3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
11 compat_urllib_parse_unquote,
12 compat_urllib_request,
14 compat_xml_parse_error,
32 from .brightcove import BrightcoveIE
33 from .nbc import NBCSportsVPlayerIE
34 from .ooyala import OoyalaIE
35 from .rutv import RUTVIE
36 from .tvc import TVCIE
37 from .sportbox import SportBoxEmbedIE
38 from .smotri import SmotriIE
39 from .myvi import MyviIE
40 from .condenast import CondeNastIE
41 from .udn import UDNEmbedIE
42 from .senateisvp import SenateISVPIE
43 from .bliptv import BlipTVIE
44 from .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
49 from .onionstudios import OnionStudiosIE
50 from .snagfilms import SnagFilmsEmbedIE
53 class GenericIE(InfoExtractor):
54 IE_DESC = 'Generic downloader that works on some sites'
58 # Direct link to a video
60 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
61 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
66 'upload_date': '20100513',
69 # Direct link to media delivered compressed (until Accept-Encoding is *)
71 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
72 'md5': '128c42e68b13950268b648275386fc74',
74 'id': 'FictionJunction-Parallel_Hearts',
76 'title': 'FictionJunction-Parallel_Hearts',
77 'upload_date': '20140522',
79 'expected_warnings': [
80 'URL could be a direct video link, returning it as such.'
83 # Direct download with broken HEAD
85 'url': 'http://ai-radio.org:8000/radio.opus',
92 'skip_download': True, # infinite live stream
94 'expected_warnings': [
95 r'501.*Not Implemented'
98 # Direct link with incorrect MIME type
100 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
101 'md5': '4ccbebe5f36706d85221f204d7eb5913',
103 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
104 'id': '5_Lennart_Poettering_-_Systemd',
106 'title': '5_Lennart_Poettering_-_Systemd',
107 'upload_date': '20141120',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
115 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
117 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'title': 'Zero Punctuation',
119 'description': 're:.*groundbreaking video review series.*'
121 'playlist_mincount': 11,
123 # RSS feed with enclosure
125 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
127 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
129 'upload_date': '20150228',
130 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
133 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
135 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
139 'title': 'Automatics, robotics and biocybernetics',
140 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
141 'formats': 'mincount:16',
142 'subtitles': 'mincount:1',
145 'force_generic_extractor': True,
146 'skip_download': True,
149 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
151 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
156 'formats': 'mincount:1',
159 'skip_download': True,
162 # SMIL from https://www.restudy.dk/video/play/id/1637
164 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
168 'title': 'video_1637',
169 'formats': 'mincount:3',
172 'skip_download': True,
175 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
177 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
179 'id': 'smil-service',
181 'title': 'smil-service',
182 'formats': 'mincount:1',
185 'skip_download': True,
188 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
190 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
194 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
195 'formats': 'mincount:3',
198 'skip_download': True,
201 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
203 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
205 'id': 'mZlp2ctYIUEB',
207 'title': 'Tikibad ontruimd wegens brand',
208 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
209 'thumbnail': 're:^https?://.*\.jpg$',
213 'skip_download': True,
218 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
222 'upload_date': '20130224',
223 'uploader_id': 'TheVerge',
224 'description': 're:^Chris Ziegler takes a look at the\.*',
225 'uploader': 'The Verge',
226 'title': 'First Firefox OS phones side-by-side',
229 'skip_download': False,
233 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
234 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
236 'id': '13601338388002',
238 'uploader': 'www.hodiho.fr',
239 'title': 'R\u00e9gis plante sa Jeep',
242 # bandcamp page with custom domain
244 'add_ie': ['Bandcamp'],
245 'url': 'http://bronyrock.com/track/the-pony-mash',
249 'title': 'The Pony Mash',
250 'uploader': 'M_Pallante',
252 'skip': 'There is a limit of 200 free downloads / month for the test song',
254 # embedded brightcove video
255 # it also tests brightcove videos that need to set the 'Referer' in the
258 'add_ie': ['Brightcove'],
259 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
261 'id': '2765128793001',
263 'title': 'Le cours de bourse : l’analyse technique',
264 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
265 'uploader': 'BFM BUSINESS',
268 'skip_download': True,
272 # https://github.com/rg3/youtube-dl/issues/2253
273 'url': 'http://bcove.me/i6nfkrc3',
274 'md5': '0ba9446db037002366bab3b3eb30c88c',
276 'id': '3101154703001',
278 'title': 'Still no power',
279 'uploader': 'thestar.com',
280 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
