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
51 from .googledrive import GoogleDriveIE
54 class GenericIE(InfoExtractor):
55 IE_DESC = 'Generic downloader that works on some sites'
59 # Direct link to a video
61 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
62 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
67 'upload_date': '20100513',
70 # Direct link to media delivered compressed (until Accept-Encoding is *)
72 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
73 'md5': '128c42e68b13950268b648275386fc74',
75 'id': 'FictionJunction-Parallel_Hearts',
77 'title': 'FictionJunction-Parallel_Hearts',
78 'upload_date': '20140522',
80 'expected_warnings': [
81 'URL could be a direct video link, returning it as such.'
84 # Direct download with broken HEAD
86 'url': 'http://ai-radio.org:8000/radio.opus',
93 'skip_download': True, # infinite live stream
95 'expected_warnings': [
96 r'501.*Not Implemented'
99 # Direct link with incorrect MIME type
101 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
102 'md5': '4ccbebe5f36706d85221f204d7eb5913',
104 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
105 'id': '5_Lennart_Poettering_-_Systemd',
107 'title': '5_Lennart_Poettering_-_Systemd',
108 'upload_date': '20141120',
110 'expected_warnings': [
111 'URL could be a direct video link, returning it as such.'
116 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
119 'title': 'Zero Punctuation',
120 'description': 're:.*groundbreaking video review series.*'
122 'playlist_mincount': 11,
124 # RSS feed with enclosure
126 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
128 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
130 'upload_date': '20150228',
131 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
136 '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',
140 'upload_date': '20130224',
141 'uploader_id': 'TheVerge',
142 'description': 're:^Chris Ziegler takes a look at the\.*',
143 'uploader': 'The Verge',
144 'title': 'First Firefox OS phones side-by-side',
147 'skip_download': False,
151 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
152 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
154 'id': '13601338388002',
156 'uploader': 'www.hodiho.fr',
157 'title': 'R\u00e9gis plante sa Jeep',
160 # bandcamp page with custom domain
162 'add_ie': ['Bandcamp'],
163 'url': 'http://bronyrock.com/track/the-pony-mash',
167 'title': 'The Pony Mash',
168 'uploader': 'M_Pallante',
170 'skip': 'There is a limit of 200 free downloads / month for the test song',
172 # embedded brightcove video
173 # it also tests brightcove videos that need to set the 'Referer' in the
176 'add_ie': ['Brightcove'],
177 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
179 'id': '2765128793001',
181 'title': 'Le cours de bourse : l’analyse technique',
182 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
183 'uploader': 'BFM BUSINESS',
186 'skip_download': True,
190 # https://github.com/rg3/youtube-dl/issues/2253
191 'url': 'http://bcove.me/i6nfkrc3',
192 'md5': '0ba9446db037002366bab3b3eb30c88c',
194 'id': '3101154703001',
196 'title': 'Still no power',
197 'uploader': 'thestar.com',
198 '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.',
200 'add_ie': ['Brightcove'],
203 'url': 'http://www.championat.com/video/football/v/87/87499.html',
204 'md5': 'fb973ecf6e4a78a67453647444222983',
206 'id': '3414141473001',
208 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
209 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
210 'uploader': 'Championat',
214 # https://github.com/rg3/youtube-dl/issues/3541
215 'add_ie': ['Brightcove'],
216 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
218 'id': '3866516442001',
220 'title': 'Leer mij vrouwen kennen: Aflevering 1',
221 'description': 'Leer mij vrouwen kennen: Aflevering 1',
222 'uploader': 'SBS Broadcasting',
224 'skip': 'Restricted to Netherlands',
226 'skip_download': True, # m3u8 download
231 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
232 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
234 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
236 'title': '2cc213299525360.mov', # that's what we get
238 'add_ie': ['Ooyala'],
240 # multiple ooyala embeds on SBN network websites
242 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
244 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
245 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
247 'playlist_mincount': 3,
249 'skip_download': True,
251 'add_ie': ['Ooyala'],
255 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
259 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
260 'upload_date': '20140225',
261 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
262 'uploader': 'Tested',
263 'uploader_id': 'testedcom',
265 # No need to test YoutubeIE here
267 'skip_download': True,
272 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
276 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
277 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
282 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
284 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
286 'playlist_mincount': 18,
290 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
294 'title': 'Охотское море стало целиком российским',
295 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
299 'skip_download': True,
304 '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/',
308 'title': 'Дошкольное воспитание',
313 'url': 'http://www.vestifinance.ru/articles/25753',
