diff options
Diffstat (limited to 'youtube_dl/extractor')
126 files changed, 5815 insertions, 954 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b8b341afd..1bf5c51b4 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -4,12 +4,13 @@ from .addanime import AddAnimeIE from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .anitube import AnitubeIE +from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aparat import AparatIE from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE -from .ard import ARDIE +from .ard import ARDIE, ARDMediathekIE from .arte import ( ArteTvIE, ArteTVPlus7IE, @@ -23,6 +24,7 @@ from .auengine import AUEngineIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE from .bbccouk import BBCCoUkIE +from .beeg import BeegIE from .bilibili import BiliBiliIE from .blinkx import BlinkxIE from .bliptv import BlipTVIE, BlipTVUserIE @@ -65,10 +67,14 @@ from .dailymotion import ( DailymotionUserIE, ) from .daum import DaumIE +from .dbtv import DBTVIE +from .deezer import DeezerPlaylistIE from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +from .drtuber import DrTuberIE from .drtv import DRTVIE +from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE @@ -77,12 +83,18 @@ from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE from .eitb import EitbIE +from .ellentv import ( + EllenTVIE, + EllenTVClipsIE, +) from .elpais import ElPaisIE -from .empflix import EmpflixIE +from .empflix import EMPFlixIE from .engadget import EngadgetIE +from .eporner import EpornerIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE +from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE @@ -110,8 +122,12 @@ from .freesound import FreesoundIE from .freespeech import FreespeechIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE -from .gameone import GameOneIE +from .gameone import ( + GameOneIE, + GameOnePlaylistIE, +) from .gamespot import GameSpotIE +from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE @@ -120,11 +136,15 @@ from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE +from .grooveshark import GroovesharkIE from .hark import HarkIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .hornbunny import HornBunnyIE +from .hostingbulk import HostingBulkIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE +from .howstuffworks import HowStuffWorksIE from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE @@ -142,8 +162,10 @@ from .ivi import ( IviIE, IviCompilationIE ) +from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE +from .jove import JoveIE from .jukebox import JukeboxIE from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE @@ -174,15 +196,20 @@ from .malemotion import MalemotionIE from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE +from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mitele import MiTeleIE from .mixcloud import MixcloudIE from .mlb import MLBIE from .mpora import MporaIE +from .moevideo import MoeVideoIE from .mofosex import MofosexIE +from .mojvideo import MojvideoIE from .mooshare import MooshareIE from .morningstar import MorningstarIE from .motherless import MotherlessIE from .motorsport import MotorsportIE +from .movieclips import MovieClipsIE from .moviezine import MoviezineIE from .movshare import MovShareIE from .mtv import ( @@ -191,6 +218,7 @@ from .mtv import ( MTVIggyIE, ) from .musicplayon import MusicPlayOnIE +from .musicvault import MusicVaultIE from .muzu import MuzuTVIE from .myspace import MySpaceIE from .myspass import MySpassIE @@ -211,6 +239,7 @@ from .niconico import NiconicoIE from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE +from .nosvideo import NosVideoIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE @@ -222,17 +251,24 @@ from .nrk import ( from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE -from .oe1 import OE1IE from .ooyala import OoyalaIE -from .orf import ORFIE +from .orf import ( + ORFTVthekIE, + ORFOE1IE, + ORFFM4IE, +) from .parliamentliveuk import ParliamentLiveUKIE +from .patreon import PatreonIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE from .pornhd import PornHdIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .pornoxo import PornoXOIE +from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE from .radiofrance import RadioFranceIE @@ -245,9 +281,10 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE -from .rtve import RTVEALaCartaIE +from .rtve import RTVEALaCartaIE, RTVELiveIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, @@ -258,10 +295,12 @@ from .rutube import ( from .rutv import RUTVIE from .sapo import SapoIE from .savefrom import SaveFromIE +from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .servingsys import ServingSysIE from .shared import SharedIE +from .sharesix import ShareSixIE from .sina import SinaIE from .slideshare import SlideshareIE from .slutload import SlutloadIE @@ -287,13 +326,15 @@ from .southpark import ( ) from .space import SpaceIE from .spankwire import SpankwireIE -from .spiegel import SpiegelIE +from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE +from .sportdeutschland import SportDeutschlandIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .sunporno import SunPornoIE from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE @@ -306,6 +347,7 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .telemb import TeleMBIE from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE @@ -313,6 +355,7 @@ from .theplatform import ThePlatformIE from .thisav import ThisAVIE from .tinypic import TinyPicIE from .tlc import TlcIE, TlcDeIE +from .tnaflix import TNAFlixIE from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE @@ -325,6 +368,7 @@ from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE from .tvplay import TVPlayIE +from .ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE @@ -337,6 +381,7 @@ from .veehd import VeeHDIE from .veoh import VeohIE from .vesti import VestiIE from .vevo import VevoIE +from .vgtv import VGTVIE from .vh1 import VH1IE from .viddler import ViddlerIE from .videobam import VideoBamIE @@ -346,6 +391,7 @@ from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE +from .vidme import VidmeIE from .vimeo import ( VimeoIE, VimeoChannelIE, @@ -363,11 +409,13 @@ from .vine import ( from .viki import VikiIE from .vk import VKIE from .vodlocker import VodlockerIE +from .vporn import VpornIE from .vube import VubeIE from .vuclip import VuClipIE from .vulture import VultureIE from .washingtonpost import WashingtonPostIE from .wat import WatIE +from .wayofthemaster import WayOfTheMasterIE from .wdr import ( WDRIE, WDRMobileIE, @@ -379,6 +427,7 @@ from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .wrzuta import WrzutaIE from .xbef import XBefIE +from .xboxclips import XboxClipsIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index 59d3bbba4..c983ef0f5 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -7,6 +7,15 @@ from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)' IE_NAME = 'AcademicEarth:Course' + _TEST = { + 'url': 'http://academicearth.org/playlists/laws-of-nature/', + 'info_dict': { + 'id': 'laws-of-nature', + 'title': 'Laws of Nature', + 'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.', + }, + 'playlist_count': 4, + } def _real_extract(self, url): m = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py new file mode 100644 index 000000000..bc64423a3 --- /dev/null +++ b/youtube_dl/extractor/anysex.py @@ -0,0 +1,61 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class AnySexIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://anysex.com/156592/', + 'md5': '023e9fbb7f7987f5529a394c34ad3d3d', + 'info_dict': { + 'id': '156592', + 'ext': 'mp4', + 'title': 'Busty and sexy blondie in her bikini strips for you', + 'description': 'md5:de9e418178e2931c10b62966474e1383', + 'categories': ['Erotic'], + 'duration': 270, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') + + title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + description = self._html_search_regex( + r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) + + categories = re.findall( + r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) + + duration = parse_duration(self._search_regex( + r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index a7bfe5a5c..47f8e4157 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -21,7 +21,7 @@ class AolIE(InfoExtractor): (?:$|\?) ''' - _TEST = { + _TESTS = [{ 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', 'md5': '18ef68f48740e86ae94b98da815eec42', 'info_dict': { @@ -30,7 +30,14 @@ class AolIE(InfoExtractor): 'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam', }, 'add_ie': ['FiveMin'], - } + }, { + 'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316', + 'info_dict': { + 'id': '152147', + 'title': 'Brace Yourself - Today\'s Weirdest News', + }, + 'playlist_mincount': 10, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 7e93bc4df..748608826 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,5 +1,7 @@ #coding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -13,13 +15,14 @@ class AparatIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' _TEST = { - u'url': u'http://www.aparat.com/v/wP8On', - u'file': u'wP8On.mp4', - u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1', - u'info_dict': { - u"title": u"تیم گلکسی 11 - زومیت", + 'url': 'http://www.aparat.com/v/wP8On', + 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1', + 'info_dict': { + 'id': 'wP8On', + 'ext': 'mp4', + 'title': 'تیم گلکسی 11 - زومیت', }, - #u'skip': u'Extremely unreliable', + # 'skip': 'Extremely unreliable', } def _real_extract(self, url): @@ -29,8 +32,8 @@ class AparatIE(InfoExtractor): # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id # but the URL in there does not work - embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' + - video_id + u'/vt/frame') + embed_url = ('http://www.aparat.com/video/video/embed/videohash/' + + video_id + '/vt/frame') webpage = self._download_webpage(embed_url, video_id) video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index dc8657b67..4359b88d1 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -6,6 +6,7 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, + int_or_none, ) @@ -110,8 +111,8 @@ class AppleTrailersIE(InfoExtractor): formats.append({ 'url': format_url, 'format': format['type'], - 'width': format['width'], - 'height': int(format['height']), + 'width': int_or_none(format['width']), + 'height': int_or_none(format['height']), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 30a85c8c1..ef94c7239 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,10 +8,16 @@ from ..utils import ( determine_ext, ExtractorError, qualities, + compat_urllib_parse_urlparse, + compat_urllib_parse, + int_or_none, + parse_duration, + unified_strdate, ) -class ARDIE(InfoExtractor): +class ARDMediathekIE(InfoExtractor): + IE_NAME = 'ARD:mediathek' _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ @@ -44,8 +50,14 @@ class ARDIE(InfoExtractor): else: video_id = m.group('video_id') + urlp = compat_urllib_parse_urlparse(url) + url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl() + webpage = self._download_webpage(url, video_id) + if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: + raise ExtractorError('Video %s is no longer available' % video_id, expected=True) + title = self._html_search_regex( [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', r'<meta name="dcterms.title" content="(.*?)"/>', @@ -120,3 +132,60 @@ class ARDIE(InfoExtractor): 'formats': formats, 'thumbnail': thumbnail, } + + +class ARDIE(InfoExtractor): + _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html' + _TEST = { + 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', + 'md5': 'd216c3a86493f9322545e045ddc3eb35', + 'info_dict': { + 'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge', + 'id': '100', + 'ext': 'mp4', + 'duration': 2600, + 'title': 'Die Story im Ersten: Mission unter falscher Flagge', + 'upload_date': '20140804', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + player_url = mobj.group('mainurl') + '~playerXml.xml' + doc = self._download_xml(player_url, display_id) + video_node = doc.find('./video') + upload_date = unified_strdate(video_node.find('./broadcastDate').text) + thumbnail = video_node.find('.//teaserImage//variant/url').text + + formats = [] + for a in video_node.findall('.//asset'): + f = { + 'format_id': a.attrib['type'], + 'width': int_or_none(a.find('./frameWidth').text), + 'height': int_or_none(a.find('./frameHeight').text), + 'vbr': int_or_none(a.find('./bitrateVideo').text), + 'abr': int_or_none(a.find('./bitrateAudio').text), + 'vcodec': a.find('./codecVideo').text, + 'tbr': int_or_none(a.find('./totalBitrate').text), + } + if a.find('./serverPrefix').text: + f['url'] = a.find('./serverPrefix').text + f['playpath'] = a.find('./fileName').text + else: + f['url'] = a.find('./fileName').text + formats.append(f) + self._sort_formats(formats) + + return { + 'id': mobj.group('id'), + 'formats': formats, + 'display_id': display_id, + 'title': video_node.find('./title').text, + 'duration': parse_duration(video_node.find('./duration').text), + 'upload_date': upload_date, + 'thumbnail': thumbnail, + } + diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 9591bad8a..957d35979 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -78,7 +78,8 @@ class ArteTVPlus7IE(InfoExtractor): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex( - r'arte_vp_url="(.*?)"', webpage, 'json vp url') + [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'], + webpage, 'json vp url') return self._extract_from_json_url(json_url, video_id, lang) def _extract_from_json_url(self, json_url, video_id, lang): @@ -109,15 +110,19 @@ class ArteTVPlus7IE(InfoExtractor): 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 + formats = list(formats) # in python3 filter returns an iterator if not formats: # Some videos are only available in the 'Originalversion' # they aren't tagged as being in French or German - if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats): - formats = all_formats - else: - raise ExtractorError(u'The formats list is empty') + # 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): @@ -173,16 +178,26 @@ class ArteTVPlus7IE(InfoExtractor): # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:creative' - _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)' + _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)' - _TEST = { + _TESTS = [{ 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', 'info_dict': { - 'id': '050489-002', + 'id': '72176', 'ext': 'mp4', - 'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design', + 'title': 'Folge 2 - Corporate Design', + 'upload_date': '20131004', }, - } + }, { + 'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion', + 'info_dict': { + 'id': '160676', + 'ext': 'mp4', + 'title': 'Monty Python live (mostly)', + 'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n', + 'upload_date': '20140805', + } + }] class ArteTVFutureIE(ArteTVPlus7IE): diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index ccd31c4c7..de5d4faf3 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -59,6 +59,13 @@ class BambuserChannelIE(InfoExtractor): _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)' # The maximum number we can get with each request _STEP = 50 + _TEST = { + 'url': 'http://bambuser.com/channel/pixelversity', + 'info_dict': { + 'title': 'pixelversity', + }, + 'playlist_mincount': 60, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -73,10 +80,10 @@ class BambuserChannelIE(InfoExtractor): req = compat_urllib_request.Request(req_url) # Without setting this header, we wouldn't get any result req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) - info_json = self._download_webpage(req, user, - 'Downloading page %d' % i) - results = json.loads(info_json)['result'] - if len(results) == 0: + data = self._download_json( + req, user, 'Downloading page %d' % i) + results = data['result'] + if not results: break last_id = results[-1]['vid'] urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index dcbbdef43..c569aa4d2 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -96,7 +96,7 @@ class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' - _TEST = { + _TESTS = [{ 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', 'playlist': [ { @@ -118,7 +118,13 @@ class BandcampAlbumIE(InfoExtractor): 'playlistend': 2 }, 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' - } + }, { + 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave', + 'info_dict': { + 'title': 'Hierophany of the Open Grave', + }, + 'playlist_mincount': 9, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py new file mode 100644 index 000000000..314e37f8b --- /dev/null +++ b/youtube_dl/extractor/beeg.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class BeegIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://beeg.com/5416503', + 'md5': '634526ae978711f6b748fe0dd6c11f57', + 'info_dict': { + 'id': '5416503', + 'ext': 'mp4', + 'title': 'Sultry Striptease', + 'description': 'md5:6db3c6177972822aaba18652ff59c773', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + quality_arr = self._search_regex( + r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats') + + formats = [{ + 'url': fmt[1], + 'format_id': fmt[0], + 'height': int(fmt[0][:-1]), + } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)] + + self._sort_formats(formats) + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title') + + description = self._html_search_regex( + r'<meta name="description" content="([^"]*)"', + webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'\'previewer.url\'\s*:\s*"([^"]*)"', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_regex( + r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index acfc4ad73..57d17bea3 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -15,7 +15,7 @@ from ..utils import ( class BlipTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))' + _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))' _TESTS = [ { @@ -49,6 +49,21 @@ class BlipTVIE(SubtitlesInfoExtractor): 'uploader_id': '792887', 'duration': 279, } + }, + { + # https://bugzilla.redhat.com/show_bug.cgi?id=967465 + 'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI', + 'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6', + 'info_dict': { + 'id': '6573122', + 'ext': 'mov', + 'upload_date': '20130520', + 'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.', + 'title': 'Red vs. Blue Season 11 Trailer', + 'timestamp': 1369029609, + 'uploader': 'redvsblue', + 'uploader_id': '792887', + } } ] @@ -150,7 +165,7 @@ class BlipTVIE(SubtitlesInfoExtractor): class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' _PAGE_SIZE = 12 IE_NAME = 'blip.tv:user' diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 25fb79e14..c51a97ce4 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -10,7 +10,7 @@ class BloombergIE(InfoExtractor): _TEST = { 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - 'md5': '7bf08858ff7c203c870e8a6190e221e5', + # The md5 checksum changes 'info_dict': { 'id': 'qurhIVlJSB6hzkVi229d8g', 'ext': 'flv', @@ -31,8 +31,7 @@ class BloombergIE(InfoExtractor): return { 'id': name.split('-')[-1], 'title': title, - 'url': f4m_url, - 'ext': 'flv', + 'formats': self._extract_f4m_formats(f4m_url, name), 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 419951b62..294670386 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -154,12 +154,14 @@ class BrightcoveIE(InfoExtractor): def _extract_brightcove_urls(cls, webpage): """Return a list of all Brightcove URLs from the webpage """ - url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage) + url_m = re.search( + r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"', + webpage) if url_m: url = unescapeHTML(url_m.group(1)) # Some sites don't add it, we can't download with this url, for example: # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/ - if 'playerKey' in url: + if 'playerKey' in url or 'videoId' in url: return [url] matches = re.findall( @@ -188,9 +190,13 @@ class BrightcoveIE(InfoExtractor): referer = smuggled_data.get('Referer', url) return self._get_video_info( videoPlayer[0], query_str, query, referer=referer) - else: + elif 'playerKey' in query: player_key = query['playerKey'] return self._get_playlist_info(player_key[0]) + else: + raise ExtractorError( + 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', + expected=True) def _get_video_info(self, video_id, query_str, query, referer=None): request_url = self._FEDERATED_URL_TEMPLATE % query_str @@ -202,6 +208,13 @@ class BrightcoveIE(InfoExtractor): req.add_header('Referer', referer) webpage = self._download_webpage(req, video_id) + error_msg = self._html_search_regex( + r"<h1>We're sorry.</h1>\s*<p>(.*?)</p>", webpage, + 'error message', default=None) + if error_msg is not None: + raise ExtractorError( + 'brightcove said: %s' % error_msg, expected=True) + self.report_extraction(video_id) info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json') info = json.loads(info)['data'] diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 822f9a7be..db48dc24f 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -25,7 +25,7 @@ class CBSIE(InfoExtractor): }, { 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/', 'info_dict': { - 'id': 'P9gjWjelt6iP', + 'id': 'WWF_5KqY3PK1', 'ext': 'flv', 'title': 'Live on Letterman - St. Vincent', 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.', diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 58846e8e7..65c12136a 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,11 +1,13 @@ from __future__ import unicode_literals +import json import re from .common import InfoExtractor +from ..utils import int_or_none -translation_table = { +_translation_table = { 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', 'y': 'l', 'z': 'i', @@ -13,6 +15,10 @@ translation_table = { } +def _decode(s): + return ''.join(_translation_table.get(c, c) for c in s) + + class CliphunterIE(InfoExtractor): IE_NAME = 'cliphunter' @@ -22,10 +28,14 @@ class CliphunterIE(InfoExtractor): ''' _TEST = { 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', - 'file': '1012420.flv', - 'md5': '15e7740f30428abf70f4223478dc1225', + 'md5': 'a2ba71eebf523859fe527a61018f723e', 'info_dict': { + 'id': '1012420', + 'ext': 'mp4', 'title': 'Fun Jynx Maze solo', + 'thumbnail': 're:^https?://.*\.jpg$', + 'age_limit': 18, + 'duration': 1317, } } @@ -35,22 +45,55 @@ class CliphunterIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + video_title = self._search_regex( + r'mediaTitle = "([^"]+)"', webpage, 'title') + pl_fiji = self._search_regex( r'pl_fiji = \'([^\']+)\'', webpage, 'video data') pl_c_qual = self._search_regex( r'pl_c_qual = "(.)"', webpage, 'video quality') - video_title = self._search_regex( - r'mediaTitle = "([^"]+)"', webpage, 'title') - - video_url = ''.join(translation_table.get(c, c) for c in pl_fiji) - + video_url = _decode(pl_fiji) formats = [{ 'url': video_url, - 'format_id': pl_c_qual, + 'format_id': 'default-%s' % pl_c_qual, }] + qualities_json = self._search_regex( + r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info') + qualities_data = json.loads(qualities_json) + + for i, t in enumerate( + re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)): + quality_id, crypted_url = t + video_url = _decode(crypted_url) + f = { + 'format_id': quality_id, + 'url': video_url, + 'quality': i, + } + if quality_id in qualities_data: + qd = qualities_data[quality_id] + m = re.match( + r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b> + \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd) + if m: + f['width'] = int(m.group('width')) + f['height'] = int(m.group('height')) + f['tbr'] = int(m.group('tbr')) + formats.append(f) + self._sort_formats(formats) + + thumbnail = self._search_regex( + r"var\s+mov_thumb\s*=\s*'([^']+)';", + webpage, 'thumbnail', fatal=False) + 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/comedycentral.py b/youtube_dl/extractor/comedycentral.py index c81ce5a96..035046120 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -43,14 +43,14 @@ class ComedyCentralShowsIE(InfoExtractor): (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| (?P<clip> - (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+)) + (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+)) |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) )| (?P<interview> extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) (?:[?#].*|$)''' - _TEST = { + _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', 'info_dict': { @@ -61,7 +61,34 @@ class ComedyCentralShowsIE(InfoExtractor): 'uploader': 'thedailyshow', 'title': 'thedailyshow kristen-stewart part 1', } - } + }, { + 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel', + 'only_matching': True, + }] _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] @@ -185,6 +212,9 @@ 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 52c00186e..929dd1e97 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import base64 import hashlib import json @@ -18,6 +20,7 @@ from ..utils import ( clean_html, compiled_regex_type, ExtractorError, + int_or_none, RegexNotFoundError, sanitize_filename, unescapeHTML, @@ -83,6 +86,12 @@ class InfoExtractor(object): format, irrespective of the file format. -1 for default (order by other properties), -2 or smaller for less than default. + * http_referer HTTP Referer header value to set. + * http_method HTTP method to use for the download. + * http_headers A dictionary of additional HTTP headers + to add to the request. + * http_post_data Additional data to send with a POST + request. url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) @@ -107,7 +116,7 @@ class InfoExtractor(object): upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. - location: Physical location of the video. + location: Physical location where the video was filmed. subtitles: The subtitle file contents as a dictionary in the format {language: subtitles}. duration: Length of the video in seconds, as an integer. @@ -195,17 +204,17 @@ class InfoExtractor(object): self.report_download_webpage(video_id) elif note is not False: if video_id is None: - self.to_screen(u'%s' % (note,)) + self.to_screen('%s' % (note,)) else: - self.to_screen(u'%s: %s' % (video_id, note)) + self.to_screen('%s: %s' % (video_id, note)) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if errnote is False: return False if errnote is None: - errnote = u'Unable to download webpage' - errmsg = u'%s: %s' % (errnote, compat_str(err)) + errnote = 'Unable to download webpage' + errmsg = '%s: %s' % (errnote, compat_str(err)) if fatal: raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) else: @@ -242,7 +251,7 @@ class InfoExtractor(object): url = url_or_request.get_full_url() except AttributeError: url = url_or_request - self.to_screen(u'Dumping request to ' + url) + self.to_screen('Dumping request to ' + url) dump = base64.b64encode(webpage_bytes).decode('ascii') self._downloader.to_screen(dump) if self._downloader.params.get('write_pages', False): @@ -252,11 +261,11 @@ class InfoExtractor(object): url = url_or_request basen = '%s_%s' % (video_id, url) if len(basen) > 240: - h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest() + h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest() basen = basen[:240 - len(h)] + h raw_filename = basen + '.dump' filename = sanitize_filename(raw_filename, restricted=True) - self.to_screen(u'Saving request to ' + filename) + self.to_screen('Saving request to ' + filename) with open(filename, 'wb') as outf: outf.write(webpage_bytes) @@ -265,14 +274,14 @@ class InfoExtractor(object): except LookupError: content = webpage_bytes.decode('utf-8', 'replace') - if (u'<title>Access to this site is blocked</title>' in content and - u'Websense' in content[:512]): - msg = u'Access to this webpage has been blocked by Websense filtering software in your network.' + if ('<title>Access to this site is blocked</title>' in content and + 'Websense' in content[:512]): + msg = 'Access to this webpage has been blocked by Websense filtering software in your network.' blocked_iframe = self._html_search_regex( r'<iframe src="([^"]+)"', content, - u'Websense information URL', default=None) + 'Websense information URL', default=None) if blocked_iframe: - msg += u' Visit %s for more details' % blocked_iframe + msg += ' Visit %s for more details' % blocked_iframe raise ExtractorError(msg, expected=True) return (content, urlh) @@ -287,7 +296,7 @@ class InfoExtractor(object): return content def _download_xml(self, url_or_request, video_id, - note=u'Downloading XML', errnote=u'Unable to download XML', + note='Downloading XML', errnote='Unable to download XML', transform_source=None, fatal=True): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( @@ -299,8 +308,8 @@ class InfoExtractor(object): return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) def _download_json(self, url_or_request, video_id, - note=u'Downloading JSON metadata', - errnote=u'Unable to download JSON metadata', + note='Downloading JSON metadata', + errnote='Unable to download JSON metadata', transform_source=None, fatal=True): json_string = self._download_webpage( @@ -315,29 +324,29 @@ class InfoExtractor(object): raise ExtractorError('Failed to download JSON', cause=ve) def report_warning(self, msg, video_id=None): - idstr = u'' if video_id is None else u'%s: ' % video_id + idstr = '' if video_id is None else '%s: ' % video_id self._downloader.report_warning( - u'[%s] %s%s' % (self.IE_NAME, idstr, msg)) + '[%s] %s%s' % (self.IE_NAME, idstr, msg)) def to_screen(self, msg): """Print msg to screen, prefixing it with '[ie_name]'""" - self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) + self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg)) def report_extraction(self, id_or_name): """Report information extraction.""" - self.to_screen(u'%s: Extracting information' % id_or_name) + self.to_screen('%s: Extracting information' % id_or_name) def report_download_webpage(self, video_id): """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) + self.to_screen('%s: Downloading webpage' % video_id) def report_age_confirmation(self): """Report attempt to confirm age.""" - self.to_screen(u'Confirming age') + self.to_screen('Confirming age') def report_login(self): """Report attempt to log