282 'add_ie': ['Brightcove'],
285 'url': 'http://www.championat.com/video/football/v/87/87499.html',
286 'md5': 'fb973ecf6e4a78a67453647444222983',
288 'id': '3414141473001',
290 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
291 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
292 'uploader': 'Championat',
296 # https://github.com/rg3/youtube-dl/issues/3541
297 'add_ie': ['Brightcove'],
298 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
300 'id': '3866516442001',
302 'title': 'Leer mij vrouwen kennen: Aflevering 1',
303 'description': 'Leer mij vrouwen kennen: Aflevering 1',
304 'uploader': 'SBS Broadcasting',
306 'skip': 'Restricted to Netherlands',
308 'skip_download': True, # m3u8 download
313 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
314 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
316 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
318 'title': '2cc213299525360.mov', # that's what we get
320 'add_ie': ['Ooyala'],
323 # ooyala video embedded with http://player.ooyala.com/iframe.js
324 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
326 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
328 'title': '"Steve Jobs: Man in the Machine" trailer',
329 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
332 'skip_download': True,
335 # multiple ooyala embeds on SBN network websites
337 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
339 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
340 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
342 'playlist_mincount': 3,
344 'skip_download': True,
346 'add_ie': ['Ooyala'],
350 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
354 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
355 'upload_date': '20140225',
356 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
357 'uploader': 'Tested',
358 'uploader_id': 'testedcom',
360 # No need to test YoutubeIE here
362 'skip_download': True,
367 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
371 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
372 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
377 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
381 'title': 'Охотское море стало целиком российским',
382 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
386 'skip_download': True,
391 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
395 'title': 'Дошкольное воспитание',
400 'url': 'http://www.vestifinance.ru/articles/25753',
403 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
408 'title': 'Госзаказ. День 3',
414 'title': 'Госзаказ. День 2',
420 'title': 'Госзаказ. День 1',
426 'skip_download': True,
431 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
433 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
435 'title': 'Ужастики, русский трейлер (2015)',
436 'thumbnail': 're:^https?://.*\.jpg$',
442 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
445 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
447 'playlist_mincount': 7,
451 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
452 'md5': '65fdff94098e4a607385a60c5177c638',
456 'title': 'Hidden miracles of the natural world',
457 'uploader': 'Louie Schwartzberg',
458 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
461 # Embeded Ustream video
463 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
464 'md5': '27b99cdb639c9b12a79bca876a073417',
468 'uploader': 'AU SPA: The NSA and Privacy',
469 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
472 # nowvideo embed hidden behind percent encoding
474 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
475 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
477 'id': '06e53103ca9aa',
479 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
480 'description': 'No description',
485 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
486 'md5': '7653032cbb25bf6c80d80f217055fa43',
488 'id': '048195-004_PLUS7-F',
491 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
492 'upload_date': '20140320',
495 'skip_download': 'Requires rtmpdump'
500 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
504 'title': 'Alcaline, le concert avec Calogero',
505 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
506 'upload_date': '20150226',
507 'timestamp': 1424989860,
512 'skip_download': True,
514 'expected_warnings': [
520 'url': 'http://www.wired.com/2014/04/honda-asimo/',
521 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
523 'id': '53501be369702d3275860000',
525 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
530 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
531 'md5': '441aeeb82eb72c422c7f14ec533999cd',
533 'id': 'k2mm4bCdJ6CQ2i7c8o2',
535 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
538 'add_ie': ['Dailymotion'],
542 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
546 'title': 'The NBL Auction 2014',
547 'uploader': 'BADMINTON England',
548 'uploader_id': 'BADMINTONEvents',
549 'upload_date': '20140603',
550 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
552 'add_ie': ['Youtube'],
554 'skip_download': True,
559 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
560 'md5': '35727f82f58c76d996fc188f9755b0d5',
562 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
565 'description': 'Mario\'s life in the fast lane has never looked so good.',
