3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .vimeo import VimeoIE
51 from .dailymotion import DailymotionCloudIE
52 from .onionstudios import OnionStudiosIE
53 from .snagfilms import SnagFilmsEmbedIE
54 from .screenwavemedia import ScreenwaveMediaIE
55 from .mtv import MTVServicesEmbeddedIE
56 from .pladform import PladformIE
57 from .videomore import VideomoreIE
58 from .googledrive import GoogleDriveIE
59 from .jwplatform import JWPlatformIE
60 from .digiteka import DigitekaIE
63 class GenericIE(InfoExtractor):
64 IE_DESC = 'Generic downloader that works on some sites'
68 # Direct link to a video
70 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
71 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
76 'upload_date': '20100513',
79 # Direct link to media delivered compressed (until Accept-Encoding is *)
81 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
82 'md5': '128c42e68b13950268b648275386fc74',
84 'id': 'FictionJunction-Parallel_Hearts',
86 'title': 'FictionJunction-Parallel_Hearts',
87 'upload_date': '20140522',
89 'expected_warnings': [
90 'URL could be a direct video link, returning it as such.'
93 # Direct download with broken HEAD
95 'url': 'http://ai-radio.org:8000/radio.opus',
102 'skip_download': True, # infinite live stream
104 'expected_warnings': [
105 r'501.*Not Implemented'
108 # Direct link with incorrect MIME type
110 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
111 'md5': '4ccbebe5f36706d85221f204d7eb5913',
113 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
114 'id': '5_Lennart_Poettering_-_Systemd',
116 'title': '5_Lennart_Poettering_-_Systemd',
117 'upload_date': '20141120',
119 'expected_warnings': [
120 'URL could be a direct video link, returning it as such.'
125 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
127 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
128 'title': 'Zero Punctuation',
129 'description': 're:.*groundbreaking video review series.*'
131 'playlist_mincount': 11,
133 # RSS feed with enclosure
135 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
137 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
139 'upload_date': '20150228',
140 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
143 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
145 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
149 'title': 'Automatics, robotics and biocybernetics',
150 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
151 'upload_date': '20130627',
152 'formats': 'mincount:16',
153 'subtitles': 'mincount:1',
156 'force_generic_extractor': True,
157 'skip_download': True,
160 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
162 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
167 'formats': 'mincount:1',
170 'skip_download': True,
173 # SMIL from https://www.restudy.dk/video/play/id/1637
175 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
179 'title': 'video_1637',
180 'formats': 'mincount:3',
183 'skip_download': True,
186 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
188 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
190 'id': 'smil-service',
192 'title': 'smil-service',
193 'formats': 'mincount:1',
196 'skip_download': True,
199 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
201 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
205 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
206 'formats': 'mincount:3',
209 'skip_download': True,
212 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
214 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
216 'id': 'mZlp2ctYIUEB',
218 'title': 'Tikibad ontruimd wegens brand',
219 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
220 'thumbnail': 're:^https?://.*\.jpg$',
224 'skip_download': True,
229 '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',
233 'upload_date': '20130224',
234 'uploader_id': 'TheVerge',
235 'description': 're:^Chris Ziegler takes a look at the\.*',
236 'uploader': 'The Verge',
237 'title': 'First Firefox OS phones side-by-side',
240 'skip_download': False,
244 # redirect in Refresh HTTP header
245 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
249 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
250 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
251 'upload_date': '20150917',
252 'uploader_id': 'brtvofficial',
253 'uploader': 'Boiler Room',
256 'skip_download': False,
260 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
261 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
263 'id': '13601338388002',
265 'uploader': 'www.hodiho.fr',
266 'title': 'R\u00e9gis plante sa Jeep',
269 # bandcamp page with custom domain
271 'add_ie': ['Bandcamp'],
272 'url': 'http://bronyrock.com/track/the-pony-mash',
276 'title': 'The Pony Mash',
277 'uploader': 'M_Pallante',
279 'skip': 'There is a limit of 200 free downloads / month for the test song',
281 # embedded brightcove video
282 # it also tests brightcove videos that need to set the 'Referer' in the
285 'add_ie': ['BrightcoveLegacy'],
286 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
288 'id': '2765128793001',
290 'title': 'Le cours de bourse : l’analyse technique',
291 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
292 'uploader': 'BFM BUSINESS',
295 'skip_download': True,
299 # https://github.com/rg3/youtube-dl/issues/2253
300 'url': 'http://bcove.me/i6nfkrc3',
301 'md5': '0ba9446db037002366bab3b3eb30c88c',
303 'id': '3101154703001',
305 'title': 'Still no power',
306 'uploader': 'thestar.com',
307 '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.',