in.""" - self.to_screen(u'Logging in') + self.to_screen('Logging in') #Methods for following #608 @staticmethod @@ -377,7 +386,7 @@ class InfoExtractor(object): break if os.name != 'nt' and sys.stderr.isatty(): - _name = u'\033[0;34m%s\033[0m' % name + _name = '\033[0;34m%s\033[0m' % name else: _name = name @@ -387,10 +396,10 @@ class InfoExtractor(object): elif default is not _NO_DEFAULT: return default elif fatal: - raise RegexNotFoundError(u'Unable to extract %s' % _name) + raise RegexNotFoundError('Unable to extract %s' % _name) else: - self._downloader.report_warning(u'unable to extract %s; ' - u'please report this issue on http://yt-dl.org/bug' % _name) + self._downloader.report_warning('unable to extract %s; ' + 'please report this issue on http://yt-dl.org/bug' % _name) return None def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0): @@ -429,10 +438,26 @@ class InfoExtractor(object): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) + self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) return (username, password) + def _get_tfa_info(self): + """ + Get the two-factor authentication info + TODO - asking the user will be required for sms/phone verify + currently just uses the command line option + If there's no info available, return None + """ + if self._downloader is None: + return None + downloader_params = self._downloader.params + + if downloader_params.get('twofactor', None) is not None: + return downloader_params['twofactor'] + + return None + # Helper functions for extracting OpenGraph info @staticmethod def _og_regexes(prop): @@ -453,7 +478,7 @@ class InfoExtractor(object): return unescapeHTML(escaped) def _og_search_thumbnail(self, html, **kargs): - return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs) + return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs) def _og_search_description(self, html, **kargs): return self._og_search_property('description', html, fatal=False, **kargs) @@ -462,8 +487,9 @@ class InfoExtractor(object): return self._og_search_property('title', html, **kargs) def _og_search_video_url(self, html, name='video url', secure=True, **kargs): - regexes = self._og_regexes('video') - if secure: regexes = self._og_regexes('video:secure_url') + regexes + regexes = self._og_regexes('video') + self._og_regexes('video:url') + if secure: + regexes = self._og_regexes('video:secure_url') + regexes return self._html_search_regex(regexes, html, name, **kargs) def _og_search_url(self, html, **kargs): @@ -511,7 +537,7 @@ class InfoExtractor(object): def _sort_formats(self, formats): if not formats: - raise ExtractorError(u'No video formats found') + raise ExtractorError('No video formats found') def _formats_key(f): # TODO remove the following workaround @@ -531,9 +557,9 @@ class InfoExtractor(object): if f.get('vcodec') == 'none': # audio only if self._downloader.params.get('prefer_free_formats'): - ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus'] + ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus'] else: - ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a'] + ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a'] ext_preference = 0 try: audio_ext_preference = ORDER.index(f['ext']) @@ -541,9 +567,9 @@ class InfoExtractor(object): audio_ext_preference = -1 else: if self._downloader.params.get('prefer_free_formats'): - ORDER = [u'flv', u'mp4', u'webm'] + ORDER = ['flv', 'mp4', 'webm'] else: - ORDER = [u'webm', u'flv', u'mp4'] + ORDER = ['webm', 'flv', 'mp4'] try: ext_preference = ORDER.index(f['ext']) except ValueError: @@ -585,11 +611,88 @@ class InfoExtractor(object): def _sleep(self, timeout, video_id, msg_template=None): if msg_template is None: - msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds' + msg_template = '%(video_id)s: Waiting for %(timeout)s seconds' msg = msg_template % {'video_id': video_id, 'timeout': timeout} self.to_screen(msg) time.sleep(timeout) + def _extract_f4m_formats(self, manifest_url, video_id): + manifest = self._download_xml( + manifest_url, video_id, 'Downloading f4m manifest', + 'Unable to download f4m manifest') + + formats = [] + media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') + for i, media_el in enumerate(media_nodes): + tbr = int_or_none(media_el.attrib.get('bitrate')) + format_id = 'f4m-%d' % (i if tbr is None else tbr) + formats.append({ + 'format_id': format_id, + 'url': manifest_url, + 'ext': 'flv', + 'tbr': tbr, + 'width': int_or_none(media_el.attrib.get('width')), + 'height': int_or_none(media_el.attrib.get('height')), + }) + self._sort_formats(formats) + + return formats + + def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None): + formats = [{ + 'format_id': 'm3u8-meta', + 'url': m3u8_url, + 'ext': ext, + 'protocol': 'm3u8', + 'preference': -1, + 'resolution': 'multiple', + 'format_note': 'Quality selection URL', + }] + + m3u8_doc = self._download_webpage(m3u8_url, video_id) + last_info = None + kv_rex = re.compile( + r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)') + for line in m3u8_doc.splitlines(): + if line.startswith('#EXT-X-STREAM-INF:'): + last_info = {} + for m in kv_rex.finditer(line): + v = m.group('val') + if v.startswith('"'): + v = v[1:-1] + last_info[m.group('key')] = v + elif line.startswith('#') or not line.strip(): + continue + else: + if last_info is None: + formats.append({'url': line}) + continue + tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000) + + f = { + 'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)), + 'url': line.strip(), + 'tbr': tbr, + 'ext': ext, + } + codecs = last_info.get('CODECS') + if codecs: + # TODO: looks like video codec is not always necessarily goes first + va_codecs = codecs.split(',') + if va_codecs[0]: + f['vcodec'] = va_codecs[0].partition('.')[0] + if len(va_codecs) > 1 and va_codecs[1]: + f['acodec'] = va_codecs[1].partition('.')[0] + resolution = last_info.get('RESOLUTION') + if resolution: + width_str, height_str = resolution.split('x') + f['width'] = int(width_str) + f['height'] = int(height_str) + formats.append(f) + last_info = {} + self._sort_formats(formats) + return formats + class SearchInfoExtractor(InfoExtractor): """ @@ -609,7 +712,7 @@ class SearchInfoExtractor(InfoExtractor): def _real_extract(self, query): mobj = re.match(self._make_valid_url(), query) if mobj is None: - raise ExtractorError(u'Invalid search query "%s"' % query) + raise ExtractorError('Invalid search query "%s"' % query) prefix = mobj.group('prefix') query = mobj.group('query') @@ -620,9 +723,9 @@ class SearchInfoExtractor(InfoExtractor): else: n = int(prefix) if n <= 0: - raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query)) + raise ExtractorError('invalid download number %s for query "%s"' % (n, query)) elif n > self._MAX_RESULTS: - self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) + self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) n = self._MAX_RESULTS return self._get_n_results(query, n) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 026a9177e..4903764f7 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,6 +5,7 @@ import re import json import base64 import zlib +import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor @@ -17,6 +18,7 @@ from ..utils import ( intlist_to_bytes, unified_strdate, clean_html, + urlencode_postdata, ) from ..aes import ( aes_cbc_decrypt, @@ -51,6 +53,26 @@ class CrunchyrollIE(InfoExtractor): '1080': ('80', '108'), } + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + login_url = 'https://www.crunchyroll.com/?a=formhandler' + data = urlencode_postdata({ + 'formname': 'RpcApiUser_Login', + 'name': username, + 'password': password, + }) + login_request = compat_urllib_request.Request(login_url, data) + login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(login_request, None, False, 'Wrong login info') + + + def _real_initialize(self): + self._login() + + def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(data) iv = bytes_to_intlist(iv) @@ -97,6 +119,75 @@ class CrunchyrollIE(InfoExtractor): output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text) return output + def _convert_subtitles_to_ass(self, subtitles): + output = '' + + def ass_bool(strvalue): + assvalue = '0' + if strvalue == '1': + 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' + output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"] + output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"] + output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"] + output += """ScaledBorderAndShadow: yes + +[V4+ Styles] +Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding +""" + for style in sub_root.findall('./styles/style'): + output += 'Style: ' + style.attrib["name"] + output += ',' + style.attrib["font_name"] + output += ',' + style.attrib["font_size"] + output += ',' + style.attrib["primary_colour"] + output += ',' + style.attrib["secondary_colour"] + output += ',' + style.attrib["outline_colour"] + output += ',' + style.attrib["back_colour"] + output += ',' + ass_bool(style.attrib["bold"]) + output += ',' + ass_bool(style.attrib["italic"]) + output += ',' + ass_bool(style.attrib["underline"]) + output += ',' + ass_bool(style.attrib["strikeout"]) + output += ',' + style.attrib["scale_x"] + output += ',' + style.attrib["scale_y"] + output += ',' + style.attrib["spacing"] + output += ',' + style.attrib["angle"] + output += ',' + style.attrib["border_style"] + output += ',' + style.attrib["outline"] + output += ',' + style.attrib["shadow"] + output += ',' + style.attrib["alignment"] + output += ',' + style.attrib["margin_l"] + output += ',' + style.attrib["margin_r"] + output += ',' + style.attrib["margin_v"] + output += ',' + style.attrib["encoding"] + output += '\n' + + output += """ +[Events] +Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text +""" + for event in sub_root.findall('./events/event'): + output += 'Dialogue: 0' + output += ',' + event.attrib["start"] + output += ',' + event.attrib["end"] + output += ',' + event.attrib["style"] + output += ',' + event.attrib["name"] + output += ',' + event.attrib["margin_l"] + output += ',' + event.attrib["margin_r"] + output += ',' + event.attrib["margin_v"] + output += ',' + event.attrib["effect"] + output += ',' + event.attrib["text"] + output += '\n' + + return output + def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -158,6 +249,7 @@ class CrunchyrollIE(InfoExtractor): }) 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) @@ -174,7 +266,10 @@ class CrunchyrollIE(InfoExtractor): lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue - subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + if sub_format == 'ass': + subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle) + else: + subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) return { 'id': video_id, diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index b6552c542..541106684 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -34,6 +34,13 @@ class CSpanIE(InfoExtractor): 'title': 'International Health Care Models', 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', } + }, { + 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', + 'info_dict': { + 'id': '342759', + 'title': 'General Motors Ignition Switch Recall', + }, + 'playlist_duration_sum': 14855, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 5d0bfe454..66a8f16d9 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,3 +1,6 @@ +#coding: utf-8 +from __future__ import unicode_literals + import re import json import itertools @@ -28,51 +31,53 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)' - IE_NAME = u'dailymotion' + IE_NAME = 'dailymotion' _FORMATS = [ - (u'stream_h264_ld_url', u'ld'), - (u'stream_h264_url', u'standard'), - (u'stream_h264_hq_url', u'hq'), - (u'stream_h264_hd_url', u'hd'), - (u'stream_h264_hd1080_url', u'hd180'), + ('stream_h264_ld_url', 'ld'), + ('stream_h264_url', 'standard'), + ('stream_h264_hq_url', 'hq'), + ('stream_h264_hd_url', 'hd'), + ('stream_h264_hd1080_url', 'hd180'), ] _TESTS = [ { - u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', - u'file': u'x33vw9.mp4', - u'md5': u'392c4b85a60a90dc4792da41ce3144eb', - u'info_dict': { - u"uploader": u"Amphora Alex and Van .", - u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\"" + 'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', + 'md5': '392c4b85a60a90dc4792da41ce3144eb', + 'info_dict': { + 'id': 'x33vw9', + 'ext': 'mp4', + 'uploader': 'Amphora Alex and Van .', + 'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"', } }, # Vevo video { - u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi', - u'file': u'USUV71301934.mp4', - u'info_dict': { - u'title': u'Roar (Official)', - u'uploader': u'Katy Perry', - u'upload_date': u'20130905', + 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi', + 'info_dict': { + 'title': 'Roar (Official)', + 'id': 'USUV71301934', + 'ext': 'mp4', + 'uploader': 'Katy Perry', + 'upload_date': '20130905', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'VEVO is only available in some countries', + 'skip': 'VEVO is only available in some countries', }, # age-restricted video { - u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband', - u'file': u'xyh2zz.mp4', - u'md5': u'0d667a7b9cebecc3c89ee93099c4159d', - u'info_dict': { - u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]', - u'uploader': 'HotWaves1012', - u'age_limit': 18, + 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband', + 'md5': '0d667a7b9cebecc3c89ee93099c4159d', + 'info_dict': { + 'id': 'xyh2zz', + 'ext': 'mp4', + 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]', + 'uploader': 'HotWaves1012', + 'age_limit': 18, } - } ] @@ -97,8 +102,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): webpage) if m_vevo is not None: vevo_id = m_vevo.group('id') - self.to_screen(u'Vevo video detected: %s' % vevo_id) - return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo') + self.to_screen('Vevo video detected: %s' % vevo_id) + return self.url_result('vevo:%s' % vevo_id, ie='Vevo') age_limit = self._rta_search(webpage) @@ -109,7 +114,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id embed_page = self._download_webpage(embed_url, video_id, - u'Downloading embed page') + 'Downloading embed page') info = self._search_regex(r'var info = ({.*?}),$', embed_page, 'video info', flags=re.MULTILINE) info = json.loads(info) @@ -134,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'height': height, }) if not formats: - raise ExtractorError(u'Unable to extract video URL') + raise ExtractorError('Unable to extract video URL') # subtitles video_subtitles = self.extract_subtitles(video_id, webpage) @@ -143,7 +148,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): return view_count = self._search_regex( - r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False) + r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, 'view count', fatal=False) if view_count is not None: view_count = str_to_int(view_count) @@ -165,28 +170,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) return {} info = json.loads(sub_list) if (info['total'] > 0): sub_lang_list = dict((l['language'], l['url']) for l in info['list']) return sub_lang_list - self._downloader.report_warning(u'video doesn\'t have subtitles') + self._downloader.report_warning('video doesn\'t have subtitles') return {} class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): - IE_NAME = u'dailymotion:playlist' + IE_NAME = 'dailymotion:playlist' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' + _TESTS = [{ + 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', + 'info_dict': { + 'title': 'SPORT', + }, + 'playlist_mincount': 20, + }] def _extract_entries(self, id): video_ids = [] for pagenum in itertools.count(1): request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum)) webpage = self._download_webpage(request, - id, u'Downloading page %s' % pagenum) + id, 'Downloading page %s' % pagenum) video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage)) @@ -209,9 +221,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): - IE_NAME = u'dailymotion:user' + IE_NAME = 'dailymotion:user' _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' + _TESTS = [{ + 'url': 'https://www.dailymotion.com/user/nqtv', + 'info_dict': { + 'id': 'nqtv', + 'title': 'Rémi Gaillard', + }, + 'playlist_mincount': 100, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -219,7 +239,7 @@ class DailymotionUserIE(DailymotionPlaylistIE): webpage = self._download_webpage(url, user) full_user = unescapeHTML(self._html_search_regex( r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user), - webpage, u'user', flags=re.DOTALL)) + webpage, 'user')) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py new file mode 100644 index 000000000..1d3e2ff08 --- /dev/null +++ b/youtube_dl/extractor/dbtv.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, + clean_html, +) + + +class DBTVIE(InfoExtractor): + _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)' + _TEST = { + 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc', + 'info_dict': { + 'id': '33100', + 'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'ext': 'mp4', + 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', + 'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1404039863.438, + 'upload_date': '20140629', + 'duration': 69.544, + 'view_count': int, + 'categories': list, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + data = self._download_json( + 'http://api.dbtv.no/discovery/%s' % video_id, display_id) + + video = data['playlist'][0] + + formats = [{ + 'url': f['URL'], + 'vcodec': f.get('container'), + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'vbr': float_or_none(f.get('rate'), 1000), + 'filesize': int_or_none(f.get('size')), + } for f in video['renditions'] if 'URL' in f] + + if not formats: + for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]: + if url_key in video: + formats.append({ + 'url': video[url_key], + 'format_id': format_id, + }) + + self._sort_formats(formats) + + return { + 'id': video['id'], + 'display_id': display_id, + 'title': video['title'], + 'description': clean_html(video['desc']), + 'thumbnail': video.get('splash') or video.get('thumb'), + 'timestamp': float_or_none(video.get('publishedAt'), 1000), + 'duration': float_or_none(video.get('length'), 1000), + 'view_count': int_or_none(video.get('views')), + 'categories': video.get('tags'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/deezer.py b/youtube_dl/extractor/deezer.py new file mode 100644 index 000000000..62c181529 --- /dev/null +++ b/youtube_dl/extractor/deezer.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + orderedSet, +) + + +class DeezerPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.deezer.com/playlist/176747451', + 'info_dict': { + 'id': '176747451', + 'title': 'Best!', + 'uploader': 'Anonymous', + 'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$', + }, + 'playlist_count': 30, + } + + def _real_extract(self, url): + if 'test' not in self._downloader.params: + self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!') + + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + data_json = self._search_regex( + r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON') + data = json.loads(data_json) + + playlist_title = data.get('DATA', {}).get('TITLE') + playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME') + playlist_thumbnail = self._search_regex( + r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage, + 'playlist thumbnail') + + preview_pattern = self._search_regex( + r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage, + 'preview URL pattern', fatal=False) + entries = [] + for s in data['SONGS']['data']: + puid = s['MD5_ORIGIN'] + preview_video_url = preview_pattern.\ + replace('{0}', puid[0]).\ + replace('{1}', puid).\ + replace('{2}', s['MEDIA_VERSION']) + formats = [{ + 'format_id': 'preview', + 'url': preview_video_url, + 'preference': -100, # Only the first 30 seconds + 'ext': 'mp3', + }] + self._sort_formats(formats) + artists = ', '.join( + orderedSet(a['ART_NAME'] for a in s['ARTISTS'])) + entries.append({ + 'id': s['SNG_ID'], + 'duration': int_or_none(s.get('DURATION')), + 'title': '%s - %s' % (artists, s['SNG_TITLE']), + 'uploader': s['ART_NAME'], + 'uploader_id': s['ART_ID'], + 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0, + 'formats': formats, + }) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': playlist_title, + 'uploader': playlist_uploader, + 'thumbnail': playlist_thumbnail, + 'entries': entries, + } diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py index cb8e06822..8049779b0 100644 --- a/youtube_dl/extractor/dfb.py +++ b/youtube_dl/extractor/dfb.py @@ -30,7 +30,7 @@ class DFBIE(InfoExtractor): video_id) video_info = player_info.find('video') - f4m_info = self._download_xml(video_info.find('url').text, video_id) + f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) token_el = f4m_info.find('token') manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py index 9f569aa93..1e1763abf 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -11,8 +11,7 @@ from ..utils import compat_urllib_parse_unquote class DropboxIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)' _TEST = { - 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4', - 'md5': '8a3d905427a6951ccb9eb292f154530b', + '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', @@ -25,7 +24,9 @@ class DropboxIE(InfoExtractor): video_id = mobj.group('id') fn = compat_urllib_parse_unquote(mobj.group('title')) title = os.path.splitext(fn)[0] - video_url = url + '?dl=1' + video_url = ( + re.sub(r'[?&]dl=0', '', url) + + ('?' if '?' in url else '&') + 'dl=1') return { 'id': video_id, diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py new file mode 100644 index 000000000..d5bfd7f22 --- /dev/null +++ b/youtube_dl/extractor/drtuber.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import str_to_int + + +class DrTuberIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', + 'md5': '93e680cf2536ad0dfb7e74d94a89facd', + 'info_dict': { + 'id': '1740434', + 'display_id': 'hot-perky-blonde-naked-golf', + 'ext': 'mp4', + 'title': 'Hot Perky Blonde Naked Golf', + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._html_search_regex( + r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Free', webpage, 'title') + + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + like_count = str_to_int(self._html_search_regex( + r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', + webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<span class="comments_count">([\d,\.]+)</span>', + webpage, 'comment count', fatal=False)) + + cats_str = self._html_search_regex( + r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) + categories = None if cats_str is None else cats_str.split(' ') + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'categories': categories, + 'age_limit': self._rta_search(webpage), + } diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py new file mode 100644 index 000000000..6b651778a --- /dev/null +++ b/youtube_dl/extractor/dump.py @@ -0,0 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DumpIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/' + + _TEST = { + 'url': 'http://www.dump.com/oneus/', + 'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99', + 'info_dict': { + 'id': 'oneus', + 'ext': 'flv', + 'title': "He's one of us.", + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex( + r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL') + + thumb = self._og_search_thumbnail(webpage) + title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumb, + } diff --git a/youtube_dl/extractor/ebaumsworld.py b/youtube_dl/extractor/ebaumsworld.py index 877113d63..63c2549d3 100644 --- a/youtube_dl/extractor/ebaumsworld.py +++ b/youtube_dl/extractor/ebaumsworld.py @@ -1,19 +1,21 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import determine_ext class EbaumsWorldIE(InfoExtractor): _VALID_URL = r'https?://www\.ebaumsworld\.com/video/watch/(?P<id>\d+)' _TEST = { - u'url': u'http://www.ebaumsworld.com/video/watch/83367677/', - u'file': u'83367677.mp4', - u'info_dict': { - u'title': u'A Giant Python Opens The Door', - u'description': u'This is how nightmares start...', - u'uploader': u'jihadpizza', + 'url': 'http://www.ebaumsworld.com/video/watch/83367677/', + 'info_dict': { + 'id': '83367677', + 'ext': 'mp4', + 'title': 'A Giant Python Opens The Door', + 'description': 'This is how nightmares start...', + 'uploader': 'jihadpizza', }, } @@ -28,7 +30,6 @@ class EbaumsWorldIE(InfoExtractor): 'id': video_id, 'title': config.find('title').text, 'url': video_url, - 'ext': determine_ext(video_url), 'description': config.find('description').text, 'thumbnail': config.find('image').text, 'uploader': config.find('username').text, diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index 88f5526b8..c1b4c729e 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -1,10 +1,13 @@ +# coding: utf-8 +from __future__ import unicode_literals + import json import random import re from .common import InfoExtractor from ..utils import ( - ExtractorError, + compat_str, ) @@ -12,86 +15,98 @@ class EightTracksIE(InfoExtractor): IE_NAME = '8tracks' _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' _TEST = { - u"name": u"EightTracks", - u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a", - u"playlist": [ + "name": "EightTracks", + "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a", + "info_dict": { + 'id': '1336550', + 'display_id': 'youtube-dl-test-tracks-a', + "description": "test chars: \"'/\\ä↭", + "title": "youtube-dl test tracks \"'/\\ä↭<>", + }, + "playlist": [ { - u"file": u"11885610.m4a", - u"md5": u"96ce57f24389fc8734ce47f4c1abcc55", - u"info_dict": { - u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "96ce57f24389fc8734ce47f4c1abcc55", + "info_dict": { + "id": "11885610", + "ext": "m4a", + "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885608.m4a", - u"md5": u"4ab26f05c1f7291ea460a3920be8021f", - u"info_dict": { - u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "4ab26f05c1f7291ea460a3920be8021f", + "info_dict": { + "id": "11885608", + "ext": "m4a", + "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885679.m4a", - u"md5": u"d30b5b5f74217410f4689605c35d1fd7", - u"info_dict": { - u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "d30b5b5f74217410f4689605c35d1fd7", + "info_dict": { + "id": "11885679", + "ext": "m4a", + "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885680.m4a", - u"md5": u"4eb0a669317cd725f6bbd336a29f923a", - u"info_dict": { - u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "4eb0a669317cd725f6bbd336a29f923a", + "info_dict": { + "id": "11885680", + "ext": "m4a", + "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885682.m4a", - u"md5": u"1893e872e263a2705558d1d319ad19e8", - u"info_dict": { - u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "1893e872e263a2705558d1d319ad19e8", + "info_dict": { + "id": "11885682", + "ext": "m4a", + "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885683.m4a", - u"md5": u"b673c46f47a216ab1741ae8836af5899", - u"info_dict": { - u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "b673c46f47a216ab1741ae8836af5899", + "info_dict": { + "id": "11885683", + "ext": "m4a", + "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885684.m4a", - u"md5": u"1d74534e95df54986da7f5abf7d842b7", - u"info_dict": { - u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "1d74534e95df54986da7f5abf7d842b7", + "info_dict": { + "id": "11885684", + "ext": "m4a", + "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885685.m4a", - u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0", - u"info_dict": { - u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "f081f47af8f6ae782ed131d38b9cd1c0", + "info_dict": { + "id": "11885685", + "ext": "m4a", + "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } } ] } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL) + json_like = self._search_regex( + r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information') data = json.loads(json_like) session = str(random.randint(0, 1000000000)) @@ -99,21 +114,30 @@ class EightTracksIE(InfoExtractor): track_count = data['tracks_count'] first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) next_url = first_url - res = [] + entries = [] for i in range(track_count): - api_json = self._download_webpage(next_url, playlist_id, - note=u'Downloading song information %s/%s' % (str(i+1), track_count), - errnote=u'Failed to download song information') + api_json = self._download_webpage( + next_url, playlist_id, + note='Downloading song information %d/%d' % (i + 1, track_count), + errnote='Failed to download song information') api_data = json.loads(api_json) - track_data = api_data[u'set']['track'] + track_data = api_data['set']['track'] info = { - 'id': track_data['id'], + 'id': compat_str(track_data['id']), 'url': track_data['track_file_stream_url'], 'title': track_data['performer'] + u' - ' + track_data['name'], 'raw_title': track_data['name'], 'uploader_id': data['user']['login'], 'ext': 'm4a', } - res.append(info) - next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) - return res + entries.append(info) + next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % ( + session, mix_id, track_data['id']) + return { + '_type': 'playlist', + 'entries': entries, + 'id': compat_str(mix_id), + 'display_id': playlist_id, + 'title': data.get('name'), + 'description': data.get('description'), + } diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py new file mode 100644 index 000000000..3e7923648 --- /dev/null +++ b/youtube_dl/extractor/ellentv.