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',
135 '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',
139 'upload_date': '20130224',
140 'uploader_id': 'TheVerge',
141 'description': 're:^Chris Ziegler takes a look at the\.*',
142 'uploader': 'The Verge',
143 'title': 'First Firefox OS phones side-by-side',
146 'skip_download': False,
150 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
151 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
153 'id': '13601338388002',
155 'uploader': 'www.hodiho.fr',
156 'title': 'R\u00e9gis plante sa Jeep',
159 # bandcamp page with custom domain
161 'add_ie': ['Bandcamp'],
162 'url': 'http://bronyrock.com/track/the-pony-mash',
166 'title': 'The Pony Mash',
167 'uploader': 'M_Pallante',
169 'skip': 'There is a limit of 200 free downloads / month for the test song',
171 # embedded brightcove video
172 # it also tests brightcove videos that need to set the 'Referer' in the
175 'add_ie': ['Brightcove'],
176 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
178 'id': '2765128793001',
180 'title': 'Le cours de bourse : l’analyse technique',
181 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
182 'uploader': 'BFM BUSINESS',
185 'skip_download': True,
189 # https://github.com/rg3/youtube-dl/issues/2253
190 'url': 'http://bcove.me/i6nfkrc3',
191 'md5': '0ba9446db037002366bab3b3eb30c88c',
193 'id': '3101154703001',
195 'title': 'Still no power',
196 'uploader': 'thestar.com',
197 '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.',
199 'add_ie': ['Brightcove'],
202 'url': 'http://www.championat.com/video/football/v/87/87499.html',
203 'md5': 'fb973ecf6e4a78a67453647444222983',
205 'id': '3414141473001',
207 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
208 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
209 'uploader': 'Championat',
213 # https://github.com/rg3/youtube-dl/issues/3541
214 'add_ie': ['Brightcove'],
215 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
217 'id': '3866516442001',
219 'title': 'Leer mij vrouwen kennen: Aflevering 1',
220 'description': 'Leer mij vrouwen kennen: Aflevering 1',
221 'uploader': 'SBS Broadcasting',
223 'skip': 'Restricted to Netherlands',
225 'skip_download': True, # m3u8 download
230 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
231 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
233 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
235 'title': '2cc213299525360.mov', # that's what we get
237 'add_ie': ['Ooyala'],
239 # multiple ooyala embeds on SBN network websites
241 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
243 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
244 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
246 'playlist_mincount': 3,
248 'skip_download': True,
250 'add_ie': ['Ooyala'],
254 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
258 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
259 'upload_date': '20140225',
260 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
261 'uploader': 'Tested',
262 'uploader_id': 'testedcom',
264 # No need to test YoutubeIE here
266 'skip_download': True,
271 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
275 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
276 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
281 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
285 'title': 'Охотское море стало целиком российским',
286 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
290 'skip_download': True,
295 '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/',
299 'title': 'Дошкольное воспитание',
304 'url': 'http://www.vestifinance.ru/articles/25753',
307 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
312 'title': 'Госзаказ. День 3',
318 'title': 'Госзаказ. День 2',
324 'title': 'Госзаказ. День 1',
330 'skip_download': True,
335 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
337 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
339 'title': 'Ужастики, русский трейлер (2015)',
340 'thumbnail': 're:^https?://.*\.jpg$',
346 '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',
349 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
351 'playlist_mincount': 7,
355 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
356 'md5': '65fdff94098e4a607385a60c5177c638',
360 'title': 'Hidden miracles of the natural world',
361 'uploader': 'Louie Schwartzberg',
362 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
365 # Embeded Ustream video
367 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
368 'md5': '27b99cdb639c9b12a79bca876a073417',
372 'uploader': 'AU SPA: The NSA and Privacy',
373 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
376 # nowvideo embed hidden behind percent encoding
378 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
379 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
381 'id': '06e53103ca9aa',
383 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
384 'description': 'No description',
389 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
390 'md5': '7653032cbb25bf6c80d80f217055fa43',
392 'id': '048195-004_PLUS7-F',
395 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
396 'upload_date': '20140320',
399 'skip_download': 'Requires rtmpdump'
404 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
408 'title': 'Alcaline, le concert avec Calogero',
409 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