568 # YouTube embed via <data-embed-url="">
570 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
574 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
575 'uploader': 'Gameloft',
576 'uploader_id': 'gameloft',
577 'upload_date': '20140828',
578 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
581 'skip_download': True,
586 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
588 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
590 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
591 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
596 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
598 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
599 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
605 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
610 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
611 'md5': '9d65602bf31c6e20014319c7d07fba27',
613 'id': '5123ea6d5e5a7',
616 'uploader': 'www.handjobhub.com',
617 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
620 # Multiple brightcove videos
621 # https://github.com/rg3/youtube-dl/issues/2283
623 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
625 'id': 'always-never',
626 'title': 'Always / Never - The New Yorker',
630 'extract_flat': False,
631 'skip_download': True,
636 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
637 'md5': '96f09a37e44da40dd083e12d9a683327',
641 'title': 'Ump changes call to ball',
642 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
644 'timestamp': 1401537900,
645 'upload_date': '20140531',
646 'thumbnail': 're:^https?://.*\.jpg$',
651 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
652 'md5': '8788b683c777a5cf25621eaf286d0c23',
656 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
658 'filesize': 182808282,
659 'uploader': 'education-portal.com',
663 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
664 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
668 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
670 'uploader': 'thoughtworks.wistia.com',
675 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
679 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
680 'uploader': 'Sophos Security',
681 'title': 'Chet Chat 171 - Oct 29, 2014',
682 'upload_date': '20141029',
687 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
691 'upload_date': '20141112',
692 'title': 'Rosetta #CometLanding webcast HL 10',
697 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
700 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
702 'playlist_mincount': 2,
706 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
710 'upload_date': '20141126',
711 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
716 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
718 'id': '730m_DandD_1901_512k',
720 'uploader': 'www.abc.net.au',
721 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
724 # embedded viddler video
726 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
730 'uploader': 'deadspin',
731 'title': 'WALL-TO-GORTAT',
732 'timestamp': 1422285291,
733 'upload_date': '20150126',
735 'add_ie': ['Viddler'],
739 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
743 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
744 'description': 'md5:601cb790edd05908957dae8aaa866465',
745 'upload_date': '20150220',
750 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
754 'upload_date': '20150212',
755 'uploader': 'The National Archives UK',
756 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
757 'uploader_id': 'NationalArchives08',
758 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
763 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
764 'playlist_mincount': 5,
766 'id': 'aanslagen-kopenhagen',
767 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
772 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
776 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
781 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
785 'upload_date': '20150226',
786 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
788 'title': 'John Carlson Postgame 2/25/15',
791 # Kaltura embed (different embed code)
793 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
797 'upload_date': '20150127',
798 'uploader_id': 'PremierMedia',
800 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
803 # Eagle.Platform embed (generic URL)
805 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
809 'title': 'Навальный вышел на свободу',
810 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
811 'thumbnail': 're:^https?://.*\.jpg$',
817 # ClipYou (Eagle.Platform) embed (custom URL)
819 'url': 'http://muz-tv.ru/play/7129/',
823 'title': "'O Sole Mio",
824 'thumbnail': 're:^https?://.*\.jpg$',
831 'url': 'http://muz-tv.ru/kinozal/view/7400/',
835 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
836 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
837 'thumbnail': 're:^https?://.*\.jpg$',
844 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
848 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
849 'thumbnail': 're:^https?://.*\.png$',
855 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
856 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
860 'title': 'Facebook Creates "On This Day" | Crunch Report',
865 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