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) + + +class EllenTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', + 'md5': 'e4af06f3bf0d5f471921a18db5764642', + 'info_dict': { + 'id': '0-7jqrsr18', + 'ext': 'mp4', + 'title': 'What\'s Wrong with These Photos? A Whole Lot', + 'timestamp': 1406876400, + 'upload_date': '20140801', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + timestamp = parse_iso8601(self._search_regex( + r'<span class="publish-date"><time datetime="([^"]+)">', + webpage, 'timestamp')) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'url': self._html_search_meta('VideoURL', webpage, 'url'), + 'timestamp': timestamp, + } + + +class EllenTVClipsIE(InfoExtractor): + IE_NAME = 'EllenTV:clips' + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', + 'info_dict': { + 'id': 'meryl-streep-vanessa-hudgens', + 'title': 'Meryl Streep, Vanessa Hudgens', + }, + 'playlist_mincount': 9, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + playlist = self._extract_playlist(webpage) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': self._og_search_title(webpage), + 'entries': self._extract_entries(playlist) + } + + def _extract_playlist(self, webpage): + json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') + try: + return json.loads("[{" + json_string + "}]") + except ValueError as ve: + raise ExtractorError('Failed to download JSON', cause=ve) + + def _extract_entries(self, playlist): + return [self.url_result(item['url'], 'EllenTV') for item in playlist] diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index e6952588f..70f8efe27 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -1,54 +1,25 @@ from __future__ import unicode_literals -import re +from .tnaflix import TNAFlixIE -from .common import InfoExtractor +class EMPFlixIE(TNAFlixIE): + _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html' + + _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"' + _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' -class EmpflixIE(InfoExtractor): - _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _TEST = { 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'info_dict': { 'id': '33051', + 'display_id': 'Amateur-Finger-Fuck', 'ext': 'mp4', 'title': 'Amateur Finger Fuck', 'description': 'Amateur solo finger fucking.', + 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) - - video_title = self._html_search_regex( - r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') - video_description = self._html_search_regex( - r'name="description" value="([^"]*)"', webpage, 'description', fatal=False) - - cfg_url = self._html_search_regex( - r'flashvars\.config = escape\("([^"]+)"', - webpage, 'flashvars.config') - - cfg_xml = self._download_xml( - cfg_url, video_id, note='Downloading metadata') - - formats = [ - { - 'url': item.find('videoLink').text, - 'format_id': item.find('res').text, - } for item in cfg_xml.findall('./quality/item') - ] - - return { - 'id': video_id, - 'title': video_title, - 'description': video_description, - 'formats': formats, - 'age_limit': age_limit, - } diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py new file mode 100644 index 000000000..522aa3d63 --- /dev/null +++ b/youtube_dl/extractor/eporner.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class EpornerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', + 'md5': '3b427ae4b9d60619106de3185c2987cd', + 'info_dict': { + 'id': '95008', + 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', + 'ext': 'flv', + 'title': 'Infamous Tiffany Teen Strip Tease Video', + 'duration': 194, + 'view_count': int, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + title = self._html_search_regex( + r'<title>(.*?) - EPORNER', webpage, 'title') + + redirect_code = self._html_search_regex( + r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id, + webpage, 'redirect_code') + redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code) + player_code = self._download_webpage( + redirect_url, display_id, note='Downloading player config') + + sources = self._search_regex( + r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources') + + formats = [] + for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources): + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + duration = parse_duration(self._search_regex( + r'class="mbtim">([0-9:]+)</div>', webpage, 'duration', + fatal=False)) + view_count = str_to_int(self._search_regex( + r'id="cinemaviews">\s*([0-9,]+)\s*<small>views', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + 'age_limit': self._rta_search(webpage), + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 272dfe1f6..476fc22b9 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -36,7 +36,7 @@ class EscapistIE(InfoExtractor): r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False) - playerUrl = self._og_search_video_url(webpage, name=u'player URL') + playerUrl = self._og_search_video_url(webpage, name='player URL') title = self._html_search_regex( r'<meta name="title" content="([^"]*)"', diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index 12829cbcc..d237a8281 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -12,10 +12,11 @@ from ..utils import ( class EveryonesMixtapeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P<id>[0-9a-zA-Z]+)(?:/(?P<songnr>[0-9]))?$' - _TEST = { + _TESTS = [{ 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', - 'file': '5bfseWNmlds.mp4', "info_dict": { + 'id': '5bfseWNmlds', + 'ext': 'mp4', "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)", "uploader": "FKR.TV", "uploader_id": "frenchkissrecords", @@ -25,7 +26,14 @@ class EveryonesMixtapeIE(InfoExtractor): 'params': { 'skip_download': True, # This is simply YouTube } - } + }, { + 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi', + 'info_dict': { + 'id': 'm7m0jJAbMQi', + 'title': 'Driving', + }, + 'playlist_count': 24 + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/expotv.py b/youtube_dl/extractor/expotv.py new file mode 100644 index 000000000..a38b773e8 --- /dev/null +++ b/youtube_dl/extractor/expotv.py @@ -0,0 +1,73 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class ExpoTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])' + _TEST = { + 'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561', + 'md5': '2985e6d7a392b2f7a05e0ca350fe41d0', + 'info_dict': { + 'id': '17561', + 'ext': 'mp4', + 'upload_date': '20060212', + 'title': 'My Favorite Online Scrapbook Store', + 'view_count': int, + 'description': 'You\'ll find most everything you need at this virtual store front.', + 'uploader': 'Anna T.', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_key = self._search_regex( + r'<param name="playerKey" value="([^"]+)"', webpage, 'player key') + config_url = 'http://client.expotv.com/video/config/%s/%s' % ( + video_id, player_key) + config = self._download_json( + config_url, video_id, + note='Downloading video configuration') + + formats = [{ + 'url': fcfg['file'], + 'height': int_or_none(fcfg.get('height')), + 'format_note': fcfg.get('label'), + 'ext': self._search_regex( + r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'], + 'file extension', default=None), + } for fcfg in config['sources']] + self._sort_formats(formats) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = config.get('image') + view_count = int_or_none(self._search_regex( + r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts')) + uploader = self._search_regex( + r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader', + fatal=False) + upload_date = unified_strdate(self._search_regex( + r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date', + fatal=False)) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'description': description, + 'view_count': view_count, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f0cd8f156..afb34ce51 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -20,15 +20,15 @@ from ..utils import ( class FacebookIE(InfoExtractor): _VALID_URL = r'''(?x) https?://(?:\w+\.)?facebook\.com/ - (?:[^#?]*\#!/)? - (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) + (?:[^#]*?\#!/)? + (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?) (?:v|video_id)=(?P<id>[0-9]+) (?:.*)''' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' IE_NAME = 'facebook' - _TEST = { + _TESTS = [{ 'url': 'https://www.facebook.com/photo.php?v=120708114770723', 'md5': '48975a41ccc4b7a581abd68651c1a5a8', 'info_dict': { @@ -37,7 +37,10 @@ class FacebookIE(InfoExtractor): 'duration': 279, 'title': 'PEOPLE ARE AWESOME 2013', } - } + }, { + 'url': 'https://www.facebook.com/video.php?v=10204634152394104', + 'only_matching': True, + }] def _login(self): (useremail, password) = self._get_login_info() @@ -76,7 +79,8 @@ class FacebookIE(InfoExtractor): check_form = { 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'), - 'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'), + 'h': self._search_regex( + r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'), 'name_action_selected': 'dont_save', } check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py index 6d73c8a4a..af439ccfe 100644 --- a/youtube_dl/extractor/firedrive.py +++ b/youtube_dl/extractor/firedrive.py @@ -42,7 +42,6 @@ class FiredriveIE(InfoExtractor): fields = dict(re.findall(r'''(?x)<input\s+ type="hidden"\s+ name="([^"]+)"\s+ - (?:id="[^"]+"\s+)? value="([^"]*)" ''', webpage)) @@ -66,7 +65,7 @@ class FiredriveIE(InfoExtractor): ext = self._search_regex(r'type:\s?\'([^\']+)\',', webpage, 'extension', fatal=False) video_url = self._search_regex( - r'file:\s?\'(http[^\']+)\',', webpage, 'file url') + r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url') formats = [{ 'format_id': 'sd', diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 1fbe6d175..1b0e8e5d5 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -19,17 +19,35 @@ class FranceTVBaseInfoExtractor(InfoExtractor): + video_id, video_id, 'Downloading XML config') manifest_url = info.find('videos/video/url').text - video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') - video_url = video_url.replace('/z/', '/i/') + manifest_url = manifest_url.replace('/z/', '/i/') + + if manifest_url.startswith('rtmp'): + formats = [{'url': manifest_url, 'ext': 'flv'}] + else: + formats = [] + available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats') + for index, format_descr in enumerate(available_formats.split(',')): + format_info = { + 'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index), + 'ext': 'mp4', + } + m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr) + if m_resolution is not None: + format_info.update({ + 'width': int(m_resolution.group('width')), + 'height': int(m_resolution.group('height')), + }) + formats.append(format_info) + thumbnail_path = info.find('image').text - return {'id': video_id, - 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4', - 'url': video_url, - 'title': info.find('titre').text, - 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), - 'description': info.find('synopsis').text, - } + return { + 'id': video_id, + 'title': info.find('titre').text, + 'formats': formats, + 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), + 'description': info.find('synopsis').text, + } class PluzzIE(FranceTVBaseInfoExtractor): diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py index b580f52fb..3022f539d 100644 --- a/youtube_dl/extractor/gameone.py +++ b/youtube_dl/extractor/gameone.py @@ -88,3 +88,28 @@ class GameOneIE(InfoExtractor): 'age_limit': age_limit, 'timestamp': timestamp, } + + +class GameOnePlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$' + IE_NAME = 'gameone:playlist' + _TEST = { + 'url': 'http://www.gameone.de/tv', + 'info_dict': { + 'title': 'GameOne', + }, + 'playlist_mincount': 294, + } + + def _real_extract(self, url): + webpage = self._download_webpage('http://www.gameone.de/tv', 'TV') + max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage))) + entries = [ + self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne') + for video_id in range(max_id, 0, -1)] + + return { + '_type': 'playlist', + 'title': 'GameOne', + 'entries': entries, + } diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py new file mode 100644 index 000000000..50f8fc7e7 --- /dev/null +++ b/youtube_dl/extractor/gamestar.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + str_to_int, + unified_strdate, +) + + +class GameStarIE(InfoExtractor): + _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html', + 'md5': '96974ecbb7fd8d0d20fca5a00810cea7', + 'info_dict': { + 'id': '76110', + 'ext': 'mp4', + 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil', + 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.', + 'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg', + 'upload_date': '20140728', + 'duration': 17 + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + og_title = self._og_search_title(webpage) + title = og_title.replace(' - Video bei GameStar.de', '').strip() + + url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id + + description = self._og_search_description(webpage).strip() + + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') + + upload_date = unified_strdate(self._html_search_regex( + r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+) ', + webpage, 'upload_date', fatal=False)) + + duration = parse_duration(self._html_search_regex( + r' Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration', + fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r' Zuschauer: ([0-9\.]+) ', webpage, + 'view_count', fatal=False)) + + comment_count = int_or_none(self._html_search_regex( + r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count', + fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'url': url, + 'ext': 'mp4', + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 9db27f9aa..2bfa20606 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -8,18 +8,20 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE from ..utils import ( - compat_urllib_error, compat_urllib_parse, - compat_urllib_request, compat_urlparse, compat_xml_parse_error, + determine_ext, ExtractorError, + float_or_none, HEADRequest, + orderedSet, parse_xml, smuggle_url, unescapeHTML, unified_strdate, + unsmuggle_url, url_basename, ) from .brightcove import BrightcoveIE @@ -289,6 +291,97 @@ class GenericIE(InfoExtractor): 'description': 'Mario\'s life in the fast lane has never looked so good.', }, }, + # YouTube embed via <data-embed-url=""> + { + 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', + 'info_dict': { + 'id': 'jpSGZsgga_I', + 'ext': 'mp4', + 'title': 'Asphalt 8: Airborne - Launch Trailer', + 'uploader': 'Gameloft', + 'uploader_id': 'gameloft', + 'upload_date': '20130821', + 'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a', + }, + 'params': { + 'skip_download': True, + } + }, + # Camtasia studio + { + 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/', + 'playlist': [{ + 'md5': '0c5e352edabf715d762b0ad4e6d9ee67', + 'info_dict': { + 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1', + 'ext': 'flv', + 'duration': 2235.90, + } + }, { + 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63', + 'info_dict': { + 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP', + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip', + 'ext': 'flv', + 'duration': 2235.93, + } + }], + 'info_dict': { + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', + } + }, + # Flowplayer + { + 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html', + 'md5': '9d65602bf31c6e20014319c7d07fba27', + 'info_dict': { + 'id': '5123ea6d5e5a7', + 'ext': 'mp4', + 'age_limit': 18, + 'uploader': 'www.handjobhub.com', + 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub', + } + }, + # RSS feed + { + 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'info_dict': { + 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'title': 'Zero Punctuation', + 'description': 're:' + }, + 'playlist_mincount': 11, + }, + # Multiple brightcove videos + # https://github.com/rg3/youtube-dl/issues/2283 + { + 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', + 'info_dict': { + 'id': 'always-never', + 'title': 'Always / Never - The New Yorker', + }, + 'playlist_count': 3, + 'params': { + 'extract_flat': False, + 'skip_download': True, + } + }, + # MLB embed + { + 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/', + 'md5': '96f09a37e44da40dd083e12d9a683327', + 'info_dict': { + 'id': '33322633', + 'ext': 'mp4', + 'title': 'Ump changes call to ball', + 'description': 'md5:71c11215384298a172a6dcb4c2e20685', + 'duration': 48, + 'timestamp': 1401537900, + 'upload_date': '20140531', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, ] def report_download_webpage(self, video_id): @@ -301,58 +394,6 @@ class GenericIE(InfoExtractor): """Report information extraction.""" self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) - def _send_head(self, url): - """Check if it is a redirect, like url shorteners, in case return the new url.""" - - class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): - """ - Subclass the HTTPRedirectHandler to make it use our - HEADRequest also on the redirected URL - """ - def redirect_request(self, req, fp, code, msg, headers, newurl): - if code in (301, 302, 303, 307): - newurl = newurl.replace(' ', '%20') - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - try: - # This function was deprecated in python 3.3 and removed in 3.4 - origin_req_host = req.get_origin_req_host() - except AttributeError: - origin_req_host = req.origin_req_host - return HEADRequest(newurl, - headers=newheaders, - origin_req_host=origin_req_host, - unverifiable=True) - else: - raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) - - class HTTPMethodFallback(compat_urllib_request.BaseHandler): - """ - Fallback to GET if HEAD is not allowed (405 HTTP error) - """ - def http_error_405(self, req, fp, code, msg, headers): - fp.read() - fp.close() - - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - return self.parent.open(compat_urllib_request.Request(req.get_full_url(), - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True)) - - # Build our opener - opener = compat_urllib_request.OpenerDirector() - for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, - HTTPMethodFallback, HEADRedirectHandler, - compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: - opener.add_handler(handler()) - - response = opener.open(HEADRequest(url)) - if response is None: - raise ExtractorError('Invalid URL protocol') - return response - def _extract_rss(self, url, video_id, doc): playlist_title = doc.find('./channel/title').text playlist_desc_el = doc.find('./channel/description') @@ -372,6 +413,43 @@ class GenericIE(InfoExtractor): 'entries': entries, } + def _extract_camtasia(self, url, video_id, webpage): + """ Returns None if no camtasia video can be found. """ + + camtasia_cfg = self._search_regex( + r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);', + webpage, 'camtasia configuration file', default=None) + if camtasia_cfg is None: + return None + + title = self._html_search_meta('DC.title', webpage, fatal=True) + + camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg) + camtasia_cfg = self._download_xml( + camtasia_url, video_id, + note='Downloading camtasia configuration', + errnote='Failed to download camtasia configuration') + fileset_node = camtasia_cfg.find('./playlist/array/fileset') + + entries = [] + for n in fileset_node.getchildren(): + url_n = n.find('./uri') + if url_n is None: + continue + + entries.append({ + 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0], + 'title': '%s - %s' % (title, n.tag), + 'url': compat_urlparse.urljoin(url, url_n.text), + 'duration': float_or_none(n.find('./duration').text), + }) + + return { + '_type': 'playlist', + 'entries': entries, + 'title': title, + } + def _real_extract(self, url): if url.startswith('//'): return { @@ -383,13 +461,13 @@ class GenericIE(InfoExtractor): if not parsed_url.scheme: default_search = self._downloader.params.get('default_search') if default_search is None: - default_search = 'error' + default_search = 'fixup_error' - if default_search in ('auto', 'auto_warning'): + if default_search in ('auto', 'auto_warning', 'fixup_error'): if '/' in url: self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) - else: + elif default_search != 'fixup_error': if default_search == 'auto_warning': if re.match(r'^(?:url|URL)$', url): raise ExtractorError( @@ -399,7 +477,8 @@ class GenericIE(InfoExtractor): self._downloader.report_warning( 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) - elif default_search == 'error': + + 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' @@ -407,17 +486,31 @@ class GenericIE(InfoExtractor): else: assert ':' in default_search return self.url_result(default_search + url) - video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] + + url, smuggled_data = unsmuggle_url(url) + force_videoid = None + if smuggled_data and 'force_videoid' in smuggled_data: + force_videoid = smuggled_data['force_videoid'] + video_id = force_videoid + else: + video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] self.to_screen('%s: Requesting header' % video_id) - try: - response = self._send_head(url) + head_req = HEADRequest(url) + 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: # Check for redirect new_url = response.geturl() if url != new_url: self.report_following_redirect(new_url) + if force_videoid: + new_url = smuggle_url( + new_url, {'force_videoid': force_videoid}) return self.url_result(new_url) # Check for direct link to a video @@ -438,10 +531,6 @@ class GenericIE(InfoExtractor): 'upload_date': upload_date, } - except compat_urllib_error.HTTPError: - # This may be a stupid server that doesn't like HEAD, our UA, or so - pass - try: webpage = self._download_webpage(url, video_id) except ValueError: @@ -459,6 +548,11 @@ class GenericIE(InfoExtractor): except compat_xml_parse_error: pass + # Is it a Camtasia project? + camtasia_res = self._extract_camtasia(url, video_id, webpage) + if camtasia_res is not None: + return camtasia_res + # Sometimes embedded video player is hidden behind percent encoding # (e.g. https://github.com/rg3/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way @@ -474,10 +568,26 @@ class GenericIE(InfoExtractor): r'(?s)<title>(.*?)</title>', webpage, 'video title', default='video') + # Try to detect age limit automatically + age_limit = self._rta_search(webpage) + # And then there are the jokers who advertise that they use RTA, + # but actually don't. + AGE_LIMIT_MARKERS = [ + r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>', + ] + if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): + age_limit = 18 + # video uploader is domain name video_uploader = self._search_regex( r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') + # Helper method + def _playlist_from_matches(matches, getter, ie=None): + urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches) + return self.playlist_result( + urlrs, playlist_id=video_id, playlist_title=video_title) + # Look for BrightCove: bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) if bc_urls: @@ -513,27 +623,24 @@ class GenericIE(InfoExtractor): matches = re.findall(r'''(?x) (?: <iframe[^>]+?src=| + data-video-url=| <embed[^>]+?src=| embedSWF\(?:\s* ) (["\']) - (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/ + (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ (?:embed|v)/.+?) \1''', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') - for tuppl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, lambda m: unescapeHTML(m[1]), ie='Youtube') # Look for embedded Dailymotion player matches = re.findall( r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(tuppl[1])) - for tuppl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, lambda m: unescapeHTML(m[1])) # Look for embedded Wistia player match = re.search( @@ -552,7 +659,7 @@ class GenericIE(InfoExtractor): mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) if mobj: return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage) + 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') @@ -647,10 +754,8 @@ class GenericIE(InfoExtractor): # Look for funnyordie embed matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie') - for eurl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, getter=unescapeHTML, ie='FunnyOrDie') # Look for embedded RUTV player rutv_url = RUTVIE._extract_url(webpage) @@ -705,6 +810,26 @@ class GenericIE(InfoExtractor): url = unescapeHTML(mobj.group('url')) return self.url_result(url, ie='MTVServicesEmbedded') + # Look for embedded yahoo player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Yahoo') + + # Look for embedded sbs.com.au player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'SBS') + + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'MLB') + # Start with something easy: JW Player in SWFObject found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if not found: @@ -723,6 +848,14 @@ class GenericIE(InfoExtractor): # Broaden the findall a little bit: JWPlayer JS loader found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage) if not found: + # Flow player + found = re.findall(r'''(?xs) + flowplayer\("[^"]+",\s* + \{[^}]+?\}\s*, + \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s* + ["']?url["']?\s*:\s*["']([^"']+)["'] + ''', webpage) + if not found: # Try to find twitter cards info found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) if not found: @@ -731,10 +864,16 @@ class GenericIE(InfoExtractor): m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage) # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: if m_video_type is not None: - found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) + 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))) if not found: # HTML5 video - found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage) + found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage) if not found: found = re.search( r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' @@ -768,6 +907,7 @@ class GenericIE(InfoExtractor): 'url': video_url, 'uploader': video_uploader, 'title': video_title, + 'age_limit': age_limit, }) if len(entries) == 1: diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index 383032d81..469e1f935 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -14,6 +14,14 @@ class GoogleSearchIE(SearchInfoExtractor): _MAX_RESULTS = 1000 IE_NAME = 'video.google:search' _SEARCH_KEY = 'gvsearch' + _TEST = { + 'url': 'gvsearch15:python language', + 'info_dict': { + 'id': 'python language', + 'title': 'python language', + }, + 'playlist_count': 15, + } def _get_n_results(self, query, n): """Get a specified number of results for a query""" diff --git a/youtube_dl/extractor/grooveshark.py b/youtube_dl/extractor/grooveshark.py new file mode 100644 index 000000000..726adff77 --- /dev/null +++ b/youtube_dl/extractor/grooveshark.py @@ -0,0 +1,190 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import time +import math +import os.path +import re + + +from .common import InfoExtractor +from ..utils import ExtractorError, compat_urllib_request, compat_html_parser + +from ..utils import ( + compat_urllib_parse, + compat_urlparse, +) + + +class GroovesharkHtmlParser(compat_html_parser.HTMLParser): + def __init__(self): + self._current_object = None + self.objects = [] + compat_html_parser.HTMLParser.__init__(self) + + def handle_starttag(self, tag, attrs): + attrs = dict((k, v) for k, v in attrs) + if tag == 'object': + self._current_object = {'attrs': attrs, 'params': []} + elif tag == 'param': + self._current_object['params'].append(attrs) + + def handle_endtag(self, tag): + if tag == 'object': + self.objects.append(self._current_object) + self._current_object = None + + @classmethod + def extract_object_tags(cls, html): + p = cls() + p.feed(html) + p.close() + return p.objects + + +class GroovesharkIE(InfoExtractor): + _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)' + _TEST = { + 'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5', + 'md5': '7ecf8aefa59d6b2098517e1baa530023', + 'info_dict': { + 'id': '6SS1DW', + 'title': 'Jolene (Tenth Key Remix ft. Will Sessions)', + 'ext': 'mp3', + 'duration': 227, + } + } + + do_playerpage_request = True + do_bootstrap_request = True + + def _parse_target(self, target): + uri = compat_urlparse.urlparse(target) + hash = uri.fragment[1:].split('?')[0] + token = os.path.basename(hash.rstrip('/')) + return (uri, hash, token) + + def _build_bootstrap_url(self, target): + (uri, hash, token) = self._parse_target(target) + query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts) + return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token) + + def _build_meta_url(self, target): + (uri, hash, token) = self._parse_target(target) + query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts) + return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token) + + def _build_stream_url(self, meta): + return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None)) + + def _build_swf_referer(self, target, obj): + (uri, _, _) = self._parse_target(target) + return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None)) + + def _transform_bootstrap(self, js): + return re.split('(?m)^\s*try\s*{', js)[0] \ + .split(' = ', 1)[1].strip().rstrip(';') + + def _transform_meta(self, js): + return js.split('\n')[0].split('=')[1].rstrip(';') + + def _get_meta(self, target): + (meta_url, token) = self._build_meta_url(target) + self.to_screen('Metadata URL: %s' % meta_url) + + headers = {'Referer': compat_urlparse.urldefrag(target)[0]} + req = compat_urllib_request.Request(meta_url, headers=headers) + res = self._download_json(req, token, + transform_source=self._transform_meta) + + if 'getStreamKeyWithSong' not in res: + raise ExtractorError( + 'Metadata not found. URL may be malformed, or Grooveshark API may have changed.') + + if res['getStreamKeyWithSong'] is None: + raise ExtractorError( + 'Metadata download failed, probably due to Grooveshark anti-abuse throttling. Wait at least an hour before retrying from this IP.', + expected=True) + + return res['getStreamKeyWithSong'] + + def _get_bootstrap(self, target): + (bootstrap_url, token) = self._build_bootstrap_url(target) + + headers = {'Referer': compat_urlparse.urldefrag(target)[0]} + req = compat_urllib_request.Request(bootstrap_url, headers=headers) + res = self._download_json(req, token, fatal=False, + note='Downloading player bootstrap data', + errnote='Unable to download player bootstrap data', + transform_source=self._transform_bootstrap) + return res + + def _get_playerpage(self, target): + (_, _, token) = self._parse_target(target) + + webpage = self._download_webpage( + target, token, + note='Downloading player page', + errnote='Unable to download player page', + fatal=False) + + if webpage is not None: + # Search (for example German) error message + error_msg = self._html_search_regex( + r'<div id="content">\s*<h2>(.*?)