diff options
Diffstat (limited to 'youtube_dl/extractor')
364 files changed, 11891 insertions, 4106 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d12e741a0..647e0a8c2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,8 +1,13 @@ +from __future__ import unicode_literals + from .abc import ABCIE from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE +from .adobetv import AdobeTVIE from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE +from .aljazeera import AlJazeeraIE +from .alphaporno import AlphaPornoIE from .anitube import AnitubeIE from .anysex import AnySexIE from .aol import AolIE @@ -20,19 +25,27 @@ from .arte import ( ArteTVDDCIE, ArteTVEmbedIE, ) +from .atresplayer import AtresPlayerIE +from .atttechchannel import ATTTechChannelIE +from .audiomack import AudiomackIE, AudiomackAlbumIE 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 @@ -43,7 +56,7 @@ 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 @@ -54,15 +67,20 @@ from .cnet import CNETIE from .cnn import ( CNNIE, CNNBlogsIE, + CNNArticleIE, ) from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE +from .comcarcoff import ComCarCoffIE +from .commonmistakes import CommonMistakesIE 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, @@ -76,12 +94,14 @@ from .dotsub import DotsubIE from .dreisat import DreiSatIE from .drtuber import DrTuberIE from .drtv import DRTVIE +from .dvtv import DVTVIE from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE +from .echomsk import EchoMskIE from .ehow import EHowIE from .eighttracks import EightTracksIE from .einthusan import EinthusanIE @@ -94,6 +114,7 @@ from .elpais import ElPaisIE from .empflix import EMPFlixIE from .engadget import EngadgetIE from .eporner import EpornerIE +from .eroprofile import EroProfileIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE @@ -111,7 +132,10 @@ 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 ( @@ -123,6 +147,7 @@ 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 ( @@ -134,15 +159,25 @@ from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE +from .giantbomb import GiantBombIE +from .giga import GigaIE +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 .groupon import GrouponIE from .hark import HarkIE +from .heise import HeiseIE +from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .hitbox import HitboxIE, HitboxLiveIE from .hornbunny import HornBunnyIE from .hostingbulk import HostingBulkIE from .hotnewhiphop import HotNewHipHopIE @@ -170,7 +205,6 @@ 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 .karaoketv import KaraoketvIE @@ -182,6 +216,7 @@ 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 ( @@ -189,6 +224,7 @@ from .livestream import ( LivestreamOriginalIE, LivestreamShortenerIE, ) +from .lrt import LRTIE from .lynda import ( LyndaIE, LyndaCourseIE @@ -201,6 +237,7 @@ 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 @@ -227,9 +264,10 @@ 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 ( @@ -238,12 +276,14 @@ from .nbc import ( ) from .ndr import NDRIE from .ndtv import NDTVIE +from .netzkino import NetzkinoIE +from .nerdcubed import NerdCubedFeedIE 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 @@ -262,7 +302,9 @@ from .nrk import ( from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE +from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE +from .openfilm import OpenFilmIE from .orf import ( ORFTVthekIE, ORFOE1IE, @@ -271,7 +313,10 @@ from .orf import ( 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 @@ -282,24 +327,31 @@ 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 .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE +from .restudy import RestudyIE from .reverbnation import ReverbNationIE from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rte import RteIE from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE +from .rtp import RTPIE from .rts import RTSIE from .rtve import RTVEALaCartaIE, RTVELiveIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, RutubeChannelIE, + RutubeEmbedIE, RutubeMovieIE, RutubePersonIE, ) @@ -309,7 +361,11 @@ from .savefrom import SaveFromIE from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE +from .screencastomatic import ScreencastOMaticIE +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 @@ -341,7 +397,9 @@ 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 @@ -351,6 +409,8 @@ 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, @@ -359,16 +419,25 @@ 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 .teletask import TeleTaskIE 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 +from .thvideo import ( + THVideoIE, + THVideoPlaylistIE +) from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE @@ -377,11 +446,14 @@ 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 .tvp import TvpIE, TvpSeriesIE from .tvplay import TVPlayIE +from .twentyfourvideo import TwentyFourVideoIE +from .twitch import TwitchIE from .ubu import UbuIE from .udemy import ( UdemyIE, @@ -397,6 +469,7 @@ 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 @@ -407,13 +480,16 @@ from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE from .vidme import VidmeIE +from .vidzi import VidziIE +from .vier import VierIE, VierVideosIE from .vimeo import ( VimeoIE, - VimeoChannelIE, - VimeoUserIE, VimeoAlbumIE, + VimeoChannelIE, VimeoGroupsIE, + VimeoLikesIE, VimeoReviewIE, + VimeoUserIE, VimeoWatchLaterIE, ) from .vimple import VimpleIE @@ -422,12 +498,17 @@ 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 @@ -436,6 +517,7 @@ from .wdr import ( WDRMobileIE, WDRMausIE, ) +from .webofstories import WebOfStoriesIE from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE @@ -444,14 +526,16 @@ 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 .xxxymovies import XXXYMoviesIE from .yahoo import ( YahooIE, - YahooNewsIE, YahooSearchIE, ) +from .yesjapan import YesJapanIE from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE @@ -469,14 +553,16 @@ from .youtube import ( YoutubeSearchURLIE, YoutubeShowIE, YoutubeSubscriptionsIE, - YoutubeTopListIE, + YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, YoutubeUserIE, YoutubeWatchLaterIE, ) - -from .zdf import ZDFIE - +from .zdf import ZDFIE, ZDFChannelIE +from .zingmp3 import ( + ZingMp3SongIE, + ZingMp3AlbumIE, +) _ALL_CLASSES = [ klass @@ -493,6 +579,17 @@ def gen_extractors(): return [klass() for klass in _ALL_CLASSES] +def list_extractors(age_limit): + """ + Return a list of extractors that are suitable for the given age, + sorted by extractor ID. + """ + + return sorted( + filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()), + key=lambda ie: ie.IE_NAME.lower()) + + 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 c983ef0f5..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 @@ -18,15 +19,14 @@ class AcademicEarthCourseIE(InfoExtractor): } 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/adobetv.py b/youtube_dl/extractor/adobetv.py new file mode 100644 index 000000000..28e07f8b0 --- /dev/null +++ b/youtube_dl/extractor/adobetv.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, + str_to_int, +) + + +class AdobeTVIE(InfoExtractor): + _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)' + + _TEST = { + 'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/', + 'md5': '9bc5727bcdd55251f35ad311ca74fa1e', + 'info_dict': { + 'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop', + 'ext': 'mp4', + 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop', + 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311', + 'thumbnail': 're:https?://.*\.jpg$', + 'upload_date': '20110914', + 'duration': 60, + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + player = self._parse_json( + self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'), + video_id) + + title = player.get('title') or self._search_regex( + r'data-title="([^"]+)"', webpage, 'title') + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + upload_date = unified_strdate( + self._html_search_meta('datepublished', webpage, 'upload date')) + + duration = parse_duration( + self._html_search_meta('duration', webpage, 'duration') + or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration')) + + view_count = str_to_int(self._search_regex( + r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>', + webpage, 'view count')) + + formats = [{ + 'url': source['src'], + 'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None, + 'tbr': source.get('bitrate'), + } for source in player['sources']] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index b4b40f2d4..502a9c25a 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -2,122 +2,150 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor +from ..utils import ( + ExtractorError, + xpath_text, + float_or_none, +) + class AdultSwimIE(InfoExtractor): - _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' - _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 - 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') + segment_title = '%s - %s' % (show_title, episode_title) + if len(segment_ids) > 1: + segment_title += ' Part %d' % (part_num + 1) - 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 = float_or_none( + xpath_text(idoc, './/trt', 'segment duration').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) @@ -126,18 +154,16 @@ 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/aljazeera.py b/youtube_dl/extractor/aljazeera.py new file mode 100644 index 000000000..612708e25 --- /dev/null +++ b/youtube_dl/extractor/aljazeera.py @@ -0,0 +1,35 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class AlJazeeraIE(InfoExtractor): + _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html' + + _TEST = { + 'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html', + 'info_dict': { + 'id': '3792260579001', + 'ext': 'mp4', + 'title': 'The Slum - Episode 1: Deliverance', + 'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.', + 'uploader': 'Al Jazeera English', + }, + 'add_ie': ['Brightcove'], + } + + def _real_extract(self, url): + program_name = self._match_id(url) + webpage = self._download_webpage(url, program_name) + brightcove_id = self._search_regex( + r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id') + + return { + '_type': 'url', + 'url': ( + 'brightcove:' + 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc' + '&%40videoPlayer={0}'.format(brightcove_id) + ), + 'ie_key': 'Brightcove', + } diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index 7bd797884..7d65b8193 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -5,15 +5,14 @@ import re import json from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_str, qualities, - determine_ext, ) class AllocineIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?' + _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?' _TESTS = [{ 'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html', @@ -22,7 +21,7 @@ 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', }, }, { @@ -45,6 +44,9 @@ class AllocineIE(InfoExtractor): 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac', 'thumbnail': 're:http://.*\.jpg', }, + }, { + 'url': 'http://www.allocine.fr/video/video-19550147/', + 'only_matching': True, }] def _real_extract(self, url): @@ -75,9 +77,7 @@ class AllocineIE(InfoExtractor): 'format_id': format_id, 'quality': quality(format_id), 'url': v, - 'ext': determine_ext(v), }) - self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/alphaporno.py b/youtube_dl/extractor/alphaporno.py new file mode 100644 index 000000000..c34719d1f --- /dev/null +++ b/youtube_dl/extractor/alphaporno.py @@ -0,0 +1,77 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + parse_duration, + parse_filesize, + int_or_none, +) + + +class AlphaPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/', + 'md5': 'feb6d3bba8848cd54467a87ad34bd38e', + 'info_dict': { + 'id': '258807', + 'display_id': 'sensual-striptease-porn-with-samantha-alexandra', + 'ext': 'mp4', + 'title': 'Sensual striptease porn with Samantha Alexandra', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1418694611, + 'upload_date': '20141216', + 'duration': 387, + 'filesize_approx': 54120000, + 'tbr': 1145, + 'categories': list, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None) + + video_url = self._search_regex( + r"video_url\s*:\s*'([^']+)'", webpage, 'video url') + ext = self._html_search_meta( + 'encodingFormat', webpage, 'ext', default='.mp4')[1:] + + title = self._search_regex( + [r'<meta content="([^"]+)" itemprop="description">', + r'class="title" itemprop="name">([^<]+)<'], + webpage, 'title') + thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date')) + duration = parse_duration(self._html_search_meta( + 'duration', webpage, 'duration')) + filesize_approx = parse_filesize(self._html_search_meta( + 'contentSize', webpage, 'file size')) + bitrate = int_or_none(self._html_search_meta( + 'bitrate', webpage, 'bitrate')) + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'filesize_approx': filesize_approx, + 'tbr': bitrate, + 'categories': categories, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index 47f8e4157..b51eafc45 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .fivemin import FiveMinIE class AolIE(InfoExtractor): @@ -42,31 +41,30 @@ class AolIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - playlist_id = mobj.group('playlist_id') - if playlist_id and not self._downloader.params.get('noplaylist'): - self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) + if not playlist_id or self._downloader.params.get('noplaylist'): + return self.url_result('5min:%s' % video_id) - webpage = self._download_webpage(url, playlist_id) - title = self._html_search_regex( - r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title') - playlist_html = self._search_regex( - r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage, - 'playlist HTML') - entries = [{ - '_type': 'url', - 'url': 'aol-video:%s' % m.group('id'), - 'ie_key': 'Aol', - } for m in re.finditer( - r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>", - playlist_html)] + self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': mobj.group('playlist_display_id'), - 'title': title, - 'entries': entries, - } + webpage = self._download_webpage(url, playlist_id) + title = self._html_search_regex( + r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title') + playlist_html = self._search_regex( + r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage, + 'playlist HTML') + entries = [{ + '_type': 'url', + 'url': 'aol-video:%s' % m.group('id'), + 'ie_key': 'Aol', + } for m in re.finditer( + r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>", + playlist_html)] - return FiveMinIE._build_result(video_id) + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': mobj.group('playlist_display_id'), + 'title': title, + 'entries': entries, + } diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 748608826..15006336f 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,5 +1,4 @@ -#coding: utf-8 - +# coding: utf-8 from __future__ import unicode_literals import re @@ -26,8 +25,7 @@ class AparatIE(InfoExtractor): } 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 @@ -40,15 +38,15 @@ class AparatIE(InfoExtractor): 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 4359b88d1..7cd0482c7 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -4,8 +4,8 @@ import re import json from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( - compat_urlparse, int_or_none, ) @@ -70,15 +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) @@ -86,7 +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() diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 34ce8429b..9fc35a42b 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -1,42 +1,48 @@ from __future__ import unicode_literals -import json -import re - from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' - _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' - _TEST = { - "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", - 'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv', + _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' + _TESTS = [{ + 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'md5': '8af1d4cf447933ed3c7f4871162602db', 'info_dict': { - "title": "1968 Demo - FJCC Conference Presentation Reel #1", - "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>", - "upload_date": "19681210", - "uploader": "SRI International" + 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect', + 'ext': 'ogv', + 'title': '1968 Demo - FJCC Conference Presentation Reel #1', + 'description': 'md5:1780b464abaca9991d8968c877bb53ed', + 'upload_date': '19681210', + 'uploader': 'SRI International' + } + }, { + 'url': 'https://archive.org/details/Cops1922', + 'md5': '18f2a19e6d89af8425671da1cf3d4e04', + 'info_dict': { + 'id': 'Cops1922', + 'ext': 'ogv', + 'title': 'Buster Keaton\'s "Cops" (1922)', + 'description': 'md5:70f72ee70882f713d4578725461ffcc3', } - } + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) json_url = url + ('?' if '?' in url else '&') + 'output=json' - json_data = self._download_webpage(json_url, video_id) - data = json.loads(json_data) + data = self._download_json(json_url, video_id) + + def get_optional(data_dict, field): + return data_dict['metadata'].get(field, [None])[0] - title = data['metadata']['title'][0] - description = data['metadata']['description'][0] - uploader = data['metadata']['creator'][0] - upload_date = unified_strdate(data['metadata']['date'][0]) + title = get_optional(data, 'title') + description = get_optional(data, 'description') + uploader = get_optional(data, 'creator') + upload_date = unified_strdate(get_optional(data, 'date')) formats = [ { diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 54cec1c2f..967bd865c 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -4,16 +4,16 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, qualities, - compat_urllib_parse_urlparse, - compat_urllib_parse, int_or_none, parse_duration, unified_strdate, xpath_text, + parse_xml, ) @@ -56,6 +56,11 @@ class ARDMediathekIE(InfoExtractor): 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="(.*?)"/>', @@ -187,4 +192,3 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } - diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 957d35979..929dd3cc5 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. @@ -38,7 +37,7 @@ class ArteTvIE(InfoExtractor): config_xml_url, video_id, note='Downloading configuration') formats = [{ - 'forma_id': q.attrib['quality'], + 'format_id': q.attrib['quality'], # The playpath starts at 'mp4:', if we don't manually # split the url, rtmpdump will incorrectly parse them 'url': q.text.split('mp4:', 1)[0], @@ -86,92 +85,70 @@ class ArteTVPlus7IE(InfoExtractor): 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 - # TODO: Might want not to drop videos that does not match requested language - # but to process those formats with lower precedence - 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 - # Sometimes there are neither videos of requested lang code - # nor original version videos available - # For such cases we just take all_formats as is - formats = all_formats - if not formats: - raise ExtractorError('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.get('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 diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py new file mode 100644 index 000000000..72e83bfc2 --- /dev/null +++ b/youtube_dl/extractor/atresplayer.py @@ -0,0 +1,114 @@ +from __future__ import unicode_literals + +import time +import hmac + +from .common import InfoExtractor +from ..utils import ( + compat_str, + compat_urllib_request, + int_or_none, + float_or_none, + xpath_text, + ExtractorError, +) + + +class AtresPlayerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html' + _TESTS = [ + { + 'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html', + 'md5': 'efd56753cda1bb64df52a3074f62e38a', + 'info_dict': { + 'id': 'capitulo-10-especial-solidario-nochebuena', + 'ext': 'mp4', + 'title': 'Especial Solidario de Nochebuena', + 'description': 'md5:e2d52ff12214fa937107d21064075bf1', + 'duration': 5527.6, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', + 'only_matching': True, + }, + ] + + _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J' + _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)' + _TIMESTAMP_SHIFT = 30000 + + _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json' + _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json' + _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s' + _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s' + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + episode_id = self._search_regex( + r'episode="([^"]+)"', webpage, 'episode id') + + timestamp = int_or_none(self._download_webpage( + self._TIME_API_URL, + video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) + timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) + token = hmac.new( + self._MAGIC.encode('ascii'), + (episode_id + timestamp_shifted).encode('utf-8') + ).hexdigest() + + formats = [] + for fmt in ['windows', 'android_tablet']: + request = compat_urllib_request.Request( + self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token)) + request.add_header('Youtubedl-user-agent', self._USER_AGENT) + + fmt_json = self._download_json( + request, video_id, 'Downloading %s video JSON' % fmt) + + result = fmt_json.get('resultDes') + if result.lower() != 'ok': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, result), expected=True) + + for _, video_url in fmt_json['resultObject'].items(): + if video_url.endswith('/Manifest'): + formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id)) + else: + formats.append({ + 'url': video_url, + 'format_id': 'android', + 'preference': 1, + }) + self._sort_formats(formats) + + player = self._download_json( + self._PLAYER_URL_TEMPLATE % episode_id, + episode_id) + + path_data = player.get('pathData') + + episode = self._download_xml( + self._EPISODE_URL_TEMPLATE % path_data, + video_id, 'Downloading episode XML') + + duration = float_or_none(xpath_text( + episode, './media/asset/info/technical/contentDuration', 'duration')) + + art = episode.find('./media/asset/info/art') + title = xpath_text(art, './name', 'title') + description = xpath_text(art, './description', 'description') + thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail') + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/atttechchannel.py b/youtube_dl/extractor/atttechchannel.py new file mode 100644 index 000000000..b01d35bb2 --- /dev/null +++ b/youtube_dl/extractor/atttechchannel.py @@ -0,0 +1,55 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class ATTTechChannelIE(InfoExtractor): + _VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)' + _TEST = { + 'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use', + 'info_dict': { + 'id': '11316', + 'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use', + 'ext': 'flv', + 'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use', + 'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20140127', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r"url\s*:\s*'(rtmp://[^']+)'", + webpage, 'video URL') + + video_id = self._search_regex( + r'mediaid\s*=\s*(\d+)', + webpage, 'video id', fatal=False) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + upload_date = unified_strdate(self._search_regex( + r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})', + webpage, 'upload date', fatal=False), False) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'ext': 'flv', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py new file mode 100644 index 000000000..8bfe50214 --- /dev/null +++ b/youtube_dl/extractor/audiomack.py @@ -0,0 +1,139 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools +import time + +from .common import InfoExtractor +from .soundcloud import SoundcloudIE +from ..utils import ( + ExtractorError, + url_basename, +) + + +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': '310086', + 'ext': 'mp3', + 'uploader': 'Roosh Williams', + 'title': 'Extraordinary' + } + }, + # audiomack wrapper around soundcloud song + { + '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): + # URLs end with [uploader name]/[uploader title] + # this title is whatever the user types in, and is rarely + # the proper song title. Real metadata is in the api response + album_url_tag = self._match_id(url) + + # Request the extended version of the api for extra fields like artist and title + api_response = self._download_json( + 'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % ( + album_url_tag, time.time()), + album_url_tag) + + # API is inconsistent with errors + if 'url' not in api_response or not api_response['url'] or 'error' in api_response: + raise ExtractorError('Invalid url %s', 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(api_response['url']): + return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'} + + return { + 'id': api_response.get('id', album_url_tag), + 'uploader': api_response.get('artist'), + 'title': api_response.get('title'), + 'url': api_response['url'], + } + + +class AudiomackAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)' + IE_NAME = 'audiomack:album' + _TESTS = [ + # Standard album playlist + { + 'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape', + 'playlist_count': 15, + 'info_dict': + { + 'id': '812251', + 'title': 'Tha Tour: Part 2 (Official Mixtape)' + } + }, + # Album playlist ripped from fakeshoredrive with no metadata + { + 'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project', + 'playlist': [{ + 'info_dict': { + 'title': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu', + 'id': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu', + 'ext': 'mp3', + } + }], + 'params': { + 'playliststart': 8, + 'playlistend': 8, + } + } + ] + + def _real_extract(self, url): + # URLs end with [uploader name]/[uploader title] + # this title is whatever the user types in, and is rarely + # the proper song title. Real metadata is in the api response + album_url_tag = self._match_id(url) + result = {'_type': 'playlist', 'entries': []} + # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata + # Therefore we don't know how many songs the album has and must infi-loop until failure + for track_no in itertools.count(): + # Get song's metadata + api_response = self._download_json( + 'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d' + % (album_url_tag, track_no, time.time()), album_url_tag, + note='Querying song information (%d)' % (track_no + 1)) + + # Total failure, only occurs when url is totally wrong + # Won't happen in middle of valid playlist (next case) + if 'url' not in api_response or 'error' in api_response: + raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url)) + # URL is good but song id doesn't exist - usually means end of playlist + elif not api_response['url']: + break + else: + # Pull out the album metadata and add to result (if it exists) + for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]: + if apikey in api_response and resultkey not in result: + result[resultkey] = api_response[apikey] + song_id = url_basename(api_response['url']).rpartition('.')[0] + result['entries'].append({ + 'id': api_response.get('id', song_id), + 'uploader': api_response.get('artist'), + 'title': api_response.get('title', song_id), + 'url': api_response['url'], + }) + return result diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 20bf12550..a1b666be0 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -3,10 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( - compat_urllib_parse, determine_ext, ExtractorError, + remove_end, ) @@ -24,27 +25,21 @@ 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') - title = title.strip() - links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage) - links = map(compat_urllib_parse.unquote, links) - - thumbnail = None - video_url = None - for link in links: - if link.endswith('.png'): - thumbnail = link - elif '/videos/' in link: - video_url = link + title = self._html_search_regex( + r'<title>\s*(?P<title>.+?)\s*</title>', webpage, 'title') + video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage) + video_url = compat_urllib_parse.unquote(video_urls[0]) + thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage) + thumbnail = compat_urllib_parse.unquote(thumbnails[0]) + if not video_url: raise ExtractorError('Could not find video URL') + ext = '.' + determine_ext(video_url) - if ext == title[-len(ext):]: - title = title[:-len(ext)] + title = remove_end(title, ext) return { 'id': video_id, 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 de5d4faf3..98e1443ab 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -5,7 +5,7 @@ import json import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, ) @@ -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'] @@ -73,10 +73,11 @@ 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) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index c569aa4d2..b45d68a61 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -4,9 +4,11 @@ import json import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urlparse, +) +from ..utils import ( ExtractorError, ) @@ -15,13 +17,23 @@ 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 +71,9 @@ 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 +85,12 @@ 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>.*)$' m_url = re.match(re_url, initial_url) - #We build the url we will use to get the final track url + # We build the url we will use to get the final track url # This url is build in Bandcamp in the script download_bunde_*.js request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts')) final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') # If we could correctly generate the .rand field the url would be - #in the "download_url" key + # in the "download_url" key final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) return { @@ -94,26 +106,31 @@ class BandcampIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' - _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' + _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+)|/?(?:$|[?#]))' _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 }, @@ -124,6 +141,12 @@ class BandcampAlbumIE(InfoExtractor): 'title': 'Hierophany of the Open Grave', }, 'playlist_mincount': 9, + }, { + 'url': 'http://dotscale.bandcamp.com', + 'info_dict': { + 'title': 'Loom', + }, + 'playlist_mincount': 7, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index 75e608f99..1cf48fe0d 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -1,15 +1,16 @@ 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): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' _TESTS = [ { @@ -17,8 +18,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope: Leonard Cohen', - 'description': 'md5:db4755d7a665ae72343779f7dacb402c', + 'title': 'Kaleidoscope, Leonard Cohen', + 'description': 'The Canadian poet and songwriter reflects on his musical career.', 'duration': 1740, }, 'params': { @@ -55,6 +56,68 @@ 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', + }, { + 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', + 'info_dict': { + 'id': 'b04v209v', + 'ext': 'flv', + 'title': 'Pete Tong, The Essential New Tune Special', + 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", + 'duration': 10800, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', + 'note': 'Audio', + 'info_dict': { + 'id': 'p02frcch', + 'ext': 'flv', + 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', + 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', + 'duration': 3507, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', + 'note': 'Video', + 'info_dict': { + 'id': 'p025c103', + 'ext': 'flv', + 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', + 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', + 'duration': 226, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', + 'only_matching': True, } ] @@ -102,6 +165,10 @@ 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 +225,101 @@ 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') + 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: + raise - 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) + formats = [] + subtitles = None + + 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) + + return formats, subtitles - playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id, - 'Downloading playlist XML') + def _download_playlist(self, playlist_id): + try: + playlist = self._download_json( + 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, + playlist_id, 'Downloading playlist JSON') + + version = playlist.get('defaultAvailableVersion') + if version: + smp_config = version['smpConfig'] + title = smp_config['title'] + description = smp_config['summary'] + for item in smp_config['items']: + kind = item['kind'] + if kind != 'programme' and kind != 'radioProgramme': + continue + programme_id = item.get('vpid') + duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) + return programme_id, title, description, duration, formats, subtitles + except ExtractorError as ee: + if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: + raise + + # fallback to legacy playlist + playlist = self._download_xml( + 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, + playlist_id, 'Downloading legacy 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 + msg = 'Episode %s is not yet available' % playlist_id elif reason == 'postAvailability': - msg = 'Episode %s is no longer available' % group_id + msg = 'Episode %s is no longer available' % playlist_id + elif reason == 'noMedia': + msg = 'Episode %s is not currently available' % playlist_id else: - msg = 'Episode %s is not available: %s' % (group_id, reason) + msg = 'Episode %s is not available: %s' % (playlist_id, reason) raise ExtractorError(msg, expected=True) - 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 - programme_id = item.get('identifier') duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) - 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') + return programme_id, title, description, duration, formats, subtitles + + def _real_extract(self, url): + group_id = self._match_id(url) - 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) + webpage = self._download_webpage(url, group_id, 'Downloading video page') + + programme_id = self._search_regex( + r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + 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: + programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) if self._downloader.params.get('listsubtitles', False): self._list_available_subtitles(programme_id, subtitles) @@ -220,4 +334,4 @@ 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 index 314e37f8b..4e79fea8f 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -40,7 +40,7 @@ class BeegIE(InfoExtractor): 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) diff --git a/youtube_dl/extractor/behindkink.py b/youtube_dl/extractor/behindkink.py index 31fdc0dcc..1bdc25812 100644 --- a/youtube_dl/extractor/behindkink.py +++ b/youtube_dl/extractor/behindkink.py @@ -10,15 +10,15 @@ 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/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/', - 'md5': '41ad01222b8442089a55528fec43ec01', + 'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/', + 'md5': '507b57d8fdcd75a41a9a7bdb7989c762', 'info_dict': { - 'id': '36370', + 'id': '37127', 'ext': 'mp4', - 'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!', - 'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...', - 'upload_date': '20140814', - 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg', + '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, } } @@ -26,26 +26,19 @@ class BehindKinkIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') - year = mobj.group('year') - month = mobj.group('month') - day = mobj.group('day') - upload_date = year + month + day webpage = self._download_webpage(url, display_id) video_url = self._search_regex( - r"'file':\s*'([^']+)'", - webpage, 'URL base') - - video_id = url_basename(video_url) - video_id = video_id.split('_')[0] + 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, - 'ext': 'mp4', 'title': self._og_search_title(webpage), - 'display_id': display_id, 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), 'upload_date': upload_date, diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py new file mode 100644 index 000000000..d2abd4d77 --- /dev/null +++ b/youtube_dl/extractor/bet.py @@ -0,0 +1,107 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urllib_parse +from ..utils import ( + 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': '740ab250-bb94-4a8a-8787-fe0de7c74471', + '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$', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', + 'info_dict': { + 'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d', + 'display_id': 'justice-for-ferguson-a-community-reacts', + 'ext': 'flv', + 'title': 'Justice for Ferguson: A Community Reacts', + 'description': 'A BET News special.', + 'duration': 1696, + 'timestamp': 1416942360, + 'upload_date': '20141125', + 'uploader': 'admin', + 'thumbnail': 're:(?i)^https?://.