869 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
874 # Crooks and Liars embed
876 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
880 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
881 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
882 'timestamp': 1428207000,
883 'upload_date': '20150405',
884 'uploader': 'Heather',
887 # Crooks and Liars external embed
889 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
891 'id': 'MTE3MjUtMzQ2MzA',
893 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
894 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
895 'timestamp': 1265032391,
896 'upload_date': '20100201',
897 'uploader': 'Heather',
900 # NBC Sports vplayer embed
902 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
904 'id': 'ln7x1qSThw4k',
906 'title': "PFT Live: New leader in the 'new-look' defense",
907 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
912 'url': 'http://www.udn.com/news/story/7314/822787',
913 'md5': 'fd2060e988c326991037b9aff9df21a6',
917 'title': '中一中男師變性 全校師生力挺',
918 'thumbnail': 're:^https?://.*\.jpg$',
923 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
925 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
927 'description': 'VIDEO: Index/Match versus VLOOKUP.',
928 'title': 'This is what separates the Excel masters from the wannabes',
932 'skip_download': True,
935 # Contains a SMIL manifest
937 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
941 'title': '+ Football: Lottery Champions League Europe',
942 'uploader': 'www.telewebion.com',
946 'skip_download': True,
949 # Brightcove URL in single quotes
951 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
952 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
954 'id': '4255764656001',
956 'title': 'SN Presents: Russell Martin, World Citizen',
957 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
958 'uploader': 'Rogers Sportsnet',
961 # Dailymotion Cloud video
963 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
964 'md5': '49444254273501a64675a7e68c502681',
966 'id': '5585de919473990de4bee11b',
969 'thumbnail': 're:^https?://.*\.jpe?g$',
974 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
978 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
979 'thumbnail': 're:^https?://.*\.jpe?g$',
980 'uploader': 'ClickHole',
981 'uploader_id': 'clickhole',
986 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
988 'id': '74849a00-85a9-11e1-9660-123139220831',
990 'title': '#whilewewatch',
995 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
996 'md5': '43662b577c018ad707a63766462b1e87',
1000 'title': 'New experience with Acrobat DC',
1001 'description': 'New experience with Acrobat DC',
1002 'duration': 248.667,
1007 def report_following_redirect(self, new_url):
1008 """Report information extraction."""
1009 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1011 def _extract_rss(self, url, video_id, doc):
1012 playlist_title = doc.find('./channel/title').text
1013 playlist_desc_el = doc.find('./channel/description')
1014 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1017 for it in doc.findall('./channel/item'):
1018 next_url = xpath_text(it, 'link', fatal=False)
1020 enclosure_nodes = it.findall('./enclosure')
1021 for e in enclosure_nodes:
1022 next_url = e.attrib.get('url')
1032 'title': it.find('title').text,
1036 '_type': 'playlist',
1038 'title': playlist_title,
1039 'description': playlist_desc,
1043 def _extract_camtasia(self, url, video_id, webpage):
1044 """ Returns None if no camtasia video can be found. """
1046 camtasia_cfg = self._search_regex(
1047 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1048 webpage, 'camtasia configuration file', default=None)
1049 if camtasia_cfg is None:
1052 title = self._html_search_meta('DC.title', webpage, fatal=True)
1054 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1055 camtasia_cfg = self._download_xml(
1056 camtasia_url, video_id,
1057 note='Downloading camtasia configuration',
1058 errnote='Failed to download camtasia configuration')
1059 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1062 for n in fileset_node.getchildren():
1063 url_n = n.find('./uri')
1068 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1069 'title': '%s - %s' % (title, n.tag),
1070 'url': compat_urlparse.urljoin(url, url_n.text),
1071 'duration': float_or_none(n.find('./duration').text),
1075 '_type': 'playlist',
1080 def _real_extract(self, url):
1081 if url.startswith('//'):
1084 'url': self.http_scheme() + url,
1087 parsed_url = compat_urlparse.urlparse(url)
1088 if not parsed_url.scheme:
1089 default_search = self._downloader.params.get('default_search')
1090 if default_search is None:
1091 default_search = 'fixup_error'
1093 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1095 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1096 return self.url_result('http://' + url)
1097 elif default_search != 'fixup_error':
1098 if default_search == 'auto_warning':
1099 if re.match(r'^(?:url|URL)$', url):
1100 raise ExtractorError(
1101 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1104 self._downloader.report_warning(
1105 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1106 return self.url_result('ytsearch:' + url)
1108 if default_search in ('error', 'fixup_error'):
1109 raise ExtractorError(