410 'upload_date': '20150226',
411 'timestamp': 1424989860,
416 'skip_download': True,
418 'expected_warnings': [
424 'url': 'http://www.wired.com/2014/04/honda-asimo/',
425 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
427 'id': '53501be369702d3275860000',
429 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
434 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
435 'md5': '441aeeb82eb72c422c7f14ec533999cd',
437 'id': 'k2mm4bCdJ6CQ2i7c8o2',
439 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
442 'add_ie': ['Dailymotion'],
446 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
450 'title': 'The NBL Auction 2014',
451 'uploader': 'BADMINTON England',
452 'uploader_id': 'BADMINTONEvents',
453 'upload_date': '20140603',
454 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
456 'add_ie': ['Youtube'],
458 'skip_download': True,
463 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
464 'md5': '35727f82f58c76d996fc188f9755b0d5',
466 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
469 'description': 'Mario\'s life in the fast lane has never looked so good.',
472 # YouTube embed via <data-embed-url="">
474 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
478 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
479 'uploader': 'Gameloft',
480 'uploader_id': 'gameloft',
481 'upload_date': '20140828',
482 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
485 'skip_download': True,
490 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
492 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
494 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
495 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
500 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
502 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
503 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
509 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
514 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
515 'md5': '9d65602bf31c6e20014319c7d07fba27',
517 'id': '5123ea6d5e5a7',
520 'uploader': 'www.handjobhub.com',
521 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
524 # Multiple brightcove videos
525 # https://github.com/rg3/youtube-dl/issues/2283
527 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
529 'id': 'always-never',
530 'title': 'Always / Never - The New Yorker',
534 'extract_flat': False,
535 'skip_download': True,
540 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
541 'md5': '96f09a37e44da40dd083e12d9a683327',
545 'title': 'Ump changes call to ball',
546 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
548 'timestamp': 1401537900,
549 'upload_date': '20140531',
550 'thumbnail': 're:^https?://.*\.jpg$',
555 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
556 'md5': '8788b683c777a5cf25621eaf286d0c23',
560 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
562 'filesize': 182808282,
563 'uploader': 'education-portal.com',
567 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
568 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
572 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
574 'uploader': 'thoughtworks.wistia.com',
579 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
583 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
584 'uploader': 'Sophos Security',
585 'title': 'Chet Chat 171 - Oct 29, 2014',
586 'upload_date': '20141029',
591 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
595 'upload_date': '20141112',
596 'title': 'Rosetta #CometLanding webcast HL 10',
601 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
604 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
606 'playlist_mincount': 2,
610 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
614 'upload_date': '20141126',
615 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
620 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
622 'id': '730m_DandD_1901_512k',
624 'uploader': 'www.abc.net.au',
625 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
628 # embedded viddler video
630 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
634 'uploader': 'deadspin',
635 'title': 'WALL-TO-GORTAT',
636 'timestamp': 1422285291,
637 'upload_date': '20150126',
639 'add_ie': ['Viddler'],
643 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
647 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
648 'description': 'md5:601cb790edd05908957dae8aaa866465',
649 'upload_date': '20150220',
654 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
658 'upload_date': '20150212',
659 'uploader': 'The National Archives UK',
660 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
661 'uploader_id': 'NationalArchives08',
662 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
667 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
668 'playlist_mincount': 5,
670 'id': 'aanslagen-kopenhagen',
671 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
676 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
680 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
685 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
689 'upload_date': '20150226',
690 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
692 'title': 'John Carlson Postgame 2/25/15',
695 # Kaltura embed (different embed code)
697 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
701 'upload_date': '20150127',
702 'uploader_id': 'PremierMedia',