309 'add_ie': ['BrightcoveLegacy'],
312 'url': 'http://www.championat.com/video/football/v/87/87499.html',
313 'md5': 'fb973ecf6e4a78a67453647444222983',
315 'id': '3414141473001',
317 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
318 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
319 'uploader': 'Championat',
323 # https://github.com/rg3/youtube-dl/issues/3541
324 'add_ie': ['BrightcoveLegacy'],
325 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
327 'id': '3866516442001',
329 'title': 'Leer mij vrouwen kennen: Aflevering 1',
330 'description': 'Leer mij vrouwen kennen: Aflevering 1',
331 'uploader': 'SBS Broadcasting',
333 'skip': 'Restricted to Netherlands',
335 'skip_download': True, # m3u8 download
340 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
341 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
343 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
345 'title': '2cc213299525360.mov', # that's what we get
348 'add_ie': ['Ooyala'],
351 # ooyala video embedded with http://player.ooyala.com/iframe.js
352 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
354 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
356 'title': '"Steve Jobs: Man in the Machine" trailer',
357 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
361 'skip_download': True,
364 # multiple ooyala embeds on SBN network websites
366 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
368 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
369 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
371 'playlist_mincount': 3,
373 'skip_download': True,
375 'add_ie': ['Ooyala'],
379 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
383 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
384 'upload_date': '20140225',
385 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
386 'uploader': 'Tested',
387 'uploader_id': 'testedcom',
389 # No need to test YoutubeIE here
391 'skip_download': True,
396 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
400 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
401 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
406 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
410 'title': 'Охотское море стало целиком российским',
411 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
415 'skip_download': True,
420 '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/',
424 'title': 'Дошкольное воспитание',
429 'url': 'http://www.vestifinance.ru/articles/25753',
432 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
437 'title': 'Госзаказ. День 3',
443 'title': 'Госзаказ. День 2',
449 'title': 'Госзаказ. День 1',
455 'skip_download': True,
460 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
462 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
464 'title': 'Ужастики, русский трейлер (2015)',
465 'thumbnail': 're:^https?://.*\.jpg$',
471 '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',
474 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
476 'playlist_mincount': 7,
480 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
481 'md5': '65fdff94098e4a607385a60c5177c638',
485 'title': 'Hidden miracles of the natural world',
486 'uploader': 'Louie Schwartzberg',
487 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
490 # Embedded Ustream video
492 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
493 'md5': '27b99cdb639c9b12a79bca876a073417',
497 'uploader': 'AU SPA: The NSA and Privacy',
498 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
501 # nowvideo embed hidden behind percent encoding
503 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
504 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
506 'id': '06e53103ca9aa',
508 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
509 'description': 'No description',
514 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
515 'md5': '7653032cbb25bf6c80d80f217055fa43',
517 'id': '048195-004_PLUS7-F',
520 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
521 'upload_date': '20140320',
524 'skip_download': 'Requires rtmpdump'
529 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
533 'title': 'Alcaline, le concert avec Calogero',
534 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
535 'upload_date': '20150226',
536 'timestamp': 1424989860,
541 'skip_download': True,
543 'expected_warnings': [
549 'url': 'http://www.wired.com/2014/04/honda-asimo/',
550 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
552 'id': '53501be369702d3275860000',
554 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
559 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
560 'md5': '441aeeb82eb72c422c7f14ec533999cd',
562 'id': 'k2mm4bCdJ6CQ2i7c8o2',
564 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
567 'add_ie': ['Dailymotion'],
571 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
575 'title': 'The NBL Auction 2014',
576 'uploader': 'BADMINTON England',
577 'uploader_id': 'BADMINTONEvents',
578 'upload_date': '20140603',
579 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
581 'add_ie': ['Youtube'],
583 'skip_download': True,
588 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
589 'md5': '35727f82f58c76d996fc188f9755b0d5',
591 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
594 'description': 'Mario\'s life in the fast lane has never looked so good.',
597 # YouTube embed via <data-embed-url="">
599 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
603 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
604 'uploader': 'Gameloft',