1110 '%r is not a valid URL. '
1111 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1112 % (url, url), expected=True)
1114 if ':' not in default_search:
1115 default_search += ':'
1116 return self.url_result(default_search + url)
1118 url, smuggled_data = unsmuggle_url(url)
1119 force_videoid = None
1120 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1121 if smuggled_data and 'force_videoid' in smuggled_data:
1122 force_videoid = smuggled_data['force_videoid']
1123 video_id = force_videoid
1125 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1127 self.to_screen('%s: Requesting header' % video_id)
1129 head_req = HEADRequest(url)
1130 head_response = self._request_webpage(
1132 note=False, errnote='Could not send HEAD request to %s' % url,
1135 if head_response is not False:
1136 # Check for redirect
1137 new_url = head_response.geturl()
1139 self.report_following_redirect(new_url)
1141 new_url = smuggle_url(
1142 new_url, {'force_videoid': force_videoid})
1143 return self.url_result(new_url)
1145 full_response = None
1146 if head_response is False:
1147 request = compat_urllib_request.Request(url)
1148 request.add_header('Accept-Encoding', '*')
1149 full_response = self._request_webpage(request, video_id)
1150 head_response = full_response
1152 # Check for direct link to a video
1153 content_type = head_response.headers.get('Content-Type', '')
1154 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1156 upload_date = unified_strdate(
1157 head_response.headers.get('Last-Modified'))
1160 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1163 'format_id': m.group('format_id'),
1165 'vcodec': 'none' if m.group('type') == 'audio' else None
1167 'upload_date': upload_date,
1170 if not self._downloader.params.get('test', False) and not is_intentional:
1171 force = self._downloader.params.get('force_generic_extractor', False)
1172 self._downloader.report_warning(
1173 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1175 if not full_response:
1176 request = compat_urllib_request.Request(url)
1177 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1178 # making it impossible to download only chunk of the file (yet we need only 512kB to
1179 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1180 # that will always result in downloading the whole file that is not desirable.
1181 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1182 # to accept raw bytes and being able to download only a chunk.
1183 # It may probably better to solve this by checking Content-Type for application/octet-stream
1184 # after HEAD request finishes, but not sure if we can rely on this.
1185 request.add_header('Accept-Encoding', '*')
1186 full_response = self._request_webpage(request, video_id)
1188 # Maybe it's a direct link to a video?
1189 # Be careful not to download the whole thing!
1190 first_bytes = full_response.read(512)
1191 if not is_html(first_bytes):
1192 self._downloader.report_warning(
1193 'URL could be a direct video link, returning it as such.')
1194 upload_date = unified_strdate(
1195 head_response.headers.get('Last-Modified'))
1198 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1201 'upload_date': upload_date,
1204 webpage = self._webpage_read_content(
1205 full_response, url, video_id, prefix=first_bytes)
1207 self.report_extraction(video_id)
1209 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1211 doc = parse_xml(webpage)
1212 if doc.tag == 'rss':
1213 return self._extract_rss(url, video_id, doc)
1214 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1215 return self._parse_smil(doc, url, video_id)
1216 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1217 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1218 except compat_xml_parse_error:
1221 # Is it a Camtasia project?
1222 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1223 if camtasia_res is not None:
1226 # Sometimes embedded video player is hidden behind percent encoding
1227 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1228 # Unescaping the whole page allows to handle those cases in a generic way
1229 webpage = compat_urllib_parse_unquote(webpage)
1231 # it's tempting to parse this further, but you would
1232 # have to take into account all the variations like
1233 # Video Title - Site Name
1234 # Site Name | Video Title
1235 # Video Title - Tagline | Site Name
1236 # and so on and so forth; it's just not practical
1237 video_title = self._html_search_regex(
1238 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1241 # Try to detect age limit automatically
1242 age_limit = self._rta_search(webpage)
1243 # And then there are the jokers who advertise that they use RTA,
1244 # but actually don't.
1245 AGE_LIMIT_MARKERS = [
1246 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1248 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1251 # video uploader is domain name
1252 video_uploader = self._search_regex(
1253 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1256 def _playlist_from_matches(matches, getter=None, ie=None):
1258 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1260 return self.playlist_result(
1261 urlrs, playlist_id=video_id, playlist_title=video_title)
1263 # Look for BrightCove:
1264 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1266 self.to_screen('Brightcove video detected.')