704 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
707 # Eagle.Platform embed (generic URL)
709 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
713 'title': 'Навальный вышел на свободу',
714 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
715 'thumbnail': 're:^https?://.*\.jpg$',
721 # ClipYou (Eagle.Platform) embed (custom URL)
723 'url': 'http://muz-tv.ru/play/7129/',
727 'title': "'O Sole Mio",
728 'thumbnail': 're:^https?://.*\.jpg$',
735 'url': 'http://muz-tv.ru/kinozal/view/7400/',
739 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
740 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
741 'thumbnail': 're:^https?://.*\.jpg$',
748 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
752 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
753 'thumbnail': 're:^https?://.*\.png$',
759 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
760 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
764 'title': 'Facebook Creates "On This Day" | Crunch Report',
769 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
773 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
778 # Crooks and Liars embed
780 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
784 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
785 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
786 'timestamp': 1428207000,
787 'upload_date': '20150405',
788 'uploader': 'Heather',
791 # Crooks and Liars external embed
793 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
795 'id': 'MTE3MjUtMzQ2MzA',
797 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
798 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
799 'timestamp': 1265032391,
800 'upload_date': '20100201',
801 'uploader': 'Heather',
804 # NBC Sports vplayer embed
806 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
808 'id': 'ln7x1qSThw4k',
810 'title': "PFT Live: New leader in the 'new-look' defense",
811 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
816 'url': 'http://www.udn.com/news/story/7314/822787',
817 'md5': 'fd2060e988c326991037b9aff9df21a6',
821 'title': '中一中男師變性 全校師生力挺',
822 'thumbnail': 're:^https?://.*\.jpg$',
827 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
829 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
831 'description': 'VIDEO: Index/Match versus VLOOKUP.',
832 'title': 'This is what separates the Excel masters from the wannabes',
836 'skip_download': True,
839 # Contains a SMIL manifest
841 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
845 'title': '+ Football: Lottery Champions League Europe',
846 'uploader': 'www.telewebion.com',
850 'skip_download': True,
853 # Brightcove URL in single quotes
855 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
856 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
858 'id': '4255764656001',
860 'title': 'SN Presents: Russell Martin, World Citizen',
861 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
862 'uploader': 'Rogers Sportsnet',
865 # Dailymotion Cloud video
867 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
868 'md5': '49444254273501a64675a7e68c502681',
870 'id': '5585de919473990de4bee11b',
873 'thumbnail': 're:^https?://.*\.jpe?g$',
878 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
882 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
883 'thumbnail': 're:^https?://.*\.jpe?g$',
884 'uploader': 'ClickHole',
885 'uploader_id': 'clickhole',
890 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
892 'id': '74849a00-85a9-11e1-9660-123139220831',
894 'title': '#whilewewatch',
899 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
900 'md5': '43662b577c018ad707a63766462b1e87',
904 'title': 'New experience with Acrobat DC',
905 'description': 'New experience with Acrobat DC',
911 def report_following_redirect(self, new_url):
912 """Report information extraction."""
913 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
915 def _extract_rss(self, url, video_id, doc):
916 playlist_title = doc.find('./channel/title').text
917 playlist_desc_el = doc.find('./channel/description')
918 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
921 for it in doc.findall('./channel/item'):
922 next_url = xpath_text(it, 'link', fatal=False)
924 enclosure_nodes = it.findall('./enclosure')
925 for e in enclosure_nodes:
926 next_url = e.attrib.get('url')
936 'title': it.find('title').text,
942 'title': playlist_title,
943 'description': playlist_desc,
947 def _extract_camtasia(self, url, video_id, webpage):
948 """ Returns None if no camtasia video can be found. """
950 camtasia_cfg = self._search_regex(
951 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
952 webpage, 'camtasia configuration file', default=None)
953 if camtasia_cfg is None:
956 title = self._html_search_meta('DC.title', webpage, fatal=True)
958 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
959 camtasia_cfg = self._download_xml(
960 camtasia_url, video_id,
961 note='Downloading camtasia configuration',
962 errnote='Failed to download camtasia configuration')
963 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
966 for n in fileset_node.getchildren():
967 url_n = n.find('./uri')
972 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
973 'title': '%s - %s' % (title, n.tag),
974 'url': compat_urlparse.urljoin(url, url_n.text),
975 'duration': float_or_none(n.find('./duration').text),
984 def _real_extract(self, url):
985 if url.startswith('//'):
