cf05efb7c', + 'ext': 'mp4', + 'title': 'Connect the Dots: Dark Side of Virgo', + 'description': 'md5:1428185051cfd1949807ad4ff6d3686a', + 'duration': 201, + } + }, { + 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', + 'only_matching': True, } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) + display_id = mobj.group('display_id') + url = mobj.group('url') + host = mobj.group('host') + webpage = self._download_webpage(url, display_id) + + # Look for iframed media first + iframe_m = re.search(r'<iframe[^>]+src="(/video/.+?-\d+\.html\?format=embed.*?)"', webpage) + if iframe_m: + iframepage = self._download_webpage( + host + iframe_m.group(1), display_id, 'Downloading iframe webpage') + items_json = self._search_regex( + r'mediaItems: (\[.+?\])$', iframepage, 'items', flags=re.MULTILINE, default=None) + if items_json: + items = json.loads(items_json) + video_id = items[0]['id'] + return self._get_info(video_id, display_id, webpage) items_json = self._search_regex( r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, @@ -60,22 +145,25 @@ class YahooIE(InfoExtractor): if items_json is None: CONTENT_ID_REGEXES = [ r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"' + r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', + r'"first_videoid"\s*:\s*"([^"]+)"', ] - long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') - video_id = long_id + video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') else: items = json.loads(items_json) info = items['mediaItems']['query']['results']['mediaObj'][0] # The 'meta' field is not always in the video webpage, we request it # from another page - long_id = info['id'] - return self._get_info(long_id, video_id, webpage) + video_id = info['id'] + return self._get_info(video_id, display_id, webpage) - def _get_info(self, long_id, video_id, webpage): + def _get_info(self, video_id, display_id, webpage): + region = self._search_regex( + r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', + webpage, 'region', fatal=False, default='US') query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' - ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"' - ' AND protocol="http"' % long_id) + ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="%s"' + ' AND protocol="http"' % (video_id, region)) data = compat_urllib_parse.urlencode({ 'q': query, 'env': 'prod', @@ -83,9 +171,17 @@ class YahooIE(InfoExtractor): }) query_result = self._download_json( 'http://video.query.yahoo.com/v1/public/yql?' + data, - video_id, 'Downloading video info') + display_id, 'Downloading video info') + info = query_result['query']['results']['mediaObj'][0] - meta = info['meta'] + meta = info.get('meta') + + if not meta: + msg = info['status'].get('msg') + if msg: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, msg), expected=True) + raise ExtractorError('Unable to extract media object meta') formats = [] for s in info['streams']: @@ -112,36 +208,15 @@ class YahooIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'title': meta['title'], 'formats': formats, 'description': clean_html(meta['description']), 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), + 'duration': int_or_none(meta.get('duration')), } -class YahooNewsIE(YahooIE): - IE_NAME = 'yahoo:news' - _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html' - - _TESTS = [{ - 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', - 'md5': '67010fdf3a08d290e060a4dd96baa07b', - 'info_dict': { - 'id': '104538833', - 'ext': 'mp4', - 'title': 'China Moses Is Crazy About the Blues', - 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', - }, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id') - return self._get_info(long_id, video_id, webpage) - - class YahooSearchIE(SearchInfoExtractor): IE_DESC = 'Yahoo screen search' _MAX_RESULTS = 1000 @@ -154,7 +229,7 @@ class YahooSearchIE(SearchInfoExtractor): for pagenum in itertools.count(0): result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) info = self._download_json(result_url, query, - note='Downloading results page '+str(pagenum+1)) + note='Downloading results page ' + str(pagenum + 1)) m = info['m'] results = info['results'] diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py new file mode 100644 index 000000000..7b621a9e3 --- /dev/null +++ b/youtube_dl/extractor/ynet.py @@ -0,0 +1,50 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import compat_urllib_parse + + +class YnetIE(InfoExtractor): + _VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html' + _TESTS = [ + { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html', + 'info_dict': { + 'id': 'L-11659-99244', + 'ext': 'flv', + 'title': 'איש לא יודע מאיפה באנו', + 'thumbnail': 're:^https?://.*\.jpg', + } + }, { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html', + 'info_dict': { + 'id': 'L-8859-84418', + 'ext': 'flv', + 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין", + 'thumbnail': 're:^https?://.*\.jpg', + } + } + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage)) + config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config')) + f4m_url = config['clip']['url'] + title = self._og_search_title(webpage) + m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title) + if m: + title = m.group('title') + + return { + 'id': video_id, + 'title': title, + 'formats': self._extract_f4m_formats(f4m_url, video_id), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index fcb5ff758..c642075dc 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -9,40 +9,30 @@ from ..utils import ( class YouJizzIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$' + _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/[^/#?]+-(?P<id>[0-9]+)\.html(?:$|[?#])' _TEST = { 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', - 'file': '2189178.flv', 'md5': '07e15fa469ba384c7693fd246905547c', 'info_dict': { + 'id': '2189178', + 'ext': 'flv', "title": "Zeichentrick 1", "age_limit": 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('videoid') - - # Get webpage content + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) - - # Get the video title - video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>', - webpage, 'title').strip() - - # Get the embed page - result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage) - if result is None: - raise ExtractorError('ERROR: unable to extract embed page') - - embed_page_url = result.group(0).strip() - video_id = result.group('videoid') - - webpage = self._download_webpage(embed_page_url, video_id) + video_title = self._html_search_regex( + r'<title>\s*(.*)\s*</title>', webpage, 'title') + + embed_page_url = self._search_regex( + r'(https?://www.youjizz.com/videos/embed/[0-9]+)', + webpage, 'embed page') + webpage = self._download_webpage( + embed_page_url, video_id, note='downloading embed page') # Get the video URL m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage) diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index a8fd40c83..97b98bbe8 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -1,6 +1,7 @@ # coding: utf-8 -import json +from __future__ import unicode_literals + import math import random import re @@ -13,35 +14,42 @@ from ..utils import ( class YoukuIE(InfoExtractor): - _VALID_URL = r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P<ID>[A-Za-z0-9]+)(?:\.html|/v\.swf|)' - _TEST = { - u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html", - u"file": u"XNDgyMDQ2NTQw_part00.flv", - u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b", - u"params": {u"test": False}, - u"info_dict": { - u"title": u"youtube-dl test video \"'/\\ä↭𝕐" + _VALID_URL = r'''(?x) + (?: + http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)| + youku:) + (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|) + ''' + _TEST = { + 'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html', + 'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b', + 'params': { + 'test': False + }, + 'info_dict': { + 'id': 'XNDgyMDQ2NTQw_part00', + 'ext': 'flv', + 'title': 'youtube-dl test video "\'/\\ä↭𝕐' } } - def _gen_sid(self): nowTime = int(time.time() * 1000) - random1 = random.randint(1000,1998) - random2 = random.randint(1000,9999) + random1 = random.randint(1000, 1998) + random2 = random.randint(1000, 9999) - return "%d%d%d" %(nowTime,random1,random2) + return "%d%d%d" % (nowTime, random1, random2) def _get_file_ID_mix_string(self, seed): mixed = [] source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") seed = float(seed) for i in range(len(source)): - seed = (seed * 211 + 30031) % 65536 - index = math.floor(seed / 65536 * len(source)) + seed = (seed * 211 + 30031) % 65536 + index = math.floor(seed / 65536 * len(source)) mixed.append(source[int(index)]) source.remove(source[int(index)]) - #return ''.join(mixed) + # return ''.join(mixed) return mixed def _get_file_id(self, fileId, seed): @@ -55,60 +63,52 @@ class YoukuIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('ID') + video_id = mobj.group('id') info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id - jsondata = self._download_webpage(info_url, video_id) - - self.report_extraction(video_id) - try: - config = json.loads(jsondata) - error_code = config['data'][0].get('error_code') - if error_code: - # -8 means blocked outside China. - error = config['data'][0].get('error') # Chinese and English, separated by newline. - raise ExtractorError(error or u'Server reported error %i' % error_code, - expected=True) - - video_title = config['data'][0]['title'] - seed = config['data'][0]['seed'] - - format = self._downloader.params.get('format', None) - supported_format = list(config['data'][0]['streamfileids'].keys()) - - if format is None or format == 'best': - if 'hd2' in supported_format: - format = 'hd2' - else: - format = 'flv' - ext = u'flv' - elif format == 'worst': - format = 'mp4' - ext = u'mp4' - else: - format = 'flv' - ext = u'flv' + config = self._download_json(info_url, video_id) + error_code = config['data'][0].get('error_code') + if error_code: + # -8 means blocked outside China. + error = config['data'][0].get('error') # Chinese and English, separated by newline. + raise ExtractorError(error or 'Server reported error %i' % error_code, + expected=True) - fileid = config['data'][0]['streamfileids'][format] - keys = [s['k'] for s in config['data'][0]['segs'][format]] - # segs is usually a dictionary, but an empty *list* if an error occured. - except (UnicodeDecodeError, ValueError, KeyError): - raise ExtractorError(u'Unable to extract info section') + video_title = config['data'][0]['title'] + seed = config['data'][0]['seed'] - files_info=[] + format = self._downloader.params.get('format', None) + supported_format = list(config['data'][0]['streamfileids'].keys()) + + # TODO