*\.jpg$', + }, + '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/bilibili.py b/youtube_dl/extractor/bilibili.py index 0d5889f5d..75d744852 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -5,8 +5,6 @@ import re from .common import InfoExtractor from ..utils import ( - compat_parse_qs, - ExtractorError, int_or_none, unified_strdate, ) @@ -29,10 +27,9 @@ class BiliBiliIE(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_code = self._search_regex( r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code') @@ -55,45 +52,38 @@ class BiliBiliIE(InfoExtractor): thumbnail = self._html_search_meta( 'thumbnailUrl', video_code, 'thumbnail', fatal=False) - player_params = compat_parse_qs(self._html_search_regex( - r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"', - webpage, 'player params')) + cid = self._search_regex(r'cid=(\d+)', webpage, 'cid') - if 'cid' in player_params: - cid = player_params['cid'][0] + lq_doc = self._download_xml( + 'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid, + video_id, + note='Downloading LQ video info' + ) + lq_durl = lq_doc.find('./durl') + formats = [{ + 'format_id': 'lq', + 'quality': 1, + 'url': lq_durl.find('./url').text, + 'filesize': int_or_none( + lq_durl.find('./size'), get_attr='text'), + }] - lq_doc = self._download_xml( - 'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid, - video_id, - note='Downloading LQ video info' - ) - lq_durl = lq_doc.find('.//durl') - formats = [{ - 'format_id': 'lq', - 'quality': 1, - 'url': lq_durl.find('./url').text, + hq_doc = self._download_xml( + 'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid, + video_id, + note='Downloading HQ video info', + fatal=False, + ) + if hq_doc is not False: + hq_durl = hq_doc.find('./durl') + formats.append({ + 'format_id': 'hq', + 'quality': 2, + 'ext': 'flv', + 'url': hq_durl.find('./url').text, 'filesize': int_or_none( - lq_durl.find('./size'), get_attr='text'), - }] - - hq_doc = self._download_xml( - 'http://interface.bilibili.cn/playurl?cid=%s' % cid, - video_id, - note='Downloading HQ video info', - fatal=False, - ) - if hq_doc is not False: - hq_durl = hq_doc.find('.//durl') - formats.append({ - 'format_id': 'hq', - 'quality': 2, - 'ext': 'flv', - 'url': hq_durl.find('./url').text, - 'filesize': int_or_none( - hq_durl.find('./size'), get_attr='text'), - }) - else: - raise ExtractorError('Unsupported player parameters: %r' % (player_params,)) + hq_durl.find('./size'), get_attr='text'), + }) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index 57d17bea3..14b814120 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -4,13 +4,17 @@ 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, ) @@ -64,20 +68,55 @@ class BlipTVIE(SubtitlesInfoExtractor): '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') @@ -113,7 +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'): @@ -128,11 +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) @@ -165,9 +204,17 @@ class BlipTVIE(SubtitlesInfoExtractor): class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' + _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' _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) @@ -178,6 +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 @@ -214,4 +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 4e2960c62..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, @@ -26,6 +24,8 @@ class BRIE(InfoExtractor): 'title': 'Wenn das Traditions-Theater wackelt', 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt', 'duration': 34, + 'uploader': 'BR', + 'upload_date': '20140802', } }, { @@ -66,8 +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 294670386..003152c4e 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -6,24 +6,26 @@ import json import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse, - find_xpath_attr, - fix_xml_ampersands, - compat_urlparse, +from ..compat import ( + compat_parse_qs, compat_str, + compat_urllib_parse, + compat_urllib_parse_urlparse, compat_urllib_request, - compat_parse_qs, - + compat_urlparse, +) +from ..utils import ( determine_ext, ExtractorError, - unsmuggle_url, + find_xpath_attr, + fix_xml_ampersands, unescapeHTML, + unsmuggle_url, ) class BrightcoveIE(InfoExtractor): - _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)' + _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)' _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' _TESTS = [ @@ -87,6 +89,15 @@ 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 +112,8 @@ 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')) @@ -209,7 +222,7 @@ class BrightcoveIE(InfoExtractor): webpage = self._download_webpage(req, video_id) error_msg = self._html_search_regex( - r"<h1>We're sorry.</h1>\s*<p>(.*?)</p>", webpage, + r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage, 'error message', default=None) if error_msg is not None: raise ExtractorError( @@ -251,12 +264,21 @@ 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..a5d2af174 --- /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': 're: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': 're:© 2014 Munchkin the Shih Tzu', + 'uploader': 'Munchkin the Shih Tzu', + 'title': 're: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..11d18d74a 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -5,17 +5,25 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, + HEADRequest, 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 +33,83 @@ 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']) + + fmt_url = next(iter(media.find('VIDEOS'))).text + if '/geo' in fmt_url.lower(): + response = self._request_webpage( + HEADRequest(fmt_url), video_id, + 'Checking if the video is georestricted') + if '/blocage' in response.geturl(): + raise ExtractorError( + 'The video is not available in your country', + expected=True) - 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 +124,4 @@ 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 db48dc24f..e43756ec6 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -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..f70e090bb 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -3,55 +3,50 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..utils import ( +from .subtitles import SubtitlesInfoExtractor +from ..compat import ( compat_urllib_request, compat_urllib_parse, compat_urllib_parse_urlparse, +) +from ..utils import ( ExtractorError, + float_or_none, ) -class CeskaTelevizeIE(InfoExtractor): +class CeskaTelevizeIE(SubtitlesInfoExtractor): _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)' _TESTS = [ { - 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka', - 'info_dict': { - 'id': '213512120230004', - 'ext': 'flv', - 'title': 'První republika: Španělská chřipka', - 'duration': 3107.4, - }, - 'params': { - 'skip_download': True, # requires rtmpdump - }, - 'skip': 'Works only from Czech Republic.', - }, - { - 'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt', + 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220', 'info_dict': { - 'id': '20138143440', - 'ext': 'flv', - 'title': 'Tsatsiki, maminka a policajt', - 'duration': 6754.1, + 'id': '214411058091220', + 'ext': 'mp4', + 'title': 'Hyde Park Civilizace', + 'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 3350, }, 'params': { - 'skip_download': True, # requires rtmpdump + # m3u8 download + 'skip_download': True, }, - 'skip': 'Works only from Czech Republic.', }, { 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina', 'info_dict': { 'id': '14716', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'První republika: Zpěvačka z Dupárny Bobina', - 'duration': 90, + 'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 88.4, }, 'params': { - 'skip_download': True, # requires rtmpdump + # m3u8 download + 'skip_download': True, }, }, ] @@ -78,8 +73,9 @@ class CeskaTelevizeIE(InfoExtractor): 'requestSource': 'iVysilani', } - req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url', - data=compat_urllib_parse.urlencode(data)) + req = compat_urllib_request.Request( + 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', + data=compat_urllib_parse.urlencode(data)) req.add_header('Content-type', 'application/x-www-form-urlencoded') req.add_header('x-addr', '127.0.0.1') @@ -88,39 +84,72 @@ class CeskaTelevizeIE(InfoExtractor): playlistpage = self._download_json(req, video_id) - req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url'])) + playlist_url = playlistpage['url'] + if playlist_url == 'error_region': + raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) + + req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url)) 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']: - base_url = i.attrib['base'] - parsedurl = compat_urllib_parse_urlparse(base_url) - duration = i.attrib['duration'] - - for video in i.findall('video'): - if video.attrib['label'] != 'AD': - format_id = video.attrib['label'] - play_path = video.attrib['src'] - vbr = int(video.attrib['system-bitrate']) - - formats.append({ - 'format_id': format_id, - 'url': base_url, - 'vbr': vbr, - 'play_path': play_path, - 'app': parsedurl.path[1:] + '?' + parsedurl.query, - 'rtmp_live': True, - 'ext': 'flv', - }) + playlist = self._download_json(req, video_id) + item = playlist['playlist'][0] + formats = [] + for format_id, stream_url in item['streamUrls'].items(): + formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4')) self._sort_formats(formats) + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + duration = float_or_none(item.get('duration')) + thumbnail = item.get('previewImageUrl') + + subtitles = {} + subs = item.get('subtitles') + if subs: + subtitles['cs'] = subs[0]['url'] + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles)) + return { 'id': episode_id, - 'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'), - 'duration': float(duration), + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, 'formats': formats, + 'subtitles': subtitles, } + + @staticmethod + def _fix_subtitles(subtitles): + """ Convert millisecond-based subtitles to SRT """ + if subtitles is None: + return subtitles # subtitles not requested + + def _msectotimecode(msec): + """ Helper utility to convert milliseconds to timecode """ + components = [] + for divider in [1000, 60, 60, 100]: + components.append(msec % divider) + msec //= divider + return "{3:02}:{2:02}:{1:02},{0:03}".format(*components) + + def _fix_subtitle(subtitle): + for line in subtitle.splitlines(): + m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line) + if m: + yield m.group(1) + start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:]) + yield "{0} --> {1}".format(start, stop) + else: + yield line + + fixed_subtitles = {} + for k, v in subtitles.items(): + fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v)) + return fixed_subtitles 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/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 65c12136a..2edab90a3 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -4,7 +4,6 @@ import json import re from .common import InfoExtractor -from ..utils import int_or_none _translation_table = { @@ -35,14 +34,11 @@ class CliphunterIE(InfoExtractor): 'title': 'Fun Jynx Maze solo', 'thumbnail': 're:^https?://.*\.jpg$', 'age_limit': 18, - 'duration': 1317, } } 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( @@ -86,14 +82,11 @@ class CliphunterIE(InfoExtractor): thumbnail = self._search_regex( r"var\s+mov_thumb\s*=\s*'([^']+)';", webpage, 'thumbnail', fatal=False) - duration = int_or_none(self._search_regex( - r'pl_dur\s*=\s*([0-9]+)', webpage, 'duration', fatal=False)) return { 'id': video_id, 'title': video_title, 'formats': formats, - 'duration': duration, '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 index 386f080d2..abf8cc280 100644 --- a/youtube_dl/extractor/cloudy.py +++ b/youtube_dl/extractor/cloudy.py @@ -4,14 +4,16 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_parse_qs, compat_urllib_parse, - remove_end, - HEADRequest, compat_HTTPError, ) +from ..utils import ( + ExtractorError, + HEADRequest, + remove_end, +) class CloudyIE(InfoExtractor): 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..93e8d0de3 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -11,29 +11,40 @@ from ..utils import ( class CNNIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/ - (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' + _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/ + (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-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", } + }, { + 'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html', + 'md5': 'f14d02ebd264df951feb2400e2c25a1b', + 'info_dict': { + 'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln', + 'ext': 'mp4', + 'title': 'Nashville Ep. 1: Hand crafted skateboards', + 'description': 'md5:e7223a503315c9f150acac52e76de086', + 'upload_date': '20141222', + } }] def _real_extract(self, url): @@ -126,3 +137,28 @@ class CNNBlogsIE(InfoExtractor): 'url': cnn_url, 'ie_key': CNNIE.ie_key(), } + + +class CNNArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)' + _TEST = { + 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/', + 'md5': '275b326f85d80dff7592a9820f5dc887', + 'info_dict': { + 'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn', + 'ext': 'mp4', + 'title': 'Obama: We\'re not going to be intimidated', + 'description': 'md5:e735586f3dc936075fa654a4d91b21f9', + 'upload_date': '20141220', + }, + 'add_ie': ['CNN'], + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, url_basename(url)) + cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') + return { + '_type': 'url', + 'url': 'http://cnn.com/video/?/video/' + cnn_url, + 'ie_key': CNNIE.ie_key(), + } 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/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py new file mode 100644 index 000000000..9c25b2223 --- /dev/null +++ b/youtube_dl/extractor/comcarcoff.py @@ -0,0 +1,57 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import parse_iso8601 + + +class ComCarCoffIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)' + _TESTS = [{ + 'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/', + 'info_dict': { + 'id': 'miranda-sings-happy-thanksgiving-miranda', + 'ext': 'mp4', + 'upload_date': '20141127', + 'timestamp': 1417107600, + 'title': 'Happy Thanksgiving Miranda', + 'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.', + 'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg', + }, + 'params': { + 'skip_download': 'requires ffmpeg', + } + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + if not display_id: + display_id = 'comediansincarsgettingcoffee.com' + webpage = self._download_webpage(url, display_id) + + full_data = json.loads(self._search_regex( + r'<script type="application/json" id="videoData">(?P<json>.+?)</script>', + webpage, 'full data json')) + + video_id = full_data['activeVideo']['video'] + video_data = full_data['videos'][video_id] + thumbnails = [{ + 'url': video_data['images']['thumb'], + }, { + 'url': video_data['images']['poster'], + }] + formats = self._extract_m3u8_formats( + video_data['mediaUrl'], video_id, ext='mp4') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': video_data['title'], + 'description': video_data.get('description'), + 'timestamp': parse_iso8601(video_data.get('pubDate')), + 'thumbnails': thumbnails, + 'formats': formats, + 'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))), + } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 035046120..8d27af5e5 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -2,11 +2,12 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor from .mtv import MTVServicesInfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urllib_parse, +) +from ..utils import ( ExtractorError, float_or_none, unified_strdate, @@ -31,7 +32,7 @@ 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: @@ -49,7 +50,7 @@ class ComedyCentralShowsIE(InfoExtractor): )| (?P<interview> extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) - (?:[?#].*|$)''' + ''' _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', @@ -83,6 +84,9 @@ class ComedyCentralShowsIE(InfoExtractor): 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', 'only_matching': True, }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo', + 'only_matching': True, + }, { 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', 'only_matching': True, }, { @@ -109,18 +113,8 @@ class ComedyCentralShowsIE(InfoExtractor): '400': (384, 216), } - @staticmethod - def _transform_rtmp_url(rtmp_video_url): - m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', 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'): @@ -212,9 +206,6 @@ class ComedyCentralShowsIE(InfoExtractor): 'ext': self._video_extensions.get(format, 'mp4'), 'height': h, 'width': w, - - 'format_note': 'HTTP 400 at the moment (patches welcome!)', - 'preference': -100, }) formats.append({ 'format_id': 'rtmp-%s' % format, diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 60cab6f4e..03f3f18c8 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals import base64 +import datetime import hashlib import json import netrc @@ -11,16 +12,20 @@ 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 ( + age_restricted, clean_html, compiled_regex_type, ExtractorError, + float_or_none, int_or_none, RegexNotFoundError, sanitize_filename, @@ -36,11 +41,15 @@ class InfoExtractor(object): information about the video (or videos) the URL refers to. This information includes the real video URL, the video title, author and others. The information is stored in a dictionary which is then - passed to the FileDownloader. The FileDownloader processes this + passed to the YoutubeDL. The YoutubeDL processes this 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. @@ -70,6 +79,7 @@ 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 @@ -83,16 +93,30 @@ 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. + < -1000 to hide the format (if there is + another one which is strictly better) + * 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. + * stretched_ratio If given and not 1, indicates that the + video's pixels are not square. + width : height ratio as float. url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) @@ -100,6 +124,7 @@ 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", @@ -111,7 +136,7 @@ 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). @@ -125,6 +150,17 @@ class InfoExtractor(object): like_count: Number of positive ratings of the video dislike_count: Number of negative ratings of the video comment_count: Number of comments on the video + comments: A list of comments, each with one or more of the following + properties (all but one of text or html optional): + * "author" - human-readable name of the comment author + * "author_id" - user ID of the comment author + * "id" - Comment ID + * "html" - Comment as HTML + * "text" - Plain text of the comment + * "timestamp" - UNIX timestamp of comment + * "parent" - ID of the comment this one is replying to. + Set to "root" to indicate that this is a + comment to the original video. age_limit: Age restriction for the video, as an integer (years) webpage_url: The url to the video webpage, if given to youtube-dl it should allow to get the same result again. (It will be set @@ -136,6 +172,41 @@ class InfoExtractor(object): 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. @@ -165,6 +236,14 @@ 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 @@ -226,7 +305,6 @@ 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] @@ -235,8 +313,14 @@ 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) @@ -269,6 +353,12 @@ class InfoExtractor(object): raw_filename = basen + '.dump' filename = sanitize_filename(raw_filename, restricted=True) 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) @@ -287,11 +377,21 @@ class InfoExtractor(object): 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): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5): """ Returns the data of the page as a string """ - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + success = False + try_count = 0 + while success is False: + try: + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + success = True + except compat_http_client.IncompleteRead as e: + try_count += 1 + if try_count >= tries: + raise e + self._sleep(timeout, video_id) if res is False: return res else: @@ -319,12 +419,20 @@ class InfoExtractor(object): 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 = '' if video_id is None else '%s: ' % video_id @@ -351,19 +459,20 @@ class InfoExtractor(object): """Report attempt to log 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} @@ -371,9 +480,11 @@ 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. @@ -394,22 +505,25 @@ class InfoExtractor(object): _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('Unable to extract %s' % _name) else: self._downloader.report_warning('unable to extract %s; ' - 'please report this issue on http://yt-dl.org/bug' % _name) + '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: @@ -442,7 +556,7 @@ class InfoExtractor(object): raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) - + return (username, password) def _get_tfa_info(self): @@ -502,10 +616,10 @@ class InfoExtractor(object): if display_name is None: 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) + r'''(?isx)<meta + (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1) + [^>]+?content=(["\'])(?P<content>.*?)\2''' % 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') @@ -536,7 +650,7 @@ 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: @@ -581,6 +695,7 @@ 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, @@ -589,14 +704,16 @@ 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) @@ -625,8 +742,14 @@ class InfoExtractor(object): 'Unable to download f4m manifest') formats = [] + manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') + if not media_nodes: + manifest_version = '2.0' + media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') for i, media_el in enumerate(media_nodes): + if manifest_version == '2.0': + manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href') tbr = int_or_none(media_el.attrib.get('bitrate')) format_id = 'f4m-%d' % (i if tbr is None else tbr) formats.append({ @@ -659,7 +782,10 @@ class InfoExtractor(object): if re.match(r'^https?://', u) else compat_urlparse.urljoin(m3u8_url, u)) - m3u8_doc = self._download_webpage(m3u8_url, video_id) + 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>"[^"]+"|[^",]+)(?:,|$)') @@ -705,6 +831,112 @@ class InfoExtractor(object): 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) + + def get_testcases(self, include_onlymatching=False): + t = getattr(self, '_TEST', None) + if t: + assert not hasattr(self, '_TESTS'), \ + '%s has _TEST and _TESTS' % type(self).__name__ + tests = [t] + else: + tests = getattr(self, '_TESTS', []) + for t in tests: + if not include_onlymatching and t.get('only_matching', False): + continue + t['name'] = type(self).__name__[:-len('IE')] + yield t + + def is_suitable(self, age_limit): + """ Test whether the extractor is generally suitable for the given + age limit (i.e. pornographic sites are not, all others usually are) """ + + any_restricted = False + for tc in self.get_testcases(include_onlymatching=False): + if 'playlist' in tc: + tc = tc['playlist'][0] + is_restricted = age_restricted( + tc.get('info_dict', {}).get('age_limit'), age_limit) + if not is_restricted: + return True + any_restricted = any_restricted or is_restricted + return not any_restricted + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/commonmistakes.py b/youtube_dl/extractor/commonmistakes.py new file mode 100644 index 000000000..75c06903f --- /dev/null +++ b/youtube_dl/extractor/commonmistakes.py @@ -0,0 +1,29 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class CommonMistakesIE(InfoExtractor): + IE_DESC = False # Do not list + _VALID_URL = r'''(?x) + (?:url|URL) + ''' + + _TESTS = [{ + 'url': 'url', + 'only_matching': True, + }, { + 'url': 'URL', + 'only_matching': True, + }] + + def _real_extract(self, url): + msg = ( + 'You\'ve asked youtube-dl to download the URL "%s". ' + 'That doesn\'t make any sense. ' + 'Simply remove the parameter in your command or configuration.' + ) % url + if self._downloader.params.get('verbose'): + msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.' + raise ExtractorError(msg, expected=True) diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index ffbe4903b..3db4db4e4 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -5,12 +5,14 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - orderedSet, compat_urllib_parse_urlparse, compat_urlparse, ) +from ..utils import ( + orderedSet, +) class CondeNastIE(InfoExtractor): @@ -34,6 +36,8 @@ 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 f99888ecc..1680f532f 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -10,27 +10,28 @@ import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( + ExtractorError, 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(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' - _TEST = { + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' + _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', - #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412', 'info_dict': { 'id': '645513', 'ext': 'flv', @@ -39,12 +40,16 @@ class CrunchyrollIE(SubtitlesInfoExtractor): 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', 'uploader': 'Yomiuri Telecasting Corporation (YTV)', 'upload_date': '20131013', + 'url': 're:(?!.*&)', }, 'params': { # rtmp 'skip_download': True, }, - } + }, { + 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', + 'only_matching': True, + }] _FORMAT_IDS = { '360': ('60', '106'), @@ -68,11 +73,9 @@ class CrunchyrollIE(SubtitlesInfoExtractor): 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) @@ -98,8 +101,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor): return shaHash + [0] * 12 key = obfuscate_key(id) + class Counter: __value = iv + def next_value(self): temp = self.__value self.__value = inc(self.__value) @@ -107,19 +112,17 @@ class CrunchyrollIE(SubtitlesInfoExtractor): 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 _convert_subtitles_to_ass(self, subtitles): + def _convert_subtitles_to_ass(self, sub_root): output = '' def ass_bool(strvalue): @@ -128,10 +131,6 @@ class CrunchyrollIE(SubtitlesInfoExtractor): assvalue = '-1' return assvalue - sub_root = xml.etree.ElementTree.fromstring(subtitles) - if not sub_root: - return output - output = '[Script Info]\n' output += 'Title: %s\n' % sub_root.attrib["title"] output += 'ScriptType: v4.00+\n' @@ -188,7 +187,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text return output - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -229,20 +228,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False) formats = [] - for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): + for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', 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, @@ -251,8 +252,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 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) @@ -266,22 +268,60 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue + sub_root = xml.etree.ElementTree.fromstring(subtitle) if sub_format == 'ass': - subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle) + subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root) else: - subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + 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 541106684..955119d40 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -27,7 +27,6 @@ class CSpanIE(InfoExtractor): 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', # For whatever reason, the served video alternates between # two different ones - #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c', 'info_dict': { 'id': '340723', 'ext': 'mp4', 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 66a8f16d9..cf5841a7c 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,4 +1,4 @@ -#coding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re @@ -8,16 +8,19 @@ import itertools from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( - compat_urllib_request, +from ..compat import ( compat_str, + compat_urllib_request, +) +from ..utils import ( + ExtractorError, + int_or_none, orderedSet, str_to_int, - int_or_none, - ExtractorError, unescapeHTML, ) + class DailymotionBaseInfoExtractor(InfoExtractor): @staticmethod def _build_request(url): @@ -27,6 +30,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor): request.add_header('Cookie', 'ff=off') return request + class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): """Information Extractor for Dailymotion""" @@ -82,11 +86,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): ] 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 @@ -98,7 +98,7 @@ 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') @@ -116,7 +116,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): embed_page = self._download_webpage(embed_url, video_id, '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'] @@ -147,18 +147,23 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): self._list_available_subtitles(video_id, webpage) return - view_count = self._search_regex( - r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, '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, @@ -205,7 +210,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): 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) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 45d66e2e6..934da765e 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -5,7 +5,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -38,7 +38,7 @@ class DaumIE(InfoExtractor): canonical_url = 'http://tvpot.daum.net/v/%s' % video_id webpage = self._download_webpage(canonical_url, video_id) full_id = self._search_regex( - r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]', + r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']', webpage, 'full id') query = compat_urllib_parse.urlencode({'vid': full_id}) info = self._download_xml( diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py index 1d3e2ff08..212217625 100644 --- a/youtube_dl/extractor/dbtv.py +++ b/youtube_dl/extractor/dbtv.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( float_or_none, int_or_none, @@ -61,7 +62,7 @@ class DBTVIE(InfoExtractor): self._sort_formats(formats) return { - 'id': video['id'], + 'id': compat_str(video['id']), 'display_id': display_id, 'title': video['title'], 'description': clean_html(video['desc']), 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/discovery.py b/youtube_dl/extractor/discovery.py index 554df6735..d3e667528 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -1,47 +1,45 @@ from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + int_or_none, +) class DiscoveryIE(InfoExtractor): - _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' + _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?' _TEST = { 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', - 'md5': 'e12614f9ee303a6ccef415cb0793eba2', + 'md5': '3c69d77d9b0d82bfd5e5932a60f26504', 'info_dict': { - 'id': '614784', - 'ext': 'mp4', - 'title': 'MythBusters: Mission Impossible Outtakes', + 'id': 'mission-impossible-outtakes', + 'ext': 'flv', + 'title': '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, + 'timestamp': 1303099200, + 'upload_date': '20110418', }, } 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_list_json = self._search_regex(r'var videoListJSON = ({.*?});', - webpage, 'video list', flags=re.DOTALL) - video_list = json.loads(video_list_json) - info = video_list['clips'][0] - formats = [] - for f in info['mp4']: - formats.append( - {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])}) + info = self._parse_json(self._search_regex( + r'(?s)<script type="application/ld\+json">(.*?)</script>', + webpage, 'video info'), video_id) return { - 'id': info['contentId'], - 'title': video_list['name'], - 'formats': formats, - 'description': info['videoCaption'], - 'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'), - 'duration': info['duration'], + 'id': video_id, + 'title': info['name'], + 'url': info['contentURL'], + 'description': info.get('description'), + 'thumbnail': info.get('thumbnailUrl'), + 'timestamp': parse_iso8601(info.get('uploadDate')), + 'duration': int_or_none(info.get('duration')), } 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 817a9bd61..14b6c00b0 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -5,23 +5,24 @@ import os.path import re from .common import InfoExtractor -from ..utils import compat_urllib_parse_unquote, url_basename +from ..compat import compat_urllib_parse_unquote +from ..utils import url_basename class DropboxIE(InfoExtractor): _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, - }, + _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): @@ -29,9 +30,8 @@ class DropboxIE(InfoExtractor): video_id = mobj.group('id') fn = compat_urllib_parse_unquote(url_basename(url)) title = os.path.splitext(fn)[0] - video_url = ( - re.sub(r'[?&]dl=0', '', url) + - ('?' if '?' in url else '&') + '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/drtv.py b/youtube_dl/extractor/drtv.py index 9d6ce1f48..93b3c9f36 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .subtitles import SubtitlesInfoExtractor from .common import ExtractorError from ..utils import parse_iso8601 @@ -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/dvtv.py b/youtube_dl/extractor/dvtv.py new file mode 100644 index 000000000..c1a4bc757 --- /dev/null +++ b/youtube_dl/extractor/dvtv.py @@ -0,0 +1,125 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + unescapeHTML, + ExtractorError, +) + + +class DVTVIE(InfoExtractor): + IE_NAME = 'dvtv' + IE_DESC = 'http://video.aktualne.cz/' + + _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})' + + _TESTS = [{ + 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/', + 'md5': '67cb83e4a955d36e1b5d31993134a0c2', + 'info_dict': { + 'id': 'dc0768de855511e49e4b0025900fea04', + 'ext': 'mp4', + 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně', + } + }, { + 'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/', + 'md5': '6388f1941b48537dbd28791f712af8bf', + 'info_dict': { + 'id': '72c02230849211e49f60002590604f2e', + 'ext': 'mp4', + 'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala', + } + }, { + 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/', + 'info_dict': { + 'title': 'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci', + 'id': '973eb3bc854e11e498be002590604f2e', + }, + 'playlist': [{ + 'md5': 'da7ca6be4935532241fa9520b3ad91e4', + 'info_dict': { + 'id': 'b0b40906854d11e4bdad0025900fea04', + 'ext': 'mp4', + 'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne' + } + }, { + 'md5': '5f7652a08b05009c1292317b449ffea2', + 'info_dict': { + 'id': '420ad9ec854a11e4bdad0025900fea04', + 'ext': 'mp4', + 'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka' + } + }, { + 'md5': '498eb9dfa97169f409126c617e2a3d64', + 'info_dict': { + 'id': '95d35580846a11e4b6d20025900fea04', + 'ext': 'mp4', + 'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?' + } + }, { + 'md5': 'b8dc6b744844032dab6ba3781a7274b9', + 'info_dict': { + 'id': '6fe14d66853511e4833a0025900fea04', + 'ext': 'mp4', + 'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády' + } + }], + }, { + 'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/', + 'only_matching': True, + }] + + def _parse_video_metadata(self, js, video_id): + metadata = self._parse_json(js, video_id, transform_source=js_to_json) + + formats = [] + for video in metadata['sources']: + ext = video['type'][6:] + formats.append({ + 'url': video['file'], + 'ext': ext, + 'format_id': '%s-%s' % (ext, video['label']), + 'height': int(video['label'].rstrip('p')), + 'fps': 25, + }) + + self._sort_formats(formats) + + return { + 'id': metadata['mediaid'], + 'title': unescapeHTML(metadata['title']), + 'thumbnail': self._proto_relative_url(metadata['image'], 'http:'), + 'formats': formats + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + # single video + item = self._search_regex( + r"(?s)embedData[0-9a-f]{32}\['asset'\]\s*=\s*(\{.