316 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
321 'title': 'Госзаказ. День 3',
327 'title': 'Госзаказ. День 2',
333 'title': 'Госзаказ. День 1',
339 'skip_download': True,
344 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
346 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
348 'title': 'Ужастики, русский трейлер (2015)',
349 'thumbnail': 're:^https?://.*\.jpg$',
355 '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',
358 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
360 'playlist_mincount': 7,
364 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
365 'md5': '65fdff94098e4a607385a60c5177c638',
369 'title': 'Hidden miracles of the natural world',
370 'uploader': 'Louie Schwartzberg',
371 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
374 # Embeded Ustream video
376 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
377 'md5': '27b99cdb639c9b12a79bca876a073417',
381 'uploader': 'AU SPA: The NSA and Privacy',
382 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
385 # nowvideo embed hidden behind percent encoding
387 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
388 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
390 'id': '06e53103ca9aa',
392 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
393 'description': 'No description',
398 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
399 'md5': '7653032cbb25bf6c80d80f217055fa43',
401 'id': '048195-004_PLUS7-F',
404 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
405 'upload_date': '20140320',
408 'skip_download': 'Requires rtmpdump'
413 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
417 'title': 'Alcaline, le concert avec Calogero',
418 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
419 'upload_date': '20150226',
420 'timestamp': 1424989860,
425 'skip_download': True,
427 'expected_warnings': [
433 'url': 'http://www.wired.com/2014/04/honda-asimo/',
434 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
436 'id': '53501be369702d3275860000',
438 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
443 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
444 'md5': '441aeeb82eb72c422c7f14ec533999cd',
446 'id': 'k2mm4bCdJ6CQ2i7c8o2',
448 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
451 'add_ie': ['Dailymotion'],
455 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
459 'title': 'The NBL Auction 2014',
460 'uploader': 'BADMINTON England',
461 'uploader_id': 'BADMINTONEvents',
462 'upload_date': '20140603',
463 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
465 'add_ie': ['Youtube'],
467 'skip_download': True,
472 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
473 'md5': '35727f82f58c76d996fc188f9755b0d5',
475 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
478 'description': 'Mario\'s life in the fast lane has never looked so good.',
481 # YouTube embed via <data-embed-url="">
483 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
487 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
488 'uploader': 'Gameloft',
489 'uploader_id': 'gameloft',
490 'upload_date': '20140828',
491 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
494 'skip_download': True,
499 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
501 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
503 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
504 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
509 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
511 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
512 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
518 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
523 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
524 'md5': '9d65602bf31c6e20014319c7d07fba27',
526 'id': '5123ea6d5e5a7',
529 'uploader': 'www.handjobhub.com',
530 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
533 # Multiple brightcove videos
534 # https://github.com/rg3/youtube-dl/issues/2283
536 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
538 'id': 'always-never',
539 'title': 'Always / Never - The New Yorker',
543 'extract_flat': False,
544 'skip_download': True,
549 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
550 'md5': '96f09a37e44da40dd083e12d9a683327',
554 'title': 'Ump changes call to ball',
555 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
557 'timestamp': 1401537900,
558 'upload_date': '20140531',
559 'thumbnail': 're:^https?://.*\.jpg$',
564 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
565 'md5': '8788b683c777a5cf25621eaf286d0c23',
569 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
571 'filesize': 182808282,
572 'uploader': 'education-portal.com',
576 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
577 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
581 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
583 'uploader': 'thoughtworks.wistia.com',
588 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
592 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
593 'uploader': 'Sophos Security',
594 'title': 'Chet Chat 171 - Oct 29, 2014',
595 'upload_date': '20141029',
600 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
604 'upload_date': '20141112',
605 'title': 'Rosetta #CometLanding webcast HL 10',
610 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
613 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
615 'playlist_mincount': 2,
619 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