988 'url': self.http_scheme() + url,
991 parsed_url = compat_urlparse.urlparse(url)
992 if not parsed_url.scheme:
993 default_search = self._downloader.params.get('default_search')
994 if default_search is None:
995 default_search = 'fixup_error'
997 if default_search in ('auto', 'auto_warning', 'fixup_error'):
999 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1000 return self.url_result('http://' + url)
1001 elif default_search != 'fixup_error':
1002 if default_search == 'auto_warning':
1003 if re.match(r'^(?:url|URL)$', url):
1004 raise ExtractorError(
1005 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1008 self._downloader.report_warning(
1009 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1010 return self.url_result('ytsearch:' + url)
1012 if default_search in ('error', 'fixup_error'):
1013 raise ExtractorError(
1014 '%r is not a valid URL. '
1015 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1016 % (url, url), expected=True)
1018 if ':' not in default_search:
1019 default_search += ':'
1020 return self.url_result(default_search + url)
1022 url, smuggled_data = unsmuggle_url(url)
1023 force_videoid = None
1024 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1025 if smuggled_data and 'force_videoid' in smuggled_data:
1026 force_videoid = smuggled_data['force_videoid']
1027 video_id = force_videoid
1029 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1031 self.to_screen('%s: Requesting header' % video_id)
1033 head_req = HEADRequest(url)
1034 head_response = self._request_webpage(
1036 note=False, errnote='Could not send HEAD request to %s' % url,
1039 if head_response is not False:
1040 # Check for redirect
1041 new_url = head_response.geturl()
1043 self.report_following_redirect(new_url)
1045 new_url = smuggle_url(
1046 new_url, {'force_videoid': force_videoid})
1047 return self.url_result(new_url)
1049 full_response = None
1050 if head_response is False:
1051 request = compat_urllib_request.Request(url)
1052 request.add_header('Accept-Encoding', '*')
1053 full_response = self._request_webpage(request, video_id)
1054 head_response = full_response
1056 # Check for direct link to a video
1057 content_type = head_response.headers.get('Content-Type', '')
1058 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1060 upload_date = unified_strdate(
1061 head_response.headers.get('Last-Modified'))
1064 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1067 'format_id': m.group('format_id'),
1069 'vcodec': 'none' if m.group('type') == 'audio' else None
1071 'upload_date': upload_date,
1074 if not self._downloader.params.get('test', False) and not is_intentional:
1075 force = self._downloader.params.get('force_generic_extractor', False)
1076 self._downloader.report_warning(
1077 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1079 if not full_response:
1080 request = compat_urllib_request.Request(url)
1081 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1082 # making it impossible to download only chunk of the file (yet we need only 512kB to
1083 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1084 # that will always result in downloading the whole file that is not desirable.
1085 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1086 # to accept raw bytes and being able to download only a chunk.
1087 # It may probably better to solve this by checking Content-Type for application/octet-stream
1088 # after HEAD request finishes, but not sure if we can rely on this.
1089 request.add_header('Accept-Encoding', '*')
1090 full_response = self._request_webpage(request, video_id)
1092 # Maybe it's a direct link to a video?
1093 # Be careful not to download the whole thing!
1094 first_bytes = full_response.read(512)
1095 if not is_html(first_bytes):
1096 self._downloader.report_warning(
1097 'URL could be a direct video link, returning it as such.')
1098 upload_date = unified_strdate(
1099 head_response.headers.get('Last-Modified'))
1102 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1105 'upload_date': upload_date,
1108 webpage = self._webpage_read_content(
1109 full_response, url, video_id, prefix=first_bytes)
1111 self.report_extraction(video_id)
1113 # Is it an RSS feed or a SMIL file?
1115 doc = parse_xml(webpage)
1116 if doc.tag == 'rss':
1117 return self._extract_rss(url, video_id, doc)
1118 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1119 return self._parse_smil(doc, url, video_id)
1120 except compat_xml_parse_error:
1123 # Is it a Camtasia project?
1124 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1125 if camtasia_res is not None:
1128 # Sometimes embedded video player is hidden behind percent encoding
1129 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1130 # Unescaping the whole page allows to handle those cases in a generic way
1131 webpage = compat_urllib_parse_unquote(webpage)
1133 # it's tempting to parse this further, but you would
1134 # have to take into account all the variations like
1135 # Video Title - Site Name
1136 # Site Name | Video Title
1137 # Video Title - Tagline | Site Name
1138 # and so on and so forth; it's just not practical
1139 video_title = self._html_search_regex(
1140 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1143 # Try to detect age limit automatically
1144 age_limit = self._rta_search(webpage)
1145 # And then there are the jokers who advertise that they use RTA,
1146 # but actually don't.