+?\});", + webpage, 'video', default=None, fatal=False) + + if item: + return self._parse_video_metadata(item, video_id) + + # playlist + items = re.findall( + r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);", + webpage) + + if items: + return { + '_type': 'playlist', + 'id': video_id, + 'title': self._og_search_title(webpage), + 'entries': [self._parse_video_metadata(i, video_id) for i in items] + } + + raise ExtractorError('Could not find neither video nor playlist') diff --git a/youtube_dl/extractor/ebaumsworld.py b/youtube_dl/extractor/ebaumsworld.py index 63c2549d3..b6bfd2b2d 100644 --- a/youtube_dl/extractor/ebaumsworld.py +++ b/youtube_dl/extractor/ebaumsworld.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -20,8 +18,7 @@ class EbaumsWorldIE(InfoExtractor): } 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://www.ebaumsworld.com/video/player/%s' % video_id, video_id) video_url = config.find('file').text diff --git a/youtube_dl/extractor/echomsk.py b/youtube_dl/extractor/echomsk.py new file mode 100644 index 000000000..d2d94049d --- /dev/null +++ b/youtube_dl/extractor/echomsk.py @@ -0,0 +1,46 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class EchoMskIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.echo.msk.ru/sounds/1464134.html', + 'md5': '2e44b3b78daff5b458e4dbc37f191f7c', + 'info_dict': { + 'id': '1464134', + 'ext': 'mp3', + 'title': 'Особое мнение - 29 декабря 2014, 19:08', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + audio_url = self._search_regex( + r'<a rel="mp3" href="([^"]+)">', webpage, 'audio URL') + + title = self._html_search_regex( + r'<a href="/programs/[^"]+" target="_blank">([^<]+)</a>', + webpage, 'title') + + air_date = self._html_search_regex( + r'(?s)<div class="date">(.+?)</div>', + webpage, 'date', fatal=False, default=None) + + if air_date: + air_date = re.sub(r'(\s)\1+', r'\1', air_date) + if air_date: + title = '%s - %s' % (title, air_date) + + return { + 'id': video_id, + 'url': audio_url, + 'title': title, + } diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index f8f49a013..9cb1bf301 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,8 +1,6 @@ from __future__ import unicode_literals -import re - -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) from .common import InfoExtractor @@ -24,11 +22,10 @@ class EHowIE(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._search_regex(r'(?:file|source)=(http[^\'"&]*)', - webpage, 'video URL') + video_url = self._search_regex( + r'(?:file|source)=(http[^\'"&]*)', 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 c1b4c729e..fb5dbbe2b 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -6,9 +6,12 @@ import random import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, ) +from ..utils import ( + ExtractorError, +) class EightTracksIE(InfoExtractor): @@ -112,25 +115,41 @@ class EightTracksIE(InfoExtractor): session = str(random.randint(0, 1000000000)) mix_id = data['id'] track_count = data['tracks_count'] + duration = data['duration'] + avg_song_duration = float(duration) / track_count first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) next_url = first_url entries = [] + for i in range(track_count): - 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_json = None + download_tries = 0 + + while api_json is None: + try: + 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') + except ExtractorError: + if download_tries > 3: + raise + else: + download_tries += 1 + self._sleep(avg_song_duration, playlist_id) + api_data = json.loads(api_json) track_data = api_data['set']['track'] info = { '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', } 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 { 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 index 3e7923648..fc92ff825 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re import json from .common import InfoExtractor @@ -12,32 +11,49 @@ from ..utils import ( class EllenTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)' + _TESTS = [{ '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', + 'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6', 'timestamp': 1406876400, 'upload_date': '20140801', } - } + }, { + 'url': 'http://ellentube.com/videos/0-dvzmabd5/', + 'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb', + 'info_dict': { + 'id': '0-dvzmabd5', + 'ext': 'mp4', + 'title': '1 year old twin sister makes her brother laugh', + 'description': '1 year old twin sister makes her brother laugh', + 'timestamp': 1419542075, + 'upload_date': '20141225', + } + }] 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_meta('VideoURL', webpage, 'url') + title = self._og_search_title(webpage, default=None) or self._search_regex( + r'pageName\s*=\s*"([^"]+)"', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') or self._og_search_description(webpage) 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'), + 'url': video_url, + 'title': title, + 'description': description, 'timestamp': timestamp, } @@ -55,8 +71,7 @@ class EllenTVClipsIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) playlist = self._extract_playlist(webpage) diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py index 4277202a2..00a69e631 100644 --- a/youtube_dl/extractor/elpais.py +++ b/youtube_dl/extractor/elpais.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import unified_strdate @@ -24,9 +22,7 @@ class ElPaisIE(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) prefix = self._html_search_regex( diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py index 92ada81d2..4ea37ebd9 100644 --- a/youtube_dl/extractor/engadget.py +++ b/youtube_dl/extractor/engadget.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .fivemin import FiveMinIE from ..utils import ( url_basename, ) @@ -27,11 +26,10 @@ class EngadgetIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) if video_id is not None: - return FiveMinIE._build_result(video_id) + return self.url_result('5min:%s' % video_id) else: title = url_basename(url) webpage = self._download_webpage(url, title) @@ -39,5 +37,5 @@ class EngadgetIE(InfoExtractor): return { '_type': 'playlist', 'title': title, - 'entries': [FiveMinIE._build_result(id) for id in ids] + 'entries': [self.url_result('5min:%s' % vid) for vid in ids] } diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index 522aa3d63..4de8d4bc5 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -14,13 +14,13 @@ 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': '3b427ae4b9d60619106de3185c2987cd', + 'md5': '39d486f046212d8e1b911c52ab4691f8', 'info_dict': { 'id': '95008', 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Infamous Tiffany Teen Strip Tease Video', - 'duration': 194, + 'duration': 1838, 'view_count': int, 'age_limit': 18, } @@ -57,9 +57,7 @@ class EpornerIE(InfoExtractor): formats.append(fmt) self._sort_formats(formats) - duration = parse_duration(self._search_regex( - r'class="mbtim">([0-9:]+)</div>', webpage, 'duration', - fatal=False)) + 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)) diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py new file mode 100644 index 000000000..79e2fbd39 --- /dev/null +++ b/youtube_dl/extractor/eroprofile.py @@ -0,0 +1,45 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class EroProfileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore', + 'md5': 'c26f351332edf23e1ea28ce9ec9de32f', + 'info_dict': { + 'id': '3733775', + 'display_id': 'sexy-babe-softcore', + 'ext': 'm4v', + 'title': 'sexy babe softcore', + 'thumbnail': 're:https?://.*\.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'], + webpage, 'video id', default=None) + + video_url = self._search_regex( + r'<source src="([^"]+)', webpage, 'video url') + title = self._html_search_regex( + r'Title:</th><td>([^<]+)</td>', webpage, 'title') + thumbnail = self._search_regex( + r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', + webpage, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 476fc22b9..e240cb859 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -3,9 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index d237a8281..d872d828f 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -3,8 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index aacbf1414..36ba33128 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -3,16 +3,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, +) +from ..utils import ( str_to_int, ) class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', @@ -31,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 60e68d98a..1ad4e77a8 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -5,15 +5,18 @@ 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, ) @@ -34,8 +37,7 @@ class FacebookIE(InfoExtractor): 'info_dict': { 'id': '637842556329505', 'ext': 'mp4', - 'duration': 38, - 'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...', + 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', } }, { 'note': 'Video without discernible title', @@ -58,8 +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') @@ -75,12 +77,12 @@ 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 @@ -94,7 +96,7 @@ class FacebookIE(InfoExtractor): 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: @@ -105,9 +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) @@ -147,6 +147,6 @@ class FacebookIE(InfoExtractor): '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..81ceace53 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -1,19 +1,20 @@ #! -*- coding: utf-8 -*- from __future__ import unicode_literals -import re import hashlib from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_request, compat_urlparse, ) +from ..utils import ( + ExtractorError, +) class FC2IE(InfoExtractor): - _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)' + _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)' IE_NAME = 'fc2' _TEST = { 'url': 'http://video.fc2.com/en/content/20121103kUan1KHs', @@ -26,9 +27,7 @@ class FC2IE(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) self._downloader.cookiejar.clear_session_cookies() # must clear @@ -40,7 +39,7 @@ 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 af439ccfe..3191116d9 100644 --- a/youtube_dl/extractor/firedrive.py +++ b/youtube_dl/extractor/firedrive.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) +from ..utils import ( + ExtractorError, +) class FiredriveIE(InfoExtractor): @@ -28,11 +30,8 @@ class FiredriveIE(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://firedrive.com/file/%s' % video_id - webpage = self._download_webpage(url, video_id) if re.search(self._FILE_DELETED_REGEX, webpage) is not None: 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..5b24b921c 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -1,11 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urllib_parse, +) +from ..utils import ( ExtractorError, ) @@ -13,7 +13,7 @@ from ..utils import ( class FiveMinIE(InfoExtractor): IE_NAME = '5min' _VALID_URL = r'''(?x) - (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=| + (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=| 5min:) (?P<id>\d+) ''' @@ -41,16 +41,11 @@ class FiveMinIE(InfoExtractor): }, ] - @classmethod - def _build_result(cls, video_id): - return cls.url_result('5min:%s' % video_id, cls.ie_key()) - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) 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..190d9f9ad 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,64 +1,69 @@ +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<id>[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', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = int(mobj.group('ep')) + episode = int(self._match_id(url)) - 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) + video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode + start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % 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 = [] for i, _ in enumerate(files, 1): video_id = '%04d%d' % (episode, i) - video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i) + video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i) videos.append({ + 'ext': 'flv', '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 }) - return videos + return { + '_type': 'multi_video', + 'entries': videos, + 'id': 'folge-%s' % episode, + } 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 +76,7 @@ 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 e09982e88..0c858b654 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -17,8 +17,8 @@ class FlickrIE(InfoExtractor): 'info_dict': { '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", + "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') 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..7187e0752 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -3,12 +3,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, - unified_strdate, - str_to_int, - parse_duration, +) +from ..utils import ( clean_html, + parse_duration, + str_to_int, + unified_strdate, ) @@ -31,9 +33,7 @@ class FourTubeIE(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_url = 'http://www.4tube.com/videos/' + video_id webpage = self._download_webpage(webpage_url, video_id) @@ -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/franceculture.py b/youtube_dl/extractor/franceculture.py index 898e0dda7..0c2972162 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -5,7 +5,7 @@ import json import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_parse_qs, compat_urlparse, ) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 0b3374d97..bbc760a49 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -6,13 +6,15 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse_urlparse, compat_urlparse, - ExtractorError, +) +from ..utils import ( clean_html, - parse_duration, - compat_urllib_parse_urlparse, + ExtractorError, int_or_none, + parse_duration, ) @@ -26,6 +28,19 @@ class FranceTVBaseInfoExtractor(InfoExtractor): 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: + georestricted = False formats = [] for video in info['videos']: @@ -36,6 +51,10 @@ class FranceTVBaseInfoExtractor(InfoExtractor): 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, @@ -46,7 +65,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor): f4m_format['preference'] = 1 formats.extend(f4m_formats) elif video_url.endswith('.m3u8'): - formats.extend(self._extract_m3u8_formats(video_url, video_id)) + formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4')) elif video_url.startswith('rtmp'): formats.append({ 'url': video_url, @@ -58,7 +77,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor): formats.append({ 'url': video_url, 'format_id': format_id, - 'preference': 2, + 'preference': -1, }) self._sort_formats(formats) @@ -93,7 +112,6 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): _TESTS = [{ 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', - 'md5': '9cecf35f99c4079c199e9817882a9a1c', 'info_dict': { 'id': '84981923', 'ext': 'flv', @@ -235,7 +253,7 @@ 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): 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 3022f539d..a07d69841 100644 --- a/youtube_dl/extractor/gameone.py +++ b/youtube_dl/extractor/gameone.py @@ -6,7 +6,9 @@ import re from .common import InfoExtractor from ..utils import ( xpath_with_ns, - parse_iso8601 + parse_iso8601, + float_or_none, + int_or_none, ) NAMESPACE_MAP = { @@ -21,25 +23,41 @@ RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/' class GameOneIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)' - _TEST = { - 'url': 'http://www.gameone.de/tv/288', - 'md5': '136656b7fb4c9cb4a8e2d500651c499b', - 'info_dict': { - 'id': '288', - 'ext': 'mp4', - 'title': 'Game One - Folge 288', - 'duration': 1238, - 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', - 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', - 'age_limit': 16, - 'upload_date': '20140513', - 'timestamp': 1399980122, + _TESTS = [ + { + 'url': 'http://www.gameone.de/tv/288', + 'md5': '136656b7fb4c9cb4a8e2d500651c499b', + 'info_dict': { + 'id': '288', + 'ext': 'mp4', + 'title': 'Game One - Folge 288', + 'duration': 1238, + 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', + 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', + 'age_limit': 16, + 'upload_date': '20140513', + 'timestamp': 1399980122, + } + }, + { + 'url': 'http://gameone.de/tv/220', + 'md5': '5227ca74c4ae6b5f74c0510a7c48839e', + 'info_dict': { + 'id': '220', + 'ext': 'mp4', + 'upload_date': '20120918', + 'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker', + 'timestamp': 1347971451, + 'title': 'Game One - Folge 220', + 'duration': 896.62, + 'age_limit': 16, + } } - } + + ] 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) og_video = self._og_search_video_url(webpage, secure=False) @@ -66,13 +84,13 @@ class GameOneIE(InfoExtractor): video_id, 'Downloading media:content') rendition_items = content.findall('.//rendition') - duration = int(rendition_items[0].get('duration')) + duration = float_or_none(rendition_items[0].get('duration')) formats = [ { 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text), - 'width': int(r.get('width')), - 'height': int(r.get('height')), - 'tbr': int(r.get('bitrate')), + 'width': int_or_none(r.get('width')), + 'height': int_or_none(r.get('height')), + 'tbr': int_or_none(r.get('bitrate')), } for r in rendition_items ] @@ -105,7 +123,8 @@ class GameOnePlaylistIE(InfoExtractor): 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') + self.url_result('http://www.gameone.de/tv/%d' % + video_id, 'GameOne') for video_id in range(max_id, 0, -1)] return { diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 3d67b9d60..47373e215 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -4,16 +4,17 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, +) +from ..utils import ( 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 +27,10 @@ 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 +42,8 @@ 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 +54,9 @@ 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/gdcvault.py b/youtube_dl/extractor/gdcvault.py index de14ae1fb..fed968f51 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -39,7 +39,8 @@ class GDCVaultIE(InfoExtractor): 'id': '1015301', 'ext': 'flv', 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment', - } + }, + 'skip': 'Requires login', } ] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 367f930dd..7a5bf9392 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,11 +7,12 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, compat_xml_parse_error, - +) +from ..utils import ( determine_ext, ExtractorError, float_or_none, @@ -22,12 +23,14 @@ from ..utils import ( unescapeHTML, unified_strdate, unsmuggle_url, + UnsupportedError, 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): @@ -98,6 +101,22 @@ 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', @@ -112,12 +131,13 @@ class GenericIE(InfoExtractor): # ooyala video { 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', - 'md5': '5644c6ca5d5782c1d0d350dad9bd840c', + 'md5': '166dd577b433b4d4ebfee10b0824d8ff', 'info_dict': { 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'ext': 'mp4', 'title': '2cc213299525360.mov', # that's what we get }, + 'add_ie': ['Ooyala'], }, # google redirect { @@ -127,7 +147,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20130224', 'uploader_id': 'TheVerge', - 'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.', + 'description': 're:^Chris Ziegler takes a look at the\.*', 'uploader': 'The Verge', 'title': 'First Firefox OS phones side-by-side', }, @@ -155,7 +175,6 @@ 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', @@ -163,6 +182,14 @@ class GenericIE(InfoExtractor): 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', }, }, + # BBC iPlayer embeds + { + 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER', + 'info_dict': { + 'title': 'BBC - Blogs - Adam Curtis - BUGGER', + }, + 'playlist_mincount': 18, + }, # RUTV embed { 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', @@ -180,13 +207,13 @@ 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 @@ -226,21 +253,6 @@ 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/', @@ -295,13 +307,13 @@ class GenericIE(InfoExtractor): { 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', 'info_dict': { - 'id': 'jpSGZsgga_I', + 'id': '4vAffPZIT44', 'ext': 'mp4', - 'title': 'Asphalt 8: Airborne - Launch Trailer', + 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!', 'uploader': 'Gameloft', 'uploader_id': 'gameloft', - 'upload_date': '20130821', - 'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a', + 'upload_date': '20140828', + 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4', }, 'params': { 'skip_download': True, @@ -340,7 +352,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'age_limit': 18, 'uploader': 'www.handjobhub.com', - 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub', + 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', } }, # RSS feed @@ -395,14 +407,89 @@ class GenericIE(InfoExtractor): '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) @@ -493,15 +580,17 @@ 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) 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 @@ -511,14 +600,14 @@ class GenericIE(InfoExtractor): self.to_screen('%s: Requesting header' % video_id) head_req = HEADRequest(url) - response = self._request_webpage( + head_response = self._request_webpage( head_req, video_id, note=False, errnote='Could not send HEAD request to %s' % url, fatal=False) - if response is not 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: @@ -526,30 +615,53 @@ class GenericIE(InfoExtractor): 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, + } - 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 self._downloader.params.get('test', False) and not is_intentional: + self._downloader.report_warning('Falling back on generic information extractor.') + + 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) @@ -596,9 +708,9 @@ class GenericIE(InfoExtractor): r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') # Helper method - def _playlist_from_matches(matches, getter, ie=None): + def _playlist_from_matches(matches, getter=None, ie=None): urlrs = orderedSet( - self.url_result(self._proto_relative_url(getter(m)), ie) + self.url_result(self._proto_relative_url(getter(m) if getter else m), ie) for m in matches) return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) @@ -626,13 +738,13 @@ 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) @@ -640,7 +752,8 @@ class GenericIE(InfoExtractor): <iframe[^>]+?src=| data-video-url=| <embed[^>]+?src=| - embedSWF\(?:\s* + embedSWF\(?:\s*| + new\s+SWFObject\( ) (["\']) (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ @@ -650,6 +763,12 @@ class GenericIE(InfoExtractor): 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) @@ -657,19 +776,32 @@ class GenericIE(InfoExtractor): 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-wistiaid=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) + + match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) if match: return { '_type': 'url_transparent', @@ -683,7 +815,7 @@ class GenericIE(InfoExtractor): # 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') + 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') @@ -719,7 +851,7 @@ 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')) @@ -782,6 +914,11 @@ class GenericIE(InfoExtractor): return _playlist_from_matches( matches, getter=unescapeHTML, ie='FunnyOrDie') + # Look for BBC iPlayer embed + matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage) + if matches: + return _playlist_from_matches(matches, ie='BBCCoUk') + # Look for embedded RUTV player rutv_url = RUTVIE._extract_url(webpage) if rutv_url: @@ -789,7 +926,7 @@ class GenericIE(InfoExtractor): # Look for embedded TED player mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'TED') @@ -813,7 +950,7 @@ 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')) @@ -849,56 +986,79 @@ class GenericIE(InfoExtractor): 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\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', + 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 = re.findall(r'''(?xs) + found = filter_video(re.findall(r'''(?xs) flowplayer\("[^"]+",\s* \{[^}]+?\}\s*, \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s* ["']?url["']?\s*:\s*["']([^"']+)["'] - ''', webpage) + ''', 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: - def check_video(vurl): - vpath = compat_urlparse.urlparse(vurl).path - vext = determine_ext(vpath) - return '.' in vpath and vext not in ('swf', 'png', 'jpg') - found = list(filter( - check_video, - 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")' @@ -912,7 +1072,7 @@ class GenericIE(InfoExtractor): 'url': new_url, } if not found: - raise ExtractorError('Unsupported URL: %s' % url) + raise UnsupportedError(url) entries = [] for video_url in found: @@ -944,4 +1104,3 @@ 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/giga.py b/youtube_dl/extractor/giga.py new file mode 100644 index 000000000..775890112 --- /dev/null +++ b/youtube_dl/extractor/giga.py @@ -0,0 +1,101 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools + +from .common import InfoExtractor +from ..utils import ( + qualities, + compat_str, + parse_duration, + parse_iso8601, + str_to_int, +) + + +class GigaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/', + 'md5': '6bc5535e945e724640664632055a584f', + 'info_dict': { + 'id': '2622086', + 'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss', + 'ext': 'mp4', + 'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss', + 'description': 'md5:afdf5862241aded4718a30dff6a57baf', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 578, + 'timestamp': 1414749706, + 'upload_date': '20141031', + 'uploader': 'Robin Schweiger', + 'view_count': int, + }, + }, { + 'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/', + 'only_matching': True, + }, { + 'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/', + 'only_matching': True, + }, { + 'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + [r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'], + webpage, 'video id') + + playlist = self._download_json( + 'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/' + % video_id, video_id)[0] + + quality = qualities(['normal', 'hd720']) + + formats = [] + for format_id in itertools.count(0): + fmt = playlist.get(compat_str(format_id)) + if not fmt: + break + formats.append({ + 'url': fmt['src'], + 'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]), + 'quality': quality(fmt['quality']), + }) + self._sort_formats(formats) + + title = self._html_search_meta( + 'title', webpage, 'title', fatal=True) + description = self._html_search_meta( + 'description', webpage, 'description') + thumbnail = self._og_search_thumbnail(webpage) + + duration = parse_duration(self._search_regex( + r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id), + webpage, 'duration', fatal=False)) + + timestamp = parse_iso8601(self._search_regex( + r'datetime="([^"]+)"', webpage, 'upload date', fatal=False)) + uploader = self._search_regex( + r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False) + + view_count = str_to_int(self._search_regex( + r'<span class="views"><strong>([\d.]+)</strong>', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader': uploader, + 'view_count': view_count, + '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..2bfb99040 --- /dev/null +++ b/youtube_dl/extractor/golem.py @@ -0,0 +1,71 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse, +) +from ..utils import ( + 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 469e1f935..498304cb2 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -4,7 +4,7 @@ import itertools import re from .common import SearchInfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py index ca5f7c417..ae24aff84 100644 --- a/youtube_dl/extractor/gorillavid.py +++ b/youtube_dl/extractor/gorillavid.py @@ -4,28 +4,33 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - determine_ext, +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) +from ..utils import ( + ExtractorError, + 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 +48,22 @@ 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 +72,23 @@ 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 +96,17 @@ 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, '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 index 726adff77..fff74a70a 100644 --- a/youtube_dl/extractor/grooveshark.py +++ b/youtube_dl/extractor/grooveshark.py @@ -8,12 +8,13 @@ import re from .common import InfoExtractor -from ..utils import ExtractorError, compat_urllib_request, compat_html_parser - -from ..utils import ( +from ..compat import ( + compat_html_parser, compat_urllib_parse, + compat_urllib_request, compat_urlparse, ) +from ..utils import ExtractorError class GroovesharkHtmlParser(compat_html_parser.HTMLParser): diff --git a/youtube_dl/extractor/groupon.py b/youtube_dl/extractor/groupon.py new file mode 100644 index 000000000..8b9e0e2f8 --- /dev/null +++ b/youtube_dl/extractor/groupon.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class GrouponIE(InfoExtractor): + _VALID_URL = r'https?://www\.groupon\.com/deals/(?P<id>[^?#]+)' + + _TEST = { + 'url': 'https://www.groupon.com/deals/bikram-yoga-huntington-beach-2#ooid=tubGNycTo_9Uxg82uESj4i61EYX8nyuf', + 'info_dict': { + 'id': 'bikram-yoga-huntington-beach-2', + 'title': '$49 for 10 Yoga Classes or One Month of Unlimited Classes at Bikram Yoga Huntington Beach ($180 Value)', + 'description': 'Studio kept at 105 degrees and 40% humidity with anti-microbial and anti-slip Flotex flooring; certified instructors', + }, + 'playlist': [{ + 'info_dict': { + 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf', + 'ext': 'mp4', + 'title': 'Bikram Yoga Huntington Beach | Orange County', + }, + }], + 'params': { + 'skip_download': 'HLS', + } + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + payload = self._parse_json(self._search_regex( + r'var\s+payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id) + videos = payload['carousel'].get('dealVideos', []) + entries = [] + for v in videos: + if v.get('provider') != 'OOYALA': + self.report_warning( + '%s: Unsupported video provider %s, skipping video' % + (playlist_id, v.get('provider'))) + continue + entries.append(self.url_result('ooyala:%s' % v['media'])) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'entries': entries, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + } 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/hellporno.py b/youtube_dl/extractor/hellporno.py new file mode 100644 index 000000000..7a1c75b65 --- /dev/null +++ b/youtube_dl/extractor/hellporno.py @@ -0,0 +1,71 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) + + +class HellPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', + 'md5': '1fee339c610d2049699ef2aa699439f1', + 'info_dict': { + 'id': '149116', + 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', + 'ext': 'mp4', + 'title': 'Dixie is posing with naked ass very erotic', + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + title = remove_end(self._html_search_regex( + r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno') + + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), + display_id, transform_source=js_to_json) + + video_id = flashvars.get('video_id') + thumbnail = flashvars.get('preview_url') + ext = flashvars.get('postfix', '.mp4')[1:] + + formats = [] + for video_url_key in ['video_url', 'video_alt_url']: + video_url = flashvars.get(video_url_key) + if not video_url: + continue + video_text = flashvars.get('%s_text' % video_url_key) + fmt = { + 'url': video_url, + 'ext': ext, + 'format_id': video_text, + } + m = re.search(r'^(?P<height>\d+)[pP]', video_text) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) + + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'thumbnail': thumbnail, + 'categories': categories, + 'age_limit': 18, + 'formats': formats, + } 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/hitbox.py b/youtube_dl/extractor/hitbox.py new file mode 100644 index 000000000..84bd7c080 --- /dev/null +++ b/youtube_dl/extractor/hitbox.py @@ -0,0 +1,166 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + parse_iso8601, + float_or_none, + int_or_none, + compat_str, +) + + +class HitboxIE(InfoExtractor): + IE_NAME = 'hitbox' + _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/video/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.hitbox.tv/video/203213', + 'info_dict': { + 'id': '203213', + 'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy', + 'alt_title': 'hitboxlive - Aug 9th #6', + 'description': '', + 'ext': 'mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 215.1666, + 'resolution': 'HD 720p', + 'uploader': 'hitboxlive', + 'view_count': int, + 'timestamp': 1407576133, + 'upload_date': '20140809', + 'categories': ['Live Show'], + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _extract_metadata(self, url, video_id): + thumb_base = 'https://edge.sf.hitbox.tv' + metadata = self._download_json( + '%s/%s' % (url, video_id), video_id) + + date = 'media_live_since' + media_type = 'livestream' + if metadata.get('media_type') == 'video': + media_type = 'video' + date = 'media_date_added' + + video_meta = metadata.get(media_type, [])[0] + title = video_meta.get('media_status') + alt_title = video_meta.get('media_title') + description = clean_html( + video_meta.get('media_description') or + video_meta.get('media_description_md')) + duration = float_or_none(video_meta.get('media_duration')) + uploader = video_meta.get('media_user_name') + views = int_or_none(video_meta.get('media_views')) + timestamp = parse_iso8601(video_meta.get(date), ' ') + categories = [video_meta.get('category_name')] + thumbs = [ + {'url': thumb_base + video_meta.get('media_thumbnail'), + 'width': 320, + 'height': 180}, + {'url': thumb_base + video_meta.get('media_thumbnail_large'), + 'width': 768, + 'height': 432}, + ] + + return { + 'id': video_id, + 'title': title, + 'alt_title': alt_title, + 'description': description, + 'ext': 'mp4', + 'thumbnails': thumbs, + 'duration': duration, + 'uploader': uploader, + 'view_count': views, + 'timestamp': timestamp, + 'categories': categories, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + metadata = self._extract_metadata( + 'https://www.hitbox.tv/api/media/video', + video_id) + + player_config = self._download_json( + 'https://www.hitbox.tv/api/player/config/video/%s' % video_id, + video_id) + + clip = player_config.get('clip') + video_url = clip.get('url') + res = clip.get('bitrates', [])[0].get('label') + + metadata['resolution'] = res + metadata['url'] = video_url + metadata['protocol'] = 'm3u8' + + return metadata + + +class HitboxLiveIE(HitboxIE): + IE_NAME = 'hitbox:live' + _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/(?!video)(?P<id>.+)' + _TEST = { + 'url': 'http://www.hitbox.tv/dimak', + 'info_dict': { + 'id': 'dimak', + 'ext': 'mp4', + 'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e', + 'timestamp': int, + 'upload_date': compat_str, + 'title': compat_str, + 'uploader': 'Dimak', + }, + 'params': { + # live + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + metadata = self._extract_metadata( + 'https://www.hitbox.tv/api/media/live', + video_id) + + player_config = self._download_json( + 'https://www.hitbox.tv/api/player/config/live/%s' % video_id, + video_id) + + formats = [] + cdns = player_config.get('cdns') + servers = [] + for cdn in cdns: + base_url = cdn.get('netConnectionUrl') + host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1) + if base_url not in servers: + servers.append(base_url) + for stream in cdn.get('bitrates'): + label = stream.get('label') + if label != 'Auto': + formats.append({ + 'url': '%s/%s' % (base_url, stream.get('url')), + 'ext': 'mp4', + 'vbr': stream.get('bitrate'), + 'resolution': label, + 'rtmp_live': True, + 'format_note': host, + 'page_url': url, + 'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf', + }) + + self._sort_formats(formats) + metadata['formats'] = formats + metadata['is_live'] = True + metadata['title'] = self._live_title(metadata.get('title')) + return metadata diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py index 7e7714438..5b6efb27e 100644 --- a/youtube_dl/extractor/hornbunny.py +++ b/youtube_dl/extractor/hornbunny.py @@ -37,7 +37,7 @@ class HornBunnyIE(InfoExtractor): 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)) diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py index 8e812b669..704d0285d 100644 --- a/youtube_dl/extractor/hostingbulk.py +++ b/youtube_dl/extractor/hostingbulk.