623 'upload_date': '20141126',
624 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
629 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
631 'id': '730m_DandD_1901_512k',
633 'uploader': 'www.abc.net.au',
634 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
637 # embedded viddler video
639 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
643 'uploader': 'deadspin',
644 'title': 'WALL-TO-GORTAT',
645 'timestamp': 1422285291,
646 'upload_date': '20150126',
648 'add_ie': ['Viddler'],
652 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
656 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
657 'description': 'md5:601cb790edd05908957dae8aaa866465',
658 'upload_date': '20150220',
663 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
667 'upload_date': '20150212',
668 'uploader': 'The National Archives UK',
669 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
670 'uploader_id': 'NationalArchives08',
671 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
676 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
677 'playlist_mincount': 5,
679 'id': 'aanslagen-kopenhagen',
680 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
685 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
689 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
694 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
698 'upload_date': '20150226',
699 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
701 'title': 'John Carlson Postgame 2/25/15',
704 # Kaltura embed (different embed code)
706 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
710 'upload_date': '20150127',
711 'uploader_id': 'PremierMedia',
713 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
716 # Eagle.Platform embed (generic URL)
718 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
722 'title': 'Навальный вышел на свободу',
723 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
724 'thumbnail': 're:^https?://.*\.jpg$',
730 # ClipYou (Eagle.Platform) embed (custom URL)
732 'url': 'http://muz-tv.ru/play/7129/',
736 'title': "'O Sole Mio",
737 'thumbnail': 're:^https?://.*\.jpg$',
744 'url': 'http://muz-tv.ru/kinozal/view/7400/',
748 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
749 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
750 'thumbnail': 're:^https?://.*\.jpg$',
757 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
761 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
762 'thumbnail': 're:^https?://.*\.png$',
768 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
769 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
773 'title': 'Facebook Creates "On This Day" | Crunch Report',
778 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
782 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
787 # Crooks and Liars embed
789 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
793 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
794 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
795 'timestamp': 1428207000,
796 'upload_date': '20150405',
797 'uploader': 'Heather',
800 # Crooks and Liars external embed
802 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
804 'id': 'MTE3MjUtMzQ2MzA',
806 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
807 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
808 'timestamp': 1265032391,
809 'upload_date': '20100201',
810 'uploader': 'Heather',
813 # NBC Sports vplayer embed
815 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
817 'id': 'ln7x1qSThw4k',
819 'title': "PFT Live: New leader in the 'new-look' defense",
820 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
825 'url': 'http://www.udn.com/news/story/7314/822787',
826 'md5': 'fd2060e988c326991037b9aff9df21a6',
830 'title': '中一中男師變性 全校師生力挺',
831 'thumbnail': 're:^https?://.*\.jpg$',
836 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
838 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
840 'description': 'VIDEO: Index/Match versus VLOOKUP.',
841 'title': 'This is what separates the Excel masters from the wannabes',
845 'skip_download': True,
848 # Contains a SMIL manifest
850 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
854 'title': '+ Football: Lottery Champions League Europe',
855 'uploader': 'www.telewebion.com',
859 'skip_download': True,
862 # Brightcove URL in single quotes
864 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
865 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
867 'id': '4255764656001',
869 'title': 'SN Presents: Russell Martin, World Citizen',
870 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
871 'uploader': 'Rogers Sportsnet',
874 # Dailymotion Cloud video
876 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
877 'md5': '49444254273501a64675a7e68c502681',
879 'id': '5585de919473990de4bee11b',
882 'thumbnail': 're:^https?://.*\.jpe?g$',
887 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
891 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
892 'thumbnail': 're:^https?://.*\.jpe?g$',
893 'uploader': 'ClickHole',
894 'uploader_id': 'clickhole',
899 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
901 'id': '74849a00-85a9-11e1-9660-123139220831',
903 'title': '#whilewewatch',
908 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
909 'md5': '43662b577c018ad707a63766462b1e87',
913 'title': 'New experience with Acrobat DC',
914 'description': 'New experience with Acrobat DC',
920 def report_following_redirect(self, new_url):
921 """Report information extraction."""