</h2>', webpage, + 'error message', default=None) + if error_msg is not None: + error_msg = error_msg.replace('\n', ' ') + raise ExtractorError('Grooveshark said: %s' % error_msg) + + if webpage is not None: + o = GroovesharkHtmlParser.extract_object_tags(webpage) + return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']) + + return (webpage, None) + + def _real_initialize(self): + self.ts = int(time.time() * 1000) # timestamp in millis + + def _real_extract(self, url): + (target_uri, _, token) = self._parse_target(url) + + # 1. Fill cookiejar by making a request to the player page + swf_referer = None + if self.do_playerpage_request: + (_, player_objs) = self._get_playerpage(url) + if player_objs is not None: + swf_referer = self._build_swf_referer(url, player_objs[0]) + self.to_screen('SWF Referer: %s' % swf_referer) + + # 2. Ask preload.php for swf bootstrap data to better mimic webapp + if self.do_bootstrap_request: + bootstrap = self._get_bootstrap(url) + self.to_screen('CommunicationToken: %s' % bootstrap['getCommunicationToken']) + + # 3. Ask preload.php for track metadata. + meta = self._get_meta(url) + + # 4. Construct stream request for track. + stream_url = self._build_stream_url(meta) + duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000)) + post_dict = {'streamKey': meta['streamKey']['streamKey']} + post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8') + headers = { + 'Content-Length': len(post_data), + 'Content-Type': 'application/x-www-form-urlencoded' + } + if swf_referer is not None: + headers['Referer'] = swf_referer + + return { + 'id': token, + 'title': meta['song']['Name'], + 'http_method': 'POST', + 'url': stream_url, + 'ext': 'mp3', + 'format': 'mp3 audio', + 'duration': duration, + 'http_post_data': post_data, + 'http_headers': headers, + } diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py new file mode 100644 index 000000000..7e7714438 --- /dev/null +++ b/youtube_dl/extractor/hornbunny.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, +) + + +class HornBunnyIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html' + _TEST = { + 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html', + 'md5': '95e40865aedd08eff60272b704852ad7', + 'info_dict': { + 'id': '5227', + 'ext': 'flv', + 'title': 'panty slut jerk off instruction', + 'duration': 550, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage( + url, video_id, note='Downloading initial webpage') + title = self._html_search_regex( + r'class="title">(.*?)</h2>', webpage, 'title') + redirect_url = self._html_search_regex( + r'pg&settings=(.*?)\|0"\);', webpage, 'title') + webpage2 = self._download_webpage(redirect_url, video_id) + video_url = self._html_search_regex( + r'flvMask:(.*?);', webpage2, 'video_url') + + duration = parse_duration(self._search_regex( + r'<strong>Runtime:</strong>\s*([0-9:]+)</div>', + webpage, 'duration', fatal=False)) + view_count = int_or_none(self._search_regex( + r'<strong>Views:</strong>\s*(\d+)</div>', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': 'flv', + 'duration': duration, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py new file mode 100644 index 000000000..8e812b669 --- /dev/null +++ b/youtube_dl/extractor/hostingbulk.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + int_or_none, + urlencode_postdata, +) + + +class HostingBulkIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:www\.)?hostingbulk\.com/ + (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html''' + _FILE_DELETED_REGEX = r'<b>File Not Found</b>' + _TEST = { + 'url': 'http://hostingbulk.com/n0ulw1hv20fm.html', + 'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f', + 'info_dict': { + 'id': 'n0ulw1hv20fm', + 'ext': 'mp4', + 'title': 'md5:5afeba33f48ec87219c269e054afd622', + 'filesize': 6816081, + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://hostingbulk.com/{0:}.html'.format(video_id) + + # Custom request with cookie to set language to English, so our file + # deleted regex would work. + request = compat_urllib_request.Request( + url, headers={'Cookie': 'lang=english'}) + webpage = self._download_webpage(request, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title') + filesize = int_or_none( + self._search_regex( + r'<small>\((\d+)\sbytes?\)</small>', + webpage, + 'filesize', + fatal=False + ) + ) + thumbnail = self._search_regex( + r'<img src="([^"]+)".+?class="pic"', + webpage, 'thumbnail', fatal=False) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + value="([^"]*)" + ''', webpage)) + + request = compat_urllib_request.Request(url, urlencode_postdata(fields)) + request.add_header('Content-type', 'application/x-www-form-urlencoded') + response = self._request_webpage(request, video_id, + 'Submiting download request') + video_url = response.geturl() + + formats = [{ + 'format_id': 'sd', + 'filesize': filesize, + 'url': video_url, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/howstuffworks.py b/youtube_dl/extractor/howstuffworks.py new file mode 100644 index 000000000..68684b997 --- /dev/null +++ b/youtube_dl/extractor/howstuffworks.py @@ -0,0 +1,134 @@ +from __future__ import unicode_literals + +import re +import json +import random +import string + +from .common import InfoExtractor +from ..utils import find_xpath_attr + + +class HowStuffWorksIE(InfoExtractor): + _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm' + _TESTS = [ + { + 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm', + 'info_dict': { + 'id': '450221', + 'display_id': 'cool-jobs-iditarod-musher', + 'ext': 'flv', + 'title': 'Cool Jobs - Iditarod Musher', + 'description': 'md5:82bb58438a88027b8186a1fccb365f90', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + { + 'url': 'http://adventure.howstuffworks.com/39516-deadliest-catch-jakes-farewell-pots-video.htm', + 'info_dict': { + 'id': '553470', + 'display_id': 'deadliest-catch-jakes-farewell-pots', + 'ext': 'mp4', + 'title': 'Deadliest Catch: Jake\'s Farewell Pots', + 'description': 'md5:9632c346d5e43ee238028c9cefd8dbbc', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + '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', + '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') + webpage = self._download_webpage(url, display_id) + + 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)) + + formats = [] + + 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 + formats.append({ + 'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX), + 'format_id': '%dk' % vbr, + 'vbr': vbr, + }) + + 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, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index 1f42c6d3a..9e8b69f57 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -18,6 +18,7 @@ class IGNIE(InfoExtractor): _DESCRIPTION_RE = [ r'<span class="page-object-description">(.+?)</span>', r'id="my_show_video">.*?<p>(.*?)</p>', + r'<meta name="description" content="(.*?)"', ] _TESTS = [ @@ -55,6 +56,17 @@ class IGNIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch', + 'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7', + 'info_dict': { + 'id': '078fdd005f6d3c02f63d795faa1b984f', + 'ext': 'mp4', + 'title': 'Rewind Theater - Wild Trailer Gamescom 2014', + 'description': 'Giant skeletons, bloody hunts, and captivating' + ' natural beauty take our breath away.', + }, + }, ] def _find_video_id(self, webpage): @@ -62,6 +74,7 @@ class IGNIE(InfoExtractor): r'data-video-id="(.+?)"', r'<object id="vid_(.+?)"', r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', + r'class="hero-poster[^"]*?"[^>]*id="(.+?)"', ] return self._search_regex(res_id, webpage, 'video id') @@ -70,10 +83,7 @@ class IGNIE(InfoExtractor): name_or_id = mobj.group('name_or_id') page_type = mobj.group('type') webpage = self._download_webpage(url, name_or_id) - if page_type == 'articles': - video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url') - return self.url_result(video_url, ie='IGN') - elif page_type != 'video': + if page_type != 'video': multiple_urls = re.findall( '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', webpage) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 7cee505c0..4536db3bf 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -63,6 +63,14 @@ class ImdbListIE(InfoExtractor): IE_NAME = 'imdb:list' IE_DESC = 'Internet Movie Database lists' _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})' + _TEST = { + 'url': 'http://www.imdb.com/list/JFs9NWw6XI0', + 'info_dict': { + 'id': 'JFs9NWw6XI0', + 'title': 'March 23, 2012 Releases', + }, + 'playlist_count': 7, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index b5372bf7a..5109f26ce 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -46,6 +46,30 @@ class InstagramUserIE(InfoExtractor): _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' + _TEST = { + 'url': 'http://instagram.com/porsche', + 'info_dict': { + 'id': 'porsche', + 'title': 'porsche', + }, + 'playlist_mincount': 2, + 'playlist': [{ + 'info_dict': { + 'id': '614605558512799803_462752227', + 'ext': 'mp4', + 'title': '#Porsche Intelligent Performance.', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Porsche', + 'uploader_id': 'porsche', + 'timestamp': 1387486713, + 'upload_date': '20131219', + }, + }], + 'params': { + 'extract_flat': True, + 'skip_download': True, + } + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 4027deb70..75b543b7c 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -127,6 +127,21 @@ class IviCompilationIE(InfoExtractor): IE_DESC = 'ivi.ru compilations' IE_NAME = 'ivi:compilation' _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$' + _TESTS = [{ + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa', + 'info_dict': { + 'id': 'dvoe_iz_lartsa', + 'title': 'Двое из ларца (2006 - 2008)', + }, + 'playlist_mincount': 24, + }, { + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1', + 'info_dict': { + 'id': 'dvoe_iz_lartsa/season1', + 'title': 'Двое из ларца (2006 - 2008) 1 сезон', + }, + 'playlist_mincount': 12, + }] def _extract_entries(self, html, compilation_id): return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py new file mode 100644 index 000000000..a83dd249f --- /dev/null +++ b/youtube_dl/extractor/izlesene.py @@ -0,0 +1,125 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + get_element_by_id, + parse_iso8601, + determine_ext, + int_or_none, + float_or_none, + str_to_int, +) + + +class IzleseneIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:(?:www|m)\.)?izlesene\.com/ + (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+) + ''' + _TESTS = [ + { + 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', + 'md5': '4384f9f0ea65086734b881085ee05ac2', + 'info_dict': { + 'id': '7599694', + 'ext': 'mp4', + 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'description': 'md5:253753e2655dde93f59f74b572454f6d', + 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'pelikzzle', + 'timestamp': 1404298698, + 'upload_date': '20140702', + 'duration': 95.395, + 'age_limit': 0, + } + }, + { + 'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997', + 'md5': '97f09b6872bffa284cb7fa4f6910cb72', + 'info_dict': { + 'id': '17997', + 'ext': 'mp4', + 'title': 'Tarkan Dortmund 2006 Konseri', + 'description': 'Tarkan Dortmund 2006 Konseri', + 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'parlayankiz', + 'timestamp': 1163318593, + 'upload_date': '20061112', + 'duration': 253.666, + 'age_limit': 0, + } + }, + ] + + 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 + + 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) + + uploader = self._html_search_regex( + r"adduserUsername\s*=\s*'([^']+)';", + webpage, 'uploader', fatal=False, default='') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date', fatal=False)) + + duration = float_or_none(self._html_search_regex( + r'"videoduration"\s*:\s*"([^"]+)"', + webpage, 'duration', fatal=False), scale=1000) + + view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) + comment_count = self._html_search_regex( + r'comment_count\s*=\s*\'([^\']+)\';', + webpage, 'comment_count', fatal=False) + + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, 'age limit', fatal=False) + + content_url = self._html_search_meta( + 'contentURL', webpage, 'content URL', fatal=False) + ext = determine_ext(content_url, 'mp4') + + # Might be empty for some videos. + streams = self._html_search_regex( + r'"qualitylevel"\s*:\s*"([^"]+)"', + webpage, 'streams', fatal=False, default='') + + formats = [] + if streams: + for stream in streams.split('|'): + quality, url = re.search(r'\[(\w+)\](.+)', stream).groups() + formats.append({ + 'format_id': '%sp' % quality if quality else 'sd', + 'url': url, + 'ext': ext, + }) + else: + stream_url = self._search_regex( + r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL') + formats.append({ + 'format_id': 'sd', + 'url': stream_url, + 'ext': ext, + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader_id': uploader, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': int_or_none(view_count), + 'comment_count': int_or_none(comment_count), + 'age_limit': 18 if family_friendly == 'False' else 0, + 'formats': formats, + } diff --git a/youtube_dl/extractor/jove.py b/youtube_dl/extractor/jove.py new file mode 100644 index 000000000..cf73cd753 --- /dev/null +++ b/youtube_dl/extractor/jove.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unified_strdate +) + + +class JoveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)' + _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' + _TESTS = [ + { + 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', + 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', + 'info_dict': { + 'id': '2744', + 'ext': 'mp4', + 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', + 'description': 'md5:015dd4509649c0908bc27f049e0262c6', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20110523', + } + }, + { + 'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation', + 'md5': '914aeb356f416811d911996434811beb', + 'info_dict': { + 'id': '51796', + 'ext': 'mp4', + 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment', + 'description': 'md5:35ff029261900583970c4023b70f1dc9', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20140802', + } + }, + + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + chapters_id = self._html_search_regex( + r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') + + chapters_xml = self._download_xml( + self._CHAPTERS_URL.format(video_id=chapters_id), + video_id, note='Downloading chapters XML', + errnote='Failed to download chapters XML') + + video_url = chapters_xml.attrib.get('video') + if not video_url: + raise ExtractorError('Failed to get the video URL') + + title = self._html_search_meta('citation_title', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._html_search_regex( + r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>', + webpage, 'description', fatal=False) + publish_date = unified_strdate(self._html_search_meta( + 'citation_publication_date', webpage, 'publish date', fatal=False)) + comment_count = self._html_search_regex( + r'<meta name="num_comments" content="(\d+) Comments?"', + webpage, 'comment count', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': publish_date, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 772bb5671..408d00944 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -9,21 +9,30 @@ from ..utils import ( class KhanAcademyIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])' + _VALID_URL = r'^https?://(?:(?:www|api)\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])' IE_NAME = 'KhanAcademy' - _TEST = { + _TESTS = [{ 'url': 'http://www.khanacademy.org/video/one-time-pad', - 'file': 'one-time-pad.mp4', 'md5': '7021db7f2d47d4fff89b13177cb1e8f4', 'info_dict': { + 'id': 'one-time-pad', + 'ext': 'mp4', 'title': 'The one-time pad', 'description': 'The perfect cipher', 'duration': 176, 'uploader': 'Brit Cruise', 'upload_date': '20120411', } - } + }, { + 'url': 'https://www.khanacademy.org/math/applied-math/cryptography', + 'info_dict': { + 'id': 'cryptography', + 'title': 'Journey into cryptography', + 'description': 'How have humans protected their secret messages through history? What has changed today?', + }, + 'playlist_mincount': 3, + }] def _real_extract(self, url): m = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index c0c2d9b09..516147417 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -19,7 +19,7 @@ from ..utils import ( class LivestreamIE(InfoExtractor): IE_NAME = 'livestream' _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' - _TEST = { + _TESTS = [{ 'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', 'md5': '53274c76ba7754fb0e8d072716f2292b', 'info_dict': { @@ -31,7 +31,13 @@ class LivestreamIE(InfoExtractor): 'view_count': int, 'thumbnail': 're:^http://.*\.jpg$' } - } + }, { + 'url': 'http://new.livestream.com/tedx/cityenglish', + 'info_dict': { + 'title': 'TEDCity2.0 (English)', + }, + 'playlist_mincount': 4, + }] def _parse_smil(self, video_id, smil_url): formats = [] @@ -111,23 +117,37 @@ class LivestreamIE(InfoExtractor): event_name = mobj.group('event_name') webpage = self._download_webpage(url, video_id or event_name) + og_video = self._og_search_video_url( + webpage, 'player url', fatal=False, default=None) + if og_video is not None: + query_str = compat_urllib_parse_urlparse(og_video).query + query = compat_urlparse.parse_qs(query_str) + if 'play_url' in query: + api_url = query['play_url'][0].replace('.smil', '') + info = json.loads(self._download_webpage( + api_url, video_id, 'Downloading video info')) + return self._extract_video_info(info) + + config_json = self._search_regex( + r'window.config = ({.*?});', webpage, 'window config') + info = json.loads(config_json)['event'] + + def is_relevant(vdata, vid): + result = vdata['type'] == 'video' + if video_id is not None: + result = result and compat_str(vdata['data']['id']) == vid + return result + + videos = [self._extract_video_info(video_data['data']) + for video_data in info['feed']['data'] + if is_relevant(video_data, video_id)] if video_id is None: # This is an event page: - config_json = self._search_regex( - r'window.config = ({.*?});', webpage, 'window config') - info = json.loads(config_json)['event'] - videos = [self._extract_video_info(video_data['data']) - for video_data in info['feed']['data'] - if video_data['type'] == 'video'] return self.playlist_result(videos, info['id'], info['full_name']) else: - og_video = self._og_search_video_url(webpage, 'player url') - query_str = compat_urllib_parse_urlparse(og_video).query - query = compat_urlparse.parse_qs(query_str) - api_url = query['play_url'][0].replace('.smil', '') - info = json.loads(self._download_webpage( - api_url, video_id, 'Downloading video info')) - return self._extract_video_info(info) + if not videos: + raise ExtractorError('Cannot find video %s' % video_id) + return videos[0] # The original version of Livestream uses a different system @@ -137,7 +157,7 @@ class LivestreamOriginalIE(InfoExtractor): (?P<user>[^/]+)/(?P<type>video|folder) (?:\?.*?Id=|/)(?P<id>.*?)(&|$) ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', 'info_dict': { 'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', @@ -148,7 +168,13 @@ class LivestreamOriginalIE(InfoExtractor): # rtmp 'skip_download': True, }, - } + }, { + 'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3', + 'info_dict': { + 'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3', + }, + 'playlist_mincount': 4, + }] def _extract_video(self, user, video_id): api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id) @@ -171,15 +197,19 @@ class LivestreamOriginalIE(InfoExtractor): def _extract_folder(self, url, folder_id): webpage = self._download_webpage(url, folder_id) - urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage)) + paths = orderedSet(re.findall( + r'''(?x)(?: + <li\s+class="folder">\s*<a\s+href="| + <a\s+href="(?=https?://livestre\.am/) + )([^"]+)"''', webpage)) return { '_type': 'playlist', 'id': folder_id, 'entries': [{ '_type': 'url', - 'url': video_url, - } for video_url in urls], + 'url': compat_urlparse.urljoin(url, p), + } for p in paths], } def _real_extract(self, url): diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 6436c05a3..1a896b536 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -9,6 +9,7 @@ from ..utils import ( compat_urllib_request, determine_ext, ExtractorError, + int_or_none, ) @@ -83,6 +84,21 @@ class MetacafeIE(InfoExtractor): 'skip_download': True, }, }, + # Movieclips.com video + { + 'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/', + 'info_dict': { + 'id': 'mv-Wy7ZU', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.', + 'uploader': 'movie_trailers', + 'duration': 176, + }, + 'params': { + 'skip_download': 'requires rtmpdump', + } + } ] def report_disclaimer(self): @@ -134,6 +150,7 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) + video_url = None mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse.unquote(mobj.group(1)) @@ -146,16 +163,17 @@ class MetacafeIE(InfoExtractor): else: gdaKey = mobj.group(1) video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: + if video_url is None: mobj = re.search(r'<video src="([^"]+)"', webpage) if mobj: video_url = mobj.group(1) video_ext = 'mp4' - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - raise ExtractorError('Unable to extract media URL') - vardict = compat_parse_qs(mobj.group(1)) + if video_url is None: + flashvars = self._search_regex( + r' name="flashvars" value="(.*?)"', webpage, 'flashvars', + default=None) + if flashvars: + vardict = compat_parse_qs(flashvars) if 'mediaData' not in vardict: raise ExtractorError('Unable to extract media URL') mobj = re.search( @@ -165,26 +183,68 @@ class MetacafeIE(InfoExtractor): mediaURL = mobj.group('mediaURL').replace('\\/', '/') video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) video_ext = determine_ext(video_url) - - video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title') + if video_url is None: + player_url = self._search_regex( + r"swfobject\.embedSWF\('([^']+)'", + webpage, 'config URL', default=None) + if player_url: + config_url = self._search_regex( + r'config=(.+)$', player_url, 'config URL') + config_doc = self._download_xml( + config_url, video_id, + note='Downloading video config') + smil_url = config_doc.find('.//properties').attrib['smil_file'] + smil_doc = self._download_xml( + smil_url, video_id, + note='Downloading SMIL document') + base_url = smil_doc.find('./head/meta').attrib['base'] + video_url = [] + for vn in smil_doc.findall('.//video'): + br = int(vn.attrib['system-bitrate']) + play_path = vn.attrib['src'] + video_url.append({ + 'format_id': 'smil-%d' % br, + 'url': base_url, + 'play_path': play_path, + 'page_url': url, + 'player_url': player_url, + 'ext': play_path.partition(':')[0], + }) + + if video_url is None: + raise ExtractorError('Unsupported video type') + + video_title = self._html_search_regex( + r'(?im)<title>(.*) - Video</title>', webpage, 'title') description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) video_uploader = self._html_search_regex( r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', webpage, 'uploader nickname', fatal=False) + duration = int_or_none( + self._html_search_meta('video:duration', webpage)) + + age_limit = ( + 18 + if re.search(r'"contentRating":"restricted"', webpage) + else 0) - if re.search(r'"contentRating":"restricted"', webpage) is not None: - age_limit = 18 + if isinstance(video_url, list): + formats = video_url else: - age_limit = 0 + formats = [{ + 'url': video_url, + 'ext': video_ext, + }] + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, 'description': description, 'uploader': video_uploader, 'title': video_title, - 'thumbnail':thumbnail, - 'ext': video_ext, + 'thumbnail': thumbnail, 'age_limit': age_limit, + 'formats': formats, + 'duration': duration, } diff --git a/youtube_dl/extractor/ministrygrid.py b/youtube_dl/extractor/ministrygrid.py new file mode 100644 index 000000000..949ad11db --- /dev/null +++ b/youtube_dl/extractor/ministrygrid.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + smuggle_url, +) + + +class MinistryGridIE(InfoExtractor): + _VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])' + + _TEST = { + 'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers', + 'md5': '844be0d2a1340422759c2a9101bab017', + 'info_dict': { + 'id': '3453494717001', + 'ext': 'mp4', + 'title': 'The Gospel by Numbers', + 'description': 'Coming soon from T4G 2014!', + 'uploader': 'LifeWay Christian Resources (MG)', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + portlets_json = self._search_regex( + r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list') + portlets = json.loads(portlets_json) + pl_id = self._search_regex( + r'<!--\s*p_l_id - ([0-9]+)<br>', webpage, 'p_l_id') + + for i, portlet in enumerate(portlets): + portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet) + portlet_code = self._download_webpage( + portlet_url, video_id, + note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)), + fatal=False) + video_iframe_url = self._search_regex( + r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe', + default=None) + if video_iframe_url: + surl = smuggle_url( + video_iframe_url, {'force_videoid': video_id}) + return { + '_type': 'url', + 'id': video_id, + 'url': surl, + } + + raise ExtractorError('Could not find video iframe in any portlets') diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py new file mode 100644 index 000000000..979f3d692 --- /dev/null +++ b/youtube_dl/extractor/mitele.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + get_element_by_attribute, + parse_duration, + strip_jsonp, +) + + +class MiTeleIE(InfoExtractor): + IE_NAME = 'mitele.es' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + + _TEST = { + 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', + 'md5': '6a75fe9d0d3275bead0cb683c616fddb', + 'info_dict': { + 'id': '0fce117d', + 'ext': 'mp4', + 'title': 'Programa 144 - Tor, la web invisible', + 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', + 'display_id': 'programa-144', + 'duration': 2913, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + episode = mobj.group('episode') + webpage = self._download_webpage(url, episode) + embed_data_json = self._search_regex( + r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', + flags=re.DOTALL + ).replace('\'', '"') + embed_data = json.loads(embed_data_json) + + info_url = 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, + transform_source=strip_jsonp + ) + + return { + 'id': embed_data['videoId'], + 'display_id': episode, + 'title': info_el.find('title').text, + 'url': token_info['tokenizedUrl'], + 'description': get_element_by_attribute('class', 'text', webpage), + 'thumbnail': info_el.find('thumb').text, + 'duration': parse_duration(info_el.find('duration').text), + } diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 5f64e7bd0..520f27fca 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + HEADRequest, int_or_none, parse_iso8601, ) @@ -38,7 +39,7 @@ class MixcloudIE(InfoExtractor): try: # We only want to know if the request succeed # don't download the whole file - self._request_webpage(url, None, False) + self._request_webpage(HEADRequest(url), None, False) return url except ExtractorError: url = None diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py index 37c72bc53..bfdb462eb 100644 --- a/youtube_dl/extractor/mlb.py +++ b/youtube_dl/extractor/mlb.py @@ -11,7 +11,7 @@ from ..utils import ( class MLBIE(InfoExtractor): - _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)' + _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?P<id>n?\d+)' _TESTS = [ { 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', @@ -69,6 +69,10 @@ class MLBIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', }, }, + { + 'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb', + 'only_matching': True, + }, ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/moevideo.py b/youtube_dl/extractor/moevideo.py new file mode 100644 index 000000000..2ff79b9b8 --- /dev/null +++ b/youtube_dl/extractor/moevideo.py @@ -0,0 +1,112 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + int_or_none, +) + + +class MoeVideoIE(InfoExtractor): + IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net' + _VALID_URL = r'''(?x) + https?://(?P<host>(?:www\.)? + (?:(?:moevideo|playreplay|videochart)\.net))/ + (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)''' + _API_URL = 'http://api.letitbit.net/' + _API_KEY = 'tVL0gjqo5' + _TESTS = [ + { + 'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29', + 'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a', + 'info_dict': { + 'id': '00297.0036103fe3d513ef27915216fd29', + 'ext': 'flv', + 'title': 'Sink cut out machine', + 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8', + 'thumbnail': 're:^https?://.*\.jpg$', + 'width': 540, + 'height': 360, + 'duration': 179, + 'filesize': 17822500, + } + }, + { + 'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a', + 'md5': '74f0a014d5b661f0f0e2361300d1620e', + 'info_dict': { + 'id': '77107.7f325710a627383d40540d8e991a', + 'ext': 'flv', + 'title': 'Operacion Condor.', + 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3', + 'thumbnail': 're:^https?://.*\.jpg$', + 'width': 480, + 'height': 296, + 'duration': 6027, + 'filesize': 588257923, + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage( + 'http://%s/video/%s' % (mobj.group('host'), video_id), + video_id, 'Downloading webpage') + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + + r = [ + self._API_KEY, + [ + 'preview/flv_link', + { + 'uid': video_id, + }, + ], + ] + r_json = json.dumps(r) + post = compat_urllib_parse.urlencode({'r': r_json}) + req = compat_urllib_request.Request(self._API_URL, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + response = self._download_json(req, video_id) + if response['status'] != 'OK': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, response['data']), + expected=True + ) + item = response['data'][0] + video_url = item['link'] + duration = int_or_none(item['length']) + width = int_or_none(item['width']) + height = int_or_none(item['height']) + filesize = int_or_none(item['convert_size']) + + formats = [{ + 'format_id': 'sd', + 'http_headers': {'Range': 'bytes=0-'}, # Required to download + 'url': video_url, + 'width': width, + 'height': height, + 'filesize': filesize, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index b9430b09b..d658647e6 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -8,15 +10,17 @@ from ..utils import ( compat_urllib_parse, ) + class MofosexIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' + _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' _TEST = { - u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', - u'file': u'5018.mp4', - u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a', - u'info_dict': { - u"title": u"Japanese Teen Music Video", - u"age_limit": 18, + 'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', + 'md5': '1b2eb47ac33cc75d4a80e3026b613c5a', + 'info_dict': { + 'id': '5018', + 'ext': 'mp4', + 'title': 'Japanese Teen Music Video', + 'age_limit': 18, } } @@ -29,8 +33,8 @@ class MofosexIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url')) + video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url')) path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py new file mode 100644 index 000000000..90b460d65 --- /dev/null +++ b/youtube_dl/extractor/mojvideo.