605 'uploader_id': 'gameloft',
606 'upload_date': '20140828',
607 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
610 'skip_download': True,
615 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
617 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
619 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
620 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
625 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
627 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
628 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
634 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
639 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
640 'md5': '9d65602bf31c6e20014319c7d07fba27',
642 'id': '5123ea6d5e5a7',
645 'uploader': 'www.handjobhub.com',
646 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
649 # Multiple brightcove videos
650 # https://github.com/rg3/youtube-dl/issues/2283
652 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
654 'id': 'always-never',
655 'title': 'Always / Never - The New Yorker',
659 'extract_flat': False,
660 'skip_download': True,
665 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
666 'md5': '96f09a37e44da40dd083e12d9a683327',
670 'title': 'Ump changes call to ball',
671 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
673 'timestamp': 1401537900,
674 'upload_date': '20140531',
675 'thumbnail': 're:^https?://.*\.jpg$',
680 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
681 'md5': '8788b683c777a5cf25621eaf286d0c23',
685 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
687 'filesize': 182808282,
688 'uploader': 'education-portal.com',
692 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
693 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
697 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
699 'uploader': 'thoughtworks.wistia.com',
704 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
708 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
709 'uploader': 'Sophos Security',
710 'title': 'Chet Chat 171 - Oct 29, 2014',
711 'upload_date': '20141029',
716 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
720 'upload_date': '20141112',
721 'title': 'Rosetta #CometLanding webcast HL 10',
726 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
729 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
731 'playlist_mincount': 2,
735 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
739 'upload_date': '20141126',
740 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
745 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
747 'id': '730m_DandD_1901_512k',
749 'uploader': 'www.abc.net.au',
750 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
753 # embedded viddler video
755 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
759 'uploader': 'deadspin',
760 'title': 'WALL-TO-GORTAT',
761 'timestamp': 1422285291,
762 'upload_date': '20150126',
764 'add_ie': ['Viddler'],
768 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
772 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
773 'description': 'md5:601cb790edd05908957dae8aaa866465',
774 'upload_date': '20150220',
779 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
783 'upload_date': '20150212',
784 'uploader': 'The National Archives UK',
785 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
786 'uploader_id': 'NationalArchives08',
787 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
792 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
793 'playlist_mincount': 5,
795 'id': 'aanslagen-kopenhagen',
796 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
801 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
805 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
810 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
814 'upload_date': '20150226',
815 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
817 'title': 'John Carlson Postgame 2/25/15',
820 # Kaltura embed (different embed code)
822 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
826 'upload_date': '20150127',
827 'uploader_id': 'PremierMedia',
829 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
832 # Kaltura embed protected with referrer
834 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
838 'title': 'Violetta - Achter De Schermen - Ruggero',
839 'description': 'Achter de schermen met Ruggero',
840 'timestamp': 1435133761,
841 'upload_date': '20150624',
842 'uploader_id': 'echojecka',
845 # Eagle.Platform embed (generic URL)
847 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
851 'title': 'Навальный вышел на свободу',
852 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
853 'thumbnail': 're:^https?://.*\.jpg$',
859 # ClipYou (Eagle.Platform) embed (custom URL)
861 'url': 'http://muz-tv.ru/play/7129/',
865 'title': "'O Sole Mio",
866 'thumbnail': 're:^https?://.*\.jpg$',
873 'url': 'http://muz-tv.ru/kinozal/view/7400/',
877 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
878 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
879 'thumbnail': 're:^https?://.*\.jpg$',
886 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
890 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
891 'thumbnail': 're:^https?://.*\.png$',
897 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
898 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
902 'title': 'Facebook Creates "On This Day" | Crunch Report',
907 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
911 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
916 # Crooks and Liars embed