proper format selection + if format is None or format == 'best': + if 'hd2' in supported_format: + format = 'hd2' + else: + format = 'flv' + ext = 'flv' + elif format == 'worst': + format = 'mp4' + ext = 'mp4' + else: + format = 'flv' + ext = 'flv' + + fileid = config['data'][0]['streamfileids'][format] + keys = [s['k'] for s in config['data'][0]['segs'][format]] + # segs is usually a dictionary, but an empty *list* if an error occured. + + files_info = [] sid = self._gen_sid() fileid = self._get_file_id(fileid, seed) - #column 8,9 of fileid represent the segment number - #fileid[7:9] should be changed + # column 8,9 of fileid represent the segment number + # fileid[7:9] should be changed for index, key in enumerate(keys): - temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) - download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) + download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) info = { 'id': '%s_part%02d' % (video_id, index), diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index d456c4da5..d9c06a2ee 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -23,7 +23,6 @@ class YouPornIE(InfoExtractor): _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))' _TEST = { 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', - 'md5': '71ec5fcfddacf80f495efa8b6a8d9a89', 'info_dict': { 'id': '505835', 'ext': 'mp4', @@ -46,11 +45,13 @@ class YouPornIE(InfoExtractor): age_limit = self._rta_search(webpage) # Get JSON parameters - json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters') + json_params = self._search_regex( + r'var currentVideo = new Video\((.*)\)[,;]', + webpage, 'JSON parameters') try: params = json.loads(json_params) except: - raise ExtractorError(u'Invalid JSON') + raise ExtractorError('Invalid JSON') self.report_extraction(video_id) try: @@ -65,7 +66,7 @@ class YouPornIE(InfoExtractor): # Get all of the links from the page DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' download_list_html = self._search_regex(DOWNLOAD_LIST_RE, - webpage, 'download list').strip() + webpage, 'download list').strip() LINK_RE = r'<a href="([^"]+)">' links = re.findall(LINK_RE, download_list_html) @@ -74,7 +75,7 @@ class YouPornIE(InfoExtractor): for encrypted_link in encrypted_links: link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8') links.append(link) - + formats = [] for link in links: # A link looks like this: @@ -104,8 +105,8 @@ class YouPornIE(InfoExtractor): self._sort_formats(formats) if not formats: - raise ExtractorError(u'ERROR: no known formats available for video') - + raise ExtractorError('ERROR: no known formats available for video') + return { 'id': video_id, 'uploader': video_uploader, diff --git a/youtube_dl/extractor/yourupload.py b/youtube_dl/extractor/yourupload.py new file mode 100644 index 000000000..40fc4165f --- /dev/null +++ b/youtube_dl/extractor/yourupload.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class YourUploadIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)? + (?:yourupload\.com/watch| + embed\.yourupload\.com| + embed\.yucache\.net + )/(?P<id>[A-Za-z0-9]+) + ''' + _TESTS = [ + { + 'url': 'http://yourupload.com/watch/14i14h', + 'md5': 'bf5c2f95c4c917536e80936af7bc51e1', + 'info_dict': { + 'id': '14i14h', + 'ext': 'mp4', + 'title': 'BigBuckBunny_320x180.mp4', + 'thumbnail': 're:^https?://.*\.jpe?g', + } + }, + { + 'url': 'http://embed.yourupload.com/14i14h', + 'only_matching': True, + }, + { + 'url': 'http://embed.yucache.net/14i14h?client_file_id=803349', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://embed.yucache.net/{0:}'.format(video_id) + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + url = self._og_search_video_url(webpage) + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index c48d1b8ef..7b6179a2a 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1,137 +1,194 @@ # coding: utf-8 -import errno -import io +from __future__ import unicode_literals + + import itertools import json import os.path import re +import time import traceback from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor from ..jsinterp import JSInterpreter from ..swfinterp import SWFInterpreter -from ..utils import ( +from ..compat import ( compat_chr, compat_parse_qs, compat_urllib_parse, compat_urllib_request, compat_urlparse, compat_str, - +) +from ..utils import ( clean_html, - get_cachedir, - get_element_by_id, - get_element_by_attribute, ExtractorError, + get_element_by_attribute, + get_element_by_id, int_or_none, - PagedList, + OnDemandPagedList, + orderedSet, unescapeHTML, unified_strdate, - orderedSet, - write_json_file, uppercase_escape, ) + class YoutubeBaseInfoExtractor(InfoExtractor): """Provide base functions for Youtube extractors""" _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' - _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' - _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' + _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' _NETRC_MACHINE = 'youtube' # If True it will raise an error if no login info is provided _LOGIN_REQUIRED = False def _set_language(self): - return bool(self._download_webpage( - self._LANG_URL, None, - note=u'Setting language', errnote='unable to set language', - fatal=False)) + self._set_cookie( + '.youtube.com', 'PREF', 'f1=50000000&hl=en', + # YouTube sets the expire time to about two months + expire_time=time.time() + 2 * 30 * 24 * 3600) def _login(self): + """ + Attempt to log in to YouTube. + True is returned if successful or skipped. + False is returned if login failed. + + If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. + """ (username, password) = self._get_login_info() # No authentication to be performed if username is None: if self._LOGIN_REQUIRED: - raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) - return False + raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) + return True login_page = self._download_webpage( self._LOGIN_URL, None, - note=u'Downloading login page', - errnote=u'unable to fetch login page', fatal=False) + note='Downloading login page', + errnote='unable to fetch login page', fatal=False) if login_page is False: return galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', - login_page, u'Login GALX parameter') + login_page, 'Login GALX parameter') # Log in login_form_strs = { - u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', - u'Email': username, - u'GALX': galx, - u'Passwd': password, - u'PersistentCookie': u'yes', - u'_utf8': u'霱', - u'bgresponse': u'js_disabled', - u'checkConnection': u'', - u'checkedDomains': u'youtube', - u'dnConn': u'', - u'pstMsg': u'0', - u'rmShown': u'1', - u'secTok': u'', - u'signIn': u'Sign in', - u'timeStmp': u'', - u'service': u'youtube', - u'uilel': u'3', - u'hl': u'en_US', + 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', + 'Email': username, + 'GALX': galx, + 'Passwd': password, + + 'PersistentCookie': 'yes', + '_utf8': '霱', + 'bgresponse': 'js_disabled', + 'checkConnection': '', + 'checkedDomains': 'youtube', + 'dnConn': '', + 'pstMsg': '0', + 'rmShown': '1', + 'secTok': '', + 'signIn': 'Sign in', + 'timeStmp': '', + 'service': 'youtube', + 'uilel': '3', + 'hl': 'en_US', } + # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # chokes on unicode - login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) + login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') req = compat_urllib_request.Request(self._LOGIN_URL, login_data) login_results = self._download_webpage( req, None, - note=u'Logging in', errnote=u'unable to log in', fatal=False) + note='Logging in', errnote='unable to log in', fatal=False) if login_results is False: return False - if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: - self._downloader.report_warning(u'unable to log in: bad username or password') - return False - return True - def _confirm_age(self): - age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - req = compat_urllib_request.Request(self._AGE_URL, - compat_urllib_parse.urlencode(age_form).encode('ascii')) + if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: + raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) + + # Two-Factor + # TODO add SMS and phone call support - these require making a request and then prompting the user + + if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: + tfa_code = self._get_tfa_info() + + if tfa_code is None: + self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>') + self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)') + return False + + # Unlike the first login form, secTok and timeStmp are both required for the TFA form + + match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) + if match is None: + self._downloader.report_warning('Failed to get secTok - did the page structure change?') + secTok = match.group(1) + match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) + if match is None: + self._downloader.report_warning('Failed to get timeStmp - did the page structure change?') + timeStmp = match.group(1) + + tfa_form_strs = { + 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', + 'smsToken': '', + 'smsUserPin': tfa_code, + 'smsVerifyPin': 'Verify', + + 'PersistentCookie': 'yes', + 'checkConnection': '', + 'checkedDomains': 'youtube', + 'pstMsg': '1', + 'secTok': secTok, + 'timeStmp': timeStmp, + 'service': 'youtube', + 'hl': 'en_US', + } + tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items()) + tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') + + tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) + tfa_results = self._download_webpage( + tfa_req, None, + note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) + + if tfa_results is False: + return False + + if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: + self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.') + return False + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: + self._downloader.report_warning('unable to log in - did the page structure change?') + return False + if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: + self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.') + return False - self._download_webpage( - req, None, - note=u'Confirming age', errnote=u'Unable to confirm age') + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: + self._downloader.report_warning('unable to log in: bad username or password') + return False return True def _real_initialize(self): if self._downloader is None: return - if not self._set_language(): - return + self._set_language() if not self._login(): return - self._confirm_age() class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): - IE_DESC = u'YouTube.com' + IE_DESC = 'YouTube.com' _VALID_URL = r"""(?x)^ ( - (?:https?://|//)? # http(s):// or protocol-independent URL (optional) + (?:https?://|//) # http(s):// or protocol-independent URL (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| (?:www\.)