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_duration, +) + + +class MojvideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)' + _TEST = { + 'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906', + 'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7', + 'info_dict': { + 'id': '3d1ed4497707730b2906', + 'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic', + 'ext': 'mp4', + 'title': 'V avtu pred mano rdečelaska - Alfi Nipič', + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 242, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + # XML is malformed + playerapi = self._download_webpage( + 'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id) + + if '<error>true</error>' in playerapi: + error_desc = self._html_search_regex( + r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True) + + title = self._html_search_regex( + r'<title>([^<]+)</title>', playerapi, 'title') + video_url = self._html_search_regex( + r'<file>([^<]+)</file>', playerapi, 'video URL') + thumbnail = self._html_search_regex( + r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False) + duration = parse_duration(self._html_search_regex( + r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py new file mode 100644 index 000000000..456807dd1 --- /dev/null +++ b/youtube_dl/extractor/movieclips.py @@ -0,0 +1,78 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_str, + clean_html, +) + + +class MovieClipsIE(InfoExtractor): + _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?' + _TEST = { + 'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/', + 'info_dict': { + 'id': 'Wy7ZU', + 'display_id': 'my-week-with-marilyn-movie-do-you-love-me', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'md5:e86795bd332fe3cff461e7c8dc542acb', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + show_id = display_id or video_id + + config = self._download_xml( + 'http://config.movieclips.com/player/config/%s' % video_id, + show_id, 'Downloading player config') + + if config.find('./country-region').text == 'false': + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True) + + properties = config.find('./video/properties') + smil_file = properties.attrib['smil_file'] + + smil = self._download_xml(smil_file, show_id, 'Downloading SMIL') + base_url = smil.find('./head/meta').attrib['base'] + + formats = [] + for video in smil.findall('./body/switch/video'): + vbr = int(video.attrib['system-bitrate']) / 1000 + src = video.attrib['src'] + formats.append({ + 'url': base_url, + 'play_path': src, + 'ext': src.split(':')[0], + 'vbr': vbr, + 'format_id': '%dk' % vbr, + }) + + self._sort_formats(formats) + + title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title']) + description = clean_html(compat_str(properties.attrib['clip_description'])) + thumbnail = properties.attrib['image'] + categories = properties.attrib['clip_categories'].split(',') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + } diff --git a/youtube_dl/extractor/musicvault.py b/youtube_dl/extractor/musicvault.py new file mode 100644 index 000000000..ebb1eb8e9 --- /dev/null +++ b/youtube_dl/extractor/musicvault.py @@ -0,0 +1,76 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, +) + + +class MusicVaultIE(InfoExtractor): + _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html', + 'md5': '2cdbb3ae75f7fb3519821507d2fb3c15', + 'info_dict': { + 'id': '1010863', + 'ext': 'mp4', + 'uploader_id': 'the-allman-brothers-band', + 'title': 'Straight from the Heart', + 'duration': 244, + 'uploader': 'The Allman Brothers Band', + 'thumbnail': 're:^https?://.*/thumbnail/.*', + 'upload_date': '19811216', + 'location': 'Capitol Theatre (Passaic, NJ)', + 'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id) + + thumbnail = self._search_regex( + r'<meta itemprop="thumbnail" content="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + data_div = self._search_regex( + r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields') + uploader = self._html_search_regex( + r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False) + title = self._html_search_regex( + r'<h2.*?>(.*?)</h2>', data_div, 'title') + upload_date = unified_strdate(self._html_search_regex( + r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False)) + location = self._html_search_regex( + r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False) + + duration = parse_duration(self._html_search_meta('duration', webpage)) + + VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http' + kaltura_id = self._search_regex( + r'<div id="video-detail-player" data-kaltura-id="([^"]+)"', + webpage, 'kaltura ID') + video_url = VIDEO_URL_TEMPLATE % { + 'entry_id': kaltura_id, + 'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'), + 'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'), + } + + return { + 'id': mobj.group('id'), + 'url': video_url, + 'ext': 'mp4', + 'display_id': display_id, + 'uploader_id': mobj.group('uploader_id'), + 'thumbnail': thumbnail, + 'description': self._html_search_meta('description', webpage), + 'upload_date': upload_date, + 'location': location, + 'title': title, + 'uploader': uploader, + 'duration': duration, + } diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 633b42f72..78e650b2d 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -3,18 +3,23 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + remove_end, + parse_duration, +) class NBAIE(InfoExtractor): _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$' _TEST = { 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', - 'md5': u'c0edcfc37607344e2ff8f13c378c88a4', + 'md5': 'c0edcfc37607344e2ff8f13c378c88a4', 'info_dict': { 'id': '0021200253-okc-bkn-recap.nba', 'ext': 'mp4', - 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'title': 'Thunder vs. Nets', + 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', + 'duration': 181, }, } @@ -27,13 +32,18 @@ class NBAIE(InfoExtractor): video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' shortened_video_id = video_id.rpartition('/')[2] - title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '') + title = remove_end( + self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') + + description = self._og_search_description(webpage) + duration = parse_duration( + self._html_search_meta('duration', webpage, 'duration', fatal=False)) - description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False) return { 'id': shortened_video_id, 'url': video_url, 'title': title, 'description': description, + 'duration': duration, } diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 2edd806a3..ceda1dcc0 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -25,8 +27,8 @@ class NHLBaseInfoExtractor(InfoExtractor): 'path': initial_video_url.replace('.mp4', '_sd.mp4'), }) path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data - path_doc = self._download_xml(path_url, video_id, - u'Downloading final video url') + path_doc = self._download_xml( + path_url, video_id, 'Downloading final video url') video_url = path_doc.find('path').text join = compat_urlparse.urljoin @@ -43,17 +45,18 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): - IE_NAME = u'nhl.com' - _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)' + IE_NAME = 'nhl.com' + _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?:[?&])id=(?P<id>[0-9]+)' _TEST = { - u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', - u'file': u'453614.mp4', - u'info_dict': { - u'title': u'Quick clip: Weise 4-3 goal vs Flames', - u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.', - u'duration': 18, - u'upload_date': u'20131006', + 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', + 'info_dict': { + 'id': '453614', + 'ext': 'mp4', + 'title': 'Quick clip: Weise 4-3 goal vs Flames', + 'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.', + 'duration': 18, + 'upload_date': '20131006', }, } @@ -61,23 +64,23 @@ class NHLIE(NHLBaseInfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id - info_json = self._download_webpage(json_url, video_id, - u'Downloading info json') - info_json = self._fix_json(info_json) - info = json.loads(info_json)[0] - return self._extract_video(info) + data = self._download_json( + json_url, video_id, transform_source=self._fix_json) + return self._extract_video(data[0]) class NHLVideocenterIE(NHLBaseInfoExtractor): - IE_NAME = u'nhl.com:videocenter' - IE_DESC = u'NHL videocenter category' - _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?' - - @classmethod - def suitable(cls, url): - if NHLIE.suitable(url): - return False - return super(NHLVideocenterIE, cls).suitable(url) + IE_NAME = 'nhl.com:videocenter' + IE_DESC = 'NHL videocenter category' + _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' + _TEST = { + 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999', + 'info_dict': { + 'id': '999', + 'title': 'Highlights', + }, + 'playlist_count': 12, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -86,10 +89,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): cat_id = self._search_regex( [r'var defaultCatId = "(.+?)";', r'{statusIndex:0,index:0,.*?id:(.*?),'], - webpage, u'category id') + webpage, 'category id') playlist_title = self._html_search_regex( r'tab0"[^>]*?>(.*?)</td>', - webpage, u'playlist title', flags=re.DOTALL).lower().capitalize() + webpage, 'playlist title', flags=re.DOTALL).lower().capitalize() data = compat_urllib_parse.urlencode({ 'cid': cat_id, @@ -104,7 +107,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): response = self._fix_json(response) if not response.strip(): self._downloader.report_warning(u'Got an empty reponse, trying ' - u'adding the "newvideos" parameter') + 'adding the "newvideos" parameter') response = self._download_webpage(request_url + '&newvideos=true', playlist_title) response = self._fix_json(response) @@ -114,5 +117,5 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): '_type': 'playlist', 'title': playlist_title, 'id': cat_id, - 'entries': [self._extract_video(i) for i in videos], + 'entries': [self._extract_video(v) for v in videos], } diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index da203538d..959fdf590 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -5,7 +5,10 @@ import re from .common import InfoExtractor from ..utils import ( + compat_urllib_request, + compat_urllib_parse, ExtractorError, + clean_html, unified_strdate, compat_str, ) @@ -13,6 +16,8 @@ from ..utils import ( class NocoIE(InfoExtractor): _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)' + _LOGIN_URL = 'http://noco.tv/do.php' + _NETRC_MACHINE = 'noco' _TEST = { 'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/', @@ -30,6 +35,28 @@ class NocoIE(InfoExtractor): 'skip': 'Requires noco account', } + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'a': 'login', + 'cookie': '1', + 'username': username, + 'password': password, + } + request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8') + + login = self._download_json(request, None, 'Logging in as %s' % username) + + if 'erreur' in login: + raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py new file mode 100644 index 000000000..8c2c428fc --- /dev/null +++ b/youtube_dl/extractor/nosvideo.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + urlencode_postdata, + xpath_with_ns, +) + +_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'}) +_find = lambda el, p: el.find(_x(p)).text.strip() + + +class NosVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \ + '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?' + _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml' + _FILE_DELETED_REGEX = r'<b>File Not Found</b>' + _TEST = { + 'url': 'http://nosvideo.com/?v=mu8fle7g7rpq', + 'md5': '6124ed47130d8be3eacae635b071e6b6', + 'info_dict': { + 'id': 'mu8fle7g7rpq', + 'ext': 'mp4', + 'title': 'big_buck_bunny_480p_surround-fix.avi.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + fields = { + 'id': video_id, + 'op': 'download1', + 'method_free': 'Continue to Video', + } + req = compat_urllib_request.Request(url, urlencode_postdata(fields)) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage(req, video_id, + 'Downloading download page') + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID') + playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id) + playlist = self._download_xml(playlist_url, video_id) + + track = playlist.find(_x('.//xspf:track')) + title = _find(track, './xspf:title') + url = _find(track, './xspf:file') + thumbnail = _find(track, './xspf:image') + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index 1c5e9401f..6b2f3f55a 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,3 +1,4 @@ +# encoding: utf-8 from __future__ import unicode_literals import re @@ -8,19 +9,34 @@ from ..utils import ExtractorError class NownessIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' - - _TEST = { - 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'md5': '068bc0202558c2e391924cb8cc470676', - 'info_dict': { - 'id': '2520295746001', - 'ext': 'mp4', - 'description': 'Candor: The Art of Gesticulation', - 'uploader': 'Nowness', - 'title': 'Candor: The Art of Gesticulation', - } - } + _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' + + _TESTS = [ + { + 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', + 'md5': '068bc0202558c2e391924cb8cc470676', + 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', + 'title': 'Candor: The Art of Gesticulation', + 'description': 'Candor: The Art of Gesticulation', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + { + 'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr', + 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', + 'info_dict': { + 'id': '3716354522001', + 'ext': 'mp4', + 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 12e85a716..902d62944 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( unified_strdate, + qualities, ) @@ -17,7 +18,7 @@ class NPOIE(InfoExtractor): 'md5': '4b3f9c429157ec4775f2c9cb7b911016', 'info_dict': { 'id': 'VPWON_1220719', - 'ext': 'mp4', + 'ext': 'm4v', 'title': 'Nieuwsuur', 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', 'upload_date': '20140622', @@ -39,24 +40,32 @@ class NPOIE(InfoExtractor): video_id, note='Downloading token' ) - token = self._search_regex(r'npoplayer.token = "(.+?)"', token_page, 'token') - streams_info = self._download_json( - 'http://ida.omroep.nl/odi/?prid=%s&puboptions=h264_std&adaptive=yes&token=%s' % (video_id, token), - video_id - ) + token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token') - stream_info = self._download_json( - streams_info['streams'][0] + '&type=json', - video_id, - 'Downloading stream info' - ) + formats = [] + quality = qualities(['adaptive', 'h264_sb', 'h264_bb', 'h264_std']) + for format_id in metadata['pubopties']: + streams_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 streams info' % format_id) + stream_info = self._download_json( + streams_info['streams'][0] + '&type=json', + video_id, 'Downloading %s stream info' % format_id) + if format_id == 'adaptive': + formats.extend(self._extract_m3u8_formats(stream_info['url'], video_id)) + else: + formats.append({ + 'url': stream_info['url'], + 'format_id': format_id, + 'quality': quality(format_id), + }) + self._sort_formats(formats) return { 'id': video_id, 'title': metadata['titel'], - 'ext': 'mp4', - 'url': stream_info['url'], 'description': metadata['info'], 'thumbnail': metadata['images'][-1]['url'], 'upload_date': unified_strdate(metadata['gidsdatum']), + 'formats': formats, } diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 280328b78..58ec81f91 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -38,7 +38,7 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( request, video_id, 'Downloading %s page' % format_id) video_url = self._html_search_regex( - r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False) + r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False) if not video_url: continue formats.append({ @@ -49,19 +49,24 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') title = self._html_search_regex( - r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip() - thumbnail = self._html_search_regex( - r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', - webpage, 'thumbnail URL', fatal=False) + [r'<span title="([^"]+)">', + r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( - r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False)) + r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_regex( - r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False)) + r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) return { 'id': video_id, 'title': title, - 'thumbnail': 'http://m.nuvid.com%s' % thumbnail, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, 'duration': duration, 'upload_date': upload_date, 'age_limit': 18, diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py deleted file mode 100644 index 38971ab4d..000000000 --- a/youtube_dl/extractor/oe1.py +++ /dev/null @@ -1,40 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import calendar -import datetime -import re - -from .common import InfoExtractor - -# audios on oe1.orf.at are only available for 7 days, so we can't -# add tests. - - -class OE1IE(InfoExtractor): - IE_DESC = 'oe1.orf.at' - _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') - - data = self._download_json( - 'http://oe1.orf.at/programm/%s/konsole' % show_id, - show_id - ) - - timestamp = datetime.datetime.strptime('%s %s' % ( - data['item']['day_label'], - data['item']['time'] - ), '%d.%m.%Y %H:%M') - unix_timestamp = calendar.timegm(timestamp.utctimetuple()) - - return { - 'id': show_id, - 'title': data['item']['title'], - 'url': data['item']['url_stream'], - 'ext': 'mp3', - 'description': data['item'].get('info'), - 'timestamp': unix_timestamp - } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 13f12824c..2044e107e 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -3,23 +3,38 @@ import re import json from .common import InfoExtractor -from ..utils import unescapeHTML +from ..utils import ( + unescapeHTML, + ExtractorError, +) class OoyalaIE(InfoExtractor): _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' - _TEST = { - # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video - 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', - 'info_dict': { - 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'ext': 'mp4', - 'title': 'Explaining Data Recovery from Hard Drives and SSDs', - 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + _TESTS = [ + { + # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video + 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', + 'info_dict': { + 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'ext': 'mp4', + 'title': 'Explaining Data Recovery from Hard Drives and SSDs', + 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + }, + }, { + # Only available for ipad + 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'md5': '4b9754921fddb68106e48c142e2a01e6', + 'info_dict': { + 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'ext': 'mp4', + 'title': 'Simulation Overview - Levels of Simulation', + 'description': '', + }, }, - } + ] @staticmethod def _url_for_embed_code(embed_code): @@ -47,13 +62,30 @@ class OoyalaIE(InfoExtractor): player = self._download_webpage(player_url, embedCode) mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', player, 'mobile player url') - mobile_player = self._download_webpage(mobile_url, embedCode) - videos_info = self._search_regex( - r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', - mobile_player, 'info').replace('\\"','"') - videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"') + # Looks like some videos are only available for particular devices + # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0 + # is only available for ipad) + # Working around with fetching URLs for all the devices found starting with 'unknown' + # until we succeed or eventually fail for each device. + devices = re.findall(r'device\s*=\s*"([^"]+)";', player) + devices.remove('unknown') + devices.insert(0, 'unknown') + for device in devices: + mobile_player = self._download_webpage( + '%s&device=%s' % (mobile_url, device), embedCode, + 'Downloading mobile player JS for %s device' % device) + videos_info = self._search_regex( + r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', + mobile_player, 'info', fatal=False, default=None) + if videos_info: + break + if not videos_info: + raise ExtractorError('Unable to extract info') + videos_info = videos_info.replace('\\"', '"') + videos_more_info = self._search_regex( + r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"') videos_info = json.loads(videos_info) - videos_more_info =json.loads(videos_more_info) + videos_more_info = json.loads(videos_more_info) if videos_more_info.get('lineup'): videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 03421d1d5..011e6be13 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals import json import re +import calendar +import datetime from .common import InfoExtractor from ..utils import ( @@ -12,7 +14,9 @@ from ..utils import ( ) -class ORFIE(InfoExtractor): +class ORFTVthekIE(InfoExtractor): + IE_NAME = 'orf:tvthek' + IE_DESC = 'ORF TVthek' _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)' _TEST = { @@ -105,3 +109,73 @@ class ORFIE(InfoExtractor): 'entries': entries, 'id': playlist_id, } + + +# Audios on ORF radio are only available for 7 days, so we can't add tests. + + +class ORFOE1IE(InfoExtractor): + IE_NAME = 'orf:oe1' + IE_DESC = 'Radio Österreich 1' + _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('id') + + data = self._download_json( + 'http://oe1.orf.at/programm/%s/konsole' % show_id, + show_id + ) + + timestamp = datetime.datetime.strptime('%s %s' % ( + data['item']['day_label'], + data['item']['time'] + ), '%d.%m.%Y %H:%M') + unix_timestamp = calendar.timegm(timestamp.utctimetuple()) + + return { + 'id': show_id, + 'title': data['item']['title'], + 'url': data['item']['url_stream'], + 'ext': 'mp3', + 'description': data['item'].get('info'), + 'timestamp': unix_timestamp + } + + +class ORFFM4IE(InfoExtractor): + IE_DESC = 'orf:fm4' + IE_DESC = 'radio FM4' + _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_date = mobj.group('date') + show_id = mobj.group('show') + + data = self._download_json( + 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), + show_id + ) + + def extract_entry_dict(info, title, subtitle): + return { + 'id': info['loopStreamId'].replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'], + 'title': title, + 'description': subtitle, + 'duration': (info['end'] - info['start']) / 1000, + 'timestamp': info['start'] / 1000, + 'ext': 'mp3' + } + + entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + + return { + '_type': 'playlist', + 'id': show_id, + 'title': data['title'], + 'description': data['subtitle'], + 'entries': entries + }
\ No newline at end of file diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py new file mode 100644 index 000000000..5429592a7 --- /dev/null +++ b/youtube_dl/extractor/patreon.py @@ -0,0 +1,100 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, +) + + +class PatreonIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(.+)' + _TESTS = [ + { + 'url': 'http://www.patreon.com/creation?hid=743933', + 'md5': 'e25505eec1053a6e6813b8ed369875cc', + 'info_dict': { + 'id': '743933', + 'ext': 'mp3', + 'title': 'Episode 166: David Smalley of Dogma Debate', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + ] + + # Currently Patreon exposes download URL via hidden CSS, so login is not + # needed. Keeping this commented for when this inevitably changes. + ''' + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'redirectUrl': 'http://www.patreon.com/', + 'email': username, + 'password': password, + } + + request = compat_urllib_request.Request( + 'https://www.patreon.com/processLogin', + compat_urllib_parse.urlencode(login_form).encode('utf-8') + ) + login_page = self._download_webpage(request, None, note='Logging in as %s' % username) + + if re.search(r'onLoginFailed', login_page): + raise ExtractorError('Unable to login, incorrect username and/or password', expected=True) + + def _real_initialize(self): + self._login() + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage).strip() + + attach_fn = self._html_search_regex( + r'<div class="attach"><a target="_blank" href="([^"]+)">', + webpage, 'attachment URL', default=None) + if attach_fn is not None: + video_url = 'http://www.patreon.com' + attach_fn + thumbnail = self._og_search_thumbnail(webpage) + uploader = self._html_search_regex( + r'<strong>(.*?)</strong> is creating', webpage, 'uploader') + else: + playlist_js = self._search_regex( + r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])', + webpage, 'playlist JSON') + playlist_json = js_to_json(playlist_js) + playlist = json.loads(playlist_json) + data = playlist[0] + video_url = self._proto_relative_url(data['mp3']) + thumbnail = self._proto_relative_url(data.get('cover')) + uploader = data.get('artist') + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'title': title, + 'uploader': uploader, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 64cded707..2adfde909 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -20,27 +20,74 @@ class PBSIE(InfoExtractor): ) ''' - _TEST = { - 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', - 'md5': 'ce1888486f0908d555a8093cac9a7362', - 'info_dict': { - 'id': '2365006249', - 'ext': 'mp4', - 'title': 'A More Perfect Union', - 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', - 'duration': 3190, + _TESTS = [ + { + 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', + 'md5': 'ce1888486f0908d555a8093cac9a7362', + 'info_dict': { + 'id': '2365006249', + 'ext': 'mp4', + 'title': 'A More Perfect Union', + 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', + 'duration': 3190, + }, + }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/', + 'md5': '143c98aa54a346738a3d78f54c925321', + 'info_dict': { + 'id': '2365297690', + 'ext': 'mp4', + 'title': 'Losing Iraq', + 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e', + 'duration': 5050, + }, + }, + { + 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', + 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', + 'info_dict': { + 'id': '2201174722', + 'ext': 'mp4', + 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', + 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', + 'duration': 801, + }, }, - } + { + 'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/', + 'md5': 'c62859342be2a0358d6c9eb306595978', + 'info_dict': { + 'id': '2365297708', + 'ext': 'mp4', + 'description': 'md5:68d87ef760660eb564455eb30ca464fe', + 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full', + 'duration': 6559, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + ] - def _real_extract(self, url): + def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') display_id = presumptive_id if presumptive_id: webpage = self._download_webpage(url, display_id) + + MEDIA_ID_REGEXES = [ + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed + r'class="coveplayerid">([^<]+)<', # coveplayer + ] + + media_id = self._search_regex( + MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) + if media_id: + return media_id, presumptive_id + url = self._search_regex( - r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', + r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', webpage, 'player URL') mobj = re.match(self._VALID_URL, url) @@ -57,6 +104,11 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id + return video_id, display_id + + def _real_extract(self, url): + video_id, display_id = self._extract_ids(url) + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py new file mode 100644 index 000000000..72df4d842 --- /dev/null +++ b/youtube_dl/extractor/playfm.