918 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
922 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
923 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
924 'timestamp': 1428207000,
925 'upload_date': '20150405',
926 'uploader': 'Heather',
929 # Crooks and Liars external embed
931 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
933 'id': 'MTE3MjUtMzQ2MzA',
935 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
936 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
937 'timestamp': 1265032391,
938 'upload_date': '20100201',
939 'uploader': 'Heather',
942 # NBC Sports vplayer embed
944 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
946 'id': 'ln7x1qSThw4k',
948 'title': "PFT Live: New leader in the 'new-look' defense",
949 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
954 'url': 'http://www.udn.com/news/story/7314/822787',
955 'md5': 'fd2060e988c326991037b9aff9df21a6',
959 'title': '中一中男師變性 全校師生力挺',
960 'thumbnail': 're:^https?://.*\.jpg$',
965 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
967 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
969 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
970 'title': 'This is what separates the Excel masters from the wannabes',
975 'skip_download': True,
978 # Contains a SMIL manifest
980 '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',
984 'title': '+ Football: Lottery Champions League Europe',
985 'uploader': 'www.telewebion.com',
989 'skip_download': True,
992 # Brightcove URL in single quotes
994 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
995 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
997 'id': '4255764656001',
999 'title': 'SN Presents: Russell Martin, World Citizen',
1000 '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.',
1001 'uploader': 'Rogers Sportsnet',
1004 # Dailymotion Cloud video
1006 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1007 'md5': '49444254273501a64675a7e68c502681',
1009 'id': '5585de919473990de4bee11b',
1011 'title': 'Le débat',
1012 'thumbnail': 're:^https?://.*\.jpe?g$',
1015 # OnionStudios embed
1017 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1021 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1022 'thumbnail': 're:^https?://.*\.jpe?g$',
1023 'uploader': 'ClickHole',
1024 'uploader_id': 'clickhole',
1029 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1031 'id': '74849a00-85a9-11e1-9660-123139220831',
1033 'title': '#whilewewatch',
1036 # AdobeTVVideo embed
1038 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1039 'md5': '43662b577c018ad707a63766462b1e87',
1043 'title': 'New experience with Acrobat DC',
1044 'description': 'New experience with Acrobat DC',
1045 'duration': 248.667,
1048 # ScreenwaveMedia embed
1050 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1051 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1053 'id': 'cinemasnob-55d26273809dd',
1055 'title': 'cinemasnob',
1058 # BrightcoveInPageEmbed embed
1060 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1062 'id': '4238694884001',
1064 'title': 'Tabletop: Dread, Last Thoughts',
1065 'description': 'Tabletop: Dread, Last Thoughts',
1069 # JWPlayer with M3U8
1071 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1075 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1076 'uploader': 'ren.tv',
1080 'skip_download': True,
1085 def report_following_redirect(self, new_url):
1086 """Report information extraction."""
1087 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1089 def _extract_rss(self, url, video_id, doc):
1090 playlist_title = doc.find('./channel/title').text
1091 playlist_desc_el = doc.find('./channel/description')
1092 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1095 for it in doc.findall('./channel/item'):
1096 next_url = xpath_text(it, 'link', fatal=False)
1098 enclosure_nodes = it.findall('./enclosure')
1099 for e in enclosure_nodes:
1100 next_url = e.attrib.get('url')
1110 'title': it.find('title').text,
1114 '_type': 'playlist',
1116 'title': playlist_title,
1117 'description': playlist_desc,
1121 def _extract_camtasia(self, url, video_id, webpage):
1122 """ Returns None if no camtasia video can be found. """
1124 camtasia_cfg = self._search_regex(
1125 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1126 webpage, 'camtasia configuration file', default=None)
1127 if camtasia_cfg is None:
1130 title = self._html_search_meta('DC.title', webpage, fatal=True)
1132 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1133 camtasia_cfg = self._download_xml(
1134 camtasia_url, video_id,
1135 note='Downloading camtasia configuration',
1136 errnote='Failed to download camtasia configuration')
1137 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1140 for n in fileset_node.getchildren():
1141 url_n = n.find('./uri')
1146 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1147 'title': '%s - %s' % (title, n.tag),
1148 'url': compat_urlparse.urljoin(url, url_n.text),
1149 'duration': float_or_none(n.find('./duration').text),
1153 '_type': 'playlist',
1158 def _real_extract(self, url):
1159 if url.startswith('//'):
1162 'url': self.http_scheme() + url,
1165 parsed_url = compat_urlparse.urlparse(url)
1166 if not parsed_url.scheme:
1167 default_search = self._downloader.params.get('default_search')
1168 if default_search is None:
1169 default_search = 'fixup_error'
1171 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1173 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1174 return self.url_result('http://' + url)
1175 elif default_search != 'fixup_error':