?deturl\.com/www\.youtube\.com/| (?:www\.)?pwnyoutube\.com/| @@ -140,7 +197,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: - (?:(?:v|embed|e)/) # v/ or embed/ or e/ + (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |(?: # or the v= param in all its forms (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! @@ -149,10 +206,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): ) )) |youtu\.be/ # just youtu.be/xxxx - |https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= + |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= ) )? # all until now is optional -> you can pass the naked ID ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID + (?!.*?&list=) # combined list/video URLs are handled by the playlist IE (?(1).+)? # if we found the ID, everything can follow $""" _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' @@ -201,6 +259,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '138': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, + '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, + '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, # Dash mp4 audio '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50}, @@ -214,6 +275,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, + '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'}, '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, @@ -223,128 +285,198 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, + '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, + '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'}, # Dash webm audio - '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50}, + '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, + # Dash webm audio with opus inside + '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, + '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, + '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, + # RTMP (unnamed) '_rtmp': {'protocol': 'rtmp'}, } - IE_NAME = u'youtube' + IE_NAME = 'youtube' _TESTS = [ { - u"url": u"http://www.youtube.com/watch?v=BaW_jenozKc", - u"file": u"BaW_jenozKc.mp4", - u"info_dict": { - u"title": u"youtube-dl test video \"'/\\ä↭𝕐", - u"uploader": u"Philipp Hagemeister", - u"uploader_id": u"phihag", - u"upload_date": u"20121002", - u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .", - u"categories": [u'Science & Technology'], + 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', + 'info_dict': { + 'id': 'BaW_jenozKc', + 'ext': 'mp4', + 'title': 'youtube-dl test video "\'/\\ä↭𝕐', + 'uploader': 'Philipp Hagemeister', + 'uploader_id': 'phihag', + 'upload_date': '20121002', + 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', + 'categories': ['Science & Technology'], + 'like_count': int, + 'dislike_count': int, } }, { - u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY", - u"file": u"UxxajLWwzqY.mp4", - u"note": u"Test generic use_cipher_signature video (#897)", - u"info_dict": { - u"upload_date": u"20120506", - u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]", - u"description": u"md5:fea86fda2d5a5784273df5c7cc994d9f", - u"uploader": u"Icona Pop", - u"uploader_id": u"IconaPop" + 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', + 'note': 'Test generic use_cipher_signature video (#897)', + 'info_dict': { + 'id': 'UxxajLWwzqY', + 'ext': 'mp4', + 'upload_date': '20120506', + 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', + 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f', + 'uploader': 'Icona Pop', + 'uploader_id': 'IconaPop', } }, { - u"url": u"https://www.youtube.com/watch?v=07FYdnEawAQ", - u"file": u"07FYdnEawAQ.mp4", - u"note": u"Test VEVO video with age protection (#956)", - u"info_dict": { - u"upload_date": u"20130703", - u"title": u"Justin Timberlake - Tunnel Vision (Explicit)", - u"description": u"md5:64249768eec3bc4276236606ea996373", - u"uploader": u"justintimberlakeVEVO", - u"uploader_id": u"justintimberlakeVEVO" + 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', + 'note': 'Test VEVO video with age protection (#956)', + 'info_dict': { + 'id': '07FYdnEawAQ', + 'ext': 'mp4', + 'upload_date': '20130703', + 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'description': 'md5:64249768eec3bc4276236606ea996373', + 'uploader': 'justintimberlakeVEVO', + 'uploader_id': 'justintimberlakeVEVO', } }, { - u"url": u"//www.YouTube.com/watch?v=yZIXLfi8CZQ", - u"file": u"yZIXLfi8CZQ.mp4", - u"note": u"Embed-only video (#1746)", - u"info_dict": { - u"upload_date": u"20120608", - u"title": u"Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012", - u"description": u"md5:09b78bd971f1e3e289601dfba15ca4f7", - u"uploader": u"SET India", - u"uploader_id": u"setindia" + 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', + 'note': 'Embed-only video (#1746)', + 'info_dict': { + 'id': 'yZIXLfi8CZQ', + 'ext': 'mp4', + 'upload_date': '20120608', + 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', + 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', + 'uploader': 'SET India', + 'uploader_id': 'setindia' } }, { - u"url": u"http://www.youtube.com/watch?v=a9LDPn-MO4I", - u"file": u"a9LDPn-MO4I.m4a", - u"note": u"256k DASH audio (format 141) via DASH manifest", - u"info_dict": { - u"upload_date": "20121002", - u"uploader_id": "8KVIDEO", - u"description": "No description available.", - u"uploader": "8KVIDEO", - u"title": "UHDTV TEST 8K VIDEO.mp4" + 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', + 'note': '256k DASH audio (format 141) via DASH manifest', + 'info_dict': { + 'id': 'a9LDPn-MO4I', + 'ext': 'm4a', + 'upload_date': '20121002', + 'uploader_id': '8KVIDEO', + 'description': '', + 'uploader': '8KVIDEO', + 'title': 'UHDTV TEST 8K VIDEO.mp4' }, - u"params": { - u"youtube_include_dash_manifest": True, - u"format": "141", + 'params': { + 'youtube_include_dash_manifest': True, + 'format': '141', }, }, # DASH manifest with encrypted signature { - u'url': u'https://www.youtube.com/watch?v=IB3lcPjvWLA', - u'info_dict': { - u'id': u'IB3lcPjvWLA', - u'ext': u'm4a', - u'title': u'Afrojack - The Spark ft. Spree Wilson', - u'description': u'md5:9717375db5a9a3992be4668bbf3bc0a8', - u'uploader': u'AfrojackVEVO', - u'uploader_id': u'AfrojackVEVO', - u'upload_date': u'20131011', + 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', + 'info_dict': { + 'id': 'IB3lcPjvWLA', + 'ext': 'm4a', + 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', + 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', + 'uploader': 'AfrojackVEVO', + 'uploader_id': 'AfrojackVEVO', + 'upload_date': '20131011', + }, + 'params': { + 'youtube_include_dash_manifest': True, + 'format': '141', + }, + }, + # Controversy video + { + 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', + 'info_dict': { + 'id': 'T4XJQO3qol8', + 'ext': 'mp4', + 'upload_date': '20100909', + 'uploader': 'The Amazing Atheist', + 'uploader_id': 'TheAmazingAtheist', + 'title': 'Burning Everyone\'s Koran', + 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', + } + }, + # Normal age-gate video (No vevo, embed allowed) + { + 'url': 'http://youtube.com/watch?v=HtVdAasjOgU', + 'info_dict': { + 'id': 'HtVdAasjOgU', + 'ext': 'mp4', + 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', + 'description': 'md5:eca57043abae25130f58f655ad9a7771', + 'uploader': 'The Witcher', + 'uploader_id': 'WitcherGame', + 'upload_date': '20140605', + }, + }, + # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) + { + 'url': '__2ABJjxzNo', + 'info_dict': { + 'id': '__2ABJjxzNo', + 'ext': 'mp4', + 'upload_date': '20100430', + 'uploader_id': 'deadmau5', + 'description': 'md5:12c56784b8032162bb936a5f76d55360', + 'uploader': 'deadmau5', + 'title': 'Deadmau5 - Some Chords (HD)', }, - u"params": { - u'youtube_include_dash_manifest': True, - u'format': '141', + 'expected_warnings': [ + 'DASH manifest missing', + ] + }, + # Olympics (https://github.com/rg3/youtube-dl/issues/4431) + { + 'url': 'lqQg6PlCWgI', + 'info_dict': { + 'id': 'lqQg6PlCWgI', + 'ext': 'mp4', + 'upload_date': '20120731', + 'uploader_id': 'olympic', + 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', + 'uploader': 'Olympics', + 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', }, + 'params': { + 'skip_download': 'requires avconv', + } }, ] - - @classmethod - def suitable(cls, url): - """Receives a URL and returns True if suitable for this IE.""" - if YoutubePlaylistIE.suitable(url): return False - return re.match(cls._VALID_URL, url) is not None - def __init__(self, *args, **kwargs): super(YoutubeIE, self).__init__(*args, **kwargs) self._player_cache = {} def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" - self.to_screen(u'%s: Downloading video info webpage' % video_id) + self.to_screen('%s: Downloading video info webpage' % video_id) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self.to_screen(u'%s: Extracting video information' % video_id) + self.to_screen('%s: Extracting video information' % video_id) def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" - self.to_screen(u'%s: Format %s not available' % (video_id, format)) + self.to_screen('%s: Format %s not available' % (video_id, format)) def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" - self.to_screen(u'RTMP download detected') + self.to_screen('RTMP download detected') - def _extract_signature_function(self, video_id, player_url, slen): + def _signature_cache_id(self, example_sig): + """ Return a string representation of a signature """ + return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) + + def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', player_url) @@ -354,63 +486,45 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): player_id = id_m.group('id') # Read from filesystem cache - func_id = '%s_%s_%d' % (player_type, player_id, slen) + func_id = '%s_%s_%s' % ( + player_type, player_id, self._signature_cache_id(example_sig)) assert os.path.basename(func_id) == func_id - cache_dir = get_cachedir(self._downloader.params) - cache_enabled = cache_dir is not None - if cache_enabled: - cache_fn = os.path.join(os.path.expanduser(cache_dir), - u'youtube-sigfuncs', - func_id + '.json') - try: - with io.open(cache_fn, 'r', encoding='utf-8') as cachef: - cache_spec = json.load(cachef) - return lambda s: u''.join(s[i] for i in cache_spec) - except IOError: - pass # No cache available + cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) + if cache_spec is not None: + return lambda s: ''.join(s[i] for i in cache_spec) if player_type == 'js': code = self._download_webpage( player_url, video_id, - note=u'Downloading %s player %s' % (player_type, player_id), - errnote=u'Download of %s failed' % player_url) + note='Downloading %s player %s' % (player_type, player_id), + errnote='Download of %s failed' % player_url) res = self._parse_sig_js(code) elif player_type == 'swf': urlh = self._request_webpage( player_url, video_id, - note=u'Downloading %s player %s' % (player_type, player_id), - errnote=u'Download of %s failed' % player_url) + note='Downloading %s player %s' % (player_type, player_id), + errnote='Download of %s failed' % player_url) code = urlh.read() res = self._parse_sig_swf(code) else: assert False, 'Invalid player type %r' % player_type - if cache_enabled: - try: - test_string = u''.join(map(compat_chr, range(slen))) - cache_res = res(test_string) - cache_spec = [ord(c) for c in cache_res] - try: - os.makedirs(os.path.dirname(cache_fn)) - except OSError as ose: - if ose.errno != errno.EEXIST: - raise - write_json_file(cache_spec, cache_fn) - except Exception: - tb = traceback.format_exc() - self._downloader.report_warning( - u'Writing cache to %r failed: %s' % (cache_fn, tb)) + if cache_spec is None: + test_string = ''.join(map(compat_chr, range(len(example_sig)))) + cache_res = res(test_string) + cache_spec = [ord(c) for c in cache_res] + self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) return res - def _print_sig_code(self, func, slen): + def _print_sig_code(self, func, example_sig): def gen_sig_code(idxs): def _genslice(start, end, step): - starts = u'' if start == 0 else str(start) - ends = (u':%d' % (end+step)) if end + step >= 0 else u':' - steps = u'' if step == 1 else (u':%d' % step) - return u's[%s%s%s]' % (starts, ends, steps) + starts = '' if start == 0 else str(start) + ends = (':%d' % (end + step)) if end + step >= 0 else ':' + steps = '' if step == 1 else (':%d' % step) + return 's[%s%s%s]' % (starts, ends, steps) step = None start = '(Never used)' # Quelch pyflakes warnings - start will be @@ -427,23 +541,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): start = prev continue else: - yield u's[%d]' % prev + yield 's[%d]' % prev if step is None: - yield u's[%d]' % i + yield 's[%d]' % i else: yield _genslice(start, i, step) - test_string = u''.join(map(compat_chr, range(slen))) + test_string = ''.join(map(compat_chr, range(len(example_sig)))) cache_res = func(test_string) cache_spec = [ord(c) for c in cache_res] - expr_code = u' + '.join(gen_sig_code(cache_spec)) - code = u'if len(s) == %d:\n return %s\n' % (slen, expr_code) - self.to_screen(u'Extracted signature function:\n' + code) + expr_code = ' + '.join(gen_sig_code(cache_spec)) + signature_id_tuple = '(%s)' % ( + ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) + code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' + ' return %s\n') % (signature_id_tuple, expr_code) + self.to_screen('Extracted signature function:\n' + code) def _parse_sig_js(self, jscode): funcname = self._search_regex( - r'signature=([$a-zA-Z]+)', jscode, - u'Initial JS player signature function name') + r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode, + 'Initial JS player signature function name') jsi = JSInterpreter(jscode) initial_function = jsi.extract_function(funcname) @@ -451,34 +568,34 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _parse_sig_swf(self, file_contents): swfi = SWFInterpreter(file_contents) - TARGET_CLASSNAME = u'SignatureDecipher' + TARGET_CLASSNAME = 'SignatureDecipher' searched_class = swfi.extract_class(TARGET_CLASSNAME) - initial_function = swfi.extract_function(searched_class, u'decipher') + initial_function = swfi.extract_function(searched_class, 'decipher') return lambda s: initial_function([s]) def _decrypt_signature(self, s, video_id, player_url, age_gate=False): """Turn the encrypted s field into a working signature""" if player_url is None: - raise ExtractorError(u'Cannot decrypt signature without player_url') + raise ExtractorError('Cannot decrypt signature without player_url') - if player_url.startswith(u'//'): - player_url = u'https:' + player_url + if player_url.startswith('//'): + player_url = 'https:' + player_url try: - player_id = (player_url, len(s)) + player_id = (player_url, self._signature_cache_id(s)) if player_id not in self._player_cache: func = self._extract_signature_function( - video_id, player_url, len(s) + video_id, player_url, s ) self._player_cache[player_id] = func func = self._player_cache[player_id] if self._downloader.params.get('youtube_print_sig_code'): - self._print_sig_code(func, len(s)) + self._print_sig_code(func, s) return func(s) except Exception as e: tb = traceback.format_exc() raise ExtractorError( - u'Automatic signature extraction failed: ' + tb, cause=e) + 'Signature extraction failed: ' + tb, cause=e) def _get_available_subtitles(self, video_id, webpage): try: @@ -486,23 +603,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) return {} lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) sub_lang_list = {} for l in lang_list: lang = l[1] + if lang in sub_lang_list: + continue params = compat_urllib_parse.urlencode({ 'lang': lang, 'v': video_id, 'fmt': self._downloader.params.get('subtitlesformat', 'srt'), 'name': unescapeHTML(l[0]).encode('utf-8'), }) - url = u'https://www.youtube.com/api/timedtext?' + params + url = 'https://www.youtube.com/api/timedtext?' + params sub_lang_list[lang] = url if not sub_lang_list: - self._downloader.report_warning(u'video doesn\'t have subtitles') + self._downloader.report_warning('video doesn\'t have subtitles') return {} return sub_lang_list @@ -510,17 +629,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): """We need the webpage for getting the captions url, pass it as an argument to speed up the process.""" sub_format = self._downloader.params.get('subtitlesformat', 'srt') - self.to_screen(u'%s: Looking for automatic captions' % video_id) + self.to_screen('%s: Looking for automatic captions' % video_id) mobj = re.search(r';ytplayer.config = ({.*?});', webpage) - err_msg = u'Couldn\'t find automatic captions for %s' % video_id + err_msg = 'Couldn\'t find automatic captions for %s' % video_id if mobj is None: self._downloader.report_warning(err_msg) return {} player_config = json.loads(mobj.group(1)) try: - args = player_config[u'args'] - caption_url = args[u'ttsurl'] - timestamp = args[u'timestamp'] + args = player_config['args'] + caption_url = args['ttsurl'] + timestamp = args['timestamp'] # We get the available subtitles list_params = compat_urllib_parse.urlencode({ 'type': 'list', @@ -530,8 +649,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): list_url = caption_url + '&' + list_params caption_list = self._download_xml(list_url, video_id) original_lang_node = caption_list.find('track') - if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr' : - self._downloader.report_warning(u'Video doesn\'t have automatic captions') + if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr': + self._downloader.report_warning('Video doesn\'t have automatic captions') return {} original_lang = original_lang_node.attrib['lang_code'] @@ -557,18 +676,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def extract_id(cls, url): mobj = re.match(cls._VALID_URL, url, re.VERBOSE) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) video_id = mobj.group(2) return video_id def _extract_from_m3u8(self, manifest_url, video_id): url_map = {} + def _get_urls(_manifest): lines = _manifest.split('\n') urls = filter(lambda l: l and not l.startswith('#'), - lines) + lines) return urls - manifest = self._download_webpage(manifest_url, video_id, u'Downloading formats manifest') + manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') formats_urls = _get_urls(manifest) for format_url in formats_urls: itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag') @@ -577,12 +697,52 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _extract_annotations(self, video_id): url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id - return self._download_webpage(url, video_id, note=u'Searching for annotations.', errnote=u'Unable to download video annotations.') + return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') + + def _parse_dash_manifest( + self, video_id, dash_manifest_url, player_url, age_gate): + def decrypt_sig(mobj): + s = mobj.group(1) + dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) + return '/signature/%s' % dec_s + dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) + dash_doc = self._download_xml( + dash_manifest_url, video_id, + note='Downloading DASH manifest', + errnote='Could not download DASH manifest') + + formats = [] + for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): + url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') + if url_el is None: + continue + format_id = r.attrib['id'] + video_url = url_el.text + filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) + f = { + 'format_id': format_id, + 'url': video_url, + 'width': int_or_none(r.attrib.get('width')), + 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), + 'asr': int_or_none(r.attrib.get('audioSamplingRate')), + 'filesize': filesize, + 'fps': int_or_none(r.attrib.get('frameRate')), + } + try: + existing_format = next( + fo for fo in formats + if fo['format_id'] == format_id) + except StopIteration: + f.update(self._formats.get(format_id, {})) + formats.append(f) + else: + existing_format.update(f) + return formats def _real_extract(self, url): proto = ( - u'http' if self._downloader.params.get('prefer_insecure', False) - else u'https') + 'http' if self._downloader.params.get('prefer_insecure', False) + else 'https') # Extract original video URL from URL with redirection, like age verification, using next_url parameter mobj = re.search(self._NEXT_URL_RE, url) @@ -591,7 +751,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): video_id = self.extract_id(url) # Get video webpage - url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id + url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id video_webpage = self._download_webpage(url, video_id) # Attempt to extract SWF player URL @@ -602,9 +762,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): player_url = None # Get video info - self.report_video_info_webpage_download(video_id) if re.search(r'player-age-gate-content">', video_webpage) is not None: - self.report_age_confirmation() age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube @@ -612,32 +770,50 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'video_id': video_id, 'eurl': 'https://youtube.googleapis.com/v/' + video_id, 'sts': self._search_regex( - r'"sts"\s*:\s*(\d+)', video_webpage, 'sts'), + r'"sts"\s*:\s*(\d+)', video_webpage, 'sts', default=''), }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data - video_info_webpage = self._download_webpage(video_info_url, video_id, - note=False, - errnote='unable to download video info webpage') + video_info_webpage = self._download_webpage( + video_info_url, video_id, + note='Refetching age-gated info webpage', + errnote='unable to download video info webpage') video_info = compat_parse_qs(video_info_webpage) else: age_gate = False - for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = (proto + '://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) - video_info_webpage = self._download_webpage(video_info_url, video_id, - note=False, - errnote='unable to download video info webpage') - video_info = compat_parse_qs(video_info_webpage) - if 'token' in video_info: - break + try: + # Try looking directly into the video webpage + mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) + if not mobj: + raise ValueError('Could not find ytplayer.config') # caught below + json_code = uppercase_escape(mobj.group(1)) + ytplayer_config = json.loads(json_code) + args = ytplayer_config['args'] + # Convert to the same format returned by compat_parse_qs + video_info = dict((k, [v]) for k, v in args.items()) + if 'url_encoded_fmt_stream_map' not in args: + raise ValueError('No stream_map present') # caught below + except ValueError: + # We fallback to the get_video_info pages (used by the embed page) + self.report_video_info_webpage_download(video_id) + for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: + video_info_url = ( + '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (proto, video_id, el_type)) + video_info_webpage = self._download_webpage( + video_info_url, + video_id, note=False, + errnote='unable to download video info webpage') + video_info = compat_parse_qs(video_info_webpage) + if 'token' in video_info: + break if 'token' not in video_info: if 'reason' in video_info: raise ExtractorError( - u'YouTube said: %s' % video_info['reason'][0], + 'YouTube said: %s' % video_info['reason'][0], expected=True, video_id=video_id) else: raise ExtractorError( - u'"token" parameter not in video info for unknown reason', + '"token" parameter not in video info for unknown reason', video_id=video_id) if 'view_count' in video_info: @@ -647,14 +823,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: - raise ExtractorError(u'"rental" videos not supported') + raise ExtractorError('"rental" videos not supported') # Start extracting information self.report_information_extraction(video_id) # uploader if 'author' not in video_info: - raise ExtractorError(u'Unable to extract uploader name') + raise ExtractorError('Unable to extract uploader name') video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) # uploader_id @@ -663,14 +839,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if mobj is not None: video_uploader_id = mobj.group(1) else: - self._downloader.report_warning(u'unable to extract uploader nickname') + self._downloader.report_warning('unable to extract uploader nickname') # title if 'title' in video_info: video_title = video_info['title'][0] else: - self._downloader.report_warning(u'Unable to extract video title') - video_title = u'_' + self._downloader.report_warning('Unable to extract video title') + video_title = '_' # thumbnail image # We try first to get a high quality image: @@ -679,7 +855,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if m_thumb is not None: video_thumbnail = m_thumb.group(1) elif 'thumbnail_url' not in video_info: - self._downloader.report_warning(u'unable to extract video thumbnail') + self._downloader.report_warning('unable to extract video thumbnail') video_thumbnail = None else: # don't panic if we can't find it video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) @@ -695,7 +871,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) - m_cat_container = get_element_by_id("eow-category", video_webpage) + m_cat_container = self._search_regex( + r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', + video_webpage, 'categories', default=None) if m_cat_container: category = self._html_search_regex( r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', @@ -722,17 +900,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if fd_mobj: video_description = unescapeHTML(fd_mobj.group(1)) else: - video_description = u'' + video_description = '' - def _extract_count(klass): + def _extract_count(count_name): count = self._search_regex( - r'class="%s">([\d,]+)</span>' % re.escape(klass), - video_webpage, klass, default=None) + r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name), + video_webpage, count_name, default=None) if count is not None: return int(count.replace(',', '')) return None - like_count = _extract_count(u'likes-count') - dislike_count = _extract_count(u'dislikes-count') + like_count = _extract_count('like') + dislike_count = _extract_count('dislike') # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) @@ -742,7 +920,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return if 'length_seconds' not in video_info: - self._downloader.report_warning(u'unable to extract video duration') + self._downloader.report_warning('unable to extract video duration') video_duration = None else: video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])) @@ -750,33 +928,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # annotations video_annotations = None if self._downloader.params.get('writeannotations', False): - video_annotations = self._extract_annotations(video_id) - - # Decide which formats to download - try: - mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) - if not mobj: - raise ValueError('Could not find vevo ID') - json_code = uppercase_escape(mobj.group(1)) - ytplayer_config = json.loads(json_code) - args = ytplayer_config['args'] - # Easy way to know if the 's' value is in url_encoded_fmt_stream_map - # this signatures are encrypted - if 'url_encoded_fmt_stream_map' not in args: - raise ValueError(u'No stream_map present') # caught below - re_signature = re.compile(r'[&,]s=') - m_s = re_signature.search(args['url_encoded_fmt_stream_map']) - if m_s is not None: - self.to_screen(u'%s: Encrypted signatures detected.' % video_id) - video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']] - m_s = re_signature.search(args.get('adaptive_fmts', u'')) - if m_s is not None: - if 'adaptive_fmts' in video_info: - video_info['adaptive_fmts'][0] += ',' + args['adaptive_fmts'] - else: - video_info['adaptive_fmts'] = [args['adaptive_fmts']] - except ValueError: - pass + video_annotations = self._extract_annotations(video_id) def _map_to_format_list(urlmap): formats = [] @@ -799,151 +951,120 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'url': video_info['conn'][0], 'player_url': player_url, }] - elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1: - encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts',[''])[0] + elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: + encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) url_map = {} for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) - if 'itag' in url_data and 'url' in url_data: - url = url_data['url'][0] - if 'sig' in url_data: - url += '&signature=' + url_data['sig'][0] - elif 's' in url_data: - encrypted_sig = url_data['s'][0] - - if not age_gate: - jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - video_webpage, u'JS player URL') - player_url = json.loads(jsplayer_url_json) + if 'itag' not in url_data or 'url' not in url_data: + continue + format_id = url_data['itag'][0] + url = url_data['url'][0] + + if 'sig' in url_data: + url += '&signature=' + url_data['sig'][0] + elif 's' in url_data: + encrypted_sig = url_data['s'][0] + + if not age_gate: + jsplayer_url_json = self._search_regex( + r'"assets":.+?"js":\s*("[^"]+")', + video_webpage, 'JS player URL') + player_url = json.loads(jsplayer_url_json) + if player_url is None: + player_url_json = self._search_regex( + r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', + video_webpage, 'age gate player URL') + player_url = json.loads(player_url_json) + + if self._downloader.params.get('verbose'): if player_url is None: - player_url_json = self._search_regex( - r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', - video_webpage, u'age gate player URL') - player_url = json.loads(player_url_json) - - if self._downloader.params.get('verbose'): - if player_url is None: - player_version = 'unknown' - player_desc = 'unknown' + player_version = 'unknown' + player_desc = 'unknown' + else: + if player_url.endswith('swf'): + player_version = self._search_regex( + r'-(.+?)(?:/watch_as3)?\.swf$', player_url, + 'flash player', fatal=False) + player_desc = 'flash player %s' % player_version else: - if player_url.endswith('swf'): - player_version = self._search_regex( - r'-(.+?)(?:/watch_as3)?\.swf$', player_url, - u'flash player', fatal=False) - player_desc = 'flash player %s' % player_version - else: - player_version = self._search_regex( - r'html5player-([^/]+?)(?:/html5player)?\.js', - player_url, - 'html5 player', fatal=False) - player_desc = u'html5 player %s' % player_version - - parts_sizes = u'.'.join(compat_str(len(part)) for part in encrypted_sig.split('.')) - self.to_screen(u'encrypted signature length %d (%s), itag %s, %s' % - (len(encrypted_sig), parts_sizes, url_data['itag'][0], player_desc)) - - signature = self._decrypt_signature( - encrypted_sig, video_id, player_url, age_gate) - url += '&signature=' + signature - if 'ratebypass' not in url: - url += '&ratebypass=yes' - url_map[url_data['itag'][0]] = url + player_version = self._search_regex( + r'html5player-([^/]+?)(?:/html5player)?\.js', + player_url, + 'html5 player', fatal=False) + player_desc = 'html5 player %s' % player_version + + parts_sizes = self._signature_cache_id(encrypted_sig) + self.to_screen('{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) + + signature = self._decrypt_signature( + encrypted_sig, video_id, player_url, age_gate) + url += '&signature=' + signature + if 'ratebypass' not in url: + url += '&ratebypass=yes' + url_map[format_id] = url formats = _map_to_format_list(url_map) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] url_map = self._extract_from_m3u8(manifest_url, video_id) formats = _map_to_format_list(url_map) else: - raise ExtractorError(u'no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') + raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') # Look for the DASH manifest - if (self._downloader.params.get('youtube_include_dash_manifest', False)): - try: - # The DASH manifest used needs to be the one from the original video_webpage. - # The one found in get_video_info seems to be using different signatures. - # However, in the case of an age restriction there won't be any embedded dashmpd in the video_webpage. - # Luckily, it seems, this case uses some kind of default signature (len == 86), so the - # combination of get_video_info and the _static_decrypt_signature() decryption fallback will work here. - if age_gate: - dash_manifest_url = video_info.get('dashmpd')[0] + if self._downloader.params.get('youtube_include_dash_manifest', True): + dash_mpd = video_info.get('dashmpd') + if dash_mpd: + dash_manifest_url = dash_mpd[0] + try: + dash_formats = self._parse_dash_manifest( + video_id, dash_manifest_url, player_url, age_gate) + except (ExtractorError, KeyError) as e: + self.report_warning( + 'Skipping DASH manifest: %r' % e, video_id) else: - dash_manifest_url = ytplayer_config['args']['dashmpd'] - def decrypt_sig(mobj): - s = mobj.group(1) - dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) - return '/signature/%s' % dec_s - dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) - dash_doc = self._download_xml( - dash_manifest_url, video_id, - note=u'Downloading DASH manifest', - errnote=u'Could not download DASH manifest') - for r in dash_doc.findall(u'.