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, int_or_none, urlencode_postdata, ) @@ -30,9 +32,7 @@ class HostingBulkIE(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://hostingbulk.com/{0:}.html'.format(video_id) # Custom request with cookie to set language to English, so our file 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 index 68684b997..e97339121 100644 --- a/youtube_dl/extractor/howstuffworks.py +++ b/youtube_dl/extractor/howstuffworks.py @@ -1,12 +1,12 @@ from __future__ import unicode_literals -import re -import json -import random -import string - from .common import InfoExtractor -from ..utils import find_xpath_attr +from ..utils import ( + find_xpath_attr, + int_or_none, + js_to_json, + unescapeHTML, +) class HowStuffWorksIE(InfoExtractor): @@ -16,98 +16,74 @@ class HowStuffWorksIE(InfoExtractor): 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm', 'info_dict': { 'id': '450221', - 'display_id': 'cool-jobs-iditarod-musher', 'ext': 'flv', 'title': 'Cool Jobs - Iditarod Musher', - 'description': 'md5:82bb58438a88027b8186a1fccb365f90', + '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, }, - 'params': { - # md5 is not consistent - 'skip_download': True - } }, { - 'url': 'http://adventure.howstuffworks.com/39516-deadliest-catch-jakes-farewell-pots-video.htm', + 'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm', 'info_dict': { - 'id': '553470', - 'display_id': 'deadliest-catch-jakes-farewell-pots', + 'id': '453464', 'ext': 'mp4', - 'title': 'Deadliest Catch: Jake\'s Farewell Pots', - 'description': 'md5:9632c346d5e43ee238028c9cefd8dbbc', + '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$', }, - 'params': { - # md5 is not consistent - 'skip_download': True - } }, { 'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm', 'info_dict': { 'id': '440011', - 'display_id': 'sword-swallowing-1-by-dan-meyer', 'ext': 'flv', 'title': 'Sword Swallowing #1 by Dan Meyer', - 'description': 'md5:b2409e88172913e2e7d3d1159b0ef735', + 'description': 'Video footage (1 of 3) used by permission of the owner Dan Meyer through Sword Swallowers Association International <www.swordswallow.org>', + 'display_id': 'sword-swallowing-1-by-dan-meyer', 'thumbnail': 're:^https?://.*\.jpg$', }, - 'params': { - # md5 is not consistent - 'skip_download': True - } }, ] 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) + 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) - content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id') - - mp4 = self._search_regex( - r'''(?xs)var\s+clip\s*=\s*{\s* - .+?\s* - content_id\s*:\s*%s\s*,\s* - .+?\s* - mp4\s*:\s*\[(.*?),?\]\s* - };\s* - videoData\.push\(clip\);''' % content_id, - webpage, 'mp4', fatal=False, default=None) - - smil = self._download_xml( - 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id, - content_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') - - def random_string(str_len=0): - return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)]) - - URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12)) - + 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' - if mp4: - for video in json.loads('[%s]' % mp4): - bitrate = video['bitrate'] - fmt = { - 'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX, - 'format_id': bitrate, - } - m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate) - if m: - fmt['vbr'] = int(m.group('vbr')) - formats.append(fmt) - else: for video in smil.findall( - './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')): - vbr = int(video.attrib['system-bitrate']) / 1000 + './{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, @@ -116,19 +92,12 @@ class HowStuffWorksIE(InfoExtractor): self._sort_formats(formats) - title = self._og_search_title(webpage) - TITLE_SUFFIX = ' : HowStuffWorks' - if title.endswith(TITLE_SUFFIX): - title = title[:-len(TITLE_SUFFIX)] - - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - return { - 'id': content_id, + 'id': '%s' % video_id, 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, + '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..a38eae421 100644 --- a/youtube_dl/extractor/huffpost.py +++ b/youtube_dl/extractor/huffpost.py @@ -33,15 +33,15 @@ 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'] video_title = data['title'] - duration = parse_duration(data['running_time']) - upload_date = unified_strdate(data['schedule']['starts_at']) + duration = parse_duration(data.get('running_time')) + upload_date = unified_strdate( + data.get('schedule', {}).get('starts_at') or data.get('segment_start_date_time')) description = data.get('description') thumbnails = [] @@ -60,16 +60,11 @@ class HuffPostIE(InfoExtractor): 'ext': 'mp4', 'url': url, 'vcodec': 'none' if key.startswith('audio/') else None, - } for key, url in data['sources']['live'].items()] - if data.get('fivemin_id'): - fid = data['fivemin_id'] - fcat = str(int(fid) // 100 + 1) - furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4' - formats.append({ - 'format': 'fivemin', - 'url': furl, - 'preference': 1, - }) + } for key, url in data.get('sources', {}).get('live', {}).items()] + + if not formats and data.get('fivemin_id'): + return self.url_result('5min:%s' % data['fivemin_id']) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index 6d0d847c6..aa0724a02 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -1,20 +1,20 @@ from __future__ import unicode_literals import json -import re import time from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, ) class HypemIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' + _VALID_URL = r'http://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/' _TEST = { 'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', 'md5': 'b9cc91b5af8995e9f0c1cee04c575828', @@ -27,8 +27,7 @@ class HypemIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - track_id = mobj.group(1) + track_id = self._match_id(url) data = {'ax': 1, 'ts': time.time()} data_encoded = compat_urllib_parse.urlencode(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 12e9e61c4..3db668cd0 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -63,8 +63,10 @@ class IGNIE(InfoExtractor): 'id': '078fdd005f6d3c02f63d795faa1b984f', 'ext': 'mp4', 'title': 'Rewind Theater - Wild Trailer Gamescom 2014', - 'description': 'Giant skeletons, bloody hunts, and captivating' - ' natural beauty take our breath away.', + 'description': ( + 'Giant skeletons, bloody hunts, and captivating' + ' natural beauty take our breath away.' + ), }, }, ] @@ -89,12 +91,17 @@ class IGNIE(InfoExtractor): '<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 diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 4536db3bf..f29df36b5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -4,9 +4,8 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, - get_element_by_attribute, ) @@ -17,7 +16,6 @@ class ImdbIE(InfoExtractor): _TEST = { 'url': 'http://www.imdb.com/video/imdb/vi2524815897', - 'md5': '9f34fa777ade3a6e57a054fdbcb3a068', 'info_dict': { 'id': '2524815897', 'ext': 'mp4', @@ -27,10 +25,11 @@ 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) @@ -71,11 +70,9 @@ class ImdbListIE(InfoExtractor): }, 'playlist_count': 7, } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') + 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/infoq.py b/youtube_dl/extractor/infoq.py index e76dd222d..f25f43664 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -1,10 +1,9 @@ from __future__ import unicode_literals import base64 -import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -24,9 +23,7 @@ class InfoQIE(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_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 5109f26ce..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, diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 4ddda2f1b..483cc6f9e 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,9 +1,13 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, compat_urllib_parse, +) +from ..utils import ( xpath_with_ns, ) @@ -12,12 +16,13 @@ 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': 152, }, } @@ -29,7 +34,7 @@ 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 +47,26 @@ 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..8529bedfc 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -6,8 +6,10 @@ from random import random from math import floor from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) @@ -54,7 +56,7 @@ 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 75b543b7c..7a400323d 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -5,8 +5,10 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) @@ -43,7 +45,7 @@ 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 +104,7 @@ 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'])) @@ -152,17 +154,17 @@ 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 = [] @@ -172,4 +174,4 @@ 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 index a83dd249f..d16d483ee 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -5,11 +5,11 @@ import re from .common import InfoExtractor from ..utils import ( - get_element_by_id, - parse_iso8601, determine_ext, - int_or_none, float_or_none, + get_element_by_id, + int_or_none, + parse_iso8601, str_to_int, ) @@ -30,7 +30,7 @@ class IzleseneIE(InfoExtractor): 'description': 'md5:253753e2655dde93f59f74b572454f6d', 'thumbnail': 're:^http://.*\.jpg', 'uploader_id': 'pelikzzle', - 'timestamp': 1404298698, + 'timestamp': 1404302298, 'upload_date': '20140702', 'duration': 95.395, 'age_limit': 0, @@ -46,7 +46,7 @@ class IzleseneIE(InfoExtractor): 'description': 'Tarkan Dortmund 2006 Konseri', 'thumbnail': 're:^http://.*\.jpg', 'uploader_id': 'parlayankiz', - 'timestamp': 1163318593, + 'timestamp': 1163322193, 'upload_date': '20061112', 'duration': 253.666, 'age_limit': 0, @@ -55,15 +55,15 @@ class IzleseneIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - url = 'http://www.izlesene.com/video/%s' % video_id + 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._og_search_thumbnail(webpage) + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') uploader = self._html_search_regex( r"adduserUsername\s*=\s*'([^']+)';", 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/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/keek.py b/youtube_dl/extractor/keek.py index 5d679e88d..c0956ba09 100644 --- a/youtube_dl/extractor/keek.py +++ b/youtube_dl/extractor/keek.py @@ -1,34 +1,39 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class KeekIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)' + _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<id>\w+)' IE_NAME = 'keek' _TEST = { 'url': 'https://www.keek.com/ytdl/keeks/NODfbab', - 'file': 'NODfbab.mp4', - 'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83', + 'md5': '09c5c109067536c1cec8bac8c21fea05', 'info_dict': { - 'uploader': 'ytdl', + 'id': 'NODfbab', + 'ext': 'mp4', + 'uploader': 'youtube-dl project', + 'uploader_id': 'ytdl', 'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .', }, } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') + video_id = self._match_id(url) video_url = 'http://cdn.keek.com/keek/video/%s' % video_id thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id webpage = self._download_webpage(url, video_id) - uploader = self._html_search_regex( - r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', - webpage, 'uploader', fatal=False) + raw_desc = self._html_search_meta('description', webpage) + if raw_desc: + uploader = self._html_search_regex( + r'Watch (.*?)\s+\(', raw_desc, 'uploader', fatal=False) + uploader_id = self._html_search_regex( + r'Watch .*?\(@(.+?)\)', raw_desc, 'uploader_id', fatal=False) + else: + uploader = None + uploader_id = None return { 'id': video_id, @@ -36,5 +41,6 @@ class KeekIE(InfoExtractor): 'ext': 'mp4', 'title': self._og_search_title(webpage), 'thumbnail': thumbnail, - 'uploader': uploader + 'uploader': uploader, + 'uploader_id': uploader_id, } diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 75b63cffb..97dcb518a 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -4,7 +4,7 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, @@ -15,7 +15,7 @@ from ..aes import ( class KeezMoviesIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)' _TEST = { 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', 'file': '1214711.mp4', @@ -27,8 +27,7 @@ class KeezMoviesIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 408d00944..08a671fa8 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -22,8 +22,10 @@ class KhanAcademyIE(InfoExtractor): 'description': 'The perfect cipher', 'duration': 176, 'uploader': 'Brit Cruise', + 'uploader_id': 'khanacademy', 'upload_date': '20120411', - } + }, + 'add_ie': ['Youtube'], }, { 'url': 'https://www.khanacademy.org/math/applied-math/cryptography', 'info_dict': { 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..720bc939b 100644 --- a/youtube_dl/extractor/kontrtube.py +++ b/youtube_dl/extractor/kontrtube.py @@ -10,13 +10,14 @@ from ..utils import int_or_none class KontrTubeIE(InfoExtractor): IE_NAME = 'kontrtube' IE_DESC = 'KontrTube.ru - Труба зовёт' - _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+' + _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/' _TEST = { 'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/', 'md5': '975a991a4926c9a85f383a736a2e6b80', 'info_dict': { 'id': '2678', + 'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag', 'ext': 'mp4', 'title': 'Над олимпийской деревней в Сочи поднят российский флаг', 'description': 'md5:80edc4c613d5887ae8ccf1d59432be41', @@ -28,21 +29,28 @@ class KontrTubeIE(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, 'Downloading page') + webpage = self._download_webpage( + url, display_id, 'Downloading page') - 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) + video_url = self._html_search_regex( + r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL') + thumbnail = self._html_search_regex( + r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False) title = self._html_search_regex( - r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage, 'video title') - description = self._html_search_meta('description', webpage, 'video description') + r'<title>(.+?)</title>', webpage, 'video title') + description = self._html_search_meta( + 'description', webpage, 'video description') mobj = re.search( - r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage) + r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', + webpage) duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None view_count = self._html_search_regex( - r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False) + r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', + webpage, 'view count', fatal=False) comment_count = None comment_str = self._html_search_regex( @@ -56,6 +64,7 @@ class KontrTubeIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'url': video_url, 'thumbnail': thumbnail, 'title': title, @@ -63,4 +72,4 @@ 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 516147417..5247c6f58 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -4,10 +4,12 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urllib_parse_urlparse, compat_urlparse, +) +from ..utils import ( ExtractorError, find_xpath_attr, int_or_none, @@ -18,7 +20,7 @@ from ..utils import ( class LivestreamIE(InfoExtractor): IE_NAME = 'livestream' - _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' + _VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])' _TESTS = [{ 'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', 'md5': '53274c76ba7754fb0e8d072716f2292b', @@ -37,6 +39,9 @@ class LivestreamIE(InfoExtractor): '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): @@ -190,7 +195,8 @@ 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, } diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py new file mode 100644 index 000000000..9c2fbdd96 --- /dev/null +++ b/youtube_dl/extractor/lrt.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +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 = self._parse_json(js, video_id, transform_source=js_to_json) + if 'provider' not in data: + continue + 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..26e84970d 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -5,12 +5,14 @@ import json from .subtitles import SubtitlesInfoExtractor from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_str, compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, int_or_none, - compat_str, ) @@ -45,7 +47,7 @@ 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 +111,7 @@ 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 +119,7 @@ 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 +189,7 @@ 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 +223,4 @@ 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..0b85a59d1 100644 --- a/youtube_dl/extractor/malemotion.py +++ b/youtube_dl/extractor/malemotion.py @@ -1,42 +1,33 @@ +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) + class MalemotionIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' + _VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' _TEST = { - 'url': 'http://malemotion.com/video/bien-dur.10ew', - 'file': '10ew.mp4', - 'md5': 'b3cc49f953b107e4a363cdff07d100ce', + 'url': 'http://malemotion.com/video/bete-de-concours.ltc', + 'md5': '3013e53a0afbde2878bc39998c33e8a5', 'info_dict': { - "title": "Bien dur", - "age_limit": 18, + 'id': 'ltc', + 'ext': 'mp4', + 'title': 'Bête de Concours', + 'age_limit': 18, }, - 'skip': 'This video 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 = self._download_webpage(url, video_id) - self.report_extraction(video_id) - - # Extract video URL - video_url = compat_urllib_parse.unquote( - self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL')) - - # Extract title + video_url = compat_urllib_parse.unquote(self._search_regex( + r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL')) video_title = self._html_search_regex( r'<title>(.*?)</title', webpage, 'title') - - # Extract video thumbnail video_thumbnail = self._search_regex( r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False) @@ -46,14 +37,12 @@ class MalemotionIE(InfoExtractor): 'format_id': 'mp4', 'preference': 1, }] + self._sort_formats(formats) return { 'id': video_id, 'formats': formats, - 'uploader': None, - 'upload_date': None, 'title': video_title, 'thumbnail': video_thumbnail, - 'description': None, 'age_limit': 18, } 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 1a896b536..8bc333b02 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -3,10 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_parse_qs, compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( determine_ext, ExtractorError, int_or_none, @@ -22,7 +24,7 @@ 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', @@ -219,8 +221,8 @@ class MetacafeIE(InfoExtractor): 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) + r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', + webpage, 'uploader nickname', fatal=False) duration = int_or_none( self._html_search_meta('video:duration', webpage)) 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/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/mit.py b/youtube_dl/extractor/mit.py index 807b1dc89..3c61a850f 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -5,8 +5,10 @@ import json from .common import InfoExtractor from .youtube import YoutubeIE -from ..utils import ( +from ..compat import ( compat_urlparse, +) +from ..utils import ( clean_html, ExtractorError, get_element_by_id, @@ -15,7 +17,7 @@ from ..utils import ( class TechTVMITIE(InfoExtractor): IE_NAME = 'techtv.mit.edu' - _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)' + _VALID_URL = r'https?://techtv\.mit\.edu/(?:videos|embeds)/(?P<id>\d+)' _TEST = { 'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set', @@ -29,8 +31,7 @@ class TechTVMITIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) raw_page = self._download_webpage( 'http://techtv.mit.edu/videos/%s' % video_id, video_id) clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page) @@ -104,7 +105,10 @@ class OCWMITIE(InfoExtractor): 'ext': 'mp4', 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence', 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.', - #'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt' + 'upload_date': '20121109', + 'uploader_id': 'MIT', + 'uploader': 'MIT OpenCourseWare', + # 'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt' } }, { @@ -113,8 +117,11 @@ class OCWMITIE(InfoExtractor): 'id': '7K1sB05pE0A', 'ext': 'mp4', 'title': 'Session 1: Introduction to Derivatives', + 'upload_date': '20090818', + 'uploader_id': 'MIT', + 'uploader': 'MIT OpenCourseWare', 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.', - #'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT' + # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT' } } ] diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 979f3d692..256758323 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,11 +1,13 @@ from __future__ import unicode_literals -import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, + compat_urlparse, +) +from ..utils import ( get_element_by_attribute, parse_duration, strip_jsonp, @@ -14,7 +16,7 @@ from ..utils import ( class MiTeleIE(InfoExtractor): IE_NAME = 'mitele.es' - _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/' _TEST = { 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', @@ -30,22 +32,28 @@ class MiTeleIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = mobj.group('episode') + episode = self._match_id(url) webpage = self._download_webpage(url, episode) embed_data_json = self._search_regex( - r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', - flags=re.DOTALL + r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', ).replace('\'', '"') embed_data = json.loads(embed_data_json) - info_url = embed_data['flashvars']['host'] + 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( - 'http://token.mitele.es/?' + token_query, episode, + embed_data['flashvars']['ov_tk'] + '?' + token_query, + episode, transform_source=strip_jsonp ) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 520f27fca..07d194562 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -3,8 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( ExtractorError, HEADRequest, int_or_none, @@ -33,22 +35,22 @@ 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(HEADRequest(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) @@ -61,16 +63,16 @@ 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 bfdb462eb..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|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?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', @@ -73,6 +72,14 @@ class MLBIE(InfoExtractor): '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): @@ -88,8 +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'): @@ -116,5 +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 index 2ff79b9b8..5a66302f6 100644 --- a/youtube_dl/extractor/moevideo.py +++ b/youtube_dl/extractor/moevideo.py @@ -5,10 +5,12 @@ import json import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( + ExtractorError, int_or_none, ) @@ -50,7 +52,8 @@ class MoeVideoIE(InfoExtractor): 'height': 296, 'duration': 6027, 'filesize': 588257923, - } + }, + 'skip': 'Video has been removed', }, ] diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index d658647e6..2cec12d35 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -4,7 +4,7 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, @@ -12,7 +12,7 @@ from ..utils import ( 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<id>[0-9]+)/.*?\.html)' _TEST = { 'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', 'md5': '1b2eb47ac33cc75d4a80e3026b613c5a', @@ -26,7 +26,7 @@ class MofosexIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py index 90b460d65..0ba435dc5 100644 --- a/youtube_dl/extractor/mojvideo.py +++ b/youtube_dl/extractor/mojvideo.py @@ -55,4 +55,4 @@ class MojvideoIE(InfoExtractor): 'title': title, 'thumbnail': thumbnail, 'duration': duration, - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py index 79bb2ca59..5de719bdc 100644 --- a/youtube_dl/extractor/moniker.py +++ b/youtube_dl/extractor/moniker.py @@ -5,7 +5,7 @@ import os.path import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -37,10 +37,9 @@ class MonikerIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) orig_webpage = self._download_webpage(url, video_id) + fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) data = dict(fields) @@ -54,7 +53,7 @@ class MonikerIE(InfoExtractor): title = os.path.splitext(data['fname'])[0] - #Could be several links with different quality + # Could be several links with different quality links = re.findall(r'"file" : "?(.+?)",', webpage) # Assume the links are ordered in quality formats = [{ diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index 7d21ea18f..7603af5e2 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -1,14 +1,15 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_request, compat_urllib_parse, ) +from ..utils import ( + ExtractorError, +) class MooshareIE(InfoExtractor): @@ -43,13 +44,11 @@ class MooshareIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) 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') @@ -64,8 +63,7 @@ class MooshareIE(InfoExtractor): 'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - self.to_screen('%s: Waiting for timeout' % video_id) - time.sleep(5) + self._sleep(5, video_id) video_page = self._download_webpage(request, video_id, 'Downloading video page') @@ -111,4 +109,4 @@ 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/motorsport.py b/youtube_dl/extractor/motorsport.py index 7c0ec6a12..c1a482dba 100644 --- a/youtube_dl/extractor/motorsport.py +++ b/youtube_dl/extractor/motorsport.py @@ -1,63 +1,49 @@ # coding: utf-8 from __future__ import unicode_literals -import hashlib -import json -import re -import time - from .common import InfoExtractor -from ..utils import ( - compat_parse_qs, - compat_str, - int_or_none, +from ..compat import ( + compat_urlparse, ) class MotorsportIE(InfoExtractor): IE_DESC = 'motorsport.com' - _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])' + _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])' _TEST = { 'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/', - 'md5': '5592cb7c5005d9b2c163df5ac3dc04e4', 'info_dict': { - 'id': '7063', + 'id': '2-T3WuR-KMM', 'ext': 'mp4', 'title': 'Red Bull Racing: 2014 Rules Explained', - 'duration': 207, + 'duration': 208, 'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.', - 'uploader': 'rainiere', - 'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$' - } + 'uploader': 'mcomstaff', + 'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ', + 'upload_date': '20140903', + 'thumbnail': r're:^https?://.+\.jpg$' + }, + 'add_ie': ['Youtube'], + 'params': { + 'skip_download': True, + }, } 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) - flashvars_code = self._html_search_regex( - r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars') - flashvars = compat_parse_qs(flashvars_code) - params = json.loads(flashvars['parameters'][0]) - - e = compat_str(int(time.time()) + 24 * 60 * 60) - base_video_url = params['location'] + '?e=' + e - s = 'h3hg713fh32' - h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest() - video_url = base_video_url + '&h=' + h - uploader = self._html_search_regex( - r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage, - 'uploader', fatal=False) + iframe_path = self._html_search_regex( + r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage, + 'iframe path') + iframe = self._download_webpage( + compat_urlparse.urljoin(url, iframe_path), display_id, + 'Downloading iframe') + youtube_id = self._search_regex( + r'www.youtube.com/embed/(.{11})', iframe, 'youtube id') return { - 'id': params['video_id'], + '_type': 'url_transparent', 'display_id': display_id, - 'title': params['title'], - 'url': video_url, - 'description': params.get('description'), - 'thumbnail': params.get('main_thumb'), - 'duration': int_or_none(params.get('duration')), - 'uploader': uploader, + 'url': 'https://youtube.com/watch?v=%s' % youtube_id, } diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py index 456807dd1..04e17d055 100644 --- a/youtube_dl/extractor/movieclips.py +++ b/youtube_dl/extractor/movieclips.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, +) from ..utils import ( ExtractorError, - compat_str, clean_html, ) 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]+$', src['src'], False, default=None) vcodec = src['type'].partition('/')[2] - + formats.append({ 'format_id': encoding_id + '-' + vcodec, 'url': src['src'], diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 228b42d2b..5ebc78033 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, @@ -33,7 +35,7 @@ class MTVServicesInfoExtractor(InfoExtractor): m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', 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 +55,23 @@ 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 +100,7 @@ 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 +128,7 @@ 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 +147,8 @@ 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 +166,7 @@ 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 +189,8 @@ 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 +242,15 @@ 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 index 3a938861b..b4e8ad17e 100644 --- a/youtube_dl/extractor/muenchentv.py +++ b/youtube_dl/extractor/muenchentv.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import datetime import json from .common import InfoExtractor @@ -23,6 +22,7 @@ class MuenchenTVIE(InfoExtractor): '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, @@ -33,9 +33,7 @@ class MuenchenTVIE(InfoExtractor): display_id = 'live' webpage = self._download_webpage(url, display_id) - now = datetime.datetime.now() - now_str = now.strftime("%Y-%m-%d %H:%M") - title = self._og_search_title(webpage) + ' ' + now_str + title = self._live_title(self._og_search_title(webpage)) data_js = self._search_regex( r'(?s)\nplaylist:\s*(\[.*?}\]),related:', @@ -73,5 +71,5 @@ class MuenchenTVIE(InfoExtractor): '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/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..5b9b9fbcd 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -2,9 +2,10 @@ from __future__ import unicode_literals import os.path from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, - +) +from ..utils import ( ExtractorError, ) @@ -13,9 +14,10 @@ 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..c10405f04 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -4,9 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( ExtractorError, + clean_html, ) @@ -25,16 +28,21 @@ class NaverIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) 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 +67,7 @@ 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 78e650b2d..862b706bf 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( remove_end, @@ -10,8 +8,8 @@ from ..utils import ( 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': 'c0edcfc37607344e2ff8f13c378c88a4', 'info_dict': { @@ -21,12 +19,13 @@ class NBAIE(InfoExtractor): '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' @@ -37,8 +36,7 @@ class NBAIE(InfoExtractor): description = self._og_search_description(webpage) duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration', fatal=False)) - + self._html_search_meta('duration', webpage, 'duration')) return { 'id': shortened_video_id, diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index e75ab7c39..690c46b6a 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -4,32 +4,47 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, +) +from ..utils import ( ExtractorError, find_xpath_attr, ) 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 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.', + _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 +72,7 @@ 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 +112,8 @@ 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/nerdcubed.py b/youtube_dl/extractor/nerdcubed.py new file mode 100644 index 000000000..efc903afa --- /dev/null +++ b/youtube_dl/extractor/nerdcubed.py @@ -0,0 +1,35 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import datetime + +from .common import InfoExtractor + + +class NerdCubedFeedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nerdcubed\.co\.uk/feed\.json' + _TEST = { + 'url': 'http://www.nerdcubed.co.uk/feed.json', + 'info_dict': { + 'title': 'nerdcubed.co.uk feed', + }, + 'playlist_mincount': 1300, + } + + def _real_extract(self, url): + feed = self._download_json(url, url, "Downloading NerdCubed JSON feed") + + entries = [{ + '_type': 'url', + 'title': feed_entry['title'], + 'uploader': feed_entry['source']['name'] if feed_entry['source'] else None, + 'upload_date': datetime.datetime.strptime(feed_entry['date'], '%Y-%m-%d').strftime('%Y%m%d'), + 'url': "http://www.youtube.com/watch?v=" + feed_entry['youtube_id'], + } for feed_entry in feed] + + return { + '_type': 'playlist', + 'title': 'nerdcubed.co.uk feed', + 'id': 'nerdcubed-feed', + 'entries': entries, + } diff --git a/youtube_dl/extractor/netzkino.py b/youtube_dl/extractor/netzkino.py new file mode 100644 index 000000000..93567d1e3 --- /dev/null +++ b/youtube_dl/extractor/netzkino.py @@ -0,0 +1,86 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + int_or_none, + js_to_json, + parse_iso8601, +) + + +class NetzkinoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/(?P<category>[^/]+)/(?P<id>[^/]+)' + + _TEST = { + 'url': 'http://www.netzkino.de/#!/scifikino/rakete-zum-mond', + 'md5': '92a3f8b76f8d7220acce5377ea5d4873', + 'info_dict': { + 'id': 'rakete-zum-mond', + 'ext': 'mp4', + 'title': 'Rakete zum Mond (Endstation Mond, Destination Moon)', + 'comments': 'mincount:3', + 'description': 'md5:1eddeacc7e62d5a25a2d1a7290c64a28', + 'upload_date': '20120813', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1344858571, + 'age_limit': 12, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + category_id = mobj.group('category') + video_id = mobj.group('id') + + api_url = 'http://api.netzkino.de.simplecache.net/capi-2.0a/categories/%s.json?d=www' % category_id + api_info = self._download_json(api_url, video_id) + info = next( + p for p in api_info['posts'] if p['slug'] == video_id) + custom_fields = info['custom_fields'] + + production_js = self._download_webpage( + 'http://www.netzkino.de/beta/dist/production.min.js', video_id, + note='Downloading player code') + avo_js = self._search_regex( + r'window\.avoCore\s*=.*?urlTemplate:\s*(\{.*?"\})', + production_js, 'URL templates') + templates = self._parse_json( + avo_js, video_id, transform_source=js_to_json) + + suffix = { + 'hds': '.mp4/manifest.f4m', + 'hls': '.mp4/master.m3u8', + 'pmd': '.mp4', + } + film_fn = custom_fields['Streaming'][0] + formats = [{ + 'format_id': key, + 'ext': 'mp4', + 'url': tpl.replace('{}', film_fn) + suffix[key], + } for key, tpl in templates.items()] + self._sort_formats(formats) + + comments = [{ + 'timestamp': parse_iso8601(c.get('date'), delimiter=' '), + 'id': c['id'], + 'author': c['name'], + 'html': c['content'], + 'parent': 'root' if c.get('parent', 0) == 0 else c['parent'], + } for c in info.get('comments', [])] + + return { + 'id': video_id, + 'formats': formats, + 'comments': comments, + 'title': info['title'], + 'age_limit': int_or_none(custom_fields.get('FSK')[0]), + 'timestamp': parse_iso8601(info.get('date'), delimiter=' '), + 'description': clean_html(info.get('content')), + 'thumbnail': info.get('thumbnail'), + 'playlist_title': api_info.get('title'), + 'playlist_id': category_id, + } 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..ea077254b 100644 --- a/youtube_dl/extractor/nfb.py +++ b/youtube_dl/extractor/nfb.py @@ -1,9 +1,7 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, compat_urllib_parse, ) @@ -12,7 +10,7 @@ from ..utils import ( class NFBIE(InfoExtractor): IE_NAME = 'nfb' IE_DESC = 'National Film Board of Canada' - _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)' + _VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)' _TEST = { 'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny', @@ -32,18 +30,18 @@ class NFBIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page') + video_id = self._match_id(url) + 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 +91,4 @@ 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 index 963c4587c..606e2294e 100644 --- a/youtube_dl/extractor/nfl.py +++ b/youtube_dl/extractor/nfl.py @@ -4,6 +4,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -13,76 +16,116 @@ from ..utils import ( class NFLIE(InfoExtractor): IE_NAME = 'nfl.com' - _VALID_URL = r'(?x)https?://(?:www\.)