1176 if default_search == 'auto_warning':
1177 if re.match(r'^(?:url|URL)$', url):
1178 raise ExtractorError(
1179 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1182 self._downloader.report_warning(
1183 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1184 return self.url_result('ytsearch:' + url)
1186 if default_search in ('error', 'fixup_error'):
1187 raise ExtractorError(
1188 '%r is not a valid URL. '
1189 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1190 % (url, url), expected=True)
1192 if ':' not in default_search:
1193 default_search += ':'
1194 return self.url_result(default_search + url)
1196 url, smuggled_data = unsmuggle_url(url)
1197 force_videoid = None
1198 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1199 if smuggled_data and 'force_videoid' in smuggled_data:
1200 force_videoid = smuggled_data['force_videoid']
1201 video_id = force_videoid
1203 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1205 self.to_screen('%s: Requesting header' % video_id)
1207 head_req = HEADRequest(url)
1208 head_response = self._request_webpage(
1210 note=False, errnote='Could not send HEAD request to %s' % url,
1213 if head_response is not False:
1214 # Check for redirect
1215 new_url = head_response.geturl()
1217 self.report_following_redirect(new_url)
1219 new_url = smuggle_url(
1220 new_url, {'force_videoid': force_videoid})
1221 return self.url_result(new_url)
1223 full_response = None
1224 if head_response is False:
1225 request = sanitized_Request(url)
1226 request.add_header('Accept-Encoding', '*')
1227 full_response = self._request_webpage(request, video_id)
1228 head_response = full_response
1230 # Check for direct link to a video
1231 content_type = head_response.headers.get('Content-Type', '')
1232 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|dash\+xml|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
1234 upload_date = unified_strdate(
1235 head_response.headers.get('Last-Modified'))
1237 if m.group('format_id').endswith('mpegurl'):
1238 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1239 elif m.group('format_id').startswith('dash+xml'):
1240 formats = self._extract_mpd_formats(url, video_id)
1243 'format_id': m.group('format_id'),
1245 'vcodec': 'none' if m.group('type') == 'audio' else None
1249 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1252 'upload_date': upload_date,
1255 if not self._downloader.params.get('test', False) and not is_intentional:
1256 force = self._downloader.params.get('force_generic_extractor', False)
1257 self._downloader.report_warning(
1258 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1260 if not full_response:
1261 request = sanitized_Request(url)
1262 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1263 # making it impossible to download only chunk of the file (yet we need only 512kB to
1264 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1265 # that will always result in downloading the whole file that is not desirable.
1266 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1267 # to accept raw bytes and being able to download only a chunk.
1268 # It may probably better to solve this by checking Content-Type for application/octet-stream
1269 # after HEAD request finishes, but not sure if we can rely on this.
1270 request.add_header('Accept-Encoding', '*')
1271 full_response = self._request_webpage(request, video_id)
1273 # Maybe it's a direct link to a video?
1274 # Be careful not to download the whole thing!
1275 first_bytes = full_response.read(512)
1276 if not is_html(first_bytes):
1277 self._downloader.report_warning(
1278 'URL could be a direct video link, returning it as such.')
1279 upload_date = unified_strdate(
1280 head_response.headers.get('Last-Modified'))
1283 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1286 'upload_date': upload_date,
1289 webpage = self._webpage_read_content(
1290 full_response, url, video_id, prefix=first_bytes)
1292 self.report_extraction(video_id)
1294 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1296 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1297 if doc.tag == 'rss':
1298 return self._extract_rss(url, video_id, doc)
1299 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1300 return self._parse_smil(doc, url, video_id)
1301 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1302 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1303 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1306 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1307 'formats': self._parse_mpd_formats(doc, video_id),
1309 except compat_xml_parse_error:
1312 # Is it a Camtasia project?
1313 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1314 if camtasia_res is not None:
1317 # Sometimes embedded video player is hidden behind percent encoding
1318 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1319 # Unescaping the whole page allows to handle those cases in a generic way
1320 webpage = compat_urllib_parse_unquote(webpage)
1322 # it's tempting to parse this further, but you would
1323 # have to take into account all the variations like
1324 # Video Title - Site Name
1325 # Site Name | Video Title
1326 # Video Title - Tagline | Site Name
1327 # and so on and so forth; it's just not practical
1328 video_title = self._html_search_regex(
1329 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1332 # Try to detect age limit automatically
1333 age_limit = self._rta_search(webpage)
1334 # And then there are the jokers who advertise that they use RTA,
1335 # but actually don't.