1269 'url': smuggle_url(bc_url, {'Referer': url}),
1270 'ie_key': 'Brightcove'
1271 } for bc_url in bc_urls]
1274 '_type': 'playlist',
1275 'title': video_title,
1280 # Look for embedded rtl.nl player
1281 matches = re.findall(
1282 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1285 return _playlist_from_matches(matches, ie='RtlNl')
1287 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1288 if vimeo_url is not None:
1289 return self.url_result(vimeo_url)
1291 vid_me_embed_url = self._search_regex(
1292 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1293 webpage, 'vid.me embed', default=None)
1294 if vid_me_embed_url is not None:
1295 return self.url_result(vid_me_embed_url, 'Vidme')
1297 # Look for embedded YouTube player
1298 matches = re.findall(r'''(?x)
1307 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1311 return _playlist_from_matches(
1312 matches, lambda m: unescapeHTML(m[1]))
1314 # Look for lazyYT YouTube embed
1315 matches = re.findall(
1316 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1318 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1320 # Look for embedded Dailymotion player
1321 matches = re.findall(
1322 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1324 return _playlist_from_matches(
1325 matches, lambda m: unescapeHTML(m[1]))
1327 # Look for embedded Dailymotion playlist player (#3822)
1329 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1331 playlists = re.findall(
1332 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1334 return _playlist_from_matches(
1335 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1337 # Look for embedded Wistia player
1339 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1341 embed_url = self._proto_relative_url(
1342 unescapeHTML(match.group('url')))
1344 '_type': 'url_transparent',
1347 'uploader': video_uploader,
1348 'title': video_title,
1352 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1355 '_type': 'url_transparent',
1356 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1358 'uploader': video_uploader,
1359 'title': video_title,
1360 'id': match.group('id')
1363 # Look for embedded blip.tv player
1364 bliptv_url = BlipTVIE._extract_url(webpage)
1366 return self.url_result(bliptv_url, 'BlipTV')
1368 # Look for SVT player
1369 svt_url = SVTIE._extract_url(webpage)
1371 return self.url_result(svt_url, 'SVT')
1373 # Look for embedded condenast player
1374 matches = re.findall(
1375 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1379 '_type': 'playlist',
1382 'ie_key': 'CondeNast',
1384 } for ma in matches],
1385 'title': video_title,
1389 # Look for Bandcamp pages with custom domain
1390 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1391 if mobj is not None:
1392 burl = unescapeHTML(mobj.group(1))
1393 # Don't set the extractor because it can be a track url or an album
1394 return self.url_result(burl)
1396 # Look for embedded Vevo player
1398 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1399 if mobj is not None:
1400 return self.url_result(mobj.group('url'))
1402 # Look for embedded Viddler player
1404 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1406 if mobj is not None:
1407 return self.url_result(mobj.group('url'))
1409 # Look for NYTimes player
1411 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1413 if mobj is not None:
1414 return self.url_result(mobj.group('url'))
1416 # Look for Libsyn player
1418 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1419 if mobj is not None:
1420 return self.url_result(mobj.group('url'))
1422 # Look for Ooyala videos
1423 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1424 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1425 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1426 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1427 if mobj is not None:
1428 return OoyalaIE._build_url_result(mobj.group('ec'))
1430 # Look for multiple Ooyala embeds on SBN network websites
1431 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1432 if mobj is not None:
1433 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1435 return _playlist_from_matches(
1436 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1438 # Look for Aparat videos
1439 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1440 if mobj is not None:
1441 return self.url_result(mobj.group(1), 'Aparat')
1443 # Look for MPORA videos
1444 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1445 if mobj is not None:
1446 return self.url_result(mobj.group(1), 'Mpora')
1448 # Look for embedded NovaMov-based player
1450 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1451 (?P<url>http://(?:(?:embed|www)\.)?