?nfl\.com/(?:videos/(?:.+)/|.*?\#video=)(?P<id>\d..[0-9]+)' - _PLAYER_CONFIG_URL = 'http://www.nfl.com/static/content/static/config/video/config.json' - _TEST = { - 'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights', - # 'md5': '5eb8c40a727dda106d510e5d6ffa79e5', # md5 checksum fluctuates - 'info_dict': { - 'id': '0ap3000000398478', - 'ext': 'mp4', - 'title': 'Week 3: Washington Redskins vs. Philadelphia Eagles highlights', - 'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478', - 'upload_date': '20140921', - 'timestamp': 1411337580, - 'thumbnail': 're:^https?://.*\.jpg$', + _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 = mobj.group('id') + video_id, host = mobj.group('id'), mobj.group('host') - config = self._download_json(self._PLAYER_CONFIG_URL, video_id, - note='Downloading player config') - url_template = 'http://nfl.com{contentURLTemplate:s}'.format(**config) - video_data = self._download_json(url_template.format(id=video_id), video_id) + webpage = self._download_webpage(url, video_id) - cdns = config.get('cdns') - if not cdns: - raise ExtractorError('Failed to get CDN data', expected=True) + 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 = [] - streams = video_data.get('cdnData', {}).get('bitrateInfo', []) - 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 - - path_prefix = cdn.get('pathprefix', '') - if path_prefix and not path_prefix.endswith('/'): - path_prefix = '%s/' % path_prefix - - get_url = lambda p: '{protocol:s}://{host:s}/{prefix:s}{path:}'.format( - protocol=protocol, - host=host, - prefix=path_prefix, - path=p, - ) - - if protocol == 'rtmp': - preference = -2 - elif 'prog' in name.lower(): - preference = -1 - else: - preference = 0 - + 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: - path = stream.get('path') - if not path: + 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 - formats.append({ - 'url': get_url(path), - 'vbr': int_or_none(stream.get('rate', 0), 1000), - 'preference': preference, - 'format_note': name, - }) + 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) @@ -94,7 +137,7 @@ class NFLIE(InfoExtractor): return { 'id': video_id, - 'title': video_data.get('storyHeadline'), + 'title': video_data.get('headline'), 'formats': formats, 'description': video_data.get('caption'), 'duration': video_data.get('duration'), diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 072d9cf8e..d3a4fc513 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -2,12 +2,15 @@ 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, ) @@ -22,21 +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, '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']), @@ -46,10 +54,11 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): IE_NAME = 'nhl.com' - _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9]+)' + _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', + 'md5': 'db704a4ea09e8d3988c85e36cc892d09', 'info_dict': { 'id': '453614', 'ext': 'mp4', @@ -59,6 +68,28 @@ class NHLIE(NHLBaseInfoExtractor): '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, }] @@ -75,7 +106,7 @@ class NHLIE(NHLBaseInfoExtractor): class NHLVideocenterIE(NHLBaseInfoExtractor): IE_NAME = 'nhl.com:videocenter' IE_DESC = 'NHL videocenter category' - _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' + _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' _TEST = { 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999', 'info_dict': { @@ -109,10 +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 ' + 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) diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index c0c139b5d..4c1890416 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -2,15 +2,19 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, compat_urlparse, - unified_strdate, - parse_duration, +) +from ..utils import ( + ExtractorError, int_or_none, + parse_duration, + unified_strdate, ) @@ -39,18 +43,17 @@ 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 +71,8 @@ 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 +87,7 @@ 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 +111,9 @@ 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 +153,37 @@ 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..7f842b5c2 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -23,12 +23,14 @@ class NineGagIE(InfoExtractor): "ext": "mp4", "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)", "title": "\"People Are Awesome 2013\" Is Absolutely Awesome", + 'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA', + 'uploader': 'CompilationChannel', + 'upload_date': '20131110', "view_count": int, "thumbnail": "re:^https?://", }, 'add_ie': ['Youtube'] - }, - { + }, { 'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar', 'info_dict': { 'id': 'KklwM', @@ -36,6 +38,9 @@ class NineGagIE(InfoExtractor): 'display_id': 'alternate-banned-opening-scene-of-gravity', "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.", 'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie", + 'uploader': 'Krishna Shenoi', + 'upload_date': '20140401', + 'uploader_id': 'krishnashenoi93', }, }] diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index 7f1bc6377..251e6da07 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -6,13 +6,15 @@ import time import hashlib from .common import InfoExtractor -from ..utils import ( - compat_urllib_request, +from ..compat import ( + compat_str, compat_urllib_parse, - ExtractorError, + compat_urllib_request, +) +from ..utils import ( clean_html, + ExtractorError, unified_strdate, - compat_str, ) @@ -20,6 +22,7 @@ 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 = { @@ -60,10 +63,12 @@ class NocoIE(InfoExtractor): if 'erreur' in login: raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) - def _call_api(self, path, video_id, note): + 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) @@ -91,31 +96,34 @@ class NocoIE(InfoExtractor): formats = [] - for format_id, fmt in medias['fr']['video_list']['none']['quality_list'].items(): - - video = self._call_api( - 'shows/%s/video/%s/fr' % (video_id, format_id.lower()), - video_id, 'Downloading %s video JSON' % format_id) - - 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, - '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'], - }) + 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) @@ -163,4 +171,4 @@ class NocoIE(InfoExtractor): '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..c13ff0d65 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -22,7 +22,11 @@ class NormalbootsIE(InfoExtractor): 'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/', 'uploader': 'JonTron', 'upload_date': '20140125', - } + }, + 'params': { + # rtmp download + 'skip_download': True, + }, } def _real_extract(self, url): @@ -31,9 +35,9 @@ 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 index f3be8f552..f5ef856db 100644 --- a/youtube_dl/extractor/nosvideo.py +++ b/youtube_dl/extractor/nosvideo.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, urlencode_postdata, xpath_text, xpath_with_ns, @@ -32,8 +34,7 @@ class NosVideoIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) fields = { 'id': video_id, diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 2e7ab1e4f..04d779890 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urlparse, +) from ..utils import ( ExtractorError, - compat_urlparse ) @@ -66,4 +68,4 @@ class NovaMovIE(InfoExtractor): 'url': video_url, 'title': title, 'description': description - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index bfba18418..dec09cdfe 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE): IE_NAME = 'nowvideo' IE_DESC = 'NowVideo' - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co|li)'} _HOST = 'www.nowvideo.ch' @@ -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 f36d446d2..8da76ae45 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -7,7 +7,9 @@ from ..utils import ( unified_strdate, parse_duration, qualities, + strip_jsonp, url_basename, + fix_xml_ampersands, ) @@ -50,7 +52,21 @@ class NPOIE(InfoExtractor): 'upload_date': '20130225', 'duration': 3000, }, - } + }, + { + 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', + 'info_dict': { + 'id': 'WO_VPRO_043706', + 'ext': 'wmv', + 'title': 'De nieuwe mens - Deel 1', + 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', + 'duration': 4680, + }, + 'params': { + # mplayer mms download + 'skip_download': True, + } + }, ] def _real_extract(self, url): @@ -63,7 +79,7 @@ class NPOIE(InfoExtractor): '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', @@ -73,31 +89,58 @@ class NPOIE(InfoExtractor): token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token') 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: + + pubopties = metadata.get('pubopties') + if pubopties: + quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) + for format_id in 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), + }) + + streams = metadata.get('streams') + if streams: + for i, stream in enumerate(streams): + stream_url = stream.get('url') + if not stream_url: + continue + asx = self._download_xml( + stream_url, video_id, + 'Downloading stream %d ASX playlist' % i, + transform_source=fix_xml_ampersands) + ref = asx.find('./ENTRY/Ref') + if ref is None: + continue + video_url = ref.get('href') + if not video_url: + continue formats.append({ 'url': video_url, - 'format_id': format_id, - 'quality': quality(format_id), + 'ext': stream.get('formaat', 'asf'), + 'quality': stream.get('kwaliteit'), }) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 96f0ae1eb..f6de26022 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -7,8 +7,10 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, float_or_none, + parse_duration, unified_strdate, ) +from .subtitles import SubtitlesInfoExtractor class NRKIE(InfoExtractor): @@ -71,13 +73,13 @@ class NRKIE(InfoExtractor): } -class NRKTVIE(InfoExtractor): - _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})' +class NRKTVIE(SubtitlesInfoExtractor): + _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?' _TESTS = [ { 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'md5': '7b96112fbae1faf09a6f9ae1aff6cb84', + 'md5': 'adf2c5454fa2bf032f47a9f8fb351342', 'info_dict': { 'id': 'MUHH48000314', 'ext': 'flv', @@ -85,11 +87,11 @@ class NRKTVIE(InfoExtractor): 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'upload_date': '20140523', 'duration': 1741.52, - } + }, }, { 'url': 'http://tv.nrk.no/program/mdfp15000514', - 'md5': 'af01795a31f1cf7265c8657534d8077b', + 'md5': '383650ece2b25ecec996ad7b5bb2a384', 'info_dict': { 'id': 'mdfp15000514', 'ext': 'flv', @@ -97,42 +99,155 @@ class NRKTVIE(InfoExtractor): 'description': 'md5:654c12511f035aed1e42bdf5db3b206a', 'upload_date': '20140524', 'duration': 4605.0, - } + }, + }, + { + # single playlist video + 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + 'skip': 'Only works from Norway', }, + { + 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', + 'playlist': [ + { + 'md5': '9480285eff92d64f06e02a5367970a7a', + 'info_dict': { + 'id': 'MSPO40010515-part1', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + }, + { + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + }, + ], + 'info_dict': { + 'id': 'MSPO40010515', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + 'duration': 6947.5199999999995, + }, + 'skip': 'Only works from Norway', + } ] + def _seconds2str(self, s): + return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000) + + def _debug_print(self, txt): + if self._downloader.params.get('verbose', False): + self.to_screen('[debug] %s' % txt) + + def _extract_captions(self, subtitlesurl, video_id, baseurl): + url = "%s%s" % (baseurl, subtitlesurl) + self._debug_print('%s: Subtitle url: %s' % (video_id, url)) + captions = self._download_xml(url, video_id, 'Downloading subtitles') + lang = captions.get('lang', 'no') + ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}')) + srt = '' + for pos, p in enumerate(ps): + begin = parse_duration(p.get('begin')) + duration = parse_duration(p.get('dur')) + starttime = self._seconds2str(begin) + endtime = self._seconds2str(begin + duration) + text = '\n'.join(p.itertext()) + srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text) + return {lang: srt} + + def _extract_f4m(self, manifest_url, video_id): + return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + part_id = mobj.group('part_id') + baseurl = mobj.group('baseurl') - page = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_meta( + 'title', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') - title = self._html_search_meta('title', page, 'title') - description = self._html_search_meta('description', page, 'description') - thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False) - upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False)) - duration = float_or_none( - self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)) + thumbnail = self._html_search_regex( + r'data-posterimage="([^"]+)"', + webpage, 'thumbnail', fatal=False) + upload_date = unified_strdate(self._html_search_meta( + 'rightsfrom', webpage, 'upload date', fatal=False)) + duration = float_or_none(self._html_search_regex( + r'data-duration="([^"]+)"', + webpage, 'duration', fatal=False)) + + # playlist + parts = re.findall( + r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage) + if parts: + entries = [] + for current_part_id, stream_url, part_title in parts: + if part_id and current_part_id != part_id: + continue + video_part_id = '%s-part%s' % (video_id, current_part_id) + formats = self._extract_f4m(stream_url, video_part_id) + entries.append({ + 'id': video_part_id, + 'title': part_title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + }) + if part_id: + if entries: + return entries[0] + else: + playlist = self.playlist_result(entries, video_id, title, description) + playlist.update({ + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + }) + return playlist formats = [] - f4m_url = re.search(r'data-media="([^"]+)"', page) + f4m_url = re.search(r'data-media="([^"]+)"', webpage) if f4m_url: - formats.append({ - 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', - 'format_id': 'f4m', - 'ext': 'flv', - }) + formats.extend(self._extract_f4m(f4m_url.group(1), video_id)) - m3u8_url = re.search(r'data-hls-media="([^"]+)"', page) + m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage) if m3u8_url: - formats.append({ - 'url': m3u8_url.group(1), - 'format_id': 'm3u8', - }) - + formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4')) self._sort_formats(formats) + subtitles_url = self._html_search_regex( + r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"', + webpage, 'subtitle URL', default=None) + subtitles = None + if subtitles_url: + subtitles = self._extract_captions(subtitles_url, video_id, baseurl) + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + return { 'id': video_id, 'title': title, @@ -141,4 +256,5 @@ class NRKTVIE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, + 'subtitles': subtitles, } 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 58ec81f91..57928f2ae 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -3,15 +3,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( parse_duration, unified_strdate, - compat_urllib_request, ) class NuvidIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)' _TEST = { 'url': 'http://m.nuvid.com/video/1310741/', 'md5': 'eab207b7ac4fccfb4e23c86201f11277', @@ -26,8 +28,7 @@ class NuvidIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) formats = [] @@ -71,4 +72,4 @@ class NuvidIE(InfoExtractor): '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/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 2044e107e..d5b05c18f 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -16,7 +16,6 @@ class OoyalaIE(InfoExtractor): { # 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', @@ -26,7 +25,6 @@ class OoyalaIE(InfoExtractor): }, { # 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', @@ -43,7 +41,7 @@ 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 { @@ -97,4 +95,3 @@ class OoyalaIE(InfoExtractor): } else: return self._extract_result(videos_info[0], videos_more_info) - diff --git a/youtube_dl/extractor/openfilm.py b/youtube_dl/extractor/openfilm.py new file mode 100644 index 000000000..2249657eb --- /dev/null +++ b/youtube_dl/extractor/openfilm.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + compat_urllib_parse, + parse_age_limit, + int_or_none, +) + + +class OpenFilmIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)openfilm\.com/videos/(?P<id>.+)' + _TEST = { + 'url': 'http://www.openfilm.com/videos/human-resources-remastered', + 'md5': '42bcd88c2f3ec13b65edf0f8ad1cac37', + 'info_dict': { + 'id': '32736', + 'display_id': 'human-resources-remastered', + 'ext': 'mp4', + 'title': 'Human Resources (Remastered)', + 'description': 'Social Engineering in the 20th Century.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 7164, + 'timestamp': 1334756988, + 'upload_date': '20120418', + 'uploader_id': '41117', + 'view_count': int, + 'age_limit': 0, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + player = compat_urllib_parse.unquote_plus( + self._og_search_video_url(webpage)) + + video = json.loads(self._search_regex( + r'\bp=({.+?})(?:&|$)', player, 'video JSON')) + + video_url = '%s1.mp4' % video['location'] + video_id = video.get('video_id') + display_id = video.get('alias') or display_id + title = video.get('title') + description = video.get('description') + thumbnail = video.get('main_thumb') + duration = int_or_none(video.get('duration')) + timestamp = parse_iso8601(video.get('dt_published'), ' ') + uploader_id = video.get('user_id') + view_count = int_or_none(video.get('views_count')) + age_limit = parse_age_limit(video.get('age_limit')) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 011e6be13..4e293392b 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -17,24 +17,39 @@ from ..utils import ( 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 = { - 'url': 'http://tvthek.orf.at/program/matinee-Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7317210/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319746/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319747', - 'file': '7319747.mp4', - 'md5': 'bd803c5d8c32d3c64a0ea4b4eeddf375', - 'info_dict': { - 'title': 'Was Sie schon immer über Klassik wissen wollten', - 'description': 'md5:0ddf0d5f0060bd53f744edaa5c2e04a4', - 'duration': 3508, - 'upload_date': '20140105', - }, - 'skip': 'Blocked outside of Austria', - } + _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389', + 'playlist': [{ + 'md5': '2942210346ed779588f428a92db88712', + 'info_dict': { + 'id': '8896777', + 'ext': 'mp4', + 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde', + 'description': 'md5:c1272f0245537812d4e36419c207b67d', + 'duration': 2668, + 'upload_date': '20141208', + }, + }], + 'skip': 'Blocked outside of Austria / Germany', + }, { + 'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256', + 'playlist': [{ + 'md5': '68f543909aea49d621dfc7703a11cfaf', + 'info_dict': { + 'id': '7982259', + 'ext': 'mp4', + 'title': 'Best of Ingrid Thurnher', + 'upload_date': '20140527', + 'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".', + } + }], + '_skip': 'Blocked outside of Austria / Germany', + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) data_json = self._search_regex( @@ -43,7 +58,9 @@ class ORFTVthekIE(InfoExtractor): def get_segments(all_data): for data in all_data: - if data['name'] == 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM': + if data['name'] in ( + 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM', + 'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'): return data['values']['segments'] sdata = get_segments(all_data) @@ -111,18 +128,19 @@ class ORFTVthekIE(InfoExtractor): } -# 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]+)' + _VALID_URL = r'http://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)' - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') + # Audios on ORF radio are only available for 7 days, so we can't add tests. + _TEST = { + 'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211', + 'only_matching': True, + } + def _real_extract(self, url): + show_id = self._match_id(url) data = self._download_json( 'http://oe1.orf.at/programm/%s/konsole' % show_id, show_id @@ -145,7 +163,7 @@ class ORFOE1IE(InfoExtractor): class ORFFM4IE(InfoExtractor): - IE_DESC = 'orf:fm4' + IE_NAME = 'orf:fm4' IE_DESC = 'radio FM4' _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' @@ -178,4 +196,4 @@ class ORFFM4IE(InfoExtractor): 'title': data['title'], 'description': data['subtitle'], 'entries': entries - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 2adfde909..afce732e1 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -4,6 +4,8 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, + unified_strdate, US_RATINGS, ) @@ -11,10 +13,10 @@ 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>[^/]+)/ ) @@ -65,10 +67,31 @@ class PBSIE(InfoExtractor): '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 _extract_ids(self, url): + def _extract_webpage(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') @@ -76,15 +99,26 @@ class PBSIE(InfoExtractor): 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 + return media_id, presumptive_id, upload_date url = self._search_regex( r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', @@ -104,14 +138,33 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id - return video_id, display_id + return video_id, display_id, None def _real_extract(self, url): - video_id, display_id = self._extract_ids(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) + redirect_url = info['alternate_encoding']['url'] + redirect_info = self._download_json( + redirect_url + '?format=json', display_id, + 'Downloading video url info') + if redirect_info['status'] == 'error': + if redirect_info['http_code'] == 403: + message = ( + 'The video is not available in your region due to ' + 'right restrictions') + else: + message = redirect_info['message'] + raise ExtractorError(message, expected=True) + rating_str = info.get('rating') if rating_str is not None: rating_str = rating_str.rpartition('-')[2] @@ -119,11 +172,13 @@ class PBSIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'title': info['title'], - 'url': info['alternate_encoding']['url'], + 'url': redirect_info['url'], 'ext': 'mp4', 'description': info['program'].get('description'), '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..c66db3cdc 100644 --- a/youtube_dl/extractor/photobucket.py +++ b/youtube_dl/extractor/photobucket.py @@ -4,16 +4,17 @@ import json import re from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..compat import compat_urllib_parse class PhotobucketIE(InfoExtractor): _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))' _TEST = { 'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0', - 'file': 'zpsc0c3b9fa.mp4', 'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99', 'info_dict': { + 'id': 'zpsc0c3b9fa', + 'ext': 'mp4', 'timestamp': 1367669341, 'upload_date': '20130504', 'uploader': 'rachaneronas', @@ -31,7 +32,7 @@ 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..45716c75d --- /dev/null +++ b/youtube_dl/extractor/played.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import os.path + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + ExtractorError, +) + + +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', + }, + 'skip': 'Removed for copyright infringement.', # oh wow + } + + 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 index ebc046804..9576aed0e 100644 --- a/youtube_dl/extractor/playfm.py +++ b/youtube_dl/extractor/playfm.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, float_or_none, int_or_none, diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py index b1322f13f..c3e667e9e 100644 --- a/youtube_dl/extractor/playvid.py +++ b/youtube_dl/extractor/playvid.py @@ -3,31 +3,38 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) +from ..utils import ( + clean_html, + ExtractorError, +) class PlayvidIE(InfoExtractor): - _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)' + _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)' _TEST = { - 'url': 'http://www.playvid.com/watch/agbDDi7WZTV', - 'md5': '44930f8afa616efdf9482daf4fe53e1e', + 'url': 'http://www.playvid.com/watch/RnmBNgtrrJu', + 'md5': 'ffa2f6b2119af359f544388d8c01eb6c', 'info_dict': { - 'id': 'agbDDi7WZTV', + 'id': 'RnmBNgtrrJu', 'ext': 'mp4', - 'title': 'Michelle Lewin in Miami Beach', - 'duration': 240, + 'title': 'md5:9256d01c6317e3f703848b5906880dc8', + 'duration': 82, '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) + 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 48ce6e730..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, } } @@ -24,8 +31,9 @@ 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) + webpage = self._download_webpage(url, display_id or video_id) title = self._html_search_regex( r'<title>(.+) porn HD.+?</title>', webpage, 'title') @@ -33,38 +41,26 @@ class PornHdIE(InfoExtractor): r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) view_count = int_or_none(self._html_search_regex( r'(\d+) views\s*</span>', webpage, 'view count', fatal=False)) + thumbnail = self._search_regex( + r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False) - videos = 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')) - for key, quality in [('hashlink', 'low'), ('hd', 'high')]: - redirect_url = flashvars.get(key) - if redirect_url: - videos.append(('flv', quality, redirect_url)) - thumbnail = flashvars['urlWallpaper'] - else: - thumbnail = self._og_search_thumbnail(webpage) - + quality = qualities(['sd', 'hd']) + sources = json.loads(js_to_json(self._search_regex( + r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}\);", webpage, 'sources'))) formats = [] - for format_, quality, redirect_url in videos: - format_id = '%s-%s' % (format_.lower(), quality.lower()) - video_url = self._download_webpage( - redirect_url, video_id, 'Downloading %s video link' % format_id, fatal=False) - if not video_url: - continue - formats.append({ - 'url': video_url, - 'ext': format_.lower(), - 'format_id': format_id, - 'quality': 1 if quality.lower() == 'high' else 0, - }) + 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..634142d0d 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -4,10 +4,12 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse, compat_urllib_parse_urlparse, compat_urllib_request, - compat_urllib_parse, +) +from ..utils import ( str_to_int, ) from ..aes import ( @@ -16,13 +18,14 @@ 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 +38,7 @@ 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 +46,7 @@ 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 +58,7 @@ 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 04bd3d979..34735c51e 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -1,56 +1,94 @@ from __future__ import unicode_literals -import re +import json from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( - compat_urllib_parse, - - unified_strdate, + int_or_none, ) class PornotubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)' _TEST = { - 'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', - 'md5': '374dd6dcedd24234453b295209aa69b6', + 'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science', + 'md5': '60fc5a4f0d93a97968fc7999d98260c9', 'info_dict': { - 'id': '1689755', - 'ext': 'flv', - 'upload_date': '20090708', - 'title': 'Marilyn-Monroe-Bathing', - 'age_limit': 18 + 'id': '4964', + 'ext': 'mp4', + 'upload_date': '20141203', + 'title': 'Weird Hot and Wet Science', + 'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0', + 'categories': ['Adult Humor', 'Blondes'], + 'uploader': 'Alpha Blue Archives', + 'thumbnail': 're:^https?://.*\\.jpg$', + 'timestamp': 1417582800, + 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + video_id = self._match_id(url) - video_id = mobj.group('videoid') - video_title = mobj.group('title') + # Fetch origin token + js_config = self._download_webpage( + 'http://www.pornotube.com/assets/src/app/config.js', video_id, + note='Download JS config') + originAuthenticationSpaceKey = self._search_regex( + r"constant\('originAuthenticationSpaceKey',\s*'([^']+)'", + js_config, 'originAuthenticationSpaceKey') + + # Fetch actual token + token_req_data = { + 'authenticationSpaceKey': originAuthenticationSpaceKey, + 'credentials': 'Clip Application', + } + token_req = compat_urllib_request.Request( + 'https://api.aebn.net/auth/v1/token/primal', + data=json.dumps(token_req_data).encode('utf-8')) + token_req.add_header('Content-Type', 'application/json') + token_req.add_header('Origin', 'http://www.pornotube.com') + token_answer = self._download_json( + token_req, video_id, note='Requesting primal token') + token = token_answer['tokenKey'] - # Get webpage content - webpage = self._download_webpage(url, video_id) + # Get video URL + delivery_req = compat_urllib_request.Request( + 'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id) + delivery_req.add_header('Authorization', token) + delivery_info = self._download_json( + delivery_req, video_id, note='Downloading delivery information') + video_url = delivery_info['mediaUrl'] - # 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, 'video url') - video_url = compat_urllib_parse.unquote(video_url) + # Get additional info (title etc.) + info_req = compat_urllib_request.Request( + 'https://api.aebn.net/content/v1/clips/%s?expand=' + 'title,description,primaryImageNumber,startSecond,endSecond,' + 'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,' + 'movie.studios,stars.name,studios.name,categories.name,' + 'clipActive,movieActive,publishDate,orientations' % video_id) + info_req.add_header('Authorization', token) + info = self._download_json( + info_req, video_id, note='Downloading metadata') - #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, 'upload date', fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - age_limit = self._rta_search(webpage) + timestamp = int_or_none(info.get('publishDate'), scale=1000) + uploader = info.get('studios', [{}])[0].get('name') + movie_id = info['movie']['movieId'] + thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % ( + movie_id, movie_id, info['primaryImageNumber']) + categories = [c['name'] for c in info.get('categories')] return { 'id': video_id, 'url': video_url, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'age_limit': age_limit, + 'title': info['title'], + 'description': info.get('description'), + 'timestamp': timestamp, + 'uploader': uploader, + 'thumbnail': thumbnail, + 'categories': categories, + 'age_limit': 18, } diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py index 463e85501..f536e6e6c 100644 --- a/youtube_dl/extractor/promptfile.py +++ b/youtube_dl/extractor/promptfile.py @@ -4,17 +4,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, - determine_ext, +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) +from ..utils import ( + determine_ext, + ExtractorError, +) class PromptFileIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' - _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]' _TEST = { 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', 'md5': 'd1451b6302da7215485837aaea882c4c', @@ -27,11 +28,10 @@ class PromptFileIE(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) - if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + 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) diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 5b2a723c1..385681d06 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -5,8 +5,10 @@ import re from hashlib import sha1 from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( unified_strdate, ) @@ -85,7 +87,7 @@ 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 +102,7 @@ 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': { @@ -144,7 +146,7 @@ class ProSiebenSat1IE(InfoExtractor): 'id': '2156342', 'ext': 'mp4', 'title': 'Kurztrips zum Valentinstag', - 'description': 'md5:8ba6301e70351ae0bedf8da00f7ba528', + 'description': 'Romantischer Kurztrip zum Valentinstag? Wir verraten, was sich hier wirklich lohnt.', 'duration': 307.24, }, 'params': { @@ -152,12 +154,22 @@ 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>', @@ -178,14 +190,20 @@ 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' @@ -234,12 +252,12 @@ 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', default=None)) + self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None)) formats = [] @@ -282,4 +300,32 @@ 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..af7d76cf4 --- /dev/null +++ b/youtube_dl/extractor/quickvid.py @@ -0,0 +1,53 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse, +) +from ..utils import ( + 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)$', + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title') + view_count = int_or_none(self._html_search_regex( + r'(?s)<div id="views">(.*?)</div>', + webpage, 'view count', fatal=False)) + video_code = self._search_regex( + r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code') + formats = [ + { + 'url': compat_urlparse.urljoin(url, src), + 'format_id': determine_ext(src, None), + } for src in re.findall('<source\s+src="([^"]+)"', video_code) + ] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': self._og_search_thumbnail(webpage), + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/radiobremen.py b/youtube_dl/extractor/radiobremen.py new file mode 100644 index 000000000..0d706312e --- /dev/null +++ b/youtube_dl/extractor/radiobremen.py @@ -0,0 +1,63 @@ +# -*- coding: utf-8 -*- + +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class RadioBremenIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(?:index\.html)?\?id=(?P<id>[0-9]+)' + IE_NAME = 'radiobremen' + + _TEST = { + 'url': 'http://www.radiobremen.de/mediathek/index.html?id=114720', + 'info_dict': { + 'id': '114720', + 'ext': 'mp4', + 'duration': 1685, + 'width': 512, + 'title': 'buten un binnen vom 22. Dezember', + 'thumbnail': 're:https?://.*\.jpg$', + 'description': 'Unter anderem mit diesen Themen: 45 Flüchtlinge sind in Worpswede angekommen +++ Freies Internet für alle: Bremer arbeiten an einem flächendeckenden W-Lan-Netzwerk +++ Aktivisten kämpfen für das Unibad +++ So war das Wetter 2014 +++', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + meta_url = "http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s" % video_id + meta_doc = self._download_webpage( + meta_url, video_id, 'Downloading metadata') + title = self._html_search_regex( + r"<h1.*>(?P<title>.+)</h1>", meta_doc, "title") + description = self._html_search_regex( + r"<p>(?P<description>.*)</p>", meta_doc, "description", fatal=False) + duration = parse_duration(self._html_search_regex( + r"Länge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>", + meta_doc, "duration", fatal=False)) + + page_doc = self._download_webpage( + url, video_id, 'Downloading video information') + mobj = re.search( + r"ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)", + page_doc) + video_url = ( + "http://dl-ondemand.radiobremen.de/mediabase/%s/%s_%s_%s.mp4" % + (video_id, video_id, mobj.group("secret"), mobj.group('width'))) + + formats = [{ + 'url': video_url, + 'ext': 'mp4', + 'width': int(mobj.group("width")), + }] + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'formats': formats, + 'thumbnail': mobj.group('thumbnail'), + } 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..aa26b7e0b 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -3,10 +3,12 @@ from __future__ import unicode_literals import re from .subtitles import SubtitlesInfoExtractor +from ..compat import ( + compat_urllib_parse, +) from ..utils import ( parse_duration, unified_strdate, - compat_urllib_parse, ) @@ -119,4 +121,4 @@ 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/restudy.py b/youtube_dl/extractor/restudy.py new file mode 100644 index 000000000..b17c2bfc0 --- /dev/null +++ b/youtube_dl/extractor/restudy.