1336 AGE_LIMIT_MARKERS = [
1337 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1339 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1342 # video uploader is domain name
1343 video_uploader = self._search_regex(
1344 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1347 def _playlist_from_matches(matches, getter=None, ie=None):
1349 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1351 return self.playlist_result(
1352 urlrs, playlist_id=video_id, playlist_title=video_title)
1354 # Look for Brightcove Legacy Studio embeds
1355 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1357 self.to_screen('Brightcove video detected.')
1360 'url': smuggle_url(bc_url, {'Referer': url}),
1361 'ie_key': 'BrightcoveLegacy'
1362 } for bc_url in bc_urls]
1365 '_type': 'playlist',
1366 'title': video_title,
1371 # Look for Brightcove New Studio embeds
1372 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1374 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1376 # Look for embedded rtl.nl player
1377 matches = re.findall(
1378 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1381 return _playlist_from_matches(matches, ie='RtlNl')
1383 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1384 if vimeo_url is not None:
1385 return self.url_result(vimeo_url)
1387 vid_me_embed_url = self._search_regex(
1388 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1389 webpage, 'vid.me embed', default=None)
1390 if vid_me_embed_url is not None:
1391 return self.url_result(vid_me_embed_url, 'Vidme')
1393 # Look for embedded YouTube player
1394 matches = re.findall(r'''(?x)
1403 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1407 return _playlist_from_matches(
1408 matches, lambda m: unescapeHTML(m[1]))
1410 # Look for lazyYT YouTube embed
1411 matches = re.findall(
1412 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1414 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1416 # Look for embedded Dailymotion player
1417 matches = re.findall(
1418 r'<(?:embed|iframe)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1420 return _playlist_from_matches(
1421 matches, lambda m: unescapeHTML(m[1]))
1423 # Look for embedded Dailymotion playlist player (#3822)
1425 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1427 playlists = re.findall(
1428 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1430 return _playlist_from_matches(
1431 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1433 # Look for embedded Wistia player
1435 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1437 embed_url = self._proto_relative_url(
1438 unescapeHTML(match.group('url')))
1440 '_type': 'url_transparent',
1443 'uploader': video_uploader,
1444 'title': video_title,
1448 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1451 '_type': 'url_transparent',
1452 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1454 'uploader': video_uploader,
1455 'title': video_title,
1456 'id': match.group('id')
1459 # Look for SVT player
1460 svt_url = SVTIE._extract_url(webpage)
1462 return self.url_result(svt_url, 'SVT')
1464 # Look for embedded condenast player
1465 matches = re.findall(
1466 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1470 '_type': 'playlist',
1473 'ie_key': 'CondeNast',
1475 } for ma in matches],
1476 'title': video_title,
1480 # Look for Bandcamp pages with custom domain
1481 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1482 if mobj is not None:
1483 burl = unescapeHTML(mobj.group(1))
1484 # Don't set the extractor because it can be a track url or an album
1485 return self.url_result(burl)
1487 # Look for embedded Vevo player
1489 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1490 if mobj is not None:
1491 return self.url_result(mobj.group('url'))
1493 # Look for embedded Viddler player
1495 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1497 if mobj is not None:
1498 return self.url_result(mobj.group('url'))
1500 # Look for NYTimes player
1502 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1504 if mobj is not None:
1505 return self.url_result(mobj.group('url'))
1507 # Look for Libsyn player
1509 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1510 if mobj is not None:
1511 return self.url_result(mobj.group('url'))
1513 # Look for Ooyala videos
1514 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1515 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1516 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1517 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1518 if mobj is not None:
1519 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1521 # Look for multiple Ooyala embeds on SBN network websites
1522 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1523 if mobj is not None:
1524 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1526 return _playlist_from_matches(
1527 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1529 # Look for Aparat videos
1530 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1531 if mobj is not None:
1532 return self.url_result(mobj.group(1), 'Aparat')
1534 # Look for MPORA videos
1535 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1536 if mobj is not None:
1537 return self.url_result(mobj.group(1), 'Mpora')
1539 # Look for embedded NovaMov-based player
1541 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1542 (?P<url>http://(?:(?:embed|www)\.)?