1453 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1454 videoweed\.(?:es|com)|
1455 movshare\.(?:net|sx|ag)|
1456 divxstage\.(?:eu|net|ch|co|at|ag))
1457 /embed\.php.+?)\1''', webpage)
1458 if mobj is not None:
1459 return self.url_result(mobj.group('url'))
1461 # Look for embedded Facebook player
1463 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1464 if mobj is not None:
1465 return self.url_result(mobj.group('url'), 'Facebook')
1467 # Look for embedded VK player
1468 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1469 if mobj is not None:
1470 return self.url_result(mobj.group('url'), 'VK')
1472 # Look for embedded ivi player
1473 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1474 if mobj is not None:
1475 return self.url_result(mobj.group('url'), 'Ivi')
1477 # Look for embedded Huffington Post player
1479 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1480 if mobj is not None:
1481 return self.url_result(mobj.group('url'), 'HuffPost')
1484 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1485 if mobj is not None:
1486 return self.url_result(mobj.group('url'))
1487 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1488 if mobj is not None:
1489 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1491 # Look for funnyordie embed
1492 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1494 return _playlist_from_matches(
1495 matches, getter=unescapeHTML, ie='FunnyOrDie')
1497 # Look for BBC iPlayer embed
1498 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1500 return _playlist_from_matches(matches, ie='BBCCoUk')
1502 # Look for embedded RUTV player
1503 rutv_url = RUTVIE._extract_url(webpage)
1505 return self.url_result(rutv_url, 'RUTV')
1507 # Look for embedded TVC player
1508 tvc_url = TVCIE._extract_url(webpage)
1510 return self.url_result(tvc_url, 'TVC')
1512 # Look for embedded SportBox player
1513 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1515 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1517 # Look for embedded PornHub player
1518 pornhub_url = PornHubIE._extract_url(webpage)
1520 return self.url_result(pornhub_url, 'PornHub')
1522 # Look for embedded XHamster player
1523 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1525 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1527 # Look for embedded Tvigle player
1529 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1530 if mobj is not None:
1531 return self.url_result(mobj.group('url'), 'Tvigle')
1533 # Look for embedded TED player
1535 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1536 if mobj is not None:
1537 return self.url_result(mobj.group('url'), 'TED')
1539 # Look for embedded Ustream videos
1541 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1542 if mobj is not None:
1543 return self.url_result(mobj.group('url'), 'Ustream')
1545 # Look for embedded arte.tv player
1547 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1549 if mobj is not None:
1550 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1552 # Look for embedded francetv player
1554 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1556 if mobj is not None:
1557 return self.url_result(mobj.group('url'))
1559 # Look for embedded smotri.com player
1560 smotri_url = SmotriIE._extract_url(webpage)
1562 return self.url_result(smotri_url, 'Smotri')
1564 # Look for embedded Myvi.ru player
1565 myvi_url = MyviIE._extract_url(webpage)
1567 return self.url_result(myvi_url)
1569 # Look for embeded soundcloud player
1571 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1573 if mobj is not None:
1574 url = unescapeHTML(mobj.group('url'))
1575 return self.url_result(url)
1577 # Look for embedded vulture.com player
1579 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1581 if mobj is not None:
1582 url = unescapeHTML(mobj.group('url'))
1583 return self.url_result(url, ie='Vulture')
1585 # Look for embedded mtvservices player
1587 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1589 if mobj is not None:
1590 url = unescapeHTML(mobj.group('url'))
1591 return self.url_result(url, ie='MTVServicesEmbedded')
1593 # Look for embedded yahoo player
1595 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1597 if mobj is not None:
1598 return self.url_result(mobj.group('url'), 'Yahoo')
1600 # Look for embedded sbs.com.au player
1604 <meta\s+property="og:video"\s+content=|
1607 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1609 if mobj is not None:
1610 return self.url_result(mobj.group('url'), 'SBS')
1612 # Look for embedded Cinchcast player
1614 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1616 if mobj is not None:
1617 return self.url_result(mobj.group('url'), 'Cinchcast')
1620 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1624 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1626 if mobj is not None:
1627 return self.url_result(mobj.group('url'), 'MLB')
1630 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1632 if mobj is not None:
1633 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1636 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1638 if mobj is not None:
1639 return self.url_result(mobj.group('url'), 'Livestream')
1641 # Look for Zapiks embed
1643 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1644 if mobj is not None:
1645 return self.url_result(mobj.group('url'), 'Zapiks')
1647 # Look for Kaltura embeds