922 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
924 def _extract_rss(self, url, video_id, doc):
925 playlist_title = doc.find('./channel/title').text
926 playlist_desc_el = doc.find('./channel/description')
927 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
930 for it in doc.findall('./channel/item'):
931 next_url = xpath_text(it, 'link', fatal=False)
933 enclosure_nodes = it.findall('./enclosure')
934 for e in enclosure_nodes:
935 next_url = e.attrib.get('url')
945 'title': it.find('title').text,
951 'title': playlist_title,
952 'description': playlist_desc,
956 def _extract_camtasia(self, url, video_id, webpage):
957 """ Returns None if no camtasia video can be found. """
959 camtasia_cfg = self._search_regex(
960 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
961 webpage, 'camtasia configuration file', default=None)
962 if camtasia_cfg is None:
965 title = self._html_search_meta('DC.title', webpage, fatal=True)
967 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
968 camtasia_cfg = self._download_xml(
969 camtasia_url, video_id,
970 note='Downloading camtasia configuration',
971 errnote='Failed to download camtasia configuration')
972 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
975 for n in fileset_node.getchildren():
976 url_n = n.find('./uri')
981 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
982 'title': '%s - %s' % (title, n.tag),
983 'url': compat_urlparse.urljoin(url, url_n.text),
984 'duration': float_or_none(n.find('./duration').text),
993 def _real_extract(self, url):
994 if url.startswith('//'):
997 'url': self.http_scheme() + url,
1000 parsed_url = compat_urlparse.urlparse(url)
1001 if not parsed_url.scheme:
1002 default_search = self._downloader.params.get('default_search')
1003 if default_search is None:
1004 default_search = 'fixup_error'
1006 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1008 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1009 return self.url_result('http://' + url)
1010 elif default_search != 'fixup_error':
1011 if default_search == 'auto_warning':
1012 if re.match(r'^(?:url|URL)$', url):
1013 raise ExtractorError(
1014 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1017 self._downloader.report_warning(
1018 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1019 return self.url_result('ytsearch:' + url)
1021 if default_search in ('error', 'fixup_error'):
1022 raise ExtractorError(
1023 '%r is not a valid URL. '
1024 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1025 % (url, url), expected=True)
1027 if ':' not in default_search:
1028 default_search += ':'
1029 return self.url_result(default_search + url)
1031 url, smuggled_data = unsmuggle_url(url)
1032 force_videoid = None
1033 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1034 if smuggled_data and 'force_videoid' in smuggled_data:
1035 force_videoid = smuggled_data['force_videoid']
1036 video_id = force_videoid
1038 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1040 self.to_screen('%s: Requesting header' % video_id)
1042 head_req = HEADRequest(url)
1043 head_response = self._request_webpage(
1045 note=False, errnote='Could not send HEAD request to %s' % url,
1048 if head_response is not False:
1049 # Check for redirect
1050 new_url = head_response.geturl()
1052 self.report_following_redirect(new_url)
1054 new_url = smuggle_url(
1055 new_url, {'force_videoid': force_videoid})
1056 return self.url_result(new_url)
1058 full_response = None
1059 if head_response is False:
1060 request = compat_urllib_request.Request(url)
1061 request.add_header('Accept-Encoding', '*')
1062 full_response = self._request_webpage(request, video_id)
1063 head_response = full_response
1065 # Check for direct link to a video
1066 content_type = head_response.headers.get('Content-Type', '')
1067 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1069 upload_date = unified_strdate(
1070 head_response.headers.get('Last-Modified'))
1073 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1076 'format_id': m.group('format_id'),
1078 'vcodec': 'none' if m.group('type') == 'audio' else None
1080 'upload_date': upload_date,
1083 if not self._downloader.params.get('test', False) and not is_intentional:
1084 force = self._downloader.params.get('force_generic_extractor', False)
1085 self._downloader.report_warning(
1086 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1088 if not full_response:
1089 request = compat_urllib_request.Request(url)
1090 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1091 # making it impossible to download only chunk of the file (yet we need only 512kB to
1092 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1093 # that will always result in downloading the whole file that is not desirable.