1147 AGE_LIMIT_MARKERS = [
1148 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1150 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1153 # video uploader is domain name
1154 video_uploader = self._search_regex(
1155 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1158 def _playlist_from_matches(matches, getter=None, ie=None):
1160 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1162 return self.playlist_result(
1163 urlrs, playlist_id=video_id, playlist_title=video_title)
1165 # Look for BrightCove:
1166 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1168 self.to_screen('Brightcove video detected.')
1171 'url': smuggle_url(bc_url, {'Referer': url}),
1172 'ie_key': 'Brightcove'
1173 } for bc_url in bc_urls]
1176 '_type': 'playlist',
1177 'title': video_title,
1182 # Look for embedded rtl.nl player
1183 matches = re.findall(
1184 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1187 return _playlist_from_matches(matches, ie='RtlNl')
1189 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1190 if vimeo_url is not None:
1191 return self.url_result(vimeo_url)
1193 vid_me_embed_url = self._search_regex(
1194 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1195 webpage, 'vid.me embed', default=None)
1196 if vid_me_embed_url is not None:
1197 return self.url_result(vid_me_embed_url, 'Vidme')
1199 # Look for embedded YouTube player
1200 matches = re.findall(r'''(?x)
1209 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1213 return _playlist_from_matches(
1214 matches, lambda m: unescapeHTML(m[1]))
1216 # Look for lazyYT YouTube embed
1217 matches = re.findall(
1218 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1220 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1222 # Look for embedded Dailymotion player
1223 matches = re.findall(
1224 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1226 return _playlist_from_matches(
1227 matches, lambda m: unescapeHTML(m[1]))
1229 # Look for embedded Dailymotion playlist player (#3822)
1231 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1233 playlists = re.findall(
1234 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1236 return _playlist_from_matches(
1237 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1239 # Look for embedded Wistia player
1241 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1243 embed_url = self._proto_relative_url(
1244 unescapeHTML(match.group('url')))
1246 '_type': 'url_transparent',
1249 'uploader': video_uploader,
1250 'title': video_title,
1254 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1257 '_type': 'url_transparent',
1258 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1260 'uploader': video_uploader,
1261 'title': video_title,
1262 'id': match.group('id')
1265 # Look for embedded blip.tv player
1266 bliptv_url = BlipTVIE._extract_url(webpage)
1268 return self.url_result(bliptv_url, 'BlipTV')
1270 # Look for SVT player
1271 svt_url = SVTIE._extract_url(webpage)
1273 return self.url_result(svt_url, 'SVT')
1275 # Look for embedded condenast player
1276 matches = re.findall(
1277 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1281 '_type': 'playlist',
1284 'ie_key': 'CondeNast',
1286 } for ma in matches],
1287 'title': video_title,
1291 # Look for Bandcamp pages with custom domain
1292 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1293 if mobj is not None:
1294 burl = unescapeHTML(mobj.group(1))
1295 # Don't set the extractor because it can be a track url or an album
1296 return self.url_result(burl)
1298 # Look for embedded Vevo player
1300 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1301 if mobj is not None:
1302 return self.url_result(mobj.group('url'))
1304 # Look for embedded Viddler player
1306 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1308 if mobj is not None:
1309 return self.url_result(mobj.group('url'))
1311 # Look for NYTimes player
1313 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1315 if mobj is not None:
1316 return self.url_result(mobj.group('url'))
1318 # Look for Libsyn player
1320 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1321 if mobj is not None:
1322 return self.url_result(mobj.group('url'))
1324 # Look for Ooyala videos
1325 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1326 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1327 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1328 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1329 if mobj is not None:
1330 return OoyalaIE._build_url_result(mobj.group('ec'))
1332 # Look for multiple Ooyala embeds on SBN network websites
1333 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1334 if mobj is not None:
1335 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1337 return _playlist_from_matches(
1338 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1340 # Look for Aparat videos
1341 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1342 if mobj is not None:
1343 return self.url_result(mobj.group(1), 'Aparat')
1345 # Look for MPORA videos
1346 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1347 if mobj is not None:
1348 return self.url_result(mobj.group(1), 'Mpora')
1350 # Look for embedded NovaMov-based player
1352 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1353 (?P<url>http://(?:(?:embed|www)\.)?