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + ExtractorError, + float_or_none, + int_or_none, +) + + +class PlayFMIE(InfoExtractor): + IE_NAME = 'play.fm' + _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])' + + _TEST = { + 'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220', + 'md5': 'c505f8307825a245d0c7ad1850001f22', + 'info_dict': { + 'id': '137220', + 'ext': 'mp3', + 'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12', + 'uploader': 'Sven Tasnadi', + 'uploader_id': 'sventasnadi', + 'duration': 5627.428, + 'upload_date': '20140712', + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + upload_date = mobj.group('upload_date') + + rec_data = compat_urllib_parse.urlencode({'rec_id': video_id}) + req = compat_urllib_request.Request( + 'http://www.play.fm/flexRead/recording', data=rec_data) + req.add_header('Content-Type', 'application/x-www-form-urlencoded') + rec_doc = self._download_xml(req, video_id) + + error_node = rec_doc.find('./error') + if error_node is not None: + raise ExtractorError('An error occured: %s (code %s)' % ( + error_node.text, rec_doc.find('./status').text)) + + recording = rec_doc.find('./recording') + title = recording.find('./title').text + view_count = int_or_none(recording.find('./stats/playcount').text) + duration = float_or_none(recording.find('./duration').text, scale=1000) + thumbnail = recording.find('./image').text + + artist = recording.find('./artists/artist') + uploader = artist.find('./name').text + uploader_id = artist.find('./slug').text + + video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % ( + 'http:', recording.find('./url').text, + recording.find('./_class').text, recording.find('./file_id').text, + rec_doc.find('./uuid').text, video_id, + rec_doc.find('./jingle/file_id').text, + 'http%3A%2F%2Fwww.play.fm%2Fplayer', + ) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'filesize': int_or_none(recording.find('./size').text), + 'title': title, + 'upload_date': upload_date, + 'view_count': view_count, + 'duration': duration, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + } diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py index 35dc5a9ff..04bd3d979 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -9,15 +11,16 @@ from ..utils import ( class PornotubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' _TEST = { - u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', - u'file': u'1689755.flv', - u'md5': u'374dd6dcedd24234453b295209aa69b6', - u'info_dict': { - u"upload_date": u"20090708", - u"title": u"Marilyn-Monroe-Bathing", - u"age_limit": 18 + 'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', + 'md5': '374dd6dcedd24234453b295209aa69b6', + 'info_dict': { + 'id': '1689755', + 'ext': 'flv', + 'upload_date': '20090708', + 'title': 'Marilyn-Monroe-Bathing', + 'age_limit': 18 } } @@ -32,22 +35,22 @@ class PornotubeIE(InfoExtractor): # Get the video URL VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') + video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') video_url = compat_urllib_parse.unquote(video_url) #Get the uploaded date VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) - if upload_date: upload_date = unified_strdate(upload_date) + upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) + if upload_date: + upload_date = unified_strdate(upload_date) age_limit = self._rta_search(webpage) - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'age_limit': age_limit} - - return [info] + return { + 'id': video_id, + 'url': video_url, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/pornoxo.py b/youtube_dl/extractor/pornoxo.py new file mode 100644 index 000000000..202f58673 --- /dev/null +++ b/youtube_dl/extractor/pornoxo.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + str_to_int, +) + + +class PornoXOIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html' + _TEST = { + 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html', + 'md5': '582f28ecbaa9e6e24cb90f50f524ce87', + 'info_dict': { + 'id': '7564', + 'ext': 'flv', + 'title': 'Striptease From Sexy Secretary!', + 'description': 'Striptease From Sexy Secretary!', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title') + + description = self._html_search_regex( + r'<meta name="description" content="([^"]+)\s*featuring', + webpage, 'description', fatal=False) + + thumbnail = self._html_search_regex( + r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) + + view_count = str_to_int(self._html_search_regex( + r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False)) + + categories_str = self._html_search_regex( + r'<meta name="description" content=".*featuring\s*([^"]+)"', + webpage, 'categories', fatal=False) + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py new file mode 100644 index 000000000..463e85501 --- /dev/null +++ b/youtube_dl/extractor/promptfile.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class PromptFileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' + _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]' + _TEST = { + 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', + 'md5': 'd1451b6302da7215485837aaea882c4c', + 'info_dict': { + 'id': 'D21B4746E9-F01462F0FF', + 'ext': 'mp4', + 'title': 'Birds.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + fields = dict(re.findall(r'''(?x)type="hidden"\s+ + name="(.+?)"\s+ + value="(.*?)" + ''', webpage)) + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL') + title = self._html_search_regex( + r'<span.+title="([^"]+)">', webpage, 'title') + thumbnail = self._html_search_regex( + r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"', + webpage, 'thumbnail', fatal=False, flags=re.DOTALL) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': determine_ext(title), + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/reverbnation.py b/youtube_dl/extractor/reverbnation.py index 49cf427a1..ec7e7df7b 100644 --- a/youtube_dl/extractor/reverbnation.py +++ b/youtube_dl/extractor/reverbnation.py @@ -1,23 +1,23 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import strip_jsonp +from ..utils import str_or_none class ReverbNationIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$' _TESTS = [{ 'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa', - 'file': '16965047.mp3', 'md5': '3da12ebca28c67c111a7f8b262d3f7a7', 'info_dict': { + "id": "16965047", + "ext": "mp3", "title": "MONA LISA", "uploader": "ALKILADOS", - "uploader_id": 216429, - "thumbnail": "//gp1.wac.edgecastcdn.net/802892/production_public/Photo/13761700/image/1366002176_AVATAR_MONA_LISA.jpg" + "uploader_id": "216429", + "thumbnail": "re:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$" }, }] @@ -26,10 +26,8 @@ class ReverbNationIE(InfoExtractor): song_id = mobj.group('id') api_res = self._download_json( - 'https://api.reverbnation.com/song/%s?callback=api_response_5&_=%d' - % (song_id, int(time.time() * 1000)), + 'https://api.reverbnation.com/song/%s' % song_id, song_id, - transform_source=strip_jsonp, note='Downloading information of song %s' % song_id ) @@ -38,8 +36,9 @@ class ReverbNationIE(InfoExtractor): 'title': api_res.get('name'), 'url': api_res.get('url'), 'uploader': api_res.get('artist', {}).get('name'), - 'uploader_id': api_res.get('artist', {}).get('id'), - 'thumbnail': api_res.get('image', api_res.get('thumbnail')), + 'uploader_id': str_or_none(api_res.get('artist', {}).get('id')), + 'thumbnail': self._proto_relative_url( + api_res.get('image', api_res.get('thumbnail'))), 'ext': 'mp3', 'vcodec': 'none', } diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py new file mode 100644 index 000000000..0ab1eb69c --- /dev/null +++ b/youtube_dl/extractor/rtlnl.py @@ -0,0 +1,67 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class RtlXlIE(InfoExtractor): + IE_NAME = 'rtlxl.nl' + _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' + + _TEST = { + 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', + 'md5': 'cc16baa36a6c169391f0764fa6b16654', + 'info_dict': { + 'id': '6e4203a6-0a5e-3596-8424-c599a59e0677', + 'ext': 'mp4', + 'title': 'RTL Nieuws - Laat', + 'description': 'md5:6b61f66510c8889923b11f2778c72dc5', + 'timestamp': 1408051800, + 'upload_date': '20140814', + 'duration': 576.880, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + uuid = mobj.group('uuid') + + info = self._download_json( + 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid, + uuid) + + material = info['material'][0] + episode_info = info['episodes'][0] + + progname = info['abstracts'][0]['name'] + subtitle = material['title'] or info['episodes'][0]['name'] + + videopath = material['videopath'] + f4m_url = 'http://manifest.us.rtl.nl' + videopath + + formats = self._extract_f4m_formats(f4m_url, uuid) + + video_urlpart = videopath.split('/flash/')[1][:-4] + PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4' + + formats.extend([ + { + 'url': PG_URL_TEMPLATE % ('a2m', video_urlpart), + 'format_id': 'pg-sd', + }, + { + 'url': PG_URL_TEMPLATE % ('a3m', video_urlpart), + 'format_id': 'pg-hd', + } + ]) + + return { + 'id': uuid, + 'title': '%s - %s' % (progname, subtitle), + 'formats': formats, + 'timestamp': material['original_date'], + 'description': episode_info['synopsis'], + 'duration': parse_duration(material.get('duration')), + } diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index c2228b2f0..4dd35a47b 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -1,21 +1,66 @@ # encoding: utf-8 from __future__ import unicode_literals -import re import base64 +import re +import time from .common import InfoExtractor from ..utils import ( struct_unpack, + remove_end, ) +def _decrypt_url(png): + encrypted_data = base64.b64decode(png) + text_index = encrypted_data.find(b'tEXt') + text_chunk = encrypted_data[text_index - 4:] + length = struct_unpack('!I', text_chunk[:4])[0] + # Use bytearray to get integers when iterating in both python 2.x and 3.x + data = bytearray(text_chunk[8:8 + length]) + data = [chr(b) for b in data if b != 0] + hash_index = data.index('#') + alphabet_data = data[:hash_index] + url_data = data[hash_index + 1:] + + alphabet = [] + e = 0 + d = 0 + for l in alphabet_data: + if d == 0: + alphabet.append(l) + d = e = (e + 1) % 4 + else: + d -= 1 + url = '' + f = 0 + e = 3 + b = 1 + for letter in url_data: + if f == 0: + l = int(letter) * 10 + f = 1 + else: + if e == 0: + l += int(letter) + url += alphabet[l] + e = (b + 3) % 4 + f = 0 + b += 1 + else: + e -= 1 + + return url + + + class RTVEALaCartaIE(InfoExtractor): IE_NAME = 'rtve.es:alacarta' IE_DESC = 'RTVE a la carta' _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43', 'info_dict': { @@ -23,48 +68,15 @@ class RTVEALaCartaIE(InfoExtractor): 'ext': 'mp4', 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', }, - } - - def _decrypt_url(self, png): - encrypted_data = base64.b64decode(png) - text_index = encrypted_data.find(b'tEXt') - text_chunk = encrypted_data[text_index-4:] - length = struct_unpack('!I', text_chunk[:4])[0] - # Use bytearray to get integers when iterating in both python 2.x and 3.x - data = bytearray(text_chunk[8:8+length]) - data = [chr(b) for b in data if b != 0] - hash_index = data.index('#') - alphabet_data = data[:hash_index] - url_data = data[hash_index+1:] - - alphabet = [] - e = 0 - d = 0 - for l in alphabet_data: - if d == 0: - alphabet.append(l) - d = e = (e + 1) % 4 - else: - d -= 1 - url = '' - f = 0 - e = 3 - b = 1 - for letter in url_data: - if f == 0: - l = int(letter)*10 - f = 1 - else: - if e == 0: - l += int(letter) - url += alphabet[l] - e = (b + 3) % 4 - f = 0 - b += 1 - else: - e -= 1 - - return url + }, { + 'note': 'Live stream', + 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/', + 'info_dict': { + 'id': '1694255', + 'ext': 'flv', + 'title': 'TODO', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -74,11 +86,57 @@ class RTVEALaCartaIE(InfoExtractor): video_id)['page']['items'][0] png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id png = self._download_webpage(png_url, video_id, 'Downloading url information') - video_url = self._decrypt_url(png) + video_url = _decrypt_url(png) return { 'id': video_id, 'title': info['title'], 'url': video_url, - 'thumbnail': info['image'], + 'thumbnail': info.get('image'), + 'page_url': url, + } + + +class RTVELiveIE(InfoExtractor): + IE_NAME = 'rtve.es:live' + IE_DESC = 'RTVE.es live streams' + _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)' + + _TESTS = [{ + 'url': 'http://www.rtve.es/noticias/directo-la-1/', + 'info_dict': { + 'id': 'directo-la-1', + 'ext': 'flv', + 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$', + }, + 'params': { + 'skip_download': 'live stream', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + start_time = time.gmtime() + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_url = self._search_regex( + r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL') + title = remove_end(self._og_search_title(webpage), ' en directo') + title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time) + + vidplayer_id = self._search_regex( + r' id="vidplayer([0-9]+)"', webpage, 'internal video ID') + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id + png = self._download_webpage(png_url, video_id, 'Downloading url information') + video_url = _decrypt_url(png) + + return { + 'id': video_id, + 'ext': 'flv', + 'title': title, + 'url': video_url, + 'app': 'rtve-live-live?ovpfv=2.1.2', + 'player_url': player_url, + 'rtmp_live': True, } diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 357edbbda..0c8790da2 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -74,6 +74,13 @@ class RutubeChannelIE(InfoExtractor): IE_NAME = 'rutube:channel' IE_DESC = 'Rutube channels' _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://rutube.ru/tags/video/1800/', + 'info_dict': { + 'id': '1800', + }, + 'playlist_mincount': 68, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json' @@ -101,6 +108,7 @@ class RutubeMovieIE(RutubeChannelIE): IE_NAME = 'rutube:movie' IE_DESC = 'Rutube movies' _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)' + _TESTS = [] _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json' _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' @@ -119,5 +127,12 @@ class RutubePersonIE(RutubeChannelIE): IE_NAME = 'rutube:person' IE_DESC = 'Rutube person videos' _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://rutube.ru/video/person/313878/', + 'info_dict': { + 'id': '313878', + }, + 'playlist_mincount': 37, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py index 6c5f5a680..f737b4e5f 100644 --- a/youtube_dl/extractor/rutv.py +++ b/youtube_dl/extractor/rutv.py @@ -100,7 +100,7 @@ class RUTVIE(InfoExtractor): return mobj.group('url') mobj = re.search( - r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>http://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)', + r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)', webpage) if mobj: return mobj.group('url') diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py new file mode 100644 index 000000000..34058fd4b --- /dev/null +++ b/youtube_dl/extractor/sbs.py @@ -0,0 +1,56 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import json +import re +from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) + + +class SBSIE(InfoExtractor): + IE_DESC = 'sbs.com.au' + _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/single/(?P<id>[0-9]+)/' + + _TESTS = [{ + # Original URL is handled by the generic IE which finds the iframe: + # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation + 'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed', + 'md5': '3150cf278965eeabb5b4cea1c963fe0a', + 'info_dict': { + 'id': '320403011771', + 'ext': 'flv', + 'title': 'Dingo Conservation', + 'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction', + 'thumbnail': 're:http://.*\.jpg', + }, + 'add_ies': ['generic'], + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + release_urls_json = js_to_json(self._search_regex( + r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', + webpage, '')) + release_urls = json.loads(release_urls_json) + theplatform_url = ( + release_urls.get('progressive') or release_urls.get('standard')) + + title = remove_end(self._og_search_title(webpage), ' (The Feed)') + description = self._html_search_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': theplatform_url, + + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 8607482be..badba2ac6 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -17,11 +17,11 @@ class SharedIE(InfoExtractor): _TEST = { 'url': 'http://shared.sx/0060718775', - 'md5': '53e1c58fc3e777ae1dfe9e57ba2f9c72', + 'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'info_dict': { 'id': '0060718775', 'ext': 'mp4', - 'title': 'Big Buck Bunny Trailer', + 'title': 'Bmp4', }, } diff --git a/youtube_dl/extractor/sharesix.py b/youtube_dl/extractor/sharesix.py new file mode 100644 index 000000000..7531e8325 --- /dev/null +++ b/youtube_dl/extractor/sharesix.py @@ -0,0 +1,91 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + parse_duration, +) + + +class ShareSixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)' + _TESTS = [ + { + 'url': 'http://sharesix.com/f/OXjQ7Y6', + 'md5': '9e8e95d8823942815a7d7c773110cc93', + 'info_dict': { + 'id': 'OXjQ7Y6', + 'ext': 'mp4', + 'title': 'big_buck_bunny_480p_surround-fix.avi', + 'duration': 596, + 'width': 854, + 'height': 480, + }, + }, + { + 'url': 'http://sharesix.com/lfrwoxp35zdd', + 'md5': 'dd19f1435b7cec2d7912c64beeee8185', + 'info_dict': { + 'id': 'lfrwoxp35zdd', + 'ext': 'flv', + 'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv', + 'duration': 65, + 'width': 1280, + 'height': 720, + }, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + fields = { + 'method_free': 'Free' + } + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage(req, video_id, + 'Downloading video page') + + video_url = self._search_regex( + r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL') + title = self._html_search_regex( + r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title') + duration = parse_duration( + self._search_regex( + r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>', + webpage, + 'duration', + fatal=False + ) + ) + + m = re.search( + r'''(?xs)<dt>Width\sx\sHeight</dt>.+? + <dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''', + webpage + ) + width = height = None + if m: + width, height = int(m.group('width')), int(m.group('height')) + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'width': width, + 'height': height, + }] + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 13e7e71cb..9bd5defa7 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -267,6 +267,14 @@ class SmotriCommunityIE(InfoExtractor): IE_DESC = 'Smotri.com community videos' IE_NAME = 'smotri:community' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)' + _TEST = { + 'url': 'http://smotri.com/community/video/kommuna', + 'info_dict': { + 'id': 'kommuna', + 'title': 'КПРФ', + }, + 'playlist_mincount': 4, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -289,6 +297,14 @@ class SmotriUserIE(InfoExtractor): IE_DESC = 'Smotri.com user videos' IE_NAME = 'smotri:user' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)' + _TESTS = [{ + 'url': 'http://smotri.com/user/inspector', + 'info_dict': { + 'id': 'inspector', + 'title': 'Inspector', + }, + 'playlist_mincount': 9, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py index dc9f80550..c663e56d4 100644 --- a/youtube_dl/extractor/sockshare.py +++ b/youtube_dl/extractor/sockshare.py @@ -61,7 +61,10 @@ class SockshareIE(InfoExtractor): r'<a href="([^"]*)".+class="download_file_link"', webpage, 'file url') video_url = "http://www.sockshare.com" + video_url - title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title') + title = self._html_search_regex(( + r'<h1>(.+)<strong>', + r'var name = "([^"]+)";'), + webpage, 'title', default=None) thumbnail = self._html_search_regex( r'<img\s+src="([^"]*)".+?name="bg"', webpage, 'thumbnail') diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 097d0e418..b78aed7f0 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -28,7 +28,8 @@ class SoundcloudIE(InfoExtractor): _VALID_URL = r'''(?x)^(?:https?://)? (?:(?:(?:www\.|m\.)?soundcloud\.com/ (?P<uploader>[\w\d-]+)/ - (?!sets/)(?P<title>[\w\d-]+)/? + (?!sets/|likes/?(?:$|[?#])) + (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)) |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) @@ -221,13 +222,16 @@ class SoundcloudIE(InfoExtractor): class SoundcloudSetIE(SoundcloudIE): _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' IE_NAME = 'soundcloud:set' - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep', + 'info_dict': { + 'title': 'The Royal Concept EP', + }, + 'playlist_mincount': 6, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) # extract uploader (which is in the url) uploader = mobj.group(1) @@ -246,20 +250,32 @@ class SoundcloudSetIE(SoundcloudIE): self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message'])) return - self.report_extraction(full_title) - return {'_type': 'playlist', - 'entries': [self._extract_info_dict(track) for track in info['tracks']], - 'id': info['id'], - 'title': info['title'], - } + return { + '_type': 'playlist', + 'entries': [self._extract_info_dict(track) for track in info['tracks']], + 'id': info['id'], + 'title': info['title'], + } class SoundcloudUserIE(SoundcloudIE): _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$' IE_NAME = 'soundcloud:user' - - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'https://soundcloud.com/the-concept-band', + 'info_dict': { + 'id': '9615865', + 'title': 'The Royal Concept', + }, + 'playlist_mincount': 12 + }, { + 'url': 'https://soundcloud.com/the-concept-band/likes', + 'info_dict': { + 'id': '9615865', + 'title': 'The Royal Concept', + }, + 'playlist_mincount': 1, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -301,9 +317,18 @@ class SoundcloudUserIE(SoundcloudIE): class SoundcloudPlaylistIE(SoundcloudIE): _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)' IE_NAME = 'soundcloud:playlist' + _TESTS = [ - # it's in tests/test_playlists.py - _TESTS = [] + { + 'url': 'http://api.soundcloud.com/playlists/4110309', + 'info_dict': { + 'id': '4110309', + 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', + 'description': 're:.*?TILT Brass - Bowery Poetry Club', + }, + 'playlist_count': 6, + } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 340a38440..a3b89f751 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import compat_urlparse class SpiegelIE(InfoExtractor): @@ -82,3 +83,34 @@ class SpiegelIE(InfoExtractor): 'duration': duration, 'formats': formats, } + + +class SpiegelArticleIE(InfoExtractor): + _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html' + IE_NAME = 'Spiegel:Article' + IE_DESC = 'Articles on spiegel.de' + _TEST = { + 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', + 'info_dict': { + 'id': '1516455', + 'ext': 'mp4', + 'title': 'Faszination Badminton: Nennt es bloß nicht Federball', + 'description': 're:^Patrick Kämnitz gehört.{100,}', + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + video_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, + } diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py new file mode 100644 index 000000000..185353bef --- /dev/null +++ b/youtube_dl/extractor/sportdeutschland.py @@ -0,0 +1,96 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + parse_iso8601, +) + + +class SportDeutschlandIE(InfoExtractor): + _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])' + _TESTS = [{ + 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'info_dict': { + 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'ext': 'mp4', + 'title': 'LIVE: Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', + 'categories': ['Badminton'], + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 're:^Die Badminton-WM 2014 aus Kopenhagen LIVE', + 'timestamp': int, + 'upload_date': 're:^201408[23][0-9]$', + }, + 'params': { + 'skip_download': 'Live stream', + }, + }, { + 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', + 'info_dict': { + 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', + 'ext': 'mp4', + 'upload_date': '20140825', + 'description': 'md5:60a20536b57cee7d9a4ec005e8687504', + 'timestamp': 1408976060, + 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee', + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, + 'categories': ['Li-Ning Badminton WM 2014'], + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + sport_id = mobj.group('sport') + + api_url = 'http://splink.tv/api/permalinks/%s/%s' % ( + sport_id, video_id) + req = compat_urllib_request.Request(api_url, headers={ + 'Accept': 'application/vnd.vidibus.v2.html+json', + 'Referer': url, + }) + data = self._download_json(req, video_id) + + categories = list(data.get('section', {}).get('tags', {}).values()) + asset = data['asset'] + + formats = [] + smil_url = asset['video'] + if '.smil' in smil_url: + m3u8_url = smil_url.replace('.smil', '.m3u8') + formats.extend( + self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')) + + smil_doc = self._download_xml( + smil_url, video_id, note='Downloading SMIL metadata') + base_url = smil_doc.find('./head/meta').attrib['base'] + formats.extend([{ + 'format_id': 'rmtp', + 'url': base_url, + 'play_path': n.attrib['src'], + 'ext': 'flv', + 'preference': -100, + 'format_note': 'Seems to fail at example stream', + } for n in smil_doc.findall('./body/video')]) + else: + formats.append({'url': smil_url}) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'formats': formats, + 'title': asset['title'], + 'thumbnail': asset.get('image'), + 'description': asset.get('teaser'), + 'categories': categories, + 'view_count': asset.get('views'), + 'rtmp_live': asset.get('live'), + 'timestamp': parse_iso8601(asset.get('date')), + } + diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py new file mode 100644 index 000000000..7de3c9dd5 --- /dev/null +++ b/youtube_dl/extractor/sunporno.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, + qualities, + determine_ext, +) + + +class SunPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.sunporno.com/videos/807778/', + 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', + 'info_dict': { + 'id': '807778', + 'ext': 'flv', + 'title': 'md5:0a400058e8105d39e35c35e7c5184164', + 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 302, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) + + duration = parse_duration(self._search_regex( + r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) + + formats = [] + quality = qualities(['mp4', 'flv']) + for video_url in re.findall(r'<source src="([^"]+)"', webpage): + video_ext = determine_ext(video_url) + formats.append({ + 'url': video_url, + 'format_id': video_ext, + 'quality': quality(video_ext), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py index 6c688c520..5d9d70367 100644 --- a/youtube_dl/extractor/swrmediathek.py +++ b/youtube_dl/extractor/swrmediathek.py @@ -8,7 +8,7 @@ from ..utils import parse_duration class SWRMediathekIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/(?:content/)?player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' _TESTS = [{ 'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6', @@ -52,6 +52,20 @@ class SWRMediathekIE(InfoExtractor): 'uploader': 'SWR 2', 'uploader_id': '284670', } + }, { + 'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6', + 'md5': '881531487d0633080a8cc88d31ef896f', + 'info_dict': { + 'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6', + 'ext': 'mp4', + 'title': 'Familienspaß am Bodensee', + 'description': 'md5:0b591225a32cfde7be1629ed49fe4315', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 1784, + 'upload_date': '20140727', + 'uploader': 'SWR Fernsehen BW', + 'uploader_id': '281130', + } }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 46d727d1d..8a95fd656 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -106,6 +106,13 @@ class TeacherTubeUserIE(InfoExtractor): \s* <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)" ''' + _TEST = { + 'url': 'http://www.teachertube.com/user/profile/rbhagwati2', + 'info_dict': { + 'id': 'rbhagwati2' + }, + 'playlist_mincount': 179, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index f8dd7e955..fa796ce72 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -37,7 +37,7 @@ class TeamcocoIE(InfoExtractor): video_id = mobj.group("video_id") if not video_id: video_id = self._html_search_regex( - r'<article class="video" data-id="(\d+?)"', + r'data-node-id="(\d+?)"', webpage, 'video id') data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id diff --git a/youtube_dl/extractor/techtalks.py b/youtube_dl/extractor/techtalks.py index a55f236cb..16e945d8e 100644 --- a/youtube_dl/extractor/techtalks.py +++ b/youtube_dl/extractor/techtalks.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -11,24 +13,30 @@ class TechTalksIE(InfoExtractor): _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/' _TEST = { - u'url': u'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/', - u'playlist': [ + 'url': 'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/', + 'info_dict': { + 'id': '57758', + 'title': 'Learning Topic Models --- Going beyond SVD', + }, + 'playlist': [ { - u'file': u'57758.flv', - u'info_dict': { - u'title': u'Learning Topic Models --- Going beyond SVD', + 'info_dict': { + 'id': '57758', + 'ext': 'flv', + 'title': 'Learning Topic Models --- Going beyond SVD', }, }, { - u'file': u'57758-slides.flv', - u'info_dict': { - u'title': u'Learning Topic Models --- Going beyond SVD', + 'info_dict': { + 'id': '57758-slides', + 'ext': 'flv', + 'title': 'Learning Topic Models --- Going beyond SVD', }, }, ], - u'params': { + 'params': { # rtmp download - u'skip_download': True, + 'skip_download': True, }, } @@ -36,30 +44,36 @@ class TechTalksIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) talk_id = mobj.group('id') webpage = self._download_webpage(url, talk_id) - rtmp_url = self._search_regex(r'netConnectionUrl: \'(.*?)\'', webpage, - u'rtmp url') - play_path = self._search_regex(r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"', - webpage, u'presenter play path') + rtmp_url = self._search_regex( + r'netConnectionUrl: \'(.*?)\'', webpage, 'rtmp url') + play_path = self._search_regex( + r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"', + webpage, 'presenter play path') title = clean_html(get_element_by_attribute('class', 'title', webpage)) video_info = { - 'id': talk_id, - 'title': title, - 'url': rtmp_url, - 'play_path': play_path, - 'ext': 'flv', - } + 'id': talk_id, + 'title': title, + 'url': rtmp_url, + 'play_path': play_path, + 'ext': 'flv', + } m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage) if m_slides is None: return video_info else: - return [ - video_info, - # The slides video - { - 'id': talk_id + '-slides', - 'title': title, - 'url': rtmp_url, - 'play_path': m_slides.group(1), - 'ext': 'flv', - }, - ] + return { + '_type': 'playlist', + 'id': talk_id, + 'title': title, + 'entries': [ + video_info, + # The slides video + { + 'id': talk_id + '-slides', + 'title': title, + 'url': rtmp_url, + 'play_path': m_slides.group(1), + 'ext': 'flv', + }, + ], + } diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index bce32a873..1cca47771 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -51,7 +51,6 @@ class TEDIE(SubtitlesInfoExtractor): } }, { 'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best', - 'md5': '49144e345a899b8cb34d315f3b9cfeeb', 'info_dict': { 'id': '1972', 'ext': 'mp4', @@ -59,6 +58,13 @@ class TEDIE(SubtitlesInfoExtractor): 'uploader': 'Gabby Giffords and Mark Kelly', 'description': 'md5:5174aed4d0f16021b704120360f72b92', }, + }, { + 'url': 'http://www.ted.com/playlists/who_are_the_hackers', + 'info_dict': { + 'id': '10', + 'title': 'Who are the hackers?', + }, + 'playlist_mincount': 6, }] _NATIVE_FORMATS = { diff --git a/youtube_dl/extractor/telemb.py b/youtube_dl/extractor/telemb.py new file mode 100644 index 000000000..1bbd0e7bd --- /dev/null +++ b/youtube_dl/extractor/telemb.py @@ -0,0 +1,78 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import remove_start + + +class TeleMBIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html' + _TESTS = [ + { + 'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html', + 'md5': 'f45ea69878516ba039835794e0f8f783', + 'info_dict': { + 'id': '13466', + 'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-', + 'ext': 'mp4', + 'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages', + 'description': 'md5:bc5225f47b17c309761c856ad4776265', + 'thumbnail': 're:^http://.