1094 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1095 # to accept raw bytes and being able to download only a chunk.
1096 # It may probably better to solve this by checking Content-Type for application/octet-stream
1097 # after HEAD request finishes, but not sure if we can rely on this.
1098 request.add_header('Accept-Encoding', '*')
1099 full_response = self._request_webpage(request, video_id)
1101 # Maybe it's a direct link to a video?
1102 # Be careful not to download the whole thing!
1103 first_bytes = full_response.read(512)
1104 if not is_html(first_bytes):
1105 self._downloader.report_warning(
1106 'URL could be a direct video link, returning it as such.')
1107 upload_date = unified_strdate(
1108 head_response.headers.get('Last-Modified'))
1111 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1114 'upload_date': upload_date,
1117 webpage = self._webpage_read_content(
1118 full_response, url, video_id, prefix=first_bytes)
1120 self.report_extraction(video_id)
1122 # Is it an RSS feed?
1124 doc = parse_xml(webpage)
1125 if doc.tag == 'rss':
1126 return self._extract_rss(url, video_id, doc)
1127 except compat_xml_parse_error:
1130 # Is it a Camtasia project?
1131 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1132 if camtasia_res is not None:
1135 # Sometimes embedded video player is hidden behind percent encoding
1136 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1137 # Unescaping the whole page allows to handle those cases in a generic way
1138 webpage = compat_urllib_parse_unquote(webpage)
1140 # it's tempting to parse this further, but you would
1141 # have to take into account all the variations like
1142 # Video Title - Site Name
1143 # Site Name | Video Title
1144 # Video Title - Tagline | Site Name
1145 # and so on and so forth; it's just not practical
1146 video_title = self._html_search_regex(
1147 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1150 # Try to detect age limit automatically
1151 age_limit = self._rta_search(webpage)
1152 # And then there are the jokers who advertise that they use RTA,
1153 # but actually don't.
1154 AGE_LIMIT_MARKERS = [
1155 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1157 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1160 # video uploader is domain name
1161 video_uploader = self._search_regex(
1162 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1165 def _playlist_from_matches(matches, getter=None, ie=None):
1167 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1169 return self.playlist_result(
1170 urlrs, playlist_id=video_id, playlist_title=video_title)
1172 # Look for BrightCove:
1173 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1175 self.to_screen('Brightcove video detected.')