1355 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1356 videoweed\.(?:es|com)|
1357 movshare\.(?:net|sx|ag)|
1358 divxstage\.(?:eu|net|ch|co|at|ag))
1359 /embed\.php.+?)\1''', webpage)
1360 if mobj is not None:
1361 return self.url_result(mobj.group('url'))
1363 # Look for embedded Facebook player
1365 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1366 if mobj is not None:
1367 return self.url_result(mobj.group('url'), 'Facebook')
1369 # Look for embedded VK player
1370 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1371 if mobj is not None:
1372 return self.url_result(mobj.group('url'), 'VK')
1374 # Look for embedded ivi player
1375 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1376 if mobj is not None:
1377 return self.url_result(mobj.group('url'), 'Ivi')
1379 # Look for embedded Huffington Post player
1381 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1382 if mobj is not None:
1383 return self.url_result(mobj.group('url'), 'HuffPost')
1386 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1387 if mobj is not None:
1388 return self.url_result(mobj.group('url'))
1389 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1390 if mobj is not None:
1391 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1393 # Look for funnyordie embed
1394 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1396 return _playlist_from_matches(
1397 matches, getter=unescapeHTML, ie='FunnyOrDie')
1399 # Look for BBC iPlayer embed
1400 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1402 return _playlist_from_matches(matches, ie='BBCCoUk')
1404 # Look for embedded RUTV player
1405 rutv_url = RUTVIE._extract_url(webpage)
1407 return self.url_result(rutv_url, 'RUTV')
1409 # Look for embedded TVC player
1410 tvc_url = TVCIE._extract_url(webpage)
1412 return self.url_result(tvc_url, 'TVC')
1414 # Look for embedded SportBox player
1415 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1417 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1419 # Look for embedded PornHub player
1420 pornhub_url = PornHubIE._extract_url(webpage)
1422 return self.url_result(pornhub_url, 'PornHub')
1424 # Look for embedded XHamster player
1425 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1427 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1429 # Look for embedded Tvigle player
1431 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1432 if mobj is not None:
1433 return self.url_result(mobj.group('url'), 'Tvigle')
1435 # Look for embedded TED player
1437 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1438 if mobj is not None:
1439 return self.url_result(mobj.group('url'), 'TED')
1441 # Look for embedded Ustream videos
1443 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1444 if mobj is not None:
1445 return self.url_result(mobj.group('url'), 'Ustream')
1447 # Look for embedded arte.tv player
1449 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1451 if mobj is not None:
1452 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1454 # Look for embedded francetv player
1456 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1458 if mobj is not None:
1459 return self.url_result(mobj.group('url'))
1461 # Look for embedded smotri.com player
1462 smotri_url = SmotriIE._extract_url(webpage)
1464 return self.url_result(smotri_url, 'Smotri')
1466 # Look for embedded Myvi.ru player
1467 myvi_url = MyviIE._extract_url(webpage)
1469 return self.url_result(myvi_url)
1471 # Look for embeded soundcloud player
1473 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1475 if mobj is not None:
1476 url = unescapeHTML(mobj.group('url'))
1477 return self.url_result(url)
1479 # Look for embedded vulture.com player
1481 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1483 if mobj is not None:
1484 url = unescapeHTML(mobj.group('url'))
1485 return self.url_result(url, ie='Vulture')
1487 # Look for embedded mtvservices player
1489 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1491 if mobj is not None:
1492 url = unescapeHTML(mobj.group('url'))
1493 return self.url_result(url, ie='MTVServicesEmbedded')
1495 # Look for embedded yahoo player
1497 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1499 if mobj is not None:
1500 return self.url_result(mobj.group('url'), 'Yahoo')
1502 # Look for embedded sbs.com.au player
1506 <meta\s+property="og:video"\s+content=|
1509 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1511 if mobj is not None:
1512 return self.url_result(mobj.group('url'), 'SBS')
1514 # Look for embedded Cinchcast player
1516 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1518 if mobj is not None:
1519 return self.url_result(mobj.group('url'), 'Cinchcast')
1522 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1526 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1528 if mobj is not None:
1529 return self.url_result(mobj.group('url'), 'MLB')
1532 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1534 if mobj is not None:
1535 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1538 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1540 if mobj is not None:
1541 return self.url_result(mobj.group('url'), 'Livestream')
1543 # Look for Zapiks embed
1545 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1546 if mobj is not None:
1547 return self.url_result(mobj.group('url'), 'Zapiks')
1549 # Look for Kaltura embeds