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class RestudyIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://www.restudy.dk/video/play/id/1637', + 'info_dict': { + 'id': '1637', + 'ext': 'flv', + 'title': 'Leiden-frosteffekt', + 'description': 'Denne video er et eksperiment med flydende kvælstof.', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage).strip() + description = self._og_search_description(webpage).strip() + + formats = self._extract_smil_formats( + 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id, + video_id) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'formats': formats, + } 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.$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - flashVars_str = self._search_regex( - r'<param name="flashVars" value="([^"]+)"', - webpage, 'flashVars') - flashVars = compat_parse_qs(flashVars_str) + url = compat_urllib_parse_unquote(self._search_regex( + r'(?s)clip\s*:\s*{.*?url\s*:\s*\'([^\']+)\'', webpage, 'url')) + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': 'mp4', + }] return { - '_type': 'video', 'id': video_id, - 'ext': 'mp4', - 'url': flashVars['videoURL'][0], - 'title': flashVars['title'][0], - 'description': clean_html(flashVars['desc'][0]), - 'thumbnail': flashVars['preview'][0], + 'formats': formats, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py new file mode 100644 index 000000000..04158b993 --- /dev/null +++ b/youtube_dl/extractor/rte.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + float_or_none, +) + + +class RteIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P<id>[0-9]+)/' + _TEST = { + 'url': 'http://www.rte.ie/player/de/show/10363114/', + 'info_dict': { + 'id': '10363114', + 'ext': 'mp4', + 'title': 'One News', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'The One O\'Clock News followed by Weather.', + 'duration': 436.844, + }, + 'params': { + 'skip_download': 'f4m fails with --test atm' + } + } + + 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_meta('description', webpage, 'description') + duration = float_or_none(self._html_search_meta( + 'duration', webpage, 'duration', fatal=False), 1000) + + thumbnail_id = self._search_regex( + r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail') + thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' + + feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id + json_string = self._download_json(feeds_url, video_id) + + # f4m_url = server + relative_url + f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url'] + f4m_formats = self._extract_f4m_formats(f4m_url, video_id) + f4m_formats = [{ + 'format_id': f['format_id'], + 'url': f['url'], + 'ext': 'mp4', + 'width': f['width'], + 'height': f['height'], + } for f in f4m_formats] + + return { + 'id': video_id, + 'title': title, + 'formats': f4m_formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + } diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py index 0ab1eb69c..a3ca79f2c 100644 --- a/youtube_dl/extractor/rtlnl.py +++ b/youtube_dl/extractor/rtlnl.py @@ -8,7 +8,7 @@ from ..utils import parse_duration class RtlXlIE(InfoExtractor): IE_NAME = 'rtlxl.nl' - _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' + _VALID_URL = r'https?://(www\.)?rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' _TEST = { 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', @@ -38,12 +38,13 @@ class RtlXlIE(InfoExtractor): progname = info['abstracts'][0]['name'] subtitle = material['title'] or info['episodes'][0]['name'] - videopath = material['videopath'] - f4m_url = 'http://manifest.us.rtl.nl' + videopath + # 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_f4m_formats(f4m_url, uuid) + formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4') - video_urlpart = videopath.split('/flash/')[1][:-4] + video_urlpart = videopath.split('/flash/')[1][:-5] PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4' formats.extend([ @@ -54,9 +55,12 @@ class RtlXlIE(InfoExtractor): { '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), 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/rtp.py b/youtube_dl/extractor/rtp.py new file mode 100644 index 000000000..7736cabba --- /dev/null +++ b/youtube_dl/extractor/rtp.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import js_to_json + + +class RTPIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?' + _TESTS = [{ + 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas', + 'info_dict': { + 'id': 'e174042', + 'ext': 'mp3', + 'title': 'Paixões Cruzadas', + 'description': 'As paixões musicais de António Cartaxo e António Macedo', + 'thumbnail': 're:^https?://.*\.jpg', + }, + 'params': { + 'skip_download': True, # RTMP download + }, + }, { + 'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._html_search_meta( + 'twitter:title', webpage, display_name='title', fatal=True) + description = self._html_search_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + player_config = self._search_regex( + r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config') + config = json.loads(js_to_json(player_config)) + + path, ext = config.get('file').rsplit('.', 1) + formats = [{ + 'app': config.get('application'), + 'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path), + 'page_url': url, + 'url': 'rtmp://{streamer:s}/{application:s}'.format(**config), + 'rtmp_live': config.get('live', False), + 'ext': ext, + 'vcodec': config.get('type') == 'audio' and 'none' or None, + 'player_url': 'http://programas.rtp.pt/play/player.swf?v3', + }] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index e8199b114..5e84c1098 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -4,18 +4,20 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, +) from ..utils import ( int_or_none, parse_duration, parse_iso8601, unescapeHTML, - compat_str, ) 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 +25,7 @@ class RTSIE(InfoExtractor): 'md5': '753b877968ad8afaeddccc374d4256a5', 'info_dict': { 'id': '3449373', + 'display_id': 'les-enfants-terribles', 'ext': 'mp4', 'duration': 1488, 'title': 'Les Enfants Terribles', @@ -30,7 +33,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Divers', 'upload_date': '19680921', 'timestamp': -40280400, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -38,6 +42,7 @@ 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 +50,8 @@ 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 +59,7 @@ 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 +67,8 @@ 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 +77,7 @@ 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 +85,8 @@ 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 +94,7 @@ 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 +103,44 @@ 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 +176,7 @@ 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 4dd35a47b..0ce22d60c 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -54,7 +54,6 @@ def _decrypt_url(png): return url - class RTVEALaCartaIE(InfoExtractor): IE_NAME = 'rtve.es:alacarta' IE_DESC = 'RTVE a la carta' 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 0c8790da2..5b1c3577a 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -5,10 +5,12 @@ import re import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, - unified_strdate, +) +from ..utils import ( ExtractorError, + unified_strdate, ) @@ -36,9 +38,7 @@ class RutubeIE(InfoExtractor): } 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://rutube.ru/api/video/%s/?format=json' % video_id, video_id, 'Downloading video JSON') @@ -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, @@ -70,6 +70,37 @@ class RutubeIE(InfoExtractor): } +class RutubeEmbedIE(InfoExtractor): + IE_NAME = 'rutube:embed' + IE_DESC = 'Rutube embedded videos' + _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)' + + _TEST = { + 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', + 'info_dict': { + 'id': 'a10e53b86e8f349080f718582ce4c661', + 'ext': 'mp4', + 'upload_date': '20131223', + 'uploader_id': '297833', + 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89', + 'uploader': 'subziro89 ILya', + 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', + }, + 'params': { + 'skip_download': 'Requires ffmpeg', + }, + } + + def _real_extract(self, url): + embed_id = self._match_id(url) + webpage = self._download_webpage(url, embed_id) + + canonical_url = self._html_search_regex( + r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage, + 'Canonical URL') + return self.url_result(canonical_url, 'Rutube') + + class RutubeChannelIE(InfoExtractor): IE_NAME = 'rutube:channel' IE_DESC = 'Rutube channels' @@ -114,8 +145,7 @@ class RutubeMovieIE(RutubeChannelIE): _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - movie_id = mobj.group('id') + movie_id = self._match_id(url) movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py index f737b4e5f..a73e6f331 100644 --- a/youtube_dl/extractor/rutv.py +++ b/youtube_dl/extractor/rutv.py @@ -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 index 409f8540a..b8775c2f9 100644 --- a/youtube_dl/extractor/sbs.py +++ b/youtube_dl/extractor/sbs.py @@ -27,8 +27,7 @@ class SBSIE(InfoExtractor): 'thumbnail': 're:http://.*\.jpg', }, 'add_ies': ['generic'], - }, - { + }, { 'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed', 'only_matching': True, }] 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..dfd897ba3 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -1,14 +1,14 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_parse_qs, compat_urllib_request, ) +from ..utils import ( + ExtractorError, +) class ScreencastIE(InfoExtractor): @@ -57,8 +57,7 @@ class ScreencastIE(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( @@ -96,7 +95,7 @@ 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/screencastomatic.py b/youtube_dl/extractor/screencastomatic.py new file mode 100644 index 000000000..05337421c --- /dev/null +++ b/youtube_dl/extractor/screencastomatic.py @@ -0,0 +1,49 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + ExtractorError, + js_to_json, +) + + +class ScreencastOMaticIE(InfoExtractor): + _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)' + _TEST = { + 'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl', + 'md5': '483583cb80d92588f15ccbedd90f0c18', + 'info_dict': { + 'id': 'c2lD3BeOPl', + 'ext': 'mp4', + 'title': 'Welcome to 3-4 Philosophy @ DECV!', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + setup_js = self._search_regex( + r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", + webpage, 'setup code') + data = self._parse_json(setup_js, video_id, transform_source=js_to_json) + try: + video_data = next( + m for m in data['modes'] if m.get('type') == 'html5') + except StopIteration: + raise ExtractorError('Could not find any video entries!') + video_url = compat_urlparse.urljoin(url, video_data['config']['file']) + thumbnail = data.get('image') + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'url': video_url, + 'ext': 'mp4', + 'thumbnail': thumbnail, + } 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..6446d26dc --- /dev/null +++ b/youtube_dl/extractor/sexykarma.py @@ -0,0 +1,120 @@ +# 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$', + 'uploader': 'wildginger7', + 'upload_date': '20141008', + 'duration': 22, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }, { + 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html', + 'md5': 'dd216c68d29b49b12842b9babe762a5d', + 'info_dict': { + 'id': '8Id6EZPbuHf', + 'display_id': 'pot-pixie-tribute', + 'ext': 'mp4', + 'title': 'pot_pixie tribute', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'banffite', + 'upload_date': '20141013', + 'duration': 16, + 'view_count': int, + 'comment_count': int, + 'categories': list, + 'age_limit': 18, + } + }, { + '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, + '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"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, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index badba2ac6..26ced716e 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -4,10 +4,12 @@ import re import base64 from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, - compat_urllib_parse, int_or_none, ) @@ -26,26 +28,30 @@ class SharedIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage(url, video_id) - - if re.search(r'>File does not exist<', page) is not None: - raise ExtractorError('Video %s does not exist' % video_id, expected=True) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page)) + if '>File does not exist<' in webpage: + raise ExtractorError( + 'Video %s does not exist' % video_id, expected=True) - request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form)) + download_form = dict(re.findall( + r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage)) + request = compat_urllib_request.Request( + url, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - video_page = self._download_webpage(request, video_id, 'Downloading video page') + video_page = self._download_webpage( + request, video_id, 'Downloading video page') - video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL') - title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8') - filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False)) + video_url = self._html_search_regex( + r'data-url="([^"]+)"', video_page, 'video URL') + title = base64.b64decode(self._html_search_meta( + 'full:title', webpage, 'title')).decode('utf-8') + filesize = int_or_none(self._html_search_meta( + 'full:size', webpage, 'file size', fatal=False)) thumbnail = self._html_search_regex( - r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None) + r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None) return { 'id': video_id, @@ -54,4 +60,4 @@ 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 index 7531e8325..ac3e3adf2 100644 --- a/youtube_dl/extractor/sharesix.py +++ b/youtube_dl/extractor/sharesix.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( parse_duration, ) diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index 2909ef18b..a63d126d4 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -4,7 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, compat_urllib_parse, ) @@ -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..9f79ff5c1 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -4,8 +4,10 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, +) +from ..utils import ( ExtractorError, ) @@ -28,7 +30,7 @@ class SlideshareIE(InfoExtractor): page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) slideshare_obj = self._search_regex( - r'var slideshare_object = ({.*?}); var user_info =', + r'var\s+slideshare_object\s*=\s*({.*?});\s*var\s+user_info\s*=', webpage, 'slideshare object') info = json.loads(slideshare_obj) if info['slideshow']['type'] != 'video': @@ -39,7 +41,7 @@ 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'(?s)<p[^>]+itemprop="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 9bd5defa7..baef3daa0 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -1,26 +1,27 @@ # encoding: utf-8 from __future__ import unicode_literals -import os.path import re import json import hashlib import uuid from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( 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 +36,6 @@ 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 +50,6 @@ 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', }, }, @@ -66,11 +65,11 @@ 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', }, + 'skip': 'Video is not approved by moderator', }, # age limit + video-password { @@ -85,11 +84,11 @@ 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' - } + }, + 'skip': 'Video is not approved by moderator', }, # swf player { @@ -102,17 +101,11 @@ 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 +130,44 @@ 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 +175,32 @@ 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 } @@ -275,7 +216,7 @@ class SmotriCommunityIE(InfoExtractor): }, 'playlist_mincount': 4, } - + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) community_id = mobj.group('communityid') @@ -337,15 +278,18 @@ 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', @@ -354,9 +298,11 @@ 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) @@ -366,7 +312,7 @@ 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 @@ -375,26 +321,31 @@ 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'] @@ -415,6 +366,9 @@ 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 c663e56d4..7d3c0e937 100644 --- a/youtube_dl/extractor/sockshare.py +++ b/youtube_dl/extractor/sockshare.py @@ -1,13 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals -from ..utils import ( - ExtractorError, +import re + +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( determine_ext, + ExtractorError, ) -import re from .common import InfoExtractor @@ -27,9 +30,7 @@ class SockshareIE(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://sockshare.com/file/%s' % video_id webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index bebcafb62..c04791997 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -1,23 +1,24 @@ # encoding: utf-8 +from __future__ import unicode_literals -import json import re from .common import InfoExtractor -from ..utils import ExtractorError +from .common import compat_str 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): @@ -26,61 +27,74 @@ 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=' - 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)) - return json.loads(data_json) + base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' + + return self._download_json( + base_data_url + vid_id, video_id, + 'Downloading JSON data for %s' % vid_id) mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') mytv = mobj.group('mytv') is not None webpage = self._download_webpage(url, video_id) - raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>', - webpage, u'video title') + raw_title = self._html_search_regex( + r'(?s)<title>(.+?)</title>', + webpage, 'video title') title = raw_title.partition('-')[0].strip() - vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage, - u'video path') - data = _fetch_data(vid, mytv) - - QUALITIES = ('ori', 'super', 'high', 'nor') - vid_ids = [data['data'][q + 'Vid'] - for q in QUALITIES - if data['data'][q + 'Vid'] != 0] - if not vid_ids: - raise ExtractorError(u'No formats available for this video') + vid = self._html_search_regex( + r'var vid ?= ?["\'](\d+)["\']', + webpage, 'video path') + vid_data = _fetch_data(vid, mytv) - # For now, we just pick the highest available quality - vid_id = vid_ids[-1] + formats_json = {} + for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'): + vid_id = vid_data['data'].get('%sVid' % format_id) + if not vid_id: + continue + vid_id = compat_str(vid_id) + formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv) - format_data = data if vid == vid_id else _fetch_data(vid_id, mytv) - part_count = format_data['data']['totalBlocks'] - allot = format_data['allot'] - prot = format_data['prot'] - clipsURL = format_data['data']['clipsURL'] - su = format_data['data']['su'] + part_count = vid_data['data']['totalBlocks'] playlist = [] for i in range(part_count): - part_url = ('http://%s/?prot=%s&file=%s&new=%s' % - (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)) - - part_info = part_str.split('|') - video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) - - video_info = { - 'id': '%s_part%02d' % (video_id, i + 1), + formats = [] + for format_id, format_data in formats_json.items(): + allot = format_data['allot'] + prot = format_data['prot'] + + data = format_data['data'] + clips_url = data['clipsURL'] + su = data['su'] + + part_str = self._download_webpage( + 'http://%s/?prot=%s&file=%s&new=%s' % + (allot, prot, clips_url[i], su[i]), + video_id, + 'Downloading %s video URL part %d of %d' + % (format_id, i + 1, part_count)) + + part_info = part_str.split('|') + video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) + + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'filesize': data['clipsBytes'][i], + 'width': data['width'], + 'height': data['height'], + 'fps': data['fps'], + }) + self._sort_formats(formats) + + playlist.append({ + 'id': '%s_part%d' % (video_id, i + 1), 'title': title, - 'url': video_url, - 'ext': 'mp4', - } - playlist.append(video_info) + 'duration': vid_data['data']['clipsDuration'][i], + 'formats': formats, + }) if len(playlist) == 1: info = playlist[0] diff --git a/youtube_dl/extractor/soulanime.py b/youtube_dl/extractor/soulanime.py new file mode 100644 index 000000000..feef33e27 --- /dev/null +++ b/youtube_dl/extractor/soulanime.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + HEADRequest, + urlhandle_detect_ext, +) + + +class SoulAnimeWatchingIE(InfoExtractor): + IE_NAME = "soulanime:watching" + IE_DESC = "SoulAnime video" + _TEST = { + 'url': 'http://www.soul-anime.net/watching/seirei-tsukai-no-blade-dance-episode-9/', + 'md5': '05fae04abf72298098b528e98abf4298', + 'info_dict': { + 'id': 'seirei-tsukai-no-blade-dance-episode-9', + 'ext': 'mp4', + 'title': 'seirei-tsukai-no-blade-dance-episode-9', + 'description': 'seirei-tsukai-no-blade-dance-episode-9' + } + } + _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/watch[^/]*/(?P<id>[^/]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + domain = mobj.group('domain') + + page = self._download_webpage(url, video_id) + + video_url_encoded = self._html_search_regex( + r'<div id="download">[^<]*<a href="(?P<url>[^"]+)"', page, 'url') + video_url = "http://www.soul-anime." + domain + video_url_encoded + + ext_req = HEADRequest(video_url) + ext_handle = self._request_webpage( + ext_req, video_id, note='Determining extension') + ext = urlhandle_detect_ext(ext_handle) + + return { + 'id': video_id, + 'url': video_url, + 'ext': ext, + 'title': video_id, + 'description': video_id + } + + +class SoulAnimeSeriesIE(InfoExtractor): + IE_NAME = "soulanime:series" + IE_DESC = "SoulAnime Series" + + _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/anime./(?P<id>[^/]+)' + + _EPISODE_REGEX = r'<option value="(/watch[^/]*/[^"]+)">[^<]*</option>' + + _TEST = { + 'url': 'http://www.soul-anime.net/anime1/black-rock-shooter-tv/', + 'info_dict': { + 'id': 'black-rock-shooter-tv' + }, + 'playlist_count': 8 + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + series_id = mobj.group('id') + domain = mobj.group('domain') + + pattern = re.compile(self._EPISODE_REGEX) + + page = self._download_webpage(url, series_id, "Downloading series page") + mobj = pattern.findall(page) + + entries = [self.url_result("http://www.soul-anime." + domain + obj) for obj in mobj] + + return self.playlist_result(entries, series_id) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 4719ba45c..5d60c4939 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -5,11 +5,12 @@ import re import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urlparse, compat_urllib_parse, - +) +from ..utils import ( ExtractorError, int_or_none, unified_strdate, @@ -32,7 +33,7 @@ class SoundcloudIE(InfoExtractor): (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) - (?:/?\?secret_token=(?P<secret_token>[^&]+?))?$) + (?:/?\?secret_token=(?P<secret_token>[^&]+))?) |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' @@ -40,14 +41,15 @@ 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 @@ -103,7 +105,7 @@ class SoundcloudIE(InfoExtractor): 'id': '128590877', 'ext': 'mp3', 'title': 'Bus Brakes', - 'description': 'md5:0170be75dd395c96025d210d261c784e', + 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', 'upload_date': '20140109', 'duration': 17, @@ -140,6 +142,7 @@ 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): @@ -157,7 +160,7 @@ 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') @@ -222,14 +225,14 @@ 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') @@ -369,7 +372,7 @@ class SoundcloudPlaylistIE(SoundcloudIE): entries = [ self._extract_info_dict(t, quiet=True, secret_token=token) - for t in data['tracks']] + 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..b936202f6 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -3,13 +3,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse, compat_urllib_parse_urlparse, compat_urllib_request, - compat_urllib_parse, - unified_strdate, +) +from ..utils import ( str_to_int, - int_or_none, + unified_strdate, ) from ..aes import aes_decrypt_text @@ -40,31 +41,42 @@ 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)) + + 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'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage))) + 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 9ed7d3b39..1e55a9ffb 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -4,11 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import compat_urlparse +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', @@ -29,16 +30,28 @@ class SpiegelIE(InfoExtractor): 'description': 'md5:c2322b65e58f385a820c10fa03b2d088', 'duration': 983, }, + }, { + 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html', + 'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51', + 'info_dict': { + 'id': '1519126', + 'ext': 'mp4', + '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( @@ -79,7 +92,7 @@ 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' - _TEST = { + _TESTS = [{ 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', 'info_dict': { 'id': '1516455', @@ -87,20 +100,34 @@ class SpiegelArticleIE(InfoExtractor): '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': { - def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + }, + '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') - video_url = compat_urlparse.urljoin( - self.http_scheme() + '//spiegel.de/', video_link) - - return { - '_type': 'url', - 'url': video_url, - } + '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 index 3f680bfc6..dfe50ed45 100644 --- a/youtube_dl/extractor/sport5.py +++ b/youtube_dl/extractor/sport5.py @@ -89,4 +89,4 @@ class Sport5IE(InfoExtractor): 'duration': duration, 'categories': categories, 'formats': formats, - }
\ No newline at end of file + } 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 index 185353bef..1a57aebf1 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -4,8 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( parse_iso8601, ) @@ -17,11 +19,11 @@ class SportDeutschlandIE(InfoExtractor): 'info_dict': { 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', 'ext': 'mp4', - 'title': 'LIVE: Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', + '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 LIVE', + 'description': 're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV', 'timestamp': int, 'upload_date': 're:^201408[23][0-9]$', }, @@ -58,9 +60,10 @@ class SportDeutschlandIE(InfoExtractor): categories = list(data.get('section', {}).get('tags', {}).values()) asset = data['asset'] + assets_info = self._download_json(asset['url'], video_id) formats = [] - smil_url = asset['video'] + smil_url = assets_info['video'] if '.smil' in smil_url: m3u8_url = smil_url.replace('.smil', '.m3u8') formats.extend( @@ -93,4 +96,3 @@ class SportDeutschlandIE(InfoExtractor): 'rtmp_live': asset.get('live'), 'timestamp': parse_iso8601(asset.get('date')), } - diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py new file mode 100644 index 000000000..666a7dcc8 --- /dev/null +++ b/youtube_dl/extractor/srmediathek.py @@ -0,0 +1,43 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import js_to_json + + +class SRMediathekIE(InfoExtractor): + IE_DESC = 'Süddeutscher Rundfunk' + _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)' + + _TEST = { + 'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455', + 'info_dict': { + 'id': '28455', + 'ext': 'mp4', + 'title': 'sportarena (26.10.2014)', + 'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + 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..d4e134015 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -2,10 +2,9 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -13,7 +12,7 @@ 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 +26,8 @@ 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) @@ -40,8 +39,7 @@ class StreamcloudIE(InfoExtractor): ''', orig_webpage) post = compat_urllib_parse.urlencode(fields) - self.to_screen('%s: Waiting for timeout' % video_id) - time.sleep(12) + self._sleep(12, video_id) headers = { b'Content-Type': b'application/x-www-form-urlencoded', } diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py index 73efe9542..c3ceb5f76 100644 --- a/youtube_dl/extractor/streamcz.py +++ b/youtube_dl/extractor/streamcz.py @@ -1,18 +1,14 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor from ..utils import ( int_or_none, - compat_str, ) class StreamCZIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)' + _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)' _TESTS = [{ 'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti', @@ -21,61 +17,63 @@ class StreamCZIE(InfoExtractor): 'id': '765767', 'ext': 'mp4', 'title': 'Peklo na talíři: Éčka pro děti', - 'description': 'md5:49ace0df986e95e331d0fe239d421519', - 'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100', + 'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE', + 'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100', 'duration': 256, }, }, { 'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka', - 'md5': '246272e753e26bbace7fcd9deca0650c', + 'md5': 'e54a254fb8b871968fd8403255f28589', 'info_dict': { 'id': '10002447', 'ext': 'mp4', 'title': 'Kancelář Blaník: Tři roky pro Mazánka', - 'description': 'md5:9177695a8b756a0a8ab160de4043b392', - 'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000', + 'description': 'md5:3862a00ba7bf0b3e44806b544032c859', + 'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000', 'duration': 368, }, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - - webpage = self._download_webpage(url, video_id) - - data = self._html_search_regex(r'Stream\.Data\.Episode\((.+?)\);', webpage, 'stream data') - - jsonData = json.loads(data) + video_id = self._match_id(url) + data = self._download_json( + 'http://www.stream.cz/API/episode/%s' % video_id, video_id) formats = [] - for video in jsonData['instances']: - for video_format in video['instances']: - format_id = video_format['quality'] - - if format_id == '240p': - quality = 0 - elif format_id == '360p': - quality = 1 - elif format_id == '480p': - quality = 2 - elif format_id == '720p': - quality = 3 - + for quality, video in enumerate(data['video_qualities']): + for f in video['formats']: + typ = f['type'].partition('/')[2] + qlabel = video.get('quality_label') formats.append({ - 'format_id': '%s-%s' % (video_format['type'].split('/')[1], format_id), - 'url': video_format['source'], + 'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ, + 'format_id': '%s-%s' % (typ, f['quality']), + 'url': f['source'], + 'height': int_or_none(f['quality'].rstrip('p')), 'quality': quality, }) - self._sort_formats(formats) + image = data.get('image') + if image: + thumbnail = self._proto_relative_url( + image.replace('{width}', '1240').replace('{height}', '697'), + scheme='http:', + ) + else: + thumbnail = None + + stream = data.get('_embedded', {}).get('stream:show', {}).get('name') + if stream: + title = '%s: %s' % (stream, data['name']) + else: + title = data['name'] + return { - 'id': compat_str(jsonData['episode_id']), - 'title': self._og_search_title(webpage), - 'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'), + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, 'formats': formats, - 'description': self._og_search_description(webpage), - 'duration': int_or_none(jsonData['duration']), - 'view_count': int_or_none(jsonData['stats_total']), + 'description': data.get('web_site_text'), + 'duration': int_or_none(data.get('duration')), + 'view_count': int_or_none(data.get('views')), } 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 index 7de3c9dd5..8a333f1d2 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -28,23 +28,27 @@ class SunPornoIE(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>([^<]+)</title>', webpage, 'title') - description = self._html_search_meta('description', webpage, 'description') + 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'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) + r'itemprop="duration">\s*(\d+:\d+)\s*<', + webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( - r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) + 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)) + r'(\d+)</b> Comments?', + webpage, 'comment count', fatal=False)) formats = [] quality = qualities(['mp4', 'flv']) diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py index 13c6ea677..58073eefe 100644 --- a/youtube_dl/extractor/swrmediathek.py +++ b/youtube_dl/extractor/swrmediathek.py @@ -80,7 +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': @@ -101,4 +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..f1f43d0a7 --- /dev/null +++ b/youtube_dl/extractor/tapely.py @@ -0,0 +1,107 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) +from ..utils import ( + clean_html, + ExtractorError, + 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 8a95fd656..82675431f 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -57,9 +57,7 @@ class TeacherTubeIE(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_meta('title', webpage, 'title', fatal=True) @@ -121,7 +119,7 @@ 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 fa796ce72..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): @@ -33,7 +32,7 @@ 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( diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 1cca47771..10b3b706a 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -5,7 +5,7 @@ import re from .subtitles import SubtitlesInfoExtractor -from ..utils import ( +from ..compat import ( compat_str, ) @@ -13,7 +13,7 @@ from ..utils import ( class TEDIE(SubtitlesInfoExtractor): _VALID_URL = r'''(?x) (?P<proto>https?://) - (?P<type>www|embed)(?P<urlmain>\.ted\.com/ + (?P<type>www|embed(?:-ssl)?)(?P<urlmain>\.ted\.com/ ( (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist | @@ -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', @@ -57,6 +58,7 @@ class TEDIE(SubtitlesInfoExtractor): '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', @@ -65,6 +67,22 @@ class TEDIE(SubtitlesInfoExtractor): '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, + }, }] _NATIVE_FORMATS = { @@ -75,12 +93,12 @@ 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): m = re.match(self._VALID_URL, url, re.VERBOSE) - if m.group('type') == 'embed': + if m.group('type').startswith('embed'): desktop_url = m.group('proto') + 'www' + m.group('urlmain') return self.url_result(desktop_url, 'TED') name = m.group('name') @@ -95,7 +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'] @@ -114,6 +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, @@ -149,12 +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): @@ -173,8 +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..be3f72df7 --- /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<id>.*?)\.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/teletask.py b/youtube_dl/extractor/teletask.py new file mode 100644 index 000000000..e54145105 --- /dev/null +++ b/youtube_dl/extractor/teletask.py @@ -0,0 +1,53 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class TeleTaskIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.tele-task.de/archive/video/html5/26168/', + 'info_dict': { + 'title': 'Duplicate Detection', + }, + 'playlist': [{ + 'md5': '290ef69fb2792e481169c3958dbfbd57', + 'info_dict': { + 'id': '26168-speaker', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + } + }, { + 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4', + 'info_dict': { + 'id': '26168-slides', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + } + }] + } + + def _real_extract(self, url): + lecture_id = self._match_id(url) + + webpage = self._download_webpage(url, lecture_id) + + title = self._html_search_regex( + r'itemprop="name">([^<]+)</a>', webpage, 'title') + upload_date = unified_strdate(self._html_search_regex( + r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False)) + + entries = [{ + 'id': '%s-%s' % (lecture_id, format_id), + 'url': video_url, + 'title': title, + 'upload_date': upload_date, + } for format_id, video_url in re.findall( + r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)] + + return self.playlist_result(entries, lecture_id, title) diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py index 81ba169fb..466155ef8 100644 --- a/youtube_dl/extractor/tenplay.py +++ b/youtube_dl/extractor/tenplay.py @@ -8,7 +8,6 @@ class TenPlayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?ten(play)?