1178 'url': smuggle_url(bc_url, {'Referer': url}),
1179 'ie_key': 'Brightcove'
1180 } for bc_url in bc_urls]
1183 '_type': 'playlist',
1184 'title': video_title,
1189 # Look for embedded rtl.nl player
1190 matches = re.findall(
1191 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1194 return _playlist_from_matches(matches, ie='RtlNl')
1196 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1197 if vimeo_url is not None:
1198 return self.url_result(vimeo_url)
1200 vid_me_embed_url = self._search_regex(
1201 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1202 webpage, 'vid.me embed', default=None)
1203 if vid_me_embed_url is not None:
1204 return self.url_result(vid_me_embed_url, 'Vidme')
1206 # Look for embedded YouTube player
1207 matches = re.findall(r'''(?x)
1216 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1220 return _playlist_from_matches(
1221 matches, lambda m: unescapeHTML(m[1]))
1223 # Look for lazyYT YouTube embed
1224 matches = re.findall(
1225 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1227 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1229 # Look for embedded Dailymotion player
1230 matches = re.findall(
1231 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1233 return _playlist_from_matches(
1234 matches, lambda m: unescapeHTML(m[1]))
1236 # Look for embedded Dailymotion playlist player (#3822)
1238 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1240 playlists = re.findall(
1241 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1243 return _playlist_from_matches(
1244 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1246 # Look for embedded Wistia player
1248 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1250 embed_url = self._proto_relative_url(
1251 unescapeHTML(match.group('url')))
1253 '_type': 'url_transparent',
1256 'uploader': video_uploader,
1257 'title': video_title,
1261 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1264 '_type': 'url_transparent',
1265 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1267 'uploader': video_uploader,
1268 'title': video_title,
1269 'id': match.group('id')
1272 # Look for embedded blip.tv player
1273 bliptv_url = BlipTVIE._extract_url(webpage)
1275 return self.url_result(bliptv_url, 'BlipTV')
1277 # Look for SVT player
1278 svt_url = SVTIE._extract_url(webpage)
1280 return self.url_result(svt_url, 'SVT')
1282 # Look for embedded condenast player
1283 matches = re.findall(
1284 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1288 '_type': 'playlist',
1291 'ie_key': 'CondeNast',
1293 } for ma in matches],
1294 'title': video_title,
1298 # Look for Bandcamp pages with custom domain
1299 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1300 if mobj is not None:
1301 burl = unescapeHTML(mobj.group(1))
1302 # Don't set the extractor because it can be a track url or an album
1303 return self.url_result(burl)
1305 # Look for embedded Vevo player
1307 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1308 if mobj is not None:
1309 return self.url_result(mobj.group('url'))
1311 # Look for embedded Viddler player
1313 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1315 if mobj is not None:
1316 return self.url_result(mobj.group('url'))
1318 # Look for NYTimes player
1320 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1322 if mobj is not None:
1323 return self.url_result(mobj.group('url'))
1325 # Look for Libsyn player
1327 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1328 if mobj is not None:
1329 return self.url_result(mobj.group('url'))
1331 # Look for Ooyala videos
1332 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1333 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1334 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1335 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1336 if mobj is not None:
1337 return OoyalaIE._build_url_result(mobj.group('ec'))
1339 # Look for multiple Ooyala embeds on SBN network websites
1340 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1341 if mobj is not None:
1342 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1344 return _playlist_from_matches(
1345 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1347 # Look for Aparat videos
1348 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1349 if mobj is not None:
1350 return self.url_result(mobj.group(1), 'Aparat')
1352 # Look for MPORA videos
1353 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1354 if mobj is not None:
1355 return self.url_result(mobj.group(1), 'Mpora')
1357 # Look for embedded NovaMov-based player
1359 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1360 (?P<url>http://(?:(?:embed|www)\.)?