*\.(?:jpg|png)$', + } + }, + { + # non-ASCII characters in download URL + 'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html', + 'md5': '6e9682736e5ccd4eab7f21e855350733', + 'info_dict': { + 'id': '13514', + 'display_id': 'les-reportages-havre-incendie-mortel', + 'ext': 'mp4', + 'title': 'Havré - Incendie mortel - Les reportages', + 'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a', + 'thumbnail': 're:^http://.*\.(?:jpg|png)$', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + formats = [] + for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage): + fmt = { + 'url': video_url, + 'format_id': video_url.split(':')[0] + } + rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url) + if rtmp: + fmt.update({ + 'play_path': rtmp.group('playpath'), + 'app': rtmp.group('app'), + 'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf', + 'page_url': 'http://www.telemb.be', + 'preference': -1, + }) + formats.append(fmt) + self._sort_formats(formats) + + title = remove_start(self._og_search_title(webpage), 'TéléMB : ') + description = self._html_search_regex( + r'<meta property="og:description" content="(.+?)" />', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py new file mode 100644 index 000000000..4956f8577 --- /dev/null +++ b/youtube_dl/extractor/tnaflix.py @@ -0,0 +1,84 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + fix_xml_ampersands, +) + + +class TNAFlixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)' + + _TITLE_REGEX = None + _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' + + _TEST = { + 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', + 'md5': 'ecf3498417d09216374fc5907f9c6ec0', + 'info_dict': { + 'id': '553878', + 'display_id': 'Carmella-Decesare-striptease', + 'ext': 'mp4', + 'title': 'Carmella Decesare - striptease', + 'description': '', + 'thumbnail': 're:https?://.*\.jpg$', + 'duration': 91, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage) + description = self._html_search_regex( + self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='') + + age_limit = self._rta_search(webpage) + + duration = self._html_search_meta('duration', webpage, 'duration', default=None) + if duration: + duration = parse_duration(duration[1:]) + + cfg_url = self._html_search_regex( + self._CONFIG_REGEX, webpage, 'flashvars.config') + + cfg_xml = self._download_xml( + cfg_url, display_id, note='Downloading metadata', + transform_source=fix_xml_ampersands) + + thumbnail = cfg_xml.find('./startThumb').text + + formats = [] + for item in cfg_xml.findall('./quality/item'): + video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text) + format_id = item.find('res').text + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/toypics.py b/youtube_dl/extractor/toypics.py index 0f389bd93..2756f56d3 100644 --- a/youtube_dl/extractor/toypics.py +++ b/youtube_dl/extractor/toypics.py @@ -42,6 +42,13 @@ class ToypicsIE(InfoExtractor): class ToypicsUserIE(InfoExtractor): IE_DESC = 'Toypics user profile' _VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])' + _TEST = { + 'url': 'http://videos.toypics.net/Mikey', + 'info_dict': { + 'id': 'Mikey', + }, + 'playlist_mincount': 19, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 7a3891b89..dcd823d08 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -1,5 +1,7 @@ # coding: utf-8 +from __future__ import unicode_literals + import re import json @@ -9,22 +11,29 @@ from .common import InfoExtractor class TudouIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' _TESTS = [{ - u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', - u'file': u'159448201.f4v', - u'md5': u'140a49ed444bd22f93330985d8475fcb', - u'info_dict': { - u"title": u"卡马乔国足开大脚长传冲吊集锦" + 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', + 'md5': '140a49ed444bd22f93330985d8475fcb', + 'info_dict': { + 'id': '159448201', + 'ext': 'f4v', + 'title': '卡马乔国足开大脚长传冲吊集锦', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, { + 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/', + 'info_dict': { + 'id': '117049447', + 'ext': 'f4v', + 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', + 'thumbnail': 're:^https?://.*\.jpg$', } - }, - { - u'url': u'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', - u'file': u'todo.mp4', - u'md5': u'todo.mp4', - u'info_dict': { - u'title': u'todo.mp4', + }, { + 'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', + 'info_dict': { + 'title': 'todo.mp4', }, - u'add_ie': [u'Youku'], - u'skip': u'Only works from China' + 'add_ie': ['Youku'], + 'skip': 'Only works from China' }] def _url_for_id(self, id, quality = None): @@ -44,20 +53,22 @@ class TudouIE(InfoExtractor): if m and m.group(1): return { '_type': 'url', - 'url': u'youku:' + m.group(1), + 'url': 'youku:' + m.group(1), 'ie_key': 'Youku' } title = self._search_regex( - r",kw:\s*['\"](.+?)[\"']", webpage, u'title') + r",kw:\s*['\"](.+?)[\"']", webpage, 'title') thumbnail_url = self._search_regex( - r",pic:\s*[\"'](.+?)[\"']", webpage, u'thumbnail URL', fatal=False) + r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segments = json.loads(segs_json) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher - quality = sorted(segments.keys())[-1] + # Also, filter non-number qualities (see issue #3643). + quality = sorted(filter(lambda k: k.isdigit(), segments.keys()), + key=lambda k: int(k))[-1] parts = segments[quality] result = [] len_parts = len(parts) @@ -67,12 +78,13 @@ class TudouIE(InfoExtractor): part_id = part['k'] final_url = self._url_for_id(part_id, quality) ext = (final_url.split('?')[0]).split('.')[-1] - part_info = {'id': part_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - } + part_info = { + 'id': '%s' % part_id, + 'url': final_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + } result.append(part_info) return result diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index 0921cc5f8..dc8697850 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -5,80 +5,82 @@ import re from .common import InfoExtractor from ..utils import ( - unified_strdate, - clean_html, - int_or_none, + float_or_none, + str_to_int, ) class TvigleIE(InfoExtractor): IE_NAME = 'tvigle' IE_DESC = 'Интернет-телевидение Tvigle.ru' - _VALID_URL = r'http://(?:www\.)?tvigle\.ru/category/.+?[\?&]v(?:ideo)?=(?P<id>\d+)' + _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$' _TESTS = [ { - 'url': 'http://www.tvigle.ru/category/cinema/1608/?video=503081', - 'md5': '09afba4616666249f087efc6dcf83cb3', + 'url': 'http://www.tvigle.ru/video/brat-2/', + 'md5': '72cb7eab33e54314e1790da402d3c9c3', 'info_dict': { - 'id': '503081', - 'ext': 'flv', + 'id': '5119390', + 'display_id': 'brat-2', + 'ext': 'mp4', 'title': 'Брат 2 ', - 'description': 'md5:f5a42970f50648cee3d7ad740f3ae769', - 'upload_date': '20110919', + 'description': 'md5:5751f4fe345a58e1692585c361294bd8', + 'duration': 7356.369, + 'age_limit': 0, }, }, { - 'url': 'http://www.tvigle.ru/category/men/vysotskiy_vospominaniya02/?flt=196&v=676433', - 'md5': 'e7efe5350dd5011d0de6550b53c3ba7b', + 'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/', + 'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574', 'info_dict': { - 'id': '676433', - 'ext': 'flv', + 'id': '5142516', + 'ext': 'mp4', 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком', 'description': 'md5:027f7dc872948f14c96d19b4178428a4', - 'upload_date': '20121218', + 'duration': 186.080, + 'age_limit': 0, }, }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + display_id = mobj.group('display_id') - video_data = self._download_xml( - 'http://www.tvigle.ru/xml/single.php?obj=%s' % video_id, video_id, 'Downloading video XML') + webpage = self._download_webpage(url, display_id) - video = video_data.find('./video') + video_id = self._html_search_regex( + r'<li class="video-preview current_playing" id="(\d+)">', webpage, 'video id') - title = video.get('name') - description = video.get('anons') - if description: - description = clean_html(description) - thumbnail = video_data.get('img') - upload_date = unified_strdate(video.get('date')) - like_count = int_or_none(video.get('vtp')) + video_data = self._download_json( + 'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id) - formats = [] - for num, (format_id, format_note) in enumerate([['low_file', 'SQ'], ['file', 'HQ'], ['hd', 'HD 720']]): - video_url = video.get(format_id) - if not video_url: - continue - formats.append({ - 'url': video_url, - 'format_id': format_id, - 'format_note': format_note, - 'quality': num, - }) + item = video_data['playlist']['items'][0] + + title = item['title'] + description = item['description'] + thumbnail = item['thumbnail'] + duration = float_or_none(item['durationMilliseconds'], 1000) + age_limit = str_to_int(item['ageRestrictions']) + formats = [] + for vcodec, fmts in item['videos'].items(): + for quality, video_url in fmts.items(): + formats.append({ + 'url': video_url, + 'format_id': '%s-%s' % (vcodec, quality), + 'vcodec': vcodec, + 'height': int(quality[:-1]), + }) self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'like_count': like_count, - 'age_limit': 18, + 'duration': duration, + 'age_limit': age_limit, 'formats': formats, }
\ No newline at end of file diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index a56a7ab5f..445e0ec41 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -6,13 +6,28 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + compat_str, parse_iso8601, qualities, ) class TVPlayIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)' + IE_DESC = 'TV3Play and related services' + _VALID_URL = r'''(?x)http://(?:www\.)? + (?:tvplay\.lv/parraides| + tv3play\.lt/programos| + tv3play\.ee/sisu| + tv3play\.se/program| + tv6play\.se/program| + tv8play\.se/program| + tv10play\.se/program| + tv3play\.no/programmer| + viasat4play\.no/programmer| + tv6play\.no/programmer| + tv3play\.dk/programmer| + )/[^/]+/(?P<id>\d+) + ''' _TESTS = [ { 'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true', @@ -30,6 +45,134 @@ class TVPlayIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.tv3play.lt/programos/moterys-meluoja-geriau/409229?autostart=true', + 'info_dict': { + 'id': '409229', + 'ext': 'flv', + 'title': 'Moterys meluoja geriau', + 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e', + 'duration': 1330, + 'timestamp': 1403769181, + 'upload_date': '20140626', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true', + 'info_dict': { + 'id': '238551', + 'ext': 'flv', + 'title': 'Kodu keset linna 398537', + 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701', + 'duration': 1257, + 'timestamp': 1292449761, + 'upload_date': '20101215', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true', + 'info_dict': { + 'id': '395385', + 'ext': 'flv', + 'title': 'Husräddarna S02E07', + 'description': 'md5:f210c6c89f42d4fc39faa551be813777', + 'duration': 2574, + 'timestamp': 1400596321, + 'upload_date': '20140520', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true', + 'info_dict': { + 'id': '266636', + 'ext': 'flv', + 'title': 'Den sista dokusåpan S01E08', + 'description': 'md5:295be39c872520221b933830f660b110', + 'duration': 1492, + 'timestamp': 1330522854, + 'upload_date': '20120229', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true', + 'info_dict': { + 'id': '282756', + 'ext': 'flv', + 'title': 'Antikjakten S01E10', + 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8', + 'duration': 2646, + 'timestamp': 1348575868, + 'upload_date': '20120925', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true', + 'info_dict': { + 'id': '230898', + 'ext': 'flv', + 'title': 'Anna Anka søker assistent - Ep. 8', + 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474', + 'duration': 2656, + 'timestamp': 1277720005, + 'upload_date': '20100628', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true', + 'info_dict': { + 'id': '21873', + 'ext': 'flv', + 'title': 'Budbringerne program 10', + 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d', + 'duration': 1297, + 'timestamp': 1254205102, + 'upload_date': '20090929', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true', + 'info_dict': { + 'id': '361883', + 'ext': 'flv', + 'title': 'Hotelinspektør Alex Polizzi - Ep. 10', + 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81', + 'duration': 2594, + 'timestamp': 1393236292, + 'upload_date': '20140224', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, ] def _real_extract(self, url): @@ -49,7 +192,7 @@ class TVPlayIE(InfoExtractor): quality = qualities(['hls', 'medium', 'high']) formats = [] for format_id, video_url in streams['streams'].items(): - if not video_url: + if not video_url or not isinstance(video_url, compat_str): continue fmt = { 'format_id': format_id, diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py new file mode 100644 index 000000000..0182d67ec --- /dev/null +++ b/youtube_dl/extractor/ubu.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class UbuIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html' + _TEST = { + 'url': 'http://ubu.com/film/her_noise.html', + 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9', + 'info_dict': { + 'id': 'her_noise', + 'ext': 'mp4', + 'title': 'Her Noise - The Making Of (2007)', + 'duration': 3600, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title') + + duration = int_or_none(self._html_search_regex( + r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None)) + if duration: + duration *= 60 + + formats = [] + + FORMAT_REGEXES = [ + ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"], + ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'] + ] + + for format_id, format_regex in FORMAT_REGEXES: + m = re.search(format_regex, webpage) + if m: + formats.append({ + 'url': m.group(1), + 'format_id': format_id, + }) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py index 474610eec..f70978299 100644 --- a/youtube_dl/extractor/unistra.py +++ b/youtube_dl/extractor/unistra.py @@ -1,32 +1,66 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import qualities + class UnistraIE(InfoExtractor): - _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)' - - _TEST = { - u'url': u'http://utv.unistra.fr/video.php?id_video=154', - u'file': u'154.mp4', - u'md5': u'736f605cfdc96724d55bb543ab3ced24', - u'info_dict': { - u'title': u'M!ss Yella', - u'description': u'md5:104892c71bd48e55d70b902736b81bbf', + _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)' + + _TESTS = [ + { + 'url': 'http://utv.unistra.fr/video.php?id_video=154', + 'md5': '736f605cfdc96724d55bb543ab3ced24', + 'info_dict': { + 'id': '154', + 'ext': 'mp4', + 'title': 'M!ss Yella', + 'description': 'md5:104892c71bd48e55d70b902736b81bbf', + }, }, - } + { + 'url': 'http://utv.unistra.fr/index.php?id_video=437', + 'md5': '1ddddd6cccaae76f622ce29b8779636d', + 'info_dict': { + 'id': '437', + 'ext': 'mp4', + 'title': 'Prix Louise Weiss 2014', + 'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a', + }, + } + ] def _real_extract(self, url): - id = re.match(self._VALID_URL, url).group(1) - webpage = self._download_webpage(url, id) - file = re.search(r'file: "(.*?)",', webpage).group(1) - title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title') + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') - video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file + webpage = self._download_webpage(url, video_id) - return {'id': id, - 'title': title, - 'ext': 'mp4', - 'url': video_url, - 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL), - 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'), - } + files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage)) + + quality = qualities(['SD', 'HD']) + formats = [] + for file_path in files: + format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD' + formats.append({ + 'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path, + 'format_id': format_id, + 'quality': quality(format_id) + }) + + title = self._html_search_regex( + r'<title>UTV - (.*?)</', webpage, 'title') + description = self._html_search_regex( + r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL) + thumbnail = self._search_regex( + r'image: "(.*?)"', webpage, 'thumbnail') + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats + } diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 488b10df9..994b60a76 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor @@ -68,21 +67,36 @@ class UstreamIE(InfoExtractor): class UstreamChannelIE(InfoExtractor): _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' IE_NAME = 'ustream:channel' + _TEST = { + 'url': 'http://www.ustream.tv/channel/channeljapan', + 'info_dict': { + 'id': '10874166', + }, + 'playlist_mincount': 54, + } def _real_extract(self, url): m = re.match(self._VALID_URL, url) - slug = m.group('slug') - webpage = self._download_webpage(url, slug) + display_id = m.group('slug') + webpage = self._download_webpage(url, display_id) channel_id = get_meta_content('ustream:channel_id', webpage) BASE = 'http://www.ustream.tv' next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id video_ids = [] while next_url: - reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id)) + reply = self._download_json( + compat_urlparse.urljoin(BASE, next_url), display_id, + note='Downloading video information (next: %d)' % (len(video_ids) + 1)) video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data'])) next_url = reply['nextUrl'] - urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids] - url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls] - return self.playlist_result(url_entries, channel_id) + entries = [ + self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream') + for vid in video_ids] + return { + '_type': 'playlist', + 'id': channel_id, + 'display_id': display_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index b1c854a64..77b1f91ce 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -16,8 +16,9 @@ class VeeHDIE(InfoExtractor): _TEST = { 'url': 'http://veehd.com/video/4686958', - 'file': '4686958.mp4', 'info_dict': { + 'id': '4686958', + 'ext': 'mp4', 'title': 'Time Lapse View from Space ( ISS)', 'uploader_id': 'spotted', 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7', diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index eada13ce9..d2ffd1b6b 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -177,6 +177,7 @@ class VevoIE(InfoExtractor): self._downloader.report_warning( 'Cannot download SMIL information, falling back to JSON ..') + self._sort_formats(formats) timestamp_ms = int(self._search_regex( r'/Date\((\d+)\)/', video_info['launchDate'], 'launch date')) diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py new file mode 100644 index 000000000..7d27d6c57 --- /dev/null +++ b/youtube_dl/extractor/vgtv.py @@ -0,0 +1,119 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import float_or_none + + +class VGTVIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)' + _TESTS = [ + { + # streamType: vod + 'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu', + 'md5': 'b8be7a234cebb840c0d512c78013e02f', + 'info_dict': { + 'id': '84196', + 'ext': 'mp4', + 'title': 'Hevnen er søt episode 10: Abu', + 'description': 'md5:e25e4badb5f544b04341e14abdc72234', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 648.000, + 'timestamp': 1404626400, + 'upload_date': '20140706', + 'view_count': int, + }, + }, + { + # streamType: wasLive + 'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen', + 'info_dict': { + 'id': '100764', + 'ext': 'mp4', + 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen', + 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 9056.000, + 'timestamp': 1410113864, + 'upload_date': '20140907', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + { + # streamType: live + 'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen', + 'info_dict': { + 'id': '100015', + 'ext': 'mp4', + 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!', + 'description': 'md5:9a60cc23fa349f761628924e56eeec2d', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 0, + 'timestamp': 1407423348, + 'upload_date': '20140807', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + data = self._download_json( + 'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id, + video_id, 'Downloading media JSON') + + streams = data['streamUrls'] + + formats = [] + + hls_url = streams.get('hls') + if hls_url: + formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4')) + + hds_url = streams.get('hds') + if hds_url: + formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id)) + + mp4_url = streams.get('mp4') + if mp4_url: + _url = hls_url or hds_url + MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1]) + for mp4_format in _url.split(','): + m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format) + if not m: + continue + width = int(m.group('width')) + height = int(m.group('height')) + vbr = int(m.group('vbr')) + formats.append({ + 'url': MP4_URL_TEMPLATE % mp4_format, + 'format_id': 'mp4-%s' % vbr, + 'width': width, + 'height': height, + 'vbr': vbr, + 'preference': 1, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': data['title'], + 'description': data['description'], + 'thumbnail': data['images']['main'] + '?t[]=900x506q80', + 'timestamp': data['published'], + 'duration': float_or_none(data['duration'], 1000), + 'view_count': data['displays'], + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py new file mode 100644 index 000000000..5c89824c1 --- /dev/null +++ b/youtube_dl/extractor/vidme.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, + str_to_int, +) + + +class VidmeIE(InfoExtractor): + _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)' + _TEST = { + 'url': 'https://vid.me/QNB', + 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', + 'info_dict': { + 'id': 'QNB', + 'ext': 'mp4', + 'title': 'Fishing for piranha - the easy way', + 'description': 'source: https://www.facebook.com/photo.php?v=312276045600871', + 'duration': 119.92, + 'timestamp': 1406313244, + 'upload_date': '20140725', + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex(r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage, default='') + thumbnail = self._og_search_thumbnail(webpage) + timestamp = int_or_none(self._og_search_property('updated_time', webpage, fatal=False)) + width = int_or_none(self._og_search_property('video:width', webpage, fatal=False)) + height = int_or_none(self._og_search_property('video:height', webpage, fatal=False)) + duration = float_or_none(self._html_search_regex( + r'data-duration="([^"]+)"', webpage, 'duration', fatal=False)) + view_count = str_to_int(self._html_search_regex( + r'<span class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">', + webpage, 'comment count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'width': width, + 'height': height, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index a3c6e83b0..bc01d7fbf 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -57,6 +57,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): (?P<proto>(?:https?:)?//)? (?:(?:www|(?P<player>player))\.)? vimeo(?P<pro>pro)?\.com/ + (?!channels/[^/?#]+/?(?:$|[?#])|album/) (?:.*?/)? (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? (?:videos?/)? @@ -122,6 +123,21 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): }, }, { + 'url': 'http://vimeo.com/channels/keypeele/75629013', + 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', + 'note': 'Video is freely available via original URL ' + 'and protected with password when accessed via http://vimeo.com/75629013', + 'info_dict': { + 'id': '75629013', + 'ext': 'mp4', + 'title': 'Key & Peele: Terrorist Interrogation', + 'description': 'md5:8678b246399b070816b12313e8b4eb5c', + 'uploader_id': 'atencio', + 'uploader': 'Peter Atencio', + 'duration': 187, + }, + }, + { 'url': 'http://vimeo.com/76979871', 'md5': '3363dd6ffebe3784d56f4132317fd446', 'note': 'Video with subtitles', @@ -138,15 +154,6 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): }, ] - @classmethod - def suitable(cls, url): - if VimeoChannelIE.suitable(url): - # Otherwise channel urls like http://vimeo.com/channels/31259 would - # match - return False - else: - return super(VimeoIE, cls).suitable(url) - def _verify_video_password(self, url, video_id, webpage): password = self._downloader.params.get('videopassword', None) if password is None: @@ -190,14 +197,14 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if data is not None: headers = headers.copy() headers.update(data) + if 'Referer' not in headers: + headers['Referer'] = url # Extract ID from URL mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id - else: - url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) @@ -263,7 +270,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if video_thumbnail is None: video_thumbs = config["video"].get("thumbs") if video_thumbs and isinstance(video_thumbs, dict): - _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1] + _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description video_description = None @@ -365,9 +372,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): class VimeoChannelIE(InfoExtractor): IE_NAME = 'vimeo:channel' - _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)/?(\?.*)?$' + _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' + _TESTS = [{ + 'url': 'http://vimeo.com/channels/tributes', + 'info_dict': { + 'title': 'Vimeo Tributes', + }, + 'playlist_mincount': 25, + }] def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) @@ -401,14 +415,15 @@ class VimeoChannelIE(InfoExtractor): class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)' + _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' - - @classmethod - def suitable(cls, url): - if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url): - return False - return super(VimeoUserIE, cls).suitable(url) + _TESTS = [{ + 'url': 'http://vimeo.com/nkistudio/videos', + 'info_dict': { + 'title': 'Nki', + }, + 'playlist_mincount': 66, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -418,8 +433,15 @@ class VimeoUserIE(VimeoChannelIE): class VimeoAlbumIE(VimeoChannelIE): IE_NAME = 'vimeo:album' - _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)' + _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' + _TESTS = [{ + 'url': 'http://vimeo.com/album/2632481', + 'info_dict': { + 'title': 'Staff Favorites: November 2013', + }, + 'playlist_mincount': 13, + }] def _page_url(self, base_url, pagenum): return '%s/page:%d/' % (base_url, pagenum) @@ -433,6 +455,13 @@ class VimeoAlbumIE(VimeoChannelIE): class VimeoGroupsIE(VimeoAlbumIE): IE_NAME = 'vimeo:group' _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)' + _TESTS = [{ + 'url': 'http://vimeo.com/groups/rolexawards', + 'info_dict': { + 'title': 'Rolex Awards for Enterprise', + }, + 'playlist_mincount': 73, + }] def _extract_list_title(self, webpage): return self._og_search_title(webpage) @@ -446,8 +475,8 @@ class VimeoGroupsIE(VimeoAlbumIE): class VimeoReviewIE(InfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)' - _TEST = { + _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' + _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'file': '75524534.mp4', 'md5': 'c507a72f780cacc12b2248bb4006d253', @@ -455,7 +484,19 @@ class VimeoReviewIE(InfoExtractor): 'title': "DICK HARDWICK 'Comedian'", 'uploader': 'Richard Hardwick', } - } + }, { + 'note': 'video player needs Referer', + 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053', + 'md5': '6295fdab8f4bf6a002d058b2c6dce276', + 'info_dict': { + 'id': '91613211', + 'ext': 'mp4', + 'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn', + 'uploader': 'DevWeek Events', + 'duration': 2773, + 'thumbnail': 're:^https?://.*\.jpg$', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -470,6 +511,10 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater' _LOGIN_REQUIRED = True _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<' + _TESTS = [{ + 'url': 'http://vimeo.com/home/watchlater', + 'only_matching': True, + }] def _real_initialize(self): self._login() diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 076c87119..e7754158d 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -65,6 +65,13 @@ class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$' _VINE_BASE_URL = "https://vine.co/" + _TEST = { + 'url': 'https://vine.co/Visa', + 'info_dict': { + 'id': 'Visa', + }, + 'playlist_mincount': 47, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index 6d3b78749..affef6507 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -44,7 +44,7 @@ class VodlockerIE(InfoExtractor): req, video_id, 'Downloading video page') title = self._search_regex( - r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title') + r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title') thumbnail = self._search_regex( r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail') url = self._search_regex( diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py new file mode 100644 index 000000000..426369c51 --- /dev/null +++ b/youtube_dl/extractor/vporn.py @@ -0,0 +1,99 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class VpornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/', + 'md5': 'facf37c1b86546fa0208058546842c55', + 'info_dict': { + 'id': '497944', + 'display_id': 'violet-on-her-th-birthday', + 'ext': 'mp4', + 'title': 'Violet on her 19th birthday', + 'description': 'Violet dances in front of the camera which is sure to get you horny.