\.com\.au/.+' _TEST = { 'url': 'http://tenplay.com.au/ten-insider/extra/season-2013/tenplay-tv-your-way', - #'md5': 'd68703d9f73dc8fccf3320ab34202590', 'info_dict': { 'id': '2695695426001', 'ext': 'flv', diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index fdae17b1b..025d0877c 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -1,15 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html' - _TEST = { + _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html' + _TESTS = { 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 'info_dict': { 'id': '10635995', @@ -21,16 +19,28 @@ class TF1IE(InfoExtractor): # Sometimes wat serves the whole file with the --test option 'skip_download': True, }, + }, { + 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', + 'info_dict': { + 'id': '12043945', + 'ext': 'mp4', + 'title': 'Le grand Mystérioso - Chuggington', + 'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.', + 'upload_date': '20150103', + }, + 'params': { + # Sometimes wat serves the whole file with the --test option + '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) webpage = self._download_webpage(url, video_id) embed_url = self._html_search_regex( - r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') + 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 0be793b1c..110ed976d 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -3,9 +3,12 @@ from __future__ import unicode_literals import re import json -from .common import InfoExtractor -from ..utils import ( +from .subtitles import SubtitlesInfoExtractor +from ..compat import ( compat_str, +) +from ..utils import ( + determine_ext, ExtractorError, xpath_with_ns, ) @@ -13,7 +16,7 @@ from ..utils import ( _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'}) -class ThePlatformIE(InfoExtractor): +class ThePlatformIE(SubtitlesInfoExtractor): _VALID_URL = r'''(?x) (?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/ (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)? @@ -35,9 +38,20 @@ 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'] @@ -52,6 +66,20 @@ class ThePlatformIE(InfoExtractor): info_json = self._download_webpage(info_url, video_id) info = json.loads(info_json) + subtitles = {} + captions = info.get('captions') + if isinstance(captions, list): + for caption in captions: + lang, src = caption.get('lang'), caption.get('src') + if lang and src: + subtitles[lang] = src + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self.extract_subtitles(video_id, subtitles) + head = meta.find(_x('smil:head')) body = meta.find(_x('smil:body')) @@ -89,32 +117,23 @@ class ThePlatformIE(InfoExtractor): 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 { 'id': video_id, 'title': info['title'], + 'subtitles': subtitles, '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 index 607e947bb..496f15d80 100644 --- a/youtube_dl/extractor/thvideo.py +++ b/youtube_dl/extractor/thvideo.py @@ -26,8 +26,7 @@ class THVideoIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) # extract download link from mobile player page webpage_player = self._download_webpage( @@ -57,3 +56,29 @@ class THVideoIE(InfoExtractor): '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..9f9e388c5 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -5,7 +5,7 @@ import re from .common import InfoExtractor from .brightcove import BrightcoveIE from .discovery import DiscoveryIE -from ..utils import compat_urlparse +from ..compat import compat_urlparse class TlcIE(DiscoveryIE): @@ -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..c5c6fdc51 --- /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': r're:http://cdnbakmi\.kaltura\.com/.*thumbnail.*', + } + } + + 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 index 4956f8577..d48cbbf14 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -12,7 +12,7 @@ from ..utils import ( 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 + _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>' _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' @@ -49,8 +49,8 @@ class TNAFlixIE(InfoExtractor): if duration: duration = parse_duration(duration[1:]) - cfg_url = self._html_search_regex( - self._CONFIG_REGEX, webpage, 'flashvars.config') + cfg_url = self._proto_relative_url(self._html_search_regex( + self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:') cfg_xml = self._download_xml( cfg_url, display_id, note='Downloading metadata', @@ -71,7 +71,7 @@ class TNAFlixIE(InfoExtractor): fmt['height'] = int(m.group(1)) formats.append(fmt) self._sort_formats(formats) - + return { 'id': video_id, 'display_id': display_id, 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 64a1e9030..d73ad3762 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -4,9 +4,11 @@ import json import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, +) +from ..utils import ( int_or_none, str_to_int, ) diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index dcd823d08..c89de5ba4 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -9,7 +9,7 @@ from .common import InfoExtractor class TudouIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])' _TESTS = [{ 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', 'md5': '140a49ed444bd22f93330985d8475fcb', @@ -27,26 +27,18 @@ class TudouIE(InfoExtractor): 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', 'thumbnail': 're:^https?://.*\.jpg$', } - }, { - 'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', - 'info_dict': { - 'title': 'todo.mp4', - }, - '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): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(2) + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) @@ -73,7 +65,7 @@ class TudouIE(InfoExtractor): 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) @@ -87,4 +79,9 @@ class TudouIE(InfoExtractor): } result.append(part_info) - return result + return { + '_type': 'multi_video', + 'entries': result, + 'id': video_id, + 'title': title, + } diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index 306fe8974..2a1ae5a71 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,9 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class TumblrIE(InfoExtractor): @@ -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', } @@ -41,18 +38,12 @@ 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 @@ -62,9 +53,9 @@ class TumblrIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, - 'title': video_title, - 'description': self._html_search_meta('description', webpage), - 'thumbnail': video_thumbnail, - 'ext': ext, + '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..b6b1f2568 --- /dev/null +++ b/youtube_dl/extractor/tunein.py @@ -0,0 +1,106 @@ +# 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 + reliability = stream.get('Reliability') + format_note = ( + 'Reliability: %d%%' % reliability + if reliability is not None else None) + formats.append({ + 'preference': ( + 0 if reliability is None or reliability > 90 + else 1), + 'abr': stream.get('Bandwidth'), + 'ext': stream.get('MediaType').lower(), + 'acodec': stream.get('MediaType'), + 'vcodec': 'none', + 'url': stream.get('Url'), + 'source_preference': reliability, + 'format_note': format_note, + }) + 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/tutv.py b/youtube_dl/extractor/tutv.py index d516b6427..4de0aac52 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -1,10 +1,9 @@ from __future__ import unicode_literals import base64 -import re from .common import InfoExtractor -from ..utils import compat_parse_qs +from ..compat import compat_parse_qs class TutvIE(InfoExtractor): @@ -20,10 +19,9 @@ class TutvIE(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) + internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') data_content = self._download_webpage( diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index dc8697850..ba65996dc 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -1,31 +1,29 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( float_or_none, - str_to_int, + parse_age_limit, ) class TvigleIE(InfoExtractor): IE_NAME = 'tvigle' IE_DESC = 'Интернет-телевидение Tvigle.ru' - _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$' + _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<id>[^/]+)/$' _TESTS = [ { - 'url': 'http://www.tvigle.ru/video/brat-2/', - 'md5': '72cb7eab33e54314e1790da402d3c9c3', + 'url': 'http://www.tvigle.ru/video/sokrat/', + 'md5': '36514aed3657d4f70b4b2cef8eb520cd', 'info_dict': { - 'id': '5119390', - 'display_id': 'brat-2', - 'ext': 'mp4', - 'title': 'Брат 2 ', - 'description': 'md5:5751f4fe345a58e1692585c361294bd8', - 'duration': 7356.369, + 'id': '1848932', + 'display_id': 'sokrat', + 'ext': 'flv', + 'title': 'Сократ', + 'description': 'md5:a05bd01be310074d5833efc6743be95e', + 'duration': 6586, 'age_limit': 0, }, }, @@ -44,8 +42,7 @@ class TvigleIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') + display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) @@ -60,8 +57,8 @@ class TvigleIE(InfoExtractor): title = item['title'] description = item['description'] thumbnail = item['thumbnail'] - duration = float_or_none(item['durationMilliseconds'], 1000) - age_limit = str_to_int(item['ageRestrictions']) + duration = float_or_none(item.get('durationMilliseconds'), 1000) + age_limit = parse_age_limit(item.get('ageRestrictions')) formats = [] for vcodec, fmts in item['videos'].items(): @@ -71,6 +68,7 @@ class TvigleIE(InfoExtractor): 'format_id': '%s-%s' % (vcodec, quality), 'vcodec': vcodec, 'height': int(quality[:-1]), + 'filesize': item['video_files_size'][vcodec][quality], }) self._sort_formats(formats) @@ -83,4 +81,4 @@ class TvigleIE(InfoExtractor): '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..cc26f417a 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,42 +1,142 @@ -import json +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + import re from .common import InfoExtractor class TvpIE(InfoExtractor): - IE_NAME = u'tvp.pl' - _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)' + IE_NAME = 'tvp.pl' + _VALID_URL = r'https?://(?:vod|www)\.tvp\.pl/.*/(?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', + _TESTS = [{ + 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem/wideo/odc-2/4278035', + 'info_dict': { + 'id': '4278035', + 'ext': 'wmv', + 'title': 'Ogniem i mieczem, odc. 2', + 'description': 'Bohun dowiaduje się o złamaniu przez kniahinię danego mu słowa i wyrusza do Rozłogów. Helenie w ostatniej chwili udaje się uciec dzięki pomocy Zagłoby.', + }, + }, { + 'url': 'http://vod.tvp.pl/seriale/obyczajowe/czas-honoru/sezon-1-1-13/i-seria-odc-13/194536', + 'info_dict': { + 'id': '194536', + 'ext': 'mp4', + 'title': 'Czas honoru, I seria – odc. 13', + # 'description': 'WŁADEK\nCzesław prosi Marię o dostarczenie Władkowi zarazki tyfusu. Jeśli zachoruje zostanie przewieziony do szpitala skąd łatwiej będzie go odbić. Czy matka zdecyduje się zarazić syna? Karol odwiedza Wandę przyznaje się, że ją oszukiwał, ale ostrzega też, że grozi jej aresztowanie i nalega, żeby wyjechała z Warszawy. Czy dziewczyna zdecyduje się znów oddalić od ukochanego? Rozpoczyna się akcja odbicia Władka.', + }, + }, { + 'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176', + 'info_dict': { + 'id': '17916176', + 'ext': 'mp4', + 'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata', + }, + 'params': { + # m3u8 download + 'skip_download': 'true', + }, + }, { + 'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272', + 'info_dict': { + 'id': '17834272', + 'ext': 'mp4', + 'title': 'Na sygnale, odc. 39', + 'description': 'Ekipa Wiktora ratuje młodą matkę, która spadła ze schodów trzymając na rękach noworodka. Okazuje się, że dziewczyna jest surogatką, a biologiczni rodzice dziecka próbują zmusić ją do oddania synka…', + }, + 'params': { + # m3u8 download + 'skip_download': 'true', }, - u'skip': u'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') - 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) - video_url = params['video_url'] - - title = self._og_search_title(webpage, fatal=True) + video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id) + + title = self._og_search_title(webpage) + series = self._search_regex( + r'{name:\s*([\'"])SeriesTitle\1,\s*value:\s*\1(?P<series>.*?)\1},', + webpage, 'series', group='series', default=None) + if series is not None and series not in title: + title = '%s, %s' % (series, title) + description = self._og_search_description(webpage, default=None) + + video_url = self._search_regex( + r'0:{src:([\'"])(?P<url>.*?)\1', webpage, 'formats', group='url', default=None) + if video_url is None: + video_url = self._download_json( + 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id, + video_id)['video_url'] + + ext = video_url.rsplit('.', 1)[-1] + if ext != 'ism/manifest': + if '/' in ext: + ext = 'mp4' + formats = [{ + 'format_id': 'direct', + 'url': video_url, + 'ext': ext, + }] + else: + m3u8_url = re.sub('([^/]*)\.ism/manifest', r'\1.ism/\1.m3u8', video_url) + formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') + + self._sort_formats(formats) + return { 'id': video_id, 'title': title, - 'ext': 'wmv', - 'url': video_url, - 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), + 'description': description, + 'formats': formats, + } + + +class TvpSeriesIE(InfoExtractor): + IE_NAME = 'tvp.pl:Series' + _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$' + + _TESTS = [{ + 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', + 'info_dict': { + 'title': 'Ogniem i mieczem', + 'id': '4278026', + }, + 'playlist_count': 4, + }, { + 'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat', + 'info_dict': { + 'title': 'Boso przez świat', + 'id': '9329207', + }, + 'playlist_count': 86, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id, tries=5) + + title = self._html_search_regex( + r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series') + playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') + playlist = self._download_webpage( + 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' + 'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5, + note='Downloading playlist') + + videos_paths = re.findall( + '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist) + entries = [ + self.url_result('http://vod.tvp.pl%s' % v_path, ie=TvpIE.ie_key()) + for v_path in videos_paths] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': display_id, + 'title': title, + 'entries': entries, } diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 445e0ec41..9a53a3c74 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -4,9 +4,8 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - ExtractorError, - compat_str, parse_iso8601, qualities, ) @@ -176,15 +175,14 @@ class TVPlayIE(InfoExtractor): ] 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') @@ -208,6 +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..b11a1d561 --- /dev/null +++ b/youtube_dl/extractor/twitch.py @@ -0,0 +1,247 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + 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>[^/]+)| + (?:(?:[^/]+)/v/(?P<vodid>[^/]+))| + (?:(?:[^/]+)/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', + 'v': 'vod', + '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])) + + if item == 'v': + access_token = self._download_json( + '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id, + 'Downloading %s access token' % ITEMS[item]) + formats = self._extract_m3u8_formats( + 'http://usher.twitch.tv/vod/%s?nauth=%s&nauthsig=%s' + % (item_id, access_token['token'], access_token['sig']), + item_id, 'mp4') + info['formats'] = formats + return info + + 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('vodid'): + return self._extract_media('v', mobj.group('vodid')) + 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/udemy.py b/youtube_dl/extractor/udemy.py index 054f42725..4667ed83b 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, ) @@ -40,8 +42,24 @@ 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 +80,9 @@ 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 +91,49 @@ 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 +167,29 @@ 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/urort.py b/youtube_dl/extractor/urort.py index 5d06fcc9e..8872cfcb2 100644 --- a/youtube_dl/extractor/urort.py +++ b/youtube_dl/extractor/urort.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( unified_strdate, ) @@ -18,11 +18,10 @@ class UrortIE(InfoExtractor): 'url': 'https://urort.p3.no/#!/Band/Gerilja', 'md5': '5ed31a924be8a05e47812678a86e127b', 'info_dict': { - 'id': '33124-4', + 'id': '33124-24', 'ext': 'mp3', 'title': 'The Bomb', 'thumbnail': 're:^https?://.+\.jpg', - 'like_count': int, 'uploader': 'Gerilja', 'uploader_id': 'Gerilja', 'upload_date': '20100323', @@ -33,25 +32,31 @@ class UrortIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) fstr = compat_urllib_parse.quote("InternalBandUrl eq '%s'" % playlist_id) - json_url = 'http://urort.p3.no/breeze/urort/TrackDtos?$filter=' + fstr + json_url = 'http://urort.p3.no/breeze/urort/TrackDTOViews?$filter=%s&$orderby=Released%%20desc&$expand=Tags%%2CFiles' % fstr songs = self._download_json(json_url, playlist_id) - print(songs[0]) - - entries = [{ - 'id': '%d-%s' % (s['BandId'], s['$id']), - 'title': s['Title'], - 'url': s['TrackUrl'], - 'ext': 'mp3', - 'uploader_id': playlist_id, - 'uploader': s.get('BandName', playlist_id), - 'like_count': s.get('LikeCount'), - 'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'], - 'upload_date': unified_strdate(s.get('Released')), - } for s in songs] + entries = [] + for s in songs: + formats = [{ + 'tbr': f.get('Quality'), + 'ext': f['FileType'], + 'format_id': '%s-%s' % (f['FileType'], f.get('Quality', '')), + 'url': 'http://p3urort.blob.core.windows.net/tracks/%s' % f['FileRef'], + 'preference': 3 if f['FileType'] == 'mp3' else 2, + } for f in s['Files']] + self._sort_formats(formats) + e = { + 'id': '%d-%s' % (s['BandId'], s['$id']), + 'title': s['Title'], + 'uploader_id': playlist_id, + 'uploader': s.get('BandName', playlist_id), + 'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'], + 'upload_date': unified_strdate(s.get('Released')), + 'formats': formats, + } + entries.append(e) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 994b60a76..68d03b999 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -3,9 +3,8 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, - get_meta_content, ) @@ -46,13 +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, @@ -72,14 +71,14 @@ class UstreamChannelIE(InfoExtractor): 'info_dict': { 'id': '10874166', }, - 'playlist_mincount': 54, + 'playlist_mincount': 17, } def _real_extract(self, url): m = re.match(self._VALID_URL, url) display_id = m.group('slug') webpage = self._download_webpage(url, display_id) - channel_id = get_meta_content('ustream:channel_id', webpage) + 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 diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index ebd64f0f5..dd026748d 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -1,19 +1,18 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, ) class Vbox7IE(InfoExtractor): - _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)' + _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)' _TEST = { 'url': 'http://vbox7.com/play:249bb972c2', 'md5': '99f65c0c9ef9b682b97313e052734c3f', @@ -25,18 +24,17 @@ class Vbox7IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) 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}) diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index 77b1f91ce..815f58468 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -4,10 +4,12 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, - get_element_by_id, +) +from ..utils import ( clean_html, + get_element_by_id, ) @@ -26,8 +28,7 @@ class VeeHDIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) # VeeHD seems to send garbage on the first request. # See https://github.com/rg3/youtube-dl/issues/2102 @@ -48,11 +49,11 @@ 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/veoh.py b/youtube_dl/extractor/veoh.py index a7953a7e7..01e258e32 100644 --- a/youtube_dl/extractor/veoh.py +++ b/youtube_dl/extractor/veoh.py @@ -4,8 +4,10 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( int_or_none, ExtractorError, ) 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 ebab8b86c..43f6b029d 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -4,9 +4,10 @@ import re import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ( - compat_HTTPError, +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) @@ -14,7 +15,7 @@ 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/(?:[^/]+/(?:[^/]+/)?)?| diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 7d27d6c57..2f111bf7e 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -17,7 +17,7 @@ class VGTVIE(InfoExtractor): 'info_dict': { 'id': '84196', 'ext': 'mp4', - 'title': 'Hevnen er søt episode 10: Abu', + 'title': 'Hevnen er søt: Episode 10 - Abu', 'description': 'md5:e25e4badb5f544b04341e14abdc72234', 'thumbnail': 're:^https?://.*\.jpg', 'duration': 648.000, @@ -31,11 +31,11 @@ class VGTVIE(InfoExtractor): 'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen', 'info_dict': { 'id': '100764', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen', 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3', 'thumbnail': 're:^https?://.*\.jpg', - 'duration': 9056.000, + 'duration': 9103.0, 'timestamp': 1410113864, 'upload_date': '20140907', 'view_count': int, @@ -50,7 +50,7 @@ class VGTVIE(InfoExtractor): 'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen', 'info_dict': { 'id': '100015', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!', 'description': 'md5:9a60cc23fa349f761628924e56eeec2d', 'thumbnail': 're:^https?://.*\.jpg', @@ -67,9 +67,7 @@ class VGTVIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + 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') @@ -116,4 +114,4 @@ class VGTVIE(InfoExtractor): 'duration': float_or_none(data['duration'], 1000), 'view_count': data['displays'], 'formats': formats, - }
\ No newline at end of file + } 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/videodetective.py b/youtube_dl/extractor/videodetective.py index ac6c25537..0ffc7ff7d 100644 --- a/youtube_dl/extractor/videodetective.py +++ b/youtube_dl/extractor/videodetective.py @@ -1,10 +1,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urlparse from .internetvideoarchive import InternetVideoArchiveIE -from ..utils import compat_urlparse class VideoDetectiveIE(InfoExtractor): @@ -17,13 +15,12 @@ class VideoDetectiveIE(InfoExtractor): 'ext': 'mp4', 'title': 'KICK-ASS 2', 'description': 'md5:65ba37ad619165afac7d432eaded6013', - 'duration': 135, + 'duration': 138, }, } 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) og_video = self._og_search_video_url(webpage) query = compat_urlparse.urlparse(og_video).query 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 index 29c4e0101..7a78f0d26 100644 --- a/youtube_dl/extractor/videomega.py +++ b/youtube_dl/extractor/videomega.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( remove_start, ) @@ -27,9 +27,7 @@ class VideoMegaIE(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://videomega.tv/iframe.php?ref={0:}'.format(video_id) webpage = self._download_webpage(url, video_id) 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/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/vier.py b/youtube_dl/extractor/vier.py new file mode 100644 index 000000000..619039e51 --- /dev/null +++ b/youtube_dl/extractor/vier.py @@ -0,0 +1,118 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class VierIE(InfoExtractor): + IE_NAME = 'vier' + _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))' + _TESTS = [{ + 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', + 'info_dict': { + 'id': '16129', + 'display_id': 'het-wordt-warm-de-moestuin', + 'ext': 'mp4', + 'title': 'Het wordt warm in De Moestuin', + 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen', + 'only_matching': True, + }, { + 'url': 'http://www.vier.be/video/v3/embed/16129', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + embed_id = mobj.group('embed_id') + display_id = mobj.group('display_id') or embed_id + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'"nid"\s*:\s*"(\d+)"', webpage, 'video id') + application = self._search_regex( + r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod') + filename = self._search_regex( + r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename') + + playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename) + formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4') + + title = self._og_search_title(webpage, default=display_id) + description = self._og_search_description(webpage, default=None) + thumbnail = self._og_search_thumbnail(webpage, default=None) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } + + +class VierVideosIE(InfoExtractor): + IE_NAME = 'vier:videos' + _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)' + _TESTS = [{ + 'url': 'http://www.vier.be/demoestuin/videos', + 'info_dict': { + 'id': 'demoestuin', + }, + 'playlist_mincount': 153, + }, { + 'url': 'http://www.vier.be/demoestuin/videos?page=6', + 'info_dict': { + 'id': 'demoestuin-page6', + }, + 'playlist_mincount': 20, + }, { + 'url': 'http://www.vier.be/demoestuin/videos?page=7', + 'info_dict': { + 'id': 'demoestuin-page7', + }, + 'playlist_mincount': 13, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + program = mobj.group('program') + + webpage = self._download_webpage(url, program) + + page_id = mobj.group('page') + if page_id: + page_id = int(page_id) + start_page = page_id + last_page = start_page + 1 + playlist_id = '%s-page%d' % (program, page_id) + else: + start_page = 0 + last_page = int(self._search_regex( + r'videos\?page=(\d+)">laatste</a>', + webpage, 'last page', default=0)) + 1 + playlist_id = program + + entries = [] + for current_page_id in range(start_page, last_page): + current_page = self._download_webpage( + 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id), + program, + 'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage + page_entries = [ + self.url_result('http://www.vier.be' + video_url, 'Vier') + for video_url in re.findall( + r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)] + entries.extend(page_entries) + + return self.playlist_result(entries, playlist_id) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 15f315298..944901e14 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -17,7 +17,6 @@ class VikiIE(SubtitlesInfoExtractor): _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)' _TEST = { 'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14', - 'md5': 'a21454021c2646f5433514177e2caa5f', 'info_dict': { 'id': '1023585v', 'ext': 'mp4', @@ -31,8 +30,7 @@ class VikiIE(SubtitlesInfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._og_search_title(webpage) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index bc01d7fbf..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, ) @@ -54,7 +56,7 @@ 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/) @@ -89,6 +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, }, }, @@ -103,6 +106,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader': 'The BLN & Business of Software', 'uploader_id': 'theblnbusinessofsoftware', 'duration': 3610, + 'description': None, }, }, { @@ -117,6 +121,7 @@ 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', @@ -152,6 +157,18 @@ 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', + }, + }, ] def _verify_video_password(self, url, video_id, webpage): @@ -203,6 +220,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # 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 @@ -238,11 +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): @@ -273,18 +291,23 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): _, 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")) @@ -491,7 +514,7 @@ class VimeoReviewIE(InfoExtractor): 'info_dict': { 'id': '91613211', 'ext': 'mp4', - 'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn', + 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', 'uploader': 'DevWeek Events', 'duration': 2773, 'thumbnail': 're:^https?://.*\.jpg$', @@ -529,3 +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/vimple.py b/youtube_dl/extractor/vimple.py index 33d370e1c..ee3d86117 100644 --- a/youtube_dl/extractor/vimple.py +++ b/youtube_dl/extractor/vimple.py @@ -14,28 +14,17 @@ class VimpleIE(InfoExtractor): IE_DESC = 'Vimple.ru' _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})' _TESTS = [ - # Quality: Large, from iframe { - 'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c', + 'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf', + 'md5': '2e750a330ed211d3fd41821c6ad9a279', 'info_dict': { - 'id': 'b132bdfd71b546d3972f9ab9a25f201c', - 'title': 'great-escape-minecraft.flv', + 'id': 'c0f6b1687dcd4000a97ebe70068039cf', 'ext': 'mp4', - 'duration': 352, - 'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c', + 'title': 'Sunset', + 'duration': 20, + 'thumbnail': 're:https?://.*?\.jpg', }, }, - # Quality: Medium, from mainpage - { - 'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', - 'info_dict': { - 'id': 'a15950562888453b8e6f9572dc8600cd', - 'title': 'DB 01', - 'ext': 'flv', - 'duration': 1484, - 'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', - } - }, ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index e7754158d..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']), @@ -63,29 +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>[^/]+)/?(\?.*)?$' _VINE_BASE_URL = "https://vine.co/" - _TEST = { - 'url': 'https://vine.co/Visa', - 'info_dict': { - 'id': 'Visa', + _TESTS = [ + { + 'url': 'https://vine.co/Visa', + 'info_dict': { + 'id': 'Visa', + }, + 'playlist_mincount': 46, }, - 'playlist_mincount': 47, - } + { + 'url': 'https://vine.co/u/941705360593584128', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user = mobj.group('user') + u = mobj.group('u') - profile_url = "%sapi/users/profiles/vanity/%s" % ( - self._VINE_BASE_URL, user) + profile_url = "%sapi/users/profiles/%s%s" % ( + self._VINE_BASE_URL, 'vanity/' if not u else '', user) profile_data = self._download_json( profile_url, user, note='Downloading user profile data') user_id = profile_data['data']['userId'] timeline_data = [] for pagenum in itertools.count(1): - timeline_url = "%sapi/timelines/users/%s?page=%s" % ( + timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % ( self._VINE_BASE_URL, user_id, pagenum) timeline_page = self._download_json( timeline_url, user, note='Downloading page %d' % pagenum) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 918bd1098..81e02a624 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -5,18 +5,22 @@ import re import json from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, - compat_urllib_parse, - compat_str, + orderedSet, unescapeHTML, + unified_strdate, ) class VKIE(InfoExtractor): IE_NAME = 'vk.com' - _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' + _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 +33,19 @@ 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 +58,12 @@ 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 +73,7 @@ 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 +86,7 @@ class VKIE(InfoExtractor): 'uploader': 'Киномания - лучшее из мира кино', 'title': ' ', 'duration': 7291, + 'upload_date': '20140328', }, 'skip': 'Requires vk account credentials', }, @@ -100,9 +99,15 @@ 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 +124,7 @@ 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): @@ -138,15 +143,35 @@ 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: self.to_screen('Youtube video detected') return self.url_result(m_yt.group(1), 'Youtube') + m_rutube = re.search( + r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) + if m_rutube is not None: + self.to_screen('rutube video detected') + rutube_url = self._proto_relative_url( + m_rutube.group(1).replace('\\', '')) + return self.url_result(rutube_url) + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page) if m_opts: m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1)) @@ -159,6 +184,13 @@ 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 +205,28 @@ 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 affef6507..1c0966a79 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -2,8 +2,9 @@ from __future__ import unicode_literals import re + from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -24,8 +25,7 @@ class VodlockerIE(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) fields = dict(re.findall(r'''(?x)<input\s+ 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 1b2f731e9..405cb9db4 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, +) from ..utils import ( int_or_none, - compat_str, ExtractorError, ) diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py index fb0600f1a..c3fde53f5 100644 --- a/youtube_dl/extractor/vuclip.py +++ b/youtube_dl/extractor/vuclip.py @@ -3,8 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, +) +from ..utils import ( + ExtractorError, parse_duration, qualities, ) @@ -14,21 +17,19 @@ 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, } } 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) + ad_m = re.search( r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage) if ad_m: @@ -37,16 +38,32 @@ 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 +73,7 @@ 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 88bbbb219..c17bebd6e 100644 --- a/youtube_dl/extractor/washingtonpost.py +++ b/youtube_dl/extractor/washingtonpost.py @@ -10,14 +10,14 @@ from ..utils import ( class WashingtonPostIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' + _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _TEST = { 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', 'info_dict': { 'title': 'Sinkhole of bureaucracy', }, 'playlist': [{ - 'md5': 'c3f4b4922ffa259243f68e928db2db8c', + 'md5': '79132cc09ec5309fa590ae46e4cc31bc', 'info_dict': { 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f', 'ext': 'mp4', @@ -29,7 +29,7 @@ class WashingtonPostIE(InfoExtractor): 'upload_date': '20140322', }, }, { - 'md5': 'f645a07652c2950cd9134bb852c5f5eb', + 'md5': 'e1d5734c06865cc504ad99dc2de0d443', 'info_dict': { 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f', 'ext': 'mp4', @@ -44,10 +44,9 @@ class WashingtonPostIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - + page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) + title = self._og_search_title(webpage) uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage) entries = [] diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 54d37da61..45466e31b 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -1,12 +1,15 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_parse_qs, compat_urlparse, +) +from ..utils import ( determine_ext, unified_strdate, ) @@ -65,6 +68,10 @@ class WDRIE(InfoExtractor): 'upload_date': '20140717', }, }, + { + 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html', + 'playlist_mincount': 146, + } ] def _real_extract(self, url): @@ -79,6 +86,27 @@ class WDRIE(InfoExtractor): self.url_result(page_url + href, 'WDR') for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage) ] + + if entries: # Playlist page + return self.playlist_result(entries, page_id) + + # Overview page + entries = [] + for page_num in itertools.count(2): + hrefs = re.findall( + r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"', + webpage) + entries.extend( + self.url_result(page_url + href, 'WDR') + for href in hrefs) + next_url_m = re.search( + r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage) + if not next_url_m: + break + next_url = page_url + next_url_m.group(1) + webpage = self._download_webpage( + next_url, page_id, + note='Downloading playlist page %d' % page_num) return self.playlist_result(entries, page_id) flashvars = compat_parse_qs( @@ -141,7 +169,6 @@ class WDRMobileIE(InfoExtractor): 'title': mobj.group('title'), 'age_limit': int(mobj.group('age_limit')), 'url': url, - 'ext': determine_ext(url), 'user_agent': 'mobile', } @@ -171,8 +198,7 @@ class WDRMausIE(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) param_code = self._html_search_regex( @@ -223,5 +249,3 @@ class WDRMausIE(InfoExtractor): 'thumbnail': thumbnail, 'upload_date': upload_date, } - -# TODO test _1