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): - url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') - if url_el is None: - continue - format_id = r.attrib['id'] - video_url = url_el.text - filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) - f = { - 'format_id': format_id, - 'url': video_url, - 'width': int_or_none(r.attrib.get('width')), - 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), - 'asr': int_or_none(r.attrib.get('audioSamplingRate')), - 'filesize': filesize, - } - try: - existing_format = next( - fo for fo in formats - if fo['format_id'] == format_id) - except StopIteration: - f.update(self._formats.get(format_id, {})) - formats.append(f) - else: - existing_format.update(f) - - except (ExtractorError, KeyError) as e: - self.report_warning(u'Skipping DASH manifest: %s' % e, video_id) + formats.extend(dash_formats) self._sort_formats(formats) return { - 'id': video_id, - 'uploader': video_uploader, - 'uploader_id': video_uploader_id, - 'upload_date': upload_date, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'categories': video_categories, - 'subtitles': video_subtitles, - 'duration': video_duration, - 'age_limit': 18 if age_gate else 0, - 'annotations': video_annotations, + 'id': video_id, + 'uploader': video_uploader, + 'uploader_id': video_uploader_id, + 'upload_date': upload_date, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'categories': video_categories, + 'subtitles': video_subtitles, + 'duration': video_duration, + 'age_limit': 18 if age_gate else 0, + 'annotations': video_annotations, 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, - 'view_count': view_count, + 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, - 'formats': formats, + 'formats': formats, } + class YoutubePlaylistIE(YoutubeBaseInfoExtractor): - IE_DESC = u'YouTube.com playlists' + IE_DESC = 'YouTube.com playlists' _VALID_URL = r"""(?x)(?: (?:https?://)? (?:\w+\.)? youtube\.com/ (?: - (?:course|view_play_list|my_playlists|artist|playlist|watch) + (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) \? (?:.*?&)*? (?:p|a|list)= | p/ ) ( (?:PL|LL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,} - # Top tracks, they can also include dots + # Top tracks, they can also include dots |(?:MC)[\w\.]* ) .* @@ -953,27 +1074,87 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' _MORE_PAGES_INDICATOR = r'data-link-type="next"' _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' - IE_NAME = u'youtube:playlist' + IE_NAME = 'youtube:playlist' + _TESTS = [{ + 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'info_dict': { + 'title': 'ytdl test PL', + 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + }, + 'playlist_count': 3, + }, { + 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', + 'info_dict': { + 'title': 'YDL_Empty_List', + }, + 'playlist_count': 0, + }, { + 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', + 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'info_dict': { + 'title': '29C3: Not my department', + }, + 'playlist_count': 95, + }, { + 'note': 'issue #673', + 'url': 'PLBB231211A4F62143', + 'info_dict': { + 'title': '[OLD]Team Fortress 2 (Class-based LP)', + }, + 'playlist_mincount': 26, + }, { + 'note': 'Large playlist', + 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', + 'info_dict': { + 'title': 'Uploads from Cauchemar', + }, + 'playlist_mincount': 799, + }, { + 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', + 'info_dict': { + 'title': 'YDL_safe_search', + }, + 'playlist_count': 2, + }, { + 'note': 'embedded', + 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'playlist_count': 4, + 'info_dict': { + 'title': 'JODA15', + } + }, { + 'note': 'Embedded SWF player', + 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', + 'playlist_count': 4, + 'info_dict': { + 'title': 'JODA7', + } + }] def _real_initialize(self): self._login() def _ids_to_results(self, ids): - return [self.url_result(vid_id, 'Youtube', video_id=vid_id) - for vid_id in ids] + return [ + self.url_result(vid_id, 'Youtube', video_id=vid_id) + for vid_id in ids] def _extract_mix(self, playlist_id): # The mixes are generated from a a single video # the id of the playlist is just 'RD' + video_id url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) - webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix') + webpage = self._download_webpage( + url, playlist_id, 'Downloading Youtube mix') search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) - title_span = (search_title('playlist-title') or - search_title('title long-title') or search_title('title')) + title_span = ( + search_title('playlist-title') or + search_title('title long-title') or + search_title('title')) title = clean_html(title_span) - video_re = r'''(?x)data-video-username=".*?".*? - href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id) - ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL)) + ids = orderedSet(re.findall( + r'''(?xs)data-video-username=".*?".*? + href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), + webpage)) url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, title) @@ -982,7 +1163,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): # Extract playlist id mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) playlist_id = mobj.group(1) or mobj.group(2) # Check if it's a video-specific URL @@ -990,17 +1171,17 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): if 'v' in query_dict: video_id = query_dict['v'][0] if self._downloader.params.get('noplaylist'): - self.to_screen(u'Downloading just video %s because of --no-playlist' % video_id) + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) return self.url_result(video_id, 'Youtube', video_id=video_id) else: - self.to_screen(u'Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) + self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) if playlist_id.startswith('RD'): # Mixes require a custom extraction process return self._extract_mix(playlist_id) if playlist_id.startswith('TL'): - raise ExtractorError(u'For downloading YouTube.com top lists, use ' - u'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True) + raise ExtractorError('For downloading YouTube.com top lists, use ' + 'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True) url = self._TEMPLATE_URL % playlist_id page = self._download_webpage(url, playlist_id) @@ -1009,7 +1190,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): # Check if the playlist exists or is private if re.search(r'<div class="yt-alert-message">[^<]*?(The|This) playlist (does not exist|is private)[^<]*?</div>', page) is not None: raise ExtractorError( - u'The playlist doesn\'t exist or is private, use --username or ' + 'The playlist doesn\'t exist or is private, use --username or ' '--netrc to access it.', expected=True) @@ -1036,36 +1217,47 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): playlist_title = self._html_search_regex( r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', - page, u'title') + page, 'title') url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, playlist_title) class YoutubeTopListIE(YoutubePlaylistIE): - IE_NAME = u'youtube:toplist' - IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"' - u' (Example: "yttoplist:music:Top Tracks")') + IE_NAME = 'youtube:toplist' + IE_DESC = ('YouTube.com top lists, "yttoplist:{channel}:{list title}"' + ' (Example: "yttoplist:music:Top Tracks")') _VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$' + _TESTS = [{ + 'url': 'yttoplist:music:Trending', + 'playlist_mincount': 5, + 'skip': 'Only works for logged-in users', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) channel = mobj.group('chann') title = mobj.group('title') query = compat_urllib_parse.urlencode({'title': title}) - playlist_re = 'href="([^"]+?%s.*?)"' % re.escape(query) - channel_page = self._download_webpage('https://www.youtube.com/%s' % channel, title) - link = self._html_search_regex(playlist_re, channel_page, u'list') + channel_page = self._download_webpage( + 'https://www.youtube.com/%s' % channel, title) + link = self._html_search_regex( + r'''(?x) + <a\s+href="([^"]+)".*?>\s* + <span\s+class="branded-page-module-title-text">\s* + <span[^>]*>.*?%s.*?