1362 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1363 videoweed\.(?:es|com)|
1364 movshare\.(?:net|sx|ag)|
1365 divxstage\.(?:eu|net|ch|co|at|ag))
1366 /embed\.php.+?)\1''', webpage)
1367 if mobj is not None:
1368 return self.url_result(mobj.group('url'))
1370 # Look for embedded Facebook player
1372 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1373 if mobj is not None:
1374 return self.url_result(mobj.group('url'), 'Facebook')
1376 # Look for embedded VK player
1377 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1378 if mobj is not None:
1379 return self.url_result(mobj.group('url'), 'VK')
1381 # Look for embedded ivi player
1382 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1383 if mobj is not None:
1384 return self.url_result(mobj.group('url'), 'Ivi')
1386 # Look for embedded Huffington Post player
1388 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1389 if mobj is not None:
1390 return self.url_result(mobj.group('url'), 'HuffPost')
1393 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1394 if mobj is not None:
1395 return self.url_result(mobj.group('url'))
1396 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1397 if mobj is not None:
1398 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1400 # Look for funnyordie embed
1401 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1403 return _playlist_from_matches(
1404 matches, getter=unescapeHTML, ie='FunnyOrDie')
1406 # Look for BBC iPlayer embed
1407 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1409 return _playlist_from_matches(matches, ie='BBCCoUk')
1411 # Look for embedded RUTV player
1412 rutv_url = RUTVIE._extract_url(webpage)
1414 return self.url_result(rutv_url, 'RUTV')
1416 # Look for embedded TVC player
1417 tvc_url = TVCIE._extract_url(webpage)
1419 return self.url_result(tvc_url, 'TVC')
1421 # Look for embedded SportBox player
1422 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1424 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1426 # Look for embedded PornHub player
1427 pornhub_url = PornHubIE._extract_url(webpage)
1429 return self.url_result(pornhub_url, 'PornHub')
1431 # Look for embedded XHamster player
1432 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1434 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1436 # Look for embedded Tvigle player
1438 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1439 if mobj is not None:
1440 return self.url_result(mobj.group('url'), 'Tvigle')
1442 # Look for embedded TED player
1444 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1445 if mobj is not None:
1446 return self.url_result(mobj.group('url'), 'TED')
1448 # Look for embedded Ustream videos
1450 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1451 if mobj is not None:
1452 return self.url_result(mobj.group('url'), 'Ustream')
1454 # Look for embedded arte.tv player
1456 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1458 if mobj is not None:
1459 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1461 # Look for embedded francetv player
1463 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1465 if mobj is not None:
1466 return self.url_result(mobj.group('url'))
1468 # Look for embedded smotri.com player
1469 smotri_url = SmotriIE._extract_url(webpage)
1471 return self.url_result(smotri_url, 'Smotri')
1473 # Look for embedded Myvi.ru player
1474 myvi_url = MyviIE._extract_url(webpage)
1476 return self.url_result(myvi_url)
1478 # Look for embeded soundcloud player
1480 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1482 if mobj is not None:
1483 url = unescapeHTML(mobj.group('url'))
1484 return self.url_result(url)
1486 # Look for embedded vulture.com player
1488 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1490 if mobj is not None:
1491 url = unescapeHTML(mobj.group('url'))
1492 return self.url_result(url, ie='Vulture')
1494 # Look for embedded mtvservices player
1496 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1498 if mobj is not None:
1499 url = unescapeHTML(mobj.group('url'))
1500 return self.url_result(url, ie='MTVServicesEmbedded')
1502 # Look for embedded yahoo player
1504 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1506 if mobj is not None:
1507 return self.url_result(mobj.group('url'), 'Yahoo')
1509 # Look for embedded sbs.com.au player
1513 <meta\s+property="og:video"\s+content=|
1516 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1518 if mobj is not None:
1519 return self.url_result(mobj.group('url'), 'SBS')
1521 # Look for embedded Cinchcast player
1523 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1525 if mobj is not None:
1526 return self.url_result(mobj.group('url'), 'Cinchcast')
1529 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1533 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1535 if mobj is not None:
1536 return self.url_result(mobj.group('url'), 'MLB')
1539 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1541 if mobj is not None:
1542 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1545 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1547 if mobj is not None:
1548 return self.url_result(mobj.group('url'), 'Livestream')
1550 # Look for Zapiks embed
1552 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1553 if mobj is not None:
1554 return self.url_result(mobj.group('url'), 'Zapiks')
1556 # Look for Kaltura embeds
1557 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1558 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))