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'kileyGrope', + 'categories': ['Masturbation', 'Teen'], + 'duration': 393, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() + description = self._html_search_regex( + r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) + if thumbnail: + thumbnail = 'http://www.vporn.com' + thumbnail + + uploader = self._html_search_regex( + r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>', + webpage, 'uploader', fatal=False) + + categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage) + + duration = parse_duration(self._search_regex( + r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False)) + + formats = [] + + for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage): + video_url = video[1] + fmt = { + 'url': video_url, + 'format_id': video[0], + } + m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url) + if m: + fmt.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + 'vbr': int(m.group('vbr')), + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'age_limit': 18, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index f1b9e9a19..2544c24bd 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -1,10 +1,12 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, +) class VubeIE(InfoExtractor): @@ -29,6 +31,7 @@ class VubeIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, + 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'], } }, { @@ -47,6 +50,7 @@ class VubeIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, + 'categories': ['seraina', 'jessica', 'krewella', 'alive'], } }, { 'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s', @@ -56,13 +60,15 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Frozen - Let It Go Cover by Siren Gene', 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.', - 'uploader': 'Siren Gene', - 'uploader_id': 'Siren', 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$', + 'uploader': 'Siren', + 'timestamp': 1395448018, + 'upload_date': '20140322', 'duration': 221.788, 'like_count': int, 'dislike_count': int, 'comment_count': int, + 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'], } } ] @@ -71,47 +77,40 @@ class VubeIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - data_json = self._search_regex( - r'(?s)window\["(?:tapiVideoData|vubeOriginalVideoData)"\]\s*=\s*(\{.*?\n});\n', - webpage, 'video data' - ) - data = json.loads(data_json) - video = ( - data.get('video') or - data) - assert isinstance(video, dict) + video = self._download_json( + 'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON') public_id = video['public_id'] - formats = [ - { - 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id), - 'height': int(fmt['height']), - 'abr': int(fmt['audio_bitrate']), - 'vbr': int(fmt['video_bitrate']), - 'format_id': fmt['media_resolution_id'] - } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed' - ] + formats = [] + + for media in video['media'].get('video', []) + video['media'].get('audio', []): + if media['transcoding_status'] != 'processed': + continue + fmt = { + 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id), + 'abr': int(media['audio_bitrate']), + 'format_id': compat_str(media['media_resolution_id']), + } + vbr = int(media['video_bitrate']) + if vbr: + fmt.update({ + 'vbr': vbr, + 'height': int(media['height']), + }) + formats.append(fmt) self._sort_formats(formats) title = video['title'] description = video.get('description') - thumbnail = self._proto_relative_url( - video.get('thumbnail') or video.get('thumbnail_src'), - scheme='http:') - uploader = data.get('user', {}).get('channel', {}).get('name') or video.get('user_alias') - uploader_id = data.get('user', {}).get('name') + thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:') + uploader = video.get('user_alias') or video.get('channel') timestamp = int_or_none(video.get('upload_time')) duration = video['duration'] view_count = video.get('raw_view_count') - like_count = video.get('rlikes') - if like_count is None: - like_count = video.get('total_likes') - dislike_count = video.get('rhates') - if dislike_count is None: - dislike_count = video.get('total_hates') + like_count = video.get('total_likes') + dislike_count = video.get('total_hates') comments = video.get('comments') comment_count = None @@ -124,6 +123,8 @@ class VubeIE(InfoExtractor): else: comment_count = len(comments) + categories = [tag['text'] for tag in video['tags']] + return { 'id': video_id, 'formats': formats, @@ -131,11 +132,11 @@ class VubeIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'uploader_id': uploader_id, 'timestamp': timestamp, 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, + 'categories': categories, } diff --git a/youtube_dl/extractor/washingtonpost.py b/youtube_dl/extractor/washingtonpost.py index cb8f0887d..88bbbb219 100644 --- a/youtube_dl/extractor/washingtonpost.py +++ b/youtube_dl/extractor/washingtonpost.py @@ -13,6 +13,9 @@ class WashingtonPostIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _TEST = { 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', + 'info_dict': { + 'title': 'Sinkhole of bureaucracy', + }, 'playlist': [{ 'md5': 'c3f4b4922ffa259243f68e928db2db8c', 'info_dict': { diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index a584e0896..46b4d9133 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -2,29 +2,43 @@ from __future__ import unicode_literals import re +import hashlib from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate class WatIE(InfoExtractor): - _VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html' + _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html' IE_NAME = 'wat.tv' - _TEST = { - 'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', - 'info_dict': { - 'id': '10631273', - 'ext': 'mp4', - 'title': 'World War Z - Philadelphia VOST', - 'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', + _TESTS = [ + { + 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', + 'md5': 'ce70e9223945ed26a8056d413ca55dc9', + 'info_dict': { + 'id': '11713067', + 'display_id': 'soupe-figues-l-orange-aux-epices', + 'ext': 'mp4', + 'title': 'Soupe de figues à l\'orange et aux épices', + 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.', + 'upload_date': '20140819', + 'duration': 120, + }, }, - 'params': { - # Sometimes wat serves the whole file with the --test option - 'skip_download': True, + { + 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', + 'md5': 'fbc84e4378165278e743956d9c1bf16b', + 'info_dict': { + 'id': '11713075', + 'display_id': 'gregory-lemarchal-voix-ange', + 'ext': 'mp4', + 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)', + 'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3', + 'upload_date': '20140816', + 'duration': 2910, + }, }, - } + ] def download_video_info(self, real_id): # 'contentv4' is used in the website, but it also returns the related @@ -36,13 +50,20 @@ class WatIE(InfoExtractor): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] mobj = re.match(self._VALID_URL, url) - short_id = mobj.group('shortID') - webpage = self._download_webpage(url, short_id) + short_id = mobj.group('short_id') + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id or short_id) real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') video_info = self.download_video_info(real_id) + + geo_list = video_info.get('geoList') + country = geo_list[0] if geo_list else '' + chapters = video_info['chapters'] first_chapter = chapters[0] + files = video_info['files'] + first_file = files[0] if real_id_for_chapter(first_chapter) != real_id: self.to_screen('Multipart video detected') @@ -61,12 +82,47 @@ class WatIE(InfoExtractor): upload_date = unified_strdate(first_chapter['date_diffusion']) # Otherwise we can continue and extract just one part, we have to use # the short id for getting the video url + + formats = [{ + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'format_id': 'Mobile', + }] + + fmts = [('SD', 'web')] + if first_file.get('hasHD'): + fmts.append(('HD', 'webhd')) + + def compute_token(param): + timestamp = '%08x' % int(self._download_webpage( + 'http://www.wat.tv/servertime', real_id, + 'Downloading server time').split('|')[0]) + magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564' + return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp) + + for fmt in fmts: + webid = '/%s/%s' % (fmt[1], real_id) + video_url = self._download_webpage( + 'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country), + real_id, + 'Downloding %s video URL' % fmt[0], + 'Failed to download %s video URL' % fmt[0], + False) + if not video_url: + continue + formats.append({ + 'url': video_url, + 'ext': 'mp4', + 'format_id': fmt[0], + }) + return { 'id': real_id, - 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'display_id': display_id, 'title': first_chapter['title'], 'thumbnail': first_chapter['preview'], 'description': first_chapter['description'], 'view_count': video_info['views'], 'upload_date': upload_date, + 'duration': first_file['duration'], + 'formats': formats, } diff --git a/youtube_dl/extractor/wayofthemaster.py b/youtube_dl/extractor/wayofthemaster.py new file mode 100644 index 000000000..af7bb8b49 --- /dev/null +++ b/youtube_dl/extractor/wayofthemaster.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class WayOfTheMasterIE(InfoExtractor): + _VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])' + + _TEST = { + 'url': 'http://www.wayofthemaster.com/hbks.shtml', + 'md5': '5316b57487ada8480606a93cb3d18d24', + 'info_dict': { + 'id': 'hbks', + 'ext': 'mp4', + 'title': 'Intelligent Design vs. Evolution', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex( + r'<img src="images/title_[^"]+".*?alt="([^"]+)"', + webpage, 'title', default=None) + if title is None: + title = self._html_search_regex( + r'<title>(.*?)</title>', webpage, 'page title') + + url_base = self._search_regex( + r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"', + webpage, 'URL base') + formats = [{ + 'format_id': 'low', + 'quality': 1, + 'url': url_base + '_low.mp4', + }, { + 'format_id': 'high', + 'quality': 2, + 'url': url_base + '_high.mp4', + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py new file mode 100644 index 000000000..a9aa72e73 --- /dev/null +++ b/youtube_dl/extractor/xboxclips.py @@ -0,0 +1,57 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + float_or_none, + int_or_none, +) + + +class XboxClipsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' + _TEST = { + 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', + 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', + 'info_dict': { + 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', + 'ext': 'mp4', + 'title': 'Iabdulelah playing Upload Studio', + 'filesize_approx': 28101836.8, + 'timestamp': 1407388500, + 'upload_date': '20140807', + 'duration': 56, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'>Link: <a href="([^"]+)">', webpage, 'video URL') + title = self._html_search_regex( + r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title') + timestamp = parse_iso8601(self._html_search_regex( + r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False)) + filesize = float_or_none(self._html_search_regex( + r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024) + duration = int_or_none(self._html_search_regex( + r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'>Views: (\d+)<', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'timestamp': timestamp, + 'filesize_approx': filesize, + 'duration': duration, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 5374495f9..00b6d1eba 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://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' + _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' _TESTS = [ { 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index b293e2665..273d93d9e 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -77,9 +77,17 @@ class XTubeIE(InfoExtractor): 'age_limit': 18, } + class XTubeUserIE(InfoExtractor): IE_DESC = 'XTube user profile' _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])' + _TEST = { + 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers', + 'info_dict': { + 'id': 'greenshowers', + }, + 'playlist_mincount': 155, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index d84be2562..3ab6017cd 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,7 +15,7 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html' + _VALID_URL = r'(?P<url>https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -46,12 +46,23 @@ class YahooIE(InfoExtractor): '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': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + url = mobj.group('url') webpage = self._download_webpage(url, video_id) items_json = self._search_regex( @@ -60,7 +71,8 @@ class YahooIE(InfoExtractor): if items_json is None: CONTENT_ID_REGEXES = [ r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"' + r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', + r'"first_videoid"\s*:\s*"([^"]+)"', ] long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') video_id = long_id diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index fcb5ff758..b86331e3c 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -9,7 +9,7 @@ from ..utils import ( class YouJizzIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$' + _VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$' _TEST = { 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', 'file': '2189178.flv', diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index cd35a1620..e28db2b5a 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1,7 +1,5 @@ # coding: utf-8 -import errno -import io import itertools import json import os.path @@ -21,7 +19,6 @@ from ..utils import ( compat_str, clean_html, - get_cachedir, get_element_by_id, get_element_by_attribute, ExtractorError, @@ -30,13 +27,13 @@ from ..utils import ( unescapeHTML, unified_strdate, orderedSet, - write_json_file, uppercase_escape, ) class YoutubeBaseInfoExtractor(InfoExtractor): """Provide base functions for Youtube extractors""" _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' + _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' @@ -50,12 +47,19 @@ class YoutubeBaseInfoExtractor(InfoExtractor): fatal=False)) def _login(self): + """ + Attempt to log in to YouTube. + True is returned if successful or skipped. + False is returned if login failed. + + If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. + """ (username, password) = self._get_login_info() # No authentication to be performed if username is None: if self._LOGIN_REQUIRED: raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) - return False + return True login_page = self._download_webpage( self._LOGIN_URL, None, @@ -73,6 +77,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): u'Email': username, u'GALX': galx, u'Passwd': password, + u'PersistentCookie': u'yes', u'_utf8': u'霱', u'bgresponse': u'js_disabled', @@ -88,6 +93,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): u'uilel': u'3', u'hl': u'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()) @@ -99,6 +105,68 @@ class YoutubeBaseInfoExtractor(InfoExtractor): note=u'Logging in', errnote=u'unable to log in', fatal=False) if login_results is False: return False + + if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: + raise ExtractorError(u'Please use your account password and a two-factor code instead of an application-specific password.', expected=True) + + # Two-Factor + # TODO add SMS and phone call support - these require making a request and then prompting the user + + if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: + tfa_code = self._get_tfa_info() + + if tfa_code is None: + self._downloader.report_warning(u'Two-factor authentication required. Provide it with --twofactor <code>') + self._downloader.report_warning(u'(Note that only TOTP (Google Authenticator App) codes work at this time.)') + return False + + # Unlike the first login form, secTok and timeStmp are both required for the TFA form + + match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) + if match is None: + self._downloader.report_warning(u'Failed to get secTok - did the page structure change?') + secTok = match.group(1) + match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) + if match is None: + self._downloader.report_warning(u'Failed to get timeStmp - did the page structure change?') + timeStmp = match.group(1) + + tfa_form_strs = { + u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', + u'smsToken': u'', + u'smsUserPin': tfa_code, + u'smsVerifyPin': u'Verify', + + u'PersistentCookie': u'yes', + u'checkConnection': u'', + u'checkedDomains': u'youtube', + u'pstMsg': u'1', + u'secTok': secTok, + u'timeStmp': timeStmp, + u'service': u'youtube', + u'hl': u'en_US', + } + tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in tfa_form_strs.items()) + tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') + + tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) + tfa_results = self._download_webpage( + tfa_req, None, + note=u'Submitting TFA code', errnote=u'unable to submit tfa', fatal=False) + + if tfa_results is False: + return False + + if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: + self._downloader.report_warning(u'Two-factor code expired. Please try again, or use a one-use backup code instead.') + return False + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: + self._downloader.report_warning(u'unable to log in - did the page structure change?') + return False + if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: + self._downloader.report_warning(u'Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.') + return False + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: self._downloader.report_warning(u'unable to log in: bad username or password') return False @@ -131,7 +199,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): IE_DESC = u'YouTube.com' _VALID_URL = r"""(?x)^ ( - (?:https?://|//)? # http(s):// or protocol-independent URL (optional) + (?:https?://|//) # http(s):// or protocol-independent URL (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| (?:www\.)?deturl\.com/www\.youtube\.com/| (?:www\.)?pwnyoutube\.com/| @@ -149,7 +217,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): ) )) |youtu\.be/ # just youtu.be/xxxx - |https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= + |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= ) )? # all until now is optional -> you can pass the naked ID ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID @@ -225,7 +293,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Dash webm audio - '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50}, + '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, # RTMP (unnamed) @@ -244,6 +312,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): u"upload_date": u"20121002", u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .", u"categories": [u'Science & Technology'], + 'like_count': int, + 'dislike_count': int, } }, { @@ -344,7 +414,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): """Indicate the download will use the RTMP protocol.""" self.to_screen(u'RTMP download detected') - def _extract_signature_function(self, video_id, player_url, slen): + def _signature_cache_id(self, example_sig): + """ Return a string representation of a signature """ + return u'.'.join(compat_str(len(part)) for part in example_sig.split('.')) + + def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', player_url) @@ -354,21 +428,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): player_id = id_m.group('id') # Read from filesystem cache - func_id = '%s_%s_%d' % (player_type, player_id, slen) + func_id = '%s_%s_%s' % ( + player_type, player_id, self._signature_cache_id(example_sig)) assert os.path.basename(func_id) == func_id - cache_dir = get_cachedir(self._downloader.params) - cache_enabled = cache_dir is not None - if cache_enabled: - cache_fn = os.path.join(os.path.expanduser(cache_dir), - u'youtube-sigfuncs', - func_id + '.json') - try: - with io.open(cache_fn, 'r', encoding='utf-8') as cachef: - cache_spec = json.load(cachef) - return lambda s: u''.join(s[i] for i in cache_spec) - except IOError: - pass # No cache available + cache_spec = self._downloader.cache.load(u'youtube-sigfuncs', func_id) + if cache_spec is not None: + return lambda s: u''.join(s[i] for i in cache_spec) if player_type == 'js': code = self._download_webpage( @@ -386,25 +452,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: assert False, 'Invalid player type %r' % player_type - if cache_enabled: - try: - test_string = u''.join(map(compat_chr, range(slen))) - cache_res = res(test_string) - cache_spec = [ord(c) for c in cache_res] - try: - os.makedirs(os.path.dirname(cache_fn)) - except OSError as ose: - if ose.errno != errno.EEXIST: - raise - write_json_file(cache_spec, cache_fn) - except Exception: - tb = traceback.format_exc() - self._downloader.report_warning( - u'Writing cache to %r failed: %s' % (cache_fn, tb)) + if cache_spec is None: + test_string = u''.join(map(compat_chr, range(len(example_sig)))) + cache_res = res(test_string) + cache_spec = [ord(c) for c in cache_res] + self._downloader.cache.store(u'youtube-sigfuncs', func_id, cache_spec) return res - def _print_sig_code(self, func, slen): + def _print_sig_code(self, func, example_sig): def gen_sig_code(idxs): def _genslice(start, end, step): starts = u'' if start == 0 else str(start) @@ -433,11 +489,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: yield _genslice(start, i, step) - test_string = u''.join(map(compat_chr, range(slen))) + test_string = u''.join(map(compat_chr, range(len(example_sig)))) cache_res = func(test_string) cache_spec = [ord(c) for c in cache_res] expr_code = u' + '.join(gen_sig_code(cache_spec)) - code = u'if len(s) == %d:\n return %s\n' % (slen, expr_code) + signature_id_tuple = '(%s)' % ( + ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) + code = (u'if tuple(len(p) for p in s.split(\'.\')) == %s:\n' + u' return %s\n') % (signature_id_tuple, expr_code) self.to_screen(u'Extracted signature function:\n' + code) def _parse_sig_js(self, jscode): @@ -465,20 +524,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if player_url.startswith(u'//'): player_url = u'https:' + player_url try: - player_id = (player_url, len(s)) + player_id = (player_url, self._signature_cache_id(s)) if player_id not in self._player_cache: func = self._extract_signature_function( - video_id, player_url, len(s) + video_id, player_url, s ) self._player_cache[player_id] = func func = self._player_cache[player_id] if self._downloader.params.get('youtube_print_sig_code'): - self._print_sig_code(func, len(s)) + self._print_sig_code(func, s) return func(s) except Exception as e: tb = traceback.format_exc() raise ExtractorError( - u'Automatic signature extraction failed: ' + tb, cause=e) + u'Signature extraction failed: ' + tb, cause=e) def _get_available_subtitles(self, video_id, webpage): try: @@ -493,6 +552,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): sub_lang_list = {} for l in lang_list: lang = l[1] + if lang in sub_lang_list: + continue params = compat_urllib_parse.urlencode({ 'lang': lang, 'v': video_id, @@ -695,7 +756,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) - m_cat_container = get_element_by_id("eow-category", video_webpage) + m_cat_container = self._search_regex( + r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', + video_webpage, 'categories', fatal=False) if m_cat_container: category = self._html_search_regex( r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', @@ -724,15 +787,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: video_description = u'' - def _extract_count(klass): + def _extract_count(count_name): count = self._search_regex( - r'class="%s">([\d,]+)</span>' % re.escape(klass), - video_webpage, klass, default=None) + r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name), + video_webpage, count_name, default=None) if count is not None: return int(count.replace(',', '')) return None - like_count = _extract_count(u'likes-count') - dislike_count = _extract_count(u'dislikes-count') + like_count = _extract_count(u'like') + dislike_count = _extract_count(u'dislike') # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) @@ -806,51 +869,54 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url_map = {} for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) - if 'itag' in url_data and 'url' in url_data: - url = url_data['url'][0] - if 'sig' in url_data: - url += '&signature=' + url_data['sig'][0] - elif 's' in url_data: - encrypted_sig = url_data['s'][0] - - if not age_gate: - jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - video_webpage, u'JS player URL') - player_url = json.loads(jsplayer_url_json) + if 'itag' not in url_data or 'url' not in url_data: + continue + format_id = url_data['itag'][0] + url = url_data['url'][0] + + if 'sig' in url_data: + url += '&signature=' + url_data['sig'][0] + elif 's' in url_data: + encrypted_sig = url_data['s'][0] + + if not age_gate: + jsplayer_url_json = self._search_regex( + r'"assets":.+?"js":\s*("[^"]+")', + video_webpage, u'JS player URL') + player_url = json.loads(jsplayer_url_json) + if player_url is None: + player_url_json = self._search_regex( + r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', + video_webpage, u'age gate player URL') + player_url = json.loads(player_url_json) + + if self._downloader.params.get('verbose'): if player_url is None: - player_url_json = self._search_regex( - r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', - video_webpage, u'age gate player URL') - player_url = json.loads(player_url_json) - - if self._downloader.params.get('verbose'): - if player_url is None: - player_version = 'unknown' - player_desc = 'unknown' + player_version = 'unknown' + player_desc = 'unknown' + else: + if player_url.endswith('swf'): + player_version = self._search_regex( + r'-(.+?)(?:/watch_as3)?\.swf$', player_url, + u'flash player', fatal=False) + player_desc = 'flash player %s' % player_version else: - if player_url.endswith('swf'): - player_version = self._search_regex( - r'-(.+?)(?:/watch_as3)?\.swf$', player_url, - u'flash player', fatal=False) - player_desc = 'flash player %s' % player_version - else: - player_version = self._search_regex( - r'html5player-([^/]+?)(?:/html5player)?\.js', - player_url, - 'html5 player', fatal=False) - player_desc = u'html5 player %s' % player_version - - parts_sizes = u'.'.join(compat_str(len(part)) for part in encrypted_sig.split('.')) - self.to_screen(u'encrypted signature length %d (%s), itag %s, %s' % - (len(encrypted_sig), parts_sizes, url_data['itag'][0], player_desc)) - - signature = self._decrypt_signature( - encrypted_sig, video_id, player_url, age_gate) - url += '&signature=' + signature - if 'ratebypass' not in url: - url += '&ratebypass=yes' - url_map[url_data['itag'][0]] = url + player_version = self._search_regex( + r'html5player-([^/]+?)(?:/html5player)?\.js', + player_url, + 'html5 player', fatal=False) + player_desc = u'html5 player %s' % player_version + + parts_sizes = self._signature_cache_id(encrypted_sig) + self.to_screen(u'{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) + + signature = self._decrypt_signature( + encrypted_sig, video_id, player_url, age_gate) + url += '&signature=' + signature + if 'ratebypass' not in url: + url += '&ratebypass=yes' + url_map[format_id] = url formats = _map_to_format_list(url_map) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] @@ -959,21 +1025,26 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): self._login() def _ids_to_results(self, ids): - return [self.url_result(vid_id, 'Youtube', video_id=vid_id) - for vid_id in ids] + return [ + self.url_result(vid_id, 'Youtube', video_id=vid_id) + for vid_id in ids] def _extract_mix(self, playlist_id): # The mixes are generated from a a single video # the id of the playlist is just 'RD' + video_id url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) - webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix') + webpage = self._download_webpage( + url, playlist_id, u'Downloading Youtube mix') search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) - title_span = (search_title('playlist-title') or - search_title('title long-title') or search_title('title')) + title_span = ( + search_title('playlist-title') or + search_title('title long-title') or + search_title('title')) title = clean_html(title_span) - video_re = r'''(?x)data-video-username=".*?".*? - href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id) - ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL)) + ids = orderedSet(re.findall( + r'''(?xs)data-video-username=".*?".*? + href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), + webpage)) url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, title) @@ -1066,6 +1137,7 @@ class YoutubeTopListIE(YoutubePlaylistIE): msg = u'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: @@ -1339,12 +1411,6 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = mobj.group('paging') return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) -class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' - _FEED_NAME = 'subscriptions' - _PLAYLIST_TITLE = u'Youtube Subscriptions' - class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): IE_DESC = u'YouTube.com recommended videos, "ytrec" keyword (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' @@ -1377,6 +1443,43 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): return self.url_result(playlist_id, 'YoutubePlaylist') +class YoutubeSubscriptionsIE(YoutubePlaylistIE): + IE_NAME = u'youtube:subscriptions' + IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' + + def _real_extract(self, url): + title = u'Youtube Subscriptions' + page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) + + # The extraction process is the same as for playlists, but the regex + # for the video ids doesn't contain an index + ids = [] + more_widget_html = content_html = page + + for page_num in itertools.count(1): + matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) + new_ids = orderedSet(matches) + ids.extend(new_ids) + + mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) + if not mobj: + break + + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), title, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) + content_html = more['content_html'] + more_widget_html = more['load_more_widget_html'] + + return { + '_type': 'playlist', + 'title': title, + 'entries': self._ids_to_results(ids), + } + + class YoutubeTruncatedURLIE(InfoExtractor): IE_NAME = 'youtube:truncated_url' IE_DESC = False # Do not list |