</span>''' % re.escape(query), + channel_page, 'list') url = compat_urlparse.urljoin('https://www.youtube.com/', link) - + video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"' ids = [] # sometimes the webpage doesn't contain the videos # retry until we get them for i in itertools.count(0): - msg = u'Downloading Youtube mix' + msg = 'Downloading Youtube mix' if i > 0: msg += ', retry #%d' % i + webpage = self._download_webpage(url, title, msg) ids = orderedSet(re.findall(video_re, webpage)) if ids: @@ -1075,11 +1267,16 @@ class YoutubeTopListIE(YoutubePlaylistIE): class YoutubeChannelIE(InfoExtractor): - IE_DESC = u'YouTube.com channels' - _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)" + IE_DESC = 'YouTube.com channels' + _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' _MORE_PAGES_INDICATOR = 'yt-uix-load-more' _MORE_PAGES_URL = 'https://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s' - IE_NAME = u'youtube:channel' + IE_NAME = 'youtube:channel' + _TESTS = [{ + 'note': 'paginated channel', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'playlist_mincount': 91, + }] def extract_videos_from_page(self, page): ids_in_page = [] @@ -1089,13 +1286,8 @@ class YoutubeChannelIE(InfoExtractor): return ids_in_page def _real_extract(self, url): - # Extract channel id - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + channel_id = self._match_id(url) - # Download channel page - channel_id = mobj.group(1) video_ids = [] url = 'https://www.youtube.com/channel/%s/videos' % channel_id channel_page = self._download_webpage(url, channel_id) @@ -1109,50 +1301,60 @@ class YoutubeChannelIE(InfoExtractor): # The videos are contained in a single page # the ajax pages can't be used, they are empty video_ids = self.extract_videos_from_page(channel_page) - else: - # Download all channel pages using the json-based channel_ajax query + entries = [ + self.url_result(video_id, 'Youtube', video_id=video_id) + for video_id in video_ids] + return self.playlist_result(entries, channel_id) + + def _entries(): for pagenum in itertools.count(1): url = self._MORE_PAGES_URL % (pagenum, channel_id) page = self._download_json( - url, channel_id, note=u'Downloading page #%s' % pagenum, + url, channel_id, note='Downloading page #%s' % pagenum, transform_source=uppercase_escape) ids_in_page = self.extract_videos_from_page(page['content_html']) - video_ids.extend(ids_in_page) - + for video_id in ids_in_page: + yield self.url_result( + video_id, 'Youtube', video_id=video_id) + if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: break - self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) - - url_entries = [self.url_result(video_id, 'Youtube', video_id=video_id) - for video_id in video_ids] - return self.playlist_result(url_entries, channel_id) + return self.playlist_result(_entries(), channel_id) class YoutubeUserIE(InfoExtractor): - IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)' - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)([A-Za-z0-9_-]+)' + IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/users/%s' _GDATA_PAGE_SIZE = 50 _GDATA_URL = 'https://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json' - IE_NAME = u'youtube:user' + IE_NAME = 'youtube:user' + + _TESTS = [{ + 'url': 'https://www.youtube.com/user/TheLinuxFoundation', + 'playlist_mincount': 320, + 'info_dict': { + 'title': 'TheLinuxFoundation', + } + }, { + 'url': 'ytuser:phihag', + 'only_matching': True, + }] @classmethod def suitable(cls, url): # Don't return True if the url can be extracted with other youtube # extractor, the regex would is too permissive and it would match. other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) - if any(ie.suitable(url) for ie in other_ies): return False - else: return super(YoutubeUserIE, cls).suitable(url) + if any(ie.suitable(url) for ie in other_ies): + return False + else: + return super(YoutubeUserIE, cls).suitable(url) def _real_extract(self, url): - # Extract username - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - username = mobj.group(1) + username = self._match_id(url) # Download video ids using YouTube Data API. Result size per # query is limited (currently to 50 videos) so we need to query @@ -1165,13 +1367,13 @@ class YoutubeUserIE(InfoExtractor): gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index) page = self._download_webpage( gdata_url, username, - u'Downloading video ids from %d to %d' % ( + 'Downloading video ids from %d to %d' % ( start_index, start_index + self._GDATA_PAGE_SIZE)) try: response = json.loads(page) except ValueError as err: - raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err)) + raise ExtractorError('Invalid JSON in API response: ' + compat_str(err)) if 'entry' not in response['feed']: return @@ -1187,16 +1389,16 @@ class YoutubeUserIE(InfoExtractor): 'id': video_id, 'title': title, } - url_results = PagedList(download_page, self._GDATA_PAGE_SIZE) + url_results = OnDemandPagedList(download_page, self._GDATA_PAGE_SIZE) return self.playlist_result(url_results, playlist_title=username) class YoutubeSearchIE(SearchInfoExtractor): - IE_DESC = u'YouTube.com searches' - _API_URL = u'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' + IE_DESC = 'YouTube.com searches' + _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' _MAX_RESULTS = 1000 - IE_NAME = u'youtube:search' + IE_NAME = 'youtube:search' _SEARCH_KEY = 'ytsearch' def _get_n_results(self, query, n): @@ -1212,15 +1414,15 @@ class YoutubeSearchIE(SearchInfoExtractor): compat_urllib_parse.quote_plus(query.encode('utf-8')), (PAGE_SIZE * pagenum) + 1) data_json = self._download_webpage( - result_url, video_id=u'query "%s"' % query, - note=u'Downloading page %s' % (pagenum + 1), - errnote=u'Unable to download API page') + result_url, video_id='query "%s"' % query, + note='Downloading page %s' % (pagenum + 1), + errnote='Unable to download API page') data = json.loads(data_json) api_response = data['data'] if 'items' not in api_response: raise ExtractorError( - u'[youtube] No video results', expected=True) + '[youtube] No video results', expected=True) new_ids = list(video['id'] for video in api_response['items']) video_ids += new_ids @@ -1239,13 +1441,20 @@ class YoutubeSearchDateIE(YoutubeSearchIE): IE_NAME = YoutubeSearchIE.IE_NAME + ':date' _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc&orderby=published' _SEARCH_KEY = 'ytsearchdate' - IE_DESC = u'YouTube.com searches, newest videos first' + IE_DESC = 'YouTube.com searches, newest videos first' class YoutubeSearchURLIE(InfoExtractor): - IE_DESC = u'YouTube.com search URLs' - IE_NAME = u'youtube:search_url' + IE_DESC = 'YouTube.com search URLs' + IE_NAME = 'youtube:search_url' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' + _TESTS = [{ + 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', + 'playlist_mincount': 5, + 'info_dict': { + 'title': 'youtube-dl test video', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -1253,7 +1462,7 @@ class YoutubeSearchURLIE(InfoExtractor): webpage = self._download_webpage(url, query) result_code = self._search_regex( - r'(?s)<ol class="item-section"(.*?)</ol>', webpage, u'result HTML') + r'(?s)<ol class="item-section"(.*?)</ol>', webpage, 'result HTML') part_codes = re.findall( r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) @@ -1279,18 +1488,39 @@ class YoutubeSearchURLIE(InfoExtractor): class YoutubeShowIE(InfoExtractor): - IE_DESC = u'YouTube.com (multi-season) shows' - _VALID_URL = r'https?://www\.youtube\.com/show/(.*)' - IE_NAME = u'youtube:show' + IE_DESC = 'YouTube.com (multi-season) shows' + _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' + IE_NAME = 'youtube:show' + _TESTS = [{ + 'url': 'http://www.youtube.com/show/airdisasters', + 'playlist_mincount': 3, + 'info_dict': { + 'id': 'airdisasters', + 'title': 'Air Disasters', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - show_name = mobj.group(1) - webpage = self._download_webpage(url, show_name, u'Downloading show webpage') + playlist_id = mobj.group('id') + webpage = self._download_webpage( + url, playlist_id, 'Downloading show webpage') # There's one playlist for each season of the show m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) - self.to_screen(u'%s: Found %s seasons' % (show_name, len(m_seasons))) - return [self.url_result('https://www.youtube.com' + season.group(1), 'YoutubePlaylist') for season in m_seasons] + self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) + entries = [ + self.url_result( + 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') + for season in m_seasons + ] + title = self._og_search_title(webpage, fatal=False) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': title, + 'entries': entries, + } class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): @@ -1312,7 +1542,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): @property def IE_NAME(self): - return u'youtube:%s' % self._FEED_NAME + return 'youtube:%s' % self._FEED_NAME def _real_initialize(self): self._login() @@ -1322,9 +1552,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = 0 for i in itertools.count(1): info = self._download_json(self._FEED_TEMPLATE % paging, - u'%s feed' % self._FEED_NAME, - u'Downloading page %s' % i) + '%s feed' % self._FEED_NAME, + 'Downloading page %s' % i) feed_html = info.get('feed_html') or info.get('content_html') + load_more_widget_html = info.get('load_more_widget_html') or feed_html m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) ids = orderedSet(m.group(1) for m in m_ids) feed_entries.extend( @@ -1332,50 +1563,86 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): for video_id in ids) mobj = re.search( r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)', - feed_html) + load_more_widget_html) if mobj is None: break paging = mobj.group('paging') return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) -class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' - _FEED_NAME = 'subscriptions' - _PLAYLIST_TITLE = u'Youtube Subscriptions' class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'YouTube.com recommended videos, "ytrec" keyword (requires authentication)' + IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' _FEED_NAME = 'recommended' - _PLAYLIST_TITLE = u'Youtube Recommended videos' + _PLAYLIST_TITLE = 'Youtube Recommended videos' + class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'Youtube watch later list, "ytwatchlater" keyword (requires authentication)' + IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater' _FEED_NAME = 'watch_later' - _PLAYLIST_TITLE = u'Youtube Watch Later' + _PLAYLIST_TITLE = 'Youtube Watch Later' _PERSONAL_FEED = True + class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'Youtube watch history, "ythistory" keyword (requires authentication)' - _VALID_URL = u'https?://www\.youtube\.com/feed/history|:ythistory' + IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' + _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' _FEED_NAME = 'history' _PERSONAL_FEED = True - _PLAYLIST_TITLE = u'Youtube Watch History' + _PLAYLIST_TITLE = 'Youtube Watch History' + class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): - IE_NAME = u'youtube:favorites' - IE_DESC = u'YouTube.com favourite videos, "ytfav" keyword (requires authentication)' + IE_NAME = 'youtube:favorites' + IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' _LOGIN_REQUIRED = True def _real_extract(self, url): webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') - playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, u'favourites playlist id') + playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') return self.url_result(playlist_id, 'YoutubePlaylist') +class YoutubeSubscriptionsIE(YoutubePlaylistIE): + IE_NAME = 'youtube:subscriptions' + IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' + _TESTS = [] + + def _real_extract(self, url): + title = 'Youtube Subscriptions' + page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) + + # The extraction process is the same as for playlists, but the regex + # for the video ids doesn't contain an index + ids = [] + more_widget_html = content_html = page + + for page_num in itertools.count(1): + matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) + new_ids = orderedSet(matches) + ids.extend(new_ids) + + mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) + if not mobj: + break + + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), title, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) + content_html = more['content_html'] + more_widget_html = more['load_more_widget_html'] + + return { + '_type': 'playlist', + 'title': title, + 'entries': self._ids_to_results(ids), + } + + class YoutubeTruncatedURLIE(InfoExtractor): IE_NAME = 'youtube:truncated_url' IE_DESC = False # Do not list @@ -1397,9 +1664,9 @@ class YoutubeTruncatedURLIE(InfoExtractor): def _real_extract(self, url): raise ExtractorError( - u'Did you forget to quote the URL? Remember that & is a meta ' - u'character in most shells, so you want to put the URL in quotes, ' - u'like youtube-dl ' - u'"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' - u' or simply youtube-dl BaW_jenozKc .', + 'Did you forget to quote the URL? Remember that & is a meta ' + 'character in most shells, so you want to put the URL in quotes, ' + 'like youtube-dl ' + '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' + ' or simply youtube-dl BaW_jenozKc .', expected=True) diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 3b1ac4e9f..74c76a9a0 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -1,17 +1,95 @@ # coding: utf-8 from __future__ import unicode_literals +import functools import re from .common import InfoExtractor from ..utils import ( int_or_none, unified_strdate, + OnDemandPagedList, ) +def extract_from_xml_url(ie, video_id, xml_url): + doc = ie._download_xml( + xml_url, video_id, + note='Downloading video info', + errnote='Failed to download video info') + + title = doc.find('.//information/title').text + description = doc.find('.//information/detail').text + duration = int(doc.find('.//details/lengthSec').text) + uploader_node = doc.find('.//details/originChannelTitle') + uploader = None if uploader_node is None else uploader_node.text + uploader_id_node = doc.find('.//details/originChannelId') + uploader_id = None if uploader_id_node is None else uploader_id_node.text + upload_date = unified_strdate(doc.find('.//details/airtime').text) + + def xml_to_format(fnode): + video_url = fnode.find('url').text + is_available = 'http://www.metafilegenerator' not in video_url + + format_id = fnode.attrib['basetype'] + format_m = re.match(r'''(?x) + (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_ + (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+) + ''', format_id) + + ext = format_m.group('container') + proto = format_m.group('proto').lower() + + quality = fnode.find('./quality').text + abr = int(fnode.find('./audioBitrate').text) // 1000 + vbr_node = fnode.find('./videoBitrate') + vbr = None if vbr_node is None else int(vbr_node.text) // 1000 + + width_node = fnode.find('./width') + width = None if width_node is None else int_or_none(width_node.text) + height_node = fnode.find('./height') + height = None if height_node is None else int_or_none(height_node.text) + + format_note = '' + if not format_note: + format_note = None + + return { + 'format_id': format_id + '-' + quality, + 'url': video_url, + 'ext': ext, + 'acodec': format_m.group('acodec'), + 'vcodec': format_m.group('vcodec'), + 'abr': abr, + 'vbr': vbr, + 'width': width, + 'height': height, + 'filesize': int_or_none(fnode.find('./filesize').text), + 'format_note': format_note, + 'protocol': proto, + '_available': is_available, + } + + format_nodes = doc.findall('.//formitaeten/formitaet') + formats = list(filter( + lambda f: f['_available'], + map(xml_to_format, format_nodes))) + ie._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'upload_date': upload_date, + 'formats': formats, + } + + class ZDFIE(InfoExtractor): - _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' + _VALID_URL = r'(?:zdf:|zdf:video:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/(.*beitrag/(?:video/)?))(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' _TEST = { 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt', @@ -29,81 +107,53 @@ class ZDFIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') - + video_id = self._match_id(url) xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id + return extract_from_xml_url(self, video_id, xml_url) + + +class ZDFChannelIE(InfoExtractor): + _VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/)(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic', + 'info_dict': { + 'id': '1586442', + }, + 'playlist_count': 4, + } + _PAGE_SIZE = 50 + + def _fetch_page(self, channel_id, page): + offset = page * self._PAGE_SIZE + xml_url = ( + 'http://www.zdf.de/ZDFmediathek/xmlservice/web/aktuellste?ak=web&offset=%d&maxLength=%d&id=%s' + % (offset, self._PAGE_SIZE, channel_id)) doc = self._download_xml( - xml_url, video_id, - note='Downloading video info', - errnote='Failed to download video info') + xml_url, channel_id, + note='Downloading channel info', + errnote='Failed to download channel info') title = doc.find('.//information/title').text description = doc.find('.//information/detail').text - duration = int(doc.find('.//details/lengthSec').text) - uploader_node = doc.find('.//details/originChannelTitle') - uploader = None if uploader_node is None else uploader_node.text - uploader_id_node = doc.find('.//details/originChannelId') - uploader_id = None if uploader_id_node is None else uploader_id_node.text - upload_date = unified_strdate(doc.find('.//details/airtime').text) - - def xml_to_format(fnode): - video_url = fnode.find('url').text - is_available = 'http://www.metafilegenerator' not in video_url - - format_id = fnode.attrib['basetype'] - format_m = re.match(r'''(?x) - (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_ - (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+) - ''', format_id) - - ext = format_m.group('container') - proto = format_m.group('proto').lower() - - quality = fnode.find('./quality').text - abr = int(fnode.find('./audioBitrate').text) // 1000 - vbr_node = fnode.find('./videoBitrate') - vbr = None if vbr_node is None else int(vbr_node.text) // 1000 - - width_node = fnode.find('./width') - width = None if width_node is None else int_or_none(width_node.text) - height_node = fnode.find('./height') - height = None if height_node is None else int_or_none(height_node.text) - - format_note = '' - if not format_note: - format_note = None - - return { - 'format_id': format_id + '-' + quality, - 'url': video_url, - 'ext': ext, - 'acodec': format_m.group('acodec'), - 'vcodec': format_m.group('vcodec'), - 'abr': abr, - 'vbr': vbr, - 'width': width, - 'height': height, - 'filesize': int_or_none(fnode.find('./filesize').text), - 'format_note': format_note, - 'protocol': proto, - '_available': is_available, + for asset in doc.findall('.//teasers/teaser'): + a_type = asset.find('./type').text + a_id = asset.find('./details/assetId').text + if a_type not in ('video', 'topic'): + continue + yield { + '_type': 'url', + 'playlist_title': title, + 'playlist_description': description, + 'url': 'zdf:%s:%s' % (a_type, a_id), } - format_nodes = doc.findall('.//formitaeten/formitaet') - formats = list(filter( - lambda f: f['_available'], - map(xml_to_format, format_nodes))) - - self._sort_formats(formats) + def _real_extract(self, url): + channel_id = self._match_id(url) + entries = OnDemandPagedList( + functools.partial(self._fetch_page, channel_id), self._PAGE_SIZE) return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': duration, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - 'formats': formats, - }
\ No newline at end of file + '_type': 'playlist', + 'id': channel_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/zingmp3.py b/youtube_dl/extractor/zingmp3.py new file mode 100644 index 000000000..1afbe68ed --- /dev/null +++ b/youtube_dl/extractor/zingmp3.py @@ -0,0 +1,107 @@ +# coding=utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class ZingMp3BaseInfoExtractor(InfoExtractor): + + @staticmethod + def _extract_item(item): + title = item.find('./title').text.strip() + source = item.find('./source').text + extension = item.attrib['type'] + thumbnail = item.find('./backimage').text + + return { + 'title': title, + 'url': source, + 'ext': extension, + 'thumbnail': thumbnail, + } + + def _extract_player_xml(self, player_xml_url, id, playlist_title=None): + player_xml = self._download_xml(player_xml_url, id, 'Downloading Player XML') + items = player_xml.findall('./item') + + if len(items) == 1: + # one single song + data = self._extract_item(items[0]) + data['id'] = id + + return data + else: + # playlist of songs + entries = [] + + for i, item in enumerate(items, 1): + entry = self._extract_item(item) + entry['id'] = '%s-%d' % (id, i) + entries.append(entry) + + return { + '_type': 'playlist', + 'id': id, + 'title': playlist_title, + 'entries': entries, + } + + +class ZingMp3SongIE(ZingMp3BaseInfoExtractor): + _VALID_URL = r'https?://mp3\.zing\.vn/bai-hat/(?P<slug>[^/]+)/(?P<song_id>\w+)\.html' + _TESTS = [{ + 'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html', + 'md5': 'ead7ae13693b3205cbc89536a077daed', + 'info_dict': { + 'id': 'ZWZB9WAB', + 'title': 'Xa Mãi Xa', + 'ext': 'mp3', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }] + IE_NAME = 'zingmp3:song' + IE_DESC = 'mp3.zing.vn songs' + + def _real_extract(self, url): + matched = re.match(self._VALID_URL, url) + slug = matched.group('slug') + song_id = matched.group('song_id') + + webpage = self._download_webpage( + 'http://mp3.zing.vn/bai-hat/%s/%s.html' % (slug, song_id), song_id) + + player_xml_url = self._search_regex( + r'&xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url') + + return self._extract_player_xml(player_xml_url, song_id) + + +class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor): + _VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html' + _TESTS = [{ + 'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html', + 'info_dict': { + '_type': 'playlist', + 'id': 'ZWZBWDAF', + 'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless', + }, + 'playlist_count': 10, + }] + IE_NAME = 'zingmp3:album' + IE_DESC = 'mp3.zing.vn albums' + + def _real_extract(self, url): + matched = re.match(self._VALID_URL, url) + slug = matched.group('slug') + album_id = matched.group('album_id') + + webpage = self._download_webpage( + 'http://mp3.zing.vn/album/%s/%s.html' % (slug, album_id), album_id) + player_xml_url = self._search_regex( + r'&xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url') + + return self._extract_player_xml( + player_xml_url, album_id, + playlist_title=self._og_search_title(webpage)) |