1559 if mobj is not None:
1560 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1562 # Look for Eagle.Platform embeds
1564 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1565 if mobj is not None:
1566 return self.url_result(mobj.group('url'), 'EaglePlatform')
1568 # Look for ClipYou (uses Eagle.Platform) embeds
1570 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1571 if mobj is not None:
1572 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1574 # Look for Pladform embeds
1576 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1577 if mobj is not None:
1578 return self.url_result(mobj.group('url'), 'Pladform')
1580 # Look for Playwire embeds
1582 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1583 if mobj is not None:
1584 return self.url_result(mobj.group('url'))
1586 # Look for 5min embeds
1588 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1589 if mobj is not None:
1590 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1592 # Look for Crooks and Liars embeds
1594 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1595 if mobj is not None:
1596 return self.url_result(mobj.group('url'))
1598 # Look for NBC Sports VPlayer embeds
1599 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1601 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1603 # Look for Google Drive embeds
1604 google_drive_url = GoogleDriveIE._extract_url(webpage)
1605 if google_drive_url:
1606 return self.url_result(google_drive_url, 'GoogleDrive')
1608 # Look for UDN embeds
1610 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1611 if mobj is not None:
1612 return self.url_result(
1613 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1615 # Look for Senate ISVP iframe
1616 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1618 return self.url_result(senate_isvp_url, 'SenateISVP')
1620 # Look for Dailymotion Cloud videos
1621 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1623 return self.url_result(dmcloud_url, 'DailymotionCloud')
1625 # Look for OnionStudios embeds
1626 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1627 if onionstudios_url:
1628 return self.url_result(onionstudios_url)
1630 # Look for SnagFilms embeds
1631 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1633 return self.url_result(snagfilms_url)
1635 # Look for AdobeTVVideo embeds
1637 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1639 if mobj is not None:
1640 return self.url_result(
1641 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1644 def check_video(vurl):
1645 if YoutubeIE.suitable(vurl):
1647 vpath = compat_urlparse.urlparse(vurl).path
1648 vext = determine_ext(vpath)
1649 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1651 def filter_video(urls):
1652 return list(filter(check_video, urls))
1654 # Start with something easy: JW Player in SWFObject
1655 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1657 # Look for gorilla-vid style embedding
1658 found = filter_video(re.findall(r'''(?sx)
1662 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1665 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1667 # Broaden the search a little bit
1668 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1670 # Broaden the findall a little bit: JWPlayer JS loader
1671 found = filter_video(re.findall(
1672 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1675 found = filter_video(re.findall(r'''(?xs)
1676 flowplayer\("[^"]+",\s*
1678 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1679 ["']?url["']?\s*:\s*["']([^"']+)["']
1684 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1686 # Try to find twitter cards info
1687 found = filter_video(re.findall(
1688 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1690 # We look for Open Graph info:
1691 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1692 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1693 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1694 if m_video_type is not None:
1695 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1698 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1700 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1702 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1703 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1706 # Look also in Refresh HTTP header
1707 refresh_header = head_response.headers.get('Refresh')
1709 found = re.search(REDIRECT_REGEX, refresh_header)
1711 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1712 self.report_following_redirect(new_url)
1718 raise UnsupportedError(url)
1721 for video_url in found:
1722 video_url = compat_urlparse.urljoin(url, video_url)
1723 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1725 # Sometimes, jwplayer extraction will result in a YouTube URL
1726 if YoutubeIE.suitable(video_url):
1727 entries.append(self.url_result(video_url, 'Youtube'))
1730 # here's a fun little line of code for you:
1731 video_id = os.path.splitext(video_id)[0]
1733 if determine_ext(video_url) == 'smil':
1736 'formats': self._extract_smil_formats(video_url, video_id),
1737 'uploader': video_uploader,
1738 'title': video_title,
1739 'age_limit': age_limit,
1745 'uploader': video_uploader,
1746 'title': video_title,
1747 'age_limit': age_limit,
1750 if len(entries) == 1:
1753 for num, e in enumerate(entries, start=1):
1754 # 'url' results don't have a title
1755 if e.get('title') is not None:
1756 e['title'] = '%s (%d)' % (e['title'], num)
1758 '_type': 'playlist',