1648 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1649 re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
1650 if mobj is not None:
1651 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1653 # Look for Eagle.Platform embeds
1655 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1656 if mobj is not None:
1657 return self.url_result(mobj.group('url'), 'EaglePlatform')
1659 # Look for ClipYou (uses Eagle.Platform) embeds
1661 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1662 if mobj is not None:
1663 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1665 # Look for Pladform embeds
1667 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1668 if mobj is not None:
1669 return self.url_result(mobj.group('url'), 'Pladform')
1671 # Look for Playwire embeds
1673 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1674 if mobj is not None:
1675 return self.url_result(mobj.group('url'))
1677 # Look for 5min embeds
1679 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1680 if mobj is not None:
1681 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1683 # Look for Crooks and Liars embeds
1685 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1686 if mobj is not None:
1687 return self.url_result(mobj.group('url'))
1689 # Look for NBC Sports VPlayer embeds
1690 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1692 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1694 # Look for UDN embeds
1696 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1697 if mobj is not None:
1698 return self.url_result(
1699 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1701 # Look for Senate ISVP iframe
1702 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1704 return self.url_result(senate_isvp_url, 'SenateISVP')
1706 # Look for Dailymotion Cloud videos
1707 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1709 return self.url_result(dmcloud_url, 'DailymotionCloud')
1711 # Look for OnionStudios embeds
1712 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1713 if onionstudios_url:
1714 return self.url_result(onionstudios_url)
1716 # Look for SnagFilms embeds
1717 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1719 return self.url_result(snagfilms_url)
1721 # Look for AdobeTVVideo embeds
1723 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1725 if mobj is not None:
1726 return self.url_result(
1727 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1730 def check_video(vurl):
1731 if YoutubeIE.suitable(vurl):
1733 vpath = compat_urlparse.urlparse(vurl).path
1734 vext = determine_ext(vpath)
1735 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1737 def filter_video(urls):
1738 return list(filter(check_video, urls))
1740 # Start with something easy: JW Player in SWFObject
1741 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1743 # Look for gorilla-vid style embedding
1744 found = filter_video(re.findall(r'''(?sx)
1748 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1751 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1753 # Broaden the search a little bit
1754 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1756 # Broaden the findall a little bit: JWPlayer JS loader
1757 found = filter_video(re.findall(
1758 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1761 found = filter_video(re.findall(r'''(?xs)
1762 flowplayer\("[^"]+",\s*
1764 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1765 ["']?url["']?\s*:\s*["']([^"']+)["']
1770 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1772 # Try to find twitter cards info
1773 found = filter_video(re.findall(
1774 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1776 # We look for Open Graph info:
1777 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1778 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1779 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1780 if m_video_type is not None:
1781 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1784 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1786 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1788 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1789 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1792 # Look also in Refresh HTTP header
1793 refresh_header = head_response.headers.get('Refresh')
1795 found = re.search(REDIRECT_REGEX, refresh_header)
1797 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1798 self.report_following_redirect(new_url)
1804 raise UnsupportedError(url)
1807 for video_url in found:
1808 video_url = compat_urlparse.urljoin(url, video_url)
1809 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1811 # Sometimes, jwplayer extraction will result in a YouTube URL
1812 if YoutubeIE.suitable(video_url):
1813 entries.append(self.url_result(video_url, 'Youtube'))
1816 # here's a fun little line of code for you:
1817 video_id = os.path.splitext(video_id)[0]
1819 ext = determine_ext(video_url)
1823 'formats': self._extract_smil_formats(video_url, video_id),
1824 'uploader': video_uploader,
1825 'title': video_title,
1826 'age_limit': age_limit,
1829 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1834 'uploader': video_uploader,
1835 'title': video_title,
1836 'age_limit': age_limit,
1839 if len(entries) == 1:
1842 for num, e in enumerate(entries, start=1):
1843 # 'url' results don't have a title
1844 if e.get('title') is not None:
1845 e['title'] = '%s (%d)' % (e['title'], num)
1847 '_type': 'playlist',