1550 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1551 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))
1552 if mobj is not None:
1553 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1555 # Look for Eagle.Platform embeds
1557 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1558 if mobj is not None:
1559 return self.url_result(mobj.group('url'), 'EaglePlatform')
1561 # Look for ClipYou (uses Eagle.Platform) embeds
1563 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1564 if mobj is not None:
1565 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1567 # Look for Pladform embeds
1569 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1570 if mobj is not None:
1571 return self.url_result(mobj.group('url'), 'Pladform')
1573 # Look for Playwire embeds
1575 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1576 if mobj is not None:
1577 return self.url_result(mobj.group('url'))
1579 # Look for 5min embeds
1581 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1582 if mobj is not None:
1583 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1585 # Look for Crooks and Liars embeds
1587 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1588 if mobj is not None:
1589 return self.url_result(mobj.group('url'))
1591 # Look for NBC Sports VPlayer embeds
1592 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1594 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1596 # Look for UDN embeds
1598 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1599 if mobj is not None:
1600 return self.url_result(
1601 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1603 # Look for Senate ISVP iframe
1604 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1606 return self.url_result(senate_isvp_url, 'SenateISVP')
1608 # Look for Dailymotion Cloud videos
1609 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1611 return self.url_result(dmcloud_url, 'DailymotionCloud')
1613 # Look for OnionStudios embeds
1614 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1615 if onionstudios_url:
1616 return self.url_result(onionstudios_url)
1618 # Look for SnagFilms embeds
1619 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1621 return self.url_result(snagfilms_url)
1623 # Look for AdobeTVVideo embeds
1625 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1627 if mobj is not None:
1628 return self.url_result(
1629 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1632 def check_video(vurl):
1633 if YoutubeIE.suitable(vurl):
1635 vpath = compat_urlparse.urlparse(vurl).path
1636 vext = determine_ext(vpath)
1637 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1639 def filter_video(urls):
1640 return list(filter(check_video, urls))
1642 # Start with something easy: JW Player in SWFObject
1643 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1645 # Look for gorilla-vid style embedding
1646 found = filter_video(re.findall(r'''(?sx)
1650 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1653 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1655 # Broaden the search a little bit
1656 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1658 # Broaden the findall a little bit: JWPlayer JS loader
1659 found = filter_video(re.findall(
1660 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1663 found = filter_video(re.findall(r'''(?xs)
1664 flowplayer\("[^"]+",\s*
1666 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1667 ["']?url["']?\s*:\s*["']([^"']+)["']
1672 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1674 # Try to find twitter cards info
1675 found = filter_video(re.findall(
1676 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1678 # We look for Open Graph info:
1679 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1680 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1681 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1682 if m_video_type is not None:
1683 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1686 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1688 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1690 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1691 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1694 # Look also in Refresh HTTP header
1695 refresh_header = head_response.headers.get('Refresh')
1697 found = re.search(REDIRECT_REGEX, refresh_header)
1699 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1700 self.report_following_redirect(new_url)
1706 raise UnsupportedError(url)
1709 for video_url in found:
1710 video_url = compat_urlparse.urljoin(url, video_url)
1711 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1713 # Sometimes, jwplayer extraction will result in a YouTube URL
1714 if YoutubeIE.suitable(video_url):
1715 entries.append(self.url_result(video_url, 'Youtube'))
1718 # here's a fun little line of code for you:
1719 video_id = os.path.splitext(video_id)[0]
1721 if determine_ext(video_url) == 'smil':
1724 'formats': self._extract_smil_formats(video_url, video_id),
1725 'uploader': video_uploader,
1726 'title': video_title,
1727 'age_limit': age_limit,
1733 'uploader': video_uploader,
1734 'title': video_title,
1735 'age_limit': age_limit,
1738 if len(entries) == 1:
1741 for num, e in enumerate(entries, start=1):
1742 # 'url' results don't have a title
1743 if e.get('title') is not None:
1744 e['title'] = '%s (%d)' % (e['title'], num)
1746 '_type': 'playlist',