\ No newline at end of file diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py new file mode 100644 index 000000000..396cf4e83 --- /dev/null +++ b/youtube_dl/extractor/webofstories.py @@ -0,0 +1,102 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class WebOfStoriesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)' + _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/' + _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/' + _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/' + _TESTS = [ + { + 'url': 'http://www.webofstories.com/play/hans.bethe/71', + 'md5': '373e4dd915f60cfe3116322642ddf364', + 'info_dict': { + 'id': '4536', + 'ext': 'mp4', + 'title': 'The temperature of the sun', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Hans Bethe talks about calculating the temperature of the sun', + 'duration': 238, + } + }, + { + 'url': 'http://www.webofstories.com/play/55908', + 'md5': '2985a698e1fe3211022422c4b5ed962c', + 'info_dict': { + 'id': '55908', + 'ext': 'mp4', + 'title': 'The story of Gemmata obscuriglobus', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus', + 'duration': 169, + } + }, + ] + + 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_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + story_filename = self._search_regex( + r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename') + speaker_id = self._search_regex( + r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID') + story_id = self._search_regex( + r'\.storyId\((\d+)\)', webpage, 'story ID') + speaker_type = self._search_regex( + r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type') + great_life = self._search_regex( + r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story') + is_great_life_series = great_life == 'true' + duration = int_or_none(self._search_regex( + r'\.duration\((\d+)\)', webpage, 'duration', fatal=False)) + + # URL building, see: http://www.webofstories.com/scripts/player.js + ms_prefix = '' + if speaker_type.lower() == 'ms': + ms_prefix = 'mini_sites/' + + if is_great_life_series: + mp4_url = '{0:}lives/{1:}/{2:}.mp4'.format( + self._VIDEO_DOMAIN, speaker_id, story_filename) + rtmp_ext = 'flv' + streamer = self._GREAT_LIFE_STREAMER + play_path = 'stories/{0:}/{1:}'.format( + speaker_id, story_filename) + else: + mp4_url = '{0:}{1:}{2:}/{3:}.mp4'.format( + self._VIDEO_DOMAIN, ms_prefix, speaker_id, story_filename) + rtmp_ext = 'mp4' + streamer = self._USER_STREAMER + play_path = 'mp4:{0:}{1:}/{2}.mp4'.format( + ms_prefix, speaker_id, story_filename) + + formats = [{ + 'format_id': 'mp4_sd', + 'url': mp4_url, + }, { + 'format_id': 'rtmp_sd', + 'page_url': url, + 'url': streamer, + 'ext': rtmp_ext, + 'play_path': play_path, + }] + + self._sort_formats(formats) + + return { + 'id': story_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + } 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 748443f81..13a079151 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,9 +1,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ExtractorError, compat_urllib_request +from ..compat import compat_urllib_request +from ..utils import ExtractorError class WistiaIE(InfoExtractor): @@ -22,8 +21,7 @@ class WistiaIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) request = compat_urllib_request.Request(self._API_URL.format(video_id)) request.add_header('Referer', url) # Some videos require this. 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..80c48c37d 100644 --- a/youtube_dl/extractor/xbef.py +++ b/youtube_dl/extractor/xbef.py @@ -1,9 +1,7 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -23,10 +21,9 @@ class XBefIE(InfoExtractor): } 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( r'<h1[^>]*>(.*?)</h1>', webpage, 'title') @@ -47,4 +44,3 @@ class XBefIE(InfoExtractor): 'thumbnail': thumbnail, 'age_limit': 18, } - diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py index a9aa72e73..9cf867807 100644 --- a/youtube_dl/extractor/xboxclips.py +++ b/youtube_dl/extractor/xboxclips.py @@ -1,46 +1,42 @@ # 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, + parse_filesize, + unified_strdate, ) class XboxClipsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' + _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, + 'title': 'Iabdulelah playing Titanfall', + 'filesize_approx': 26800000, 'upload_date': '20140807', 'duration': 56, } } 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'>Link: <a href="([^"]+)">', webpage, 'video URL') + r'>(?:Link|Download): <a href="([^"]+)">', webpage, 'video URL') title = self._html_search_regex( r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title') - timestamp = parse_iso8601(self._html_search_regex( + upload_date = unified_strdate(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) + filesize = parse_filesize(self._html_search_regex( + r'>Size: ([^<]+)<', webpage, 'file size', fatal=False)) 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( @@ -50,7 +46,7 @@ class XboxClipsIE(InfoExtractor): 'id': video_id, 'url': video_url, 'title': title, - 'timestamp': timestamp, + 'upload_date': upload_date, 'filesize_approx': filesize, 'duration': duration, 'view_count': view_count, diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 4e8fbde8d..4527567f8 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -14,7 +14,7 @@ from ..utils import ( class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" - _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' + _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' _TESTS = [ { 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', @@ -39,10 +39,14 @@ class XHamsterIE(InfoExtractor): 'duration': 200, 'age_limit': 18, } - } + }, + { + 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', + 'only_matching': True, + }, ] - 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: @@ -57,7 +61,8 @@ class XHamsterIE(InfoExtractor): video_id = mobj.group('id') seo = mobj.group('seo') - mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo) + proto = mobj.group('proto') + mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo) webpage = self._download_webpage(mrss_url, video_id) title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title') @@ -67,17 +72,17 @@ 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..79ed6c744 100644 --- a/youtube_dl/extractor/xnxx.py +++ b/youtube_dl/extractor/xnxx.py @@ -1,10 +1,8 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -23,21 +21,18 @@ class XNXXIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - # Get webpage content + video_id = self._match_id(url) 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 273d93d9e..e8490b028 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -1,18 +1,20 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, + compat_urllib_parse, +) +from ..utils import ( parse_duration, str_to_int, ) class XTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))' + _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))' _TEST = { 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', @@ -20,7 +22,7 @@ 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, @@ -28,41 +30,49 @@ class XTubeIE(InfoExtractor): } 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') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title') + video_title = self._html_search_regex( + r'<p class="title">([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False) + [r"var\s+contentOwnerId\s*=\s*'([^']+)", + r'By:\s*<a href="/community/profile\.php\?user=([^"]+)'], + webpage, 'uploader', fatal=False) video_description = self._html_search_regex( - r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False) + r'<p class="fieldsDesc">([^<]+)', + webpage, 'description', fatal=False) duration = parse_duration(self._html_search_regex( - r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False)) - view_count = self._html_search_regex( - r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = self._html_search_regex( - r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False) - if comment_count: - comment_count = str_to_int(comment_count) - - player_quality_option = json.loads(self._html_search_regex( - r'playerQualityOption = ({.+?});', webpage, 'player quality option')) - - QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080'] - formats = [ - { - 'url': furl, + r'<span class="bold">Runtime:</span> ([^<]+)</p>', + webpage, 'duration', fatal=False)) + view_count = str_to_int(self._html_search_regex( + r'<span class="bold">Views:</span> ([\d,\.]+)</p>', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<div id="commentBar">([\d,\.]+) Comments</div>', + webpage, 'comment count', fatal=False)) + + formats = [] + for format_id, video_url in re.findall( + r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage): + fmt = { + 'url': compat_urllib_parse.unquote(video_url), 'format_id': format_id, - 'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1, - } for format_id, furl in player_quality_option.items() - ] + } + m = re.search(r'^(?P<height>\d+)[pP]', format_id) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + + if not formats: + video_url = compat_urllib_parse.unquote(self._search_regex( + r'flashvars\.video_url\s*=\s*"([^"]+)"', + webpage, 'video URL')) + formats.append({'url': video_url}) + self._sort_formats(formats) return { @@ -85,6 +95,7 @@ class XTubeUserIE(InfoExtractor): 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers', 'info_dict': { 'id': 'greenshowers', + 'age_limit': 18, }, 'playlist_mincount': 155, } @@ -97,7 +108,7 @@ 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 @@ -114,6 +125,7 @@ class XTubeUserIE(InfoExtractor): return { '_type': 'playlist', 'id': username, + 'age_limit': 18, 'entries': [{ '_type': 'url', 'url': eurl, diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 7e0044824..2a45dc574 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -3,15 +3,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - ExtractorError, +) +from ..utils import ( clean_html, + ExtractorError, ) class XVideosIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)' _TEST = { 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl', 'md5': '4b46ae6ea5e6e9086e714d883313c0c9', @@ -24,37 +26,25 @@ class XVideosIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage) if mobj: raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) - # Extract video URL video_url = compat_urllib_parse.unquote( self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL')) - - # Extract title video_title = self._html_search_regex( r'<title>(.*?)\s+-\s+XVID', webpage, 'title') - - # Extract video thumbnail video_thumbnail = self._search_regex( r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False) return { 'id': video_id, 'url': video_url, - 'uploader': None, - 'upload_date': None, 'title': video_title, 'ext': 'flv', 'thumbnail': video_thumbnail, - 'description': None, 'age_limit': 18, } diff --git a/youtube_dl/extractor/xxxymovies.py b/youtube_dl/extractor/xxxymovies.py new file mode 100644 index 000000000..5c8f17eb2 --- /dev/null +++ b/youtube_dl/extractor/xxxymovies.py @@ -0,0 +1,81 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class XXXYMoviesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)' + _TEST = { + 'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/', + 'md5': '810b1bdbbffff89dd13bdb369fe7be4b', + 'info_dict': { + 'id': '138669', + 'display_id': 'ecstatic-orgasm-sofcore', + 'ext': 'mp4', + 'title': 'Ecstatic Orgasm Sofcore', + 'duration': 931, + 'categories': list, + 'view_count': int, + 'like_count': int, + 'dislike_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) + + video_url = self._search_regex( + r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') + + title = self._html_search_regex( + [r'<div class="block_header">\s*<h1>([^<]+)</h1>', + r'<title>(.*?)\s*-\s*XXXYMovies\.com</title>'], + webpage, 'title') + + thumbnail = self._search_regex( + r"preview_url\s*:\s*'([^']+)'", + webpage, 'thumbnail', fatal=False) + + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + duration = parse_duration(self._search_regex( + r'<span>Duration:</span>\s*(\d+:\d+)', + webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'<div class="video_views">\s*(\d+)', + webpage, 'view count', fatal=False)) + like_count = int_or_none(self._search_regex( + r'>\s*Likes? <b>\((\d+)\)', + webpage, 'like count', fatal=False)) + dislike_count = int_or_none(self._search_regex( + r'>\s*Dislike <b>\((\d+)\)</b>', + webpage, 'dislike count', fatal=False)) + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 3ab6017cd..f8e7041a0 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 @@ -5,17 +6,21 @@ import json import re from .common import InfoExtractor, SearchInfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, +) +from ..utils import ( clean_html, + unescapeHTML, + ExtractorError, int_or_none, ) class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?P<url>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 +30,7 @@ class YahooIE(InfoExtractor): 'ext': 'mp4', 'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith', + 'duration': 6863, }, }, { @@ -34,20 +40,11 @@ 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', - 'info_dict': { - 'id': '516ed8e2-2c4f-339f-a211-7a8b49d30845', - '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.''', - } - }, - { 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', 'md5': '60e8ac193d8fb71997caa8fce54c6460', 'info_dict': { @@ -55,15 +52,106 @@ class YahooIE(InfoExtractor): 'ext': 'mp4', 'title': "Yahoo Saves 'Community'", 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + 'duration': 170, } }, + { + 'url': 'https://tw.screen.yahoo.com/election-2014-askmayor/敢問市長-黃秀霜批賴清德-非常高傲-033009720.html', + 'md5': '3a09cf59349cfaddae1797acc3c087fc', + 'info_dict': { + 'id': 'cac903b3-fcf4-3c14-b632-643ab541712f', + 'ext': 'mp4', + 'title': '敢問市長／黃秀霜批賴清德「非常高傲」', + 'description': '直言台南沒捷運 交通居五都之末', + 'duration': 396, + } + }, + { + '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/hackers-sony-more-trouble-well-154609075.html', + 'md5': '226a895aae7e21b0129e2a2006fe9690', + 'info_dict': { + 'id': 'e624c4bc-3389-34de-9dfc-025f74943409', + 'ext': 'mp4', + 'title': '\'The Interview\' TV Spot: War', + 'description': 'The Interview', + 'duration': 30, + } + }, { + '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://www.yahoo.com/movies/v/true-story-trailer-173000497.html', + 'md5': '989396ae73d20c6f057746fb226aa215', + 'info_dict': { + 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', + 'ext': 'mp4', + 'title': '\'True Story\' Trailer', + 'description': 'True Story', + 'duration': 150, + }, + }, { + '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') + display_id = mobj.group('display_id') + page_id = mobj.group('id') url = mobj.group('url') - webpage = self._download_webpage(url, video_id) + 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, @@ -73,31 +161,40 @@ class YahooIE(InfoExtractor): r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', r'"first_videoid"\s*:\s*"([^"]+)"', + r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), ] - 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): - query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' - ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"' - ' AND protocol="http"' % long_id) + def _get_info(self, video_id, display_id, webpage): + region = self._search_regex( + r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', + webpage, 'region', fatal=False, default='US') data = compat_urllib_parse.urlencode({ - 'q': query, - 'env': 'prod', - 'format': 'json', + 'protocol': 'http', + 'region': region, }) + query_url = ( + 'https://video.media.yql.yahoo.com/v1/video/sapi/streams/' + '{id}?{data}'.format(id=video_id, data=data)) query_result = self._download_json( - 'http://video.query.yahoo.com/v1/public/yql?' + data, - video_id, 'Downloading video info') + query_url, 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']: @@ -124,36 +221,15 @@ class YahooIE(InfoExtractor): return { 'id': video_id, - 'title': meta['title'], + 'display_id': display_id, + 'title': unescapeHTML(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 @@ -166,7 +242,7 @@ 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/yesjapan.py b/youtube_dl/extractor/yesjapan.py new file mode 100644 index 000000000..112a6c030 --- /dev/null +++ b/youtube_dl/extractor/yesjapan.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + HEADRequest, + get_element_by_attribute, + parse_iso8601, +) + + +class YesJapanIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yesjapan\.com/video/(?P<slug>[A-Za-z0-9\-]*)_(?P<id>[A-Za-z0-9]+)\.html' + _TEST = { + 'url': 'http://www.yesjapan.com/video/japanese-in-5-20-wa-and-ga-particle-usages_726497834.html', + 'md5': 'f0be416314e5be21a12b499b330c21cf', + 'info_dict': { + 'id': '726497834', + 'title': 'Japanese in 5! #20 - WA And GA Particle Usages', + 'description': 'This should clear up some issues most students of Japanese encounter with WA and GA....', + 'ext': 'mp4', + 'timestamp': 1416391590, + 'upload_date': '20141119', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + video_url = self._og_search_video_url(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + timestamp = None + submit_info = get_element_by_attribute('class', 'pm-submit-data', webpage) + if submit_info: + timestamp = parse_iso8601(self._search_regex( + r'datetime="([^"]+)"', submit_info, 'upload date', fatal=False, default=None)) + + # attempt to resolve the final URL in order to get a proper extension + redirect_req = HEADRequest(video_url) + req = self._request_webpage( + redirect_req, video_id, note='Resolving final URL', errnote='Could not resolve final URL', fatal=False) + if req: + video_url = req.geturl() + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + }] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'timestamp': timestamp, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py index 24872861a..894678a23 100644 --- a/youtube_dl/extractor/ynet.py +++ b/youtube_dl/extractor/ynet.py @@ -5,7 +5,7 @@ import re import json from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..compat import compat_urllib_parse class YnetIE(InfoExtractor): @@ -13,7 +13,6 @@ class YnetIE(InfoExtractor): _TESTS = [ { 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html', - 'md5': '002b44ee2f33d50363a1c153bed524cf', 'info_dict': { 'id': 'L-11659-99244', 'ext': 'flv', @@ -22,7 +21,6 @@ class YnetIE(InfoExtractor): } }, { 'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html', - 'md5': '6455046ae1b48cf7e2b7cae285e53a16', 'info_dict': { 'id': 'L-8859-84418', 'ext': 'flv', @@ -33,9 +31,7 @@ class YnetIE(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) content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage)) @@ -51,4 +47,4 @@ class YnetIE(InfoExtractor): 'title': title, 'formats': self._extract_f4m_formats(f4m_url, video_id), 'thumbnail': self._og_search_thumbnail(webpage), - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index b86331e3c..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 07ed7cbd1..97b98bbe8 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals -import json import math import random import re @@ -36,21 +35,21 @@ class YoukuIE(InfoExtractor): 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): @@ -75,7 +74,7 @@ class YoukuIE(InfoExtractor): # -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) + expected=True) video_title = config['data'][0]['title'] seed = config['data'][0]['seed'] @@ -101,12 +100,12 @@ class YoukuIE(InfoExtractor): 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=[] + 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://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 7bfda45e7..107c9ac36 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -6,10 +6,11 @@ import re import sys from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, unescapeHTML, unified_strdate, @@ -45,11 +46,13 @@ 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: @@ -64,7 +67,7 @@ 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) @@ -73,7 +76,7 @@ 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: @@ -103,8 +106,8 @@ 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/youtube.py b/youtube_dl/extractor/youtube.py index 99198e380..c7611a3a0 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -7,47 +7,48 @@ 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_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, uppercase_escape, ) + class YoutubeBaseInfoExtractor(InfoExtractor): """Provide base functions for Youtube extractors""" _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' - _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' _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='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): """ @@ -76,30 +77,30 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # Log in login_form_strs = { - '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', + '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) @@ -149,7 +150,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): '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_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) @@ -175,27 +176,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor): 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')) - - self._download_webpage( - req, None, - note='Confirming age', errnote='Unable to confirm age') - 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): @@ -270,14 +256,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, - '138': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) '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}, - '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 128, 'preference': -50}, - '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 256, 'preference': -50}, + '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50}, + '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50}, + '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50}, # Dash webm '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, @@ -286,6 +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}, @@ -295,11 +285,21 @@ 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'}, + '308': {'ext': 'webm', 'height': 1440, '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'}, + '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, # Dash webm audio '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'}, } @@ -383,8 +383,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'info_dict': { 'id': 'IB3lcPjvWLA', 'ext': 'm4a', - 'title': 'Afrojack - The Spark ft. Spree Wilson', - 'description': 'md5:9717375db5a9a3992be4668bbf3bc0a8', + 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', + 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', 'uploader': 'AfrojackVEVO', 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', @@ -394,6 +394,91 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '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': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', + 'uploader': 'The Witcher', + 'uploader_id': 'WitcherGame', + 'upload_date': '20140605', + }, + }, + # Age-gate video with encrypted signature + { + 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', + 'info_dict': { + 'id': '6kLq3WMV1nU', + 'ext': 'mp4', + 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', + 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', + 'uploader': 'LloydVEVO', + 'uploader_id': 'LloydVEVO', + 'upload_date': '20110629', + }, + }, + # 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)', + }, + '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', + } + }, + # Non-square pixels + { + 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', + 'info_dict': { + 'id': '_b-2C3KPAM0', + 'ext': 'mp4', + 'stretched_ratio': 16 / 9., + 'upload_date': '20110310', + 'uploader_id': 'AllenMeow', + 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', + 'uploader': '孫艾倫', + 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', + }, + } ] def __init__(self, *args, **kwargs): @@ -422,7 +507,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 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]+)$', + r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -466,13 +551,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def gen_sig_code(idxs): def _genslice(start, end, step): starts = '' if start == 0 else str(start) - ends = (':%d' % (end+step)) if end + step >= 0 else ':' + 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 - # set as soon as step is set + # Quelch pyflakes warnings - start will be set when step is set + start = '(Never used)' for i, prev in zip(idxs[1:], idxs[:-1]): if step is not None: if i - prev == step: @@ -503,8 +588,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _parse_sig_js(self, jscode): funcname = self._search_regex( - r'signature=([$a-zA-Z]+)', jscode, - '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) @@ -543,24 +628,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _get_available_subtitles(self, video_id, webpage): try: - sub_list = self._download_webpage( + subs_doc = self._download_xml( '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('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] + for track in subs_doc.findall('track'): + lang = track.attrib['lang_code'] 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'), + 'name': track.attrib['name'].encode('utf-8'), }) url = 'https://www.youtube.com/api/timedtext?' + params sub_lang_list[lang] = url @@ -581,9 +665,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 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', @@ -593,10 +677,11 @@ 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' : + if original_lang_node is None: self._downloader.report_warning('Video doesn\'t have automatic captions') return {} original_lang = original_lang_node.attrib['lang_code'] + caption_kind = original_lang_node.attrib.get('kind', '') sub_lang_list = {} for lang_node in caption_list.findall('target'): @@ -606,7 +691,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'tlang': sub_lang, 'fmt': sub_format, 'ts': timestamp, - 'kind': 'asr', + 'kind': caption_kind, }) sub_lang_list[sub_lang] = caption_url + '&' + params return sub_lang_list @@ -626,10 +711,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 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, 'Downloading formats manifest') formats_urls = _get_urls(manifest) @@ -642,6 +728,47 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id 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')), + 'height': int_or_none(r.attrib.get('height')), + '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, {}).items()) + formats.append(f) + else: + existing_format.update(f) + return formats + def _real_extract(self, url): proto = ( 'http' if self._downloader.params.get('prefer_insecure', False) @@ -654,7 +781,7 @@ 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 @@ -665,34 +792,52 @@ 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 + url = proto + '://www.youtube.com/embed/%s' % video_id + embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') data = compat_urllib_parse.urlencode({ '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+)', embed_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( @@ -760,7 +905,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): m_cat_container = self._search_regex( r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', - video_webpage, 'categories', fatal=False) + video_webpage, 'categories', default=None) if m_cat_container: category = self._html_search_regex( r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', @@ -815,33 +960,7 @@ 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('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('%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', '')) - 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 = [] @@ -864,8 +983,8 @@ 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 = {} @@ -881,11 +1000,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 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) + jsplayer_url_json = self._search_regex( + r'"assets":.+?"js":\s*("[^"]+")', + embed_webpage if age_gate else 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*("[^"]+")', @@ -911,7 +1029,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): parts_sizes = self._signature_cache_id(encrypted_sig) self.to_screen('{%s} signature length %s, %s' % - (format_id, parts_sizes, player_desc)) + (format_id, parts_sizes, player_desc)) signature = self._decrypt_signature( encrypted_sig, video_id, player_url, age_gate) @@ -928,76 +1046,58 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 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='Downloading DASH manifest', - errnote='Could not download DASH manifest') - 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, - } - 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('Skipping DASH manifest: %s' % e, video_id) + # Hide the formats we found through non-DASH + dash_keys = set(df['format_id'] for df in dash_formats) + for f in formats: + if f['format_id'] in dash_keys: + f['format_id'] = 'nondash-%s' % f['format_id'] + f['preference'] = f.get('preference', 0) - 10000 + formats.extend(dash_formats) + + # Check for malformed aspect ratio + stretched_m = re.search( + r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', + video_webpage) + if stretched_m: + ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) + for f in formats: + if f.get('vcodec') != 'none': + f['stretched_ratio'] = ratio 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 = 'YouTube.com playlists' _VALID_URL = r"""(?x)(?: @@ -1011,7 +1111,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): ) ( (?: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\.]* ) .* @@ -1019,13 +1119,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): ((?:PL|LL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,}) )""" _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 = 'youtube:playlist' _TESTS = [{ 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', 'info_dict': { 'title': 'ytdl test PL', + 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', }, 'playlist_count': 3, }, { @@ -1045,7 +1145,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'note': 'issue #673', 'url': 'PLBB231211A4F62143', 'info_dict': { - 'title': 'Team Fortress 2 (Class-based LP)', + 'title': '[OLD]Team Fortress 2 (Class-based LP)', }, 'playlist_mincount': 26, }, { @@ -1075,6 +1175,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'info_dict': { 'title': 'JODA7', } + }, { + 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', + 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', + 'info_dict': { + 'title': 'Uploads from Interstellar Movie', + }, + 'playlist_mincout': 21, }] def _real_initialize(self): @@ -1125,9 +1232,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): if playlist_id.startswith('RD'): # Mixes require a custom extraction process return self._extract_mix(playlist_id) - if playlist_id.startswith('TL'): - 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) @@ -1159,6 +1263,10 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'Downloading page #%s' % page_num, transform_source=uppercase_escape) content_html = more['content_html'] + if not content_html.strip(): + # Some webpages show a "Load more" button but they don't + # have more videos + break more_widget_html = more['load_more_widget_html'] playlist_title = self._html_search_regex( @@ -1169,54 +1277,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): return self.playlist_result(url_results, playlist_id, playlist_title) -class YoutubeTopListIE(YoutubePlaylistIE): - 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}) - 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 = '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: - break - url_results = self._ids_to_results(ids) - return self.playlist_result(url_results, playlist_title=title) - - class YoutubeChannelIE(InfoExtractor): IE_DESC = 'YouTube.com channels' - _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([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' + _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' IE_NAME = 'youtube:channel' _TESTS = [{ 'note': 'paginated channel', @@ -1232,13 +1295,8 @@ 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('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) @@ -1252,30 +1310,39 @@ 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(): + more_widget_html = content_html = channel_page for pagenum in itertools.count(1): - url = self._MORE_PAGES_URL % (pagenum, channel_id) - page = self._download_json( - 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) - - if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: + ids_in_page = self.extract_videos_from_page(content_html) + for video_id in ids_in_page: + yield self.url_result( + video_id, 'Youtube', video_id=video_id) + + mobj = re.search( + r'data-uix-load-more-href="/?(?P<more>[^"]+)"', + more_widget_html) + if not mobj: break - self._downloader.to_screen('[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), channel_id, + 'Downloading page #%s' % (pagenum + 1), + transform_source=uppercase_escape) + content_html = more['content_html'] + more_widget_html = more['load_more_widget_html'] - 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 = '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_-]+)' + _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' @@ -1297,16 +1364,13 @@ class YoutubeUserIE(InfoExtractor): # 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('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 @@ -1341,7 +1405,7 @@ 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) @@ -1503,9 +1567,11 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): feed_entries = [] paging = 0 for i in itertools.count(1): - info = self._download_json(self._FEED_TEMPLATE % paging, - '%s feed' % self._FEED_NAME, - 'Downloading page %s' % i) + info = self._download_json( + self._FEED_TEMPLATE % paging, + '%s feed' % self._FEED_NAME, + 'Downloading page %s' % i, + transform_source=uppercase_escape) 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) @@ -1521,29 +1587,33 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = mobj.group('paging') return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) + class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): - IE_DESC = '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 = 'Youtube Recommended videos' + class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor): - IE_DESC = '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 = 'Youtube Watch Later' _PERSONAL_FEED = True + class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'Youtube watch history, "ythistory" keyword (requires authentication)' + 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 = 'Youtube Watch History' + class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): IE_NAME = 'youtube:favorites' - IE_DESC = 'YouTube.com favourite videos, "ytfav" keyword (requires authentication)' + 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 @@ -1618,3 +1688,20 @@ class YoutubeTruncatedURLIE(InfoExtractor): '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' ' or simply youtube-dl BaW_jenozKc .', expected=True) + + +class YoutubeTruncatedIDIE(InfoExtractor): + IE_NAME = 'youtube:truncated_id' + IE_DESC = False # Do not list + _VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' + + _TESTS = [{ + 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + raise ExtractorError( + 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), + expected=True) diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 3b1ac4e9f..98f15177b 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': 3, + } + _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)) |