1544 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1545 videoweed\.(?:es|com)|
1546 movshare\.(?:net|sx|ag)|
1547 divxstage\.(?:eu|net|ch|co|at|ag))
1548 /embed\.php.+?)\1''', webpage)
1549 if mobj is not None:
1550 return self.url_result(mobj.group('url'))
1552 # Look for embedded Facebook player
1554 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1555 if mobj is not None:
1556 return self.url_result(mobj.group('url'), 'Facebook')
1558 # Look for embedded VK player
1559 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1560 if mobj is not None:
1561 return self.url_result(mobj.group('url'), 'VK')
1563 # Look for embedded ivi player
1564 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1565 if mobj is not None:
1566 return self.url_result(mobj.group('url'), 'Ivi')
1568 # Look for embedded Huffington Post player
1570 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1571 if mobj is not None:
1572 return self.url_result(mobj.group('url'), 'HuffPost')
1575 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1576 if mobj is not None:
1577 return self.url_result(mobj.group('url'))
1578 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1579 if mobj is not None:
1580 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1582 # Look for funnyordie embed
1583 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1585 return _playlist_from_matches(
1586 matches, getter=unescapeHTML, ie='FunnyOrDie')
1588 # Look for BBC iPlayer embed
1589 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1591 return _playlist_from_matches(matches, ie='BBCCoUk')
1593 # Look for embedded RUTV player
1594 rutv_url = RUTVIE._extract_url(webpage)
1596 return self.url_result(rutv_url, 'RUTV')
1598 # Look for embedded TVC player
1599 tvc_url = TVCIE._extract_url(webpage)
1601 return self.url_result(tvc_url, 'TVC')
1603 # Look for embedded SportBox player
1604 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1606 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1608 # Look for embedded PornHub player
1609 pornhub_url = PornHubIE._extract_url(webpage)
1611 return self.url_result(pornhub_url, 'PornHub')
1613 # Look for embedded XHamster player
1614 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1616 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1618 # Look for embedded Tvigle player
1620 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1621 if mobj is not None:
1622 return self.url_result(mobj.group('url'), 'Tvigle')
1624 # Look for embedded TED player
1626 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'), 'TED')
1630 # Look for embedded Ustream videos
1632 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1633 if mobj is not None:
1634 return self.url_result(mobj.group('url'), 'Ustream')
1636 # Look for embedded arte.tv player
1638 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1640 if mobj is not None:
1641 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1643 # Look for embedded francetv player
1645 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1647 if mobj is not None:
1648 return self.url_result(mobj.group('url'))
1650 # Look for embedded smotri.com player
1651 smotri_url = SmotriIE._extract_url(webpage)
1653 return self.url_result(smotri_url, 'Smotri')
1655 # Look for embedded Myvi.ru player
1656 myvi_url = MyviIE._extract_url(webpage)
1658 return self.url_result(myvi_url)
1660 # Look for embedded soundcloud player
1662 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1664 if mobj is not None:
1665 url = unescapeHTML(mobj.group('url'))
1666 return self.url_result(url)
1668 # Look for embedded vulture.com player
1670 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1672 if mobj is not None:
1673 url = unescapeHTML(mobj.group('url'))
1674 return self.url_result(url, ie='Vulture')
1676 # Look for embedded mtvservices player
1677 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1679 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1681 # Look for embedded yahoo player
1683 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1685 if mobj is not None:
1686 return self.url_result(mobj.group('url'), 'Yahoo')
1688 # Look for embedded sbs.com.au player
1692 <meta\s+property="og:video"\s+content=|
1695 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'SBS')
1700 # Look for embedded Cinchcast player
1702 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1704 if mobj is not None:
1705 return self.url_result(mobj.group('url'), 'Cinchcast')
1708 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1712 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1714 if mobj is not None:
1715 return self.url_result(mobj.group('url'), 'MLB')
1718 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1720 if mobj is not None:
1721 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1724 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1726 if mobj is not None:
1727 return self.url_result(mobj.group('url'), 'Livestream')
1729 # Look for Zapiks embed
1731 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1732 if mobj is not None:
1733 return self.url_result(mobj.group('url'), 'Zapiks')
1735 # Look for Kaltura embeds
1736 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1737 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1738 if mobj is not None:
1739 return self.url_result(smuggle_url(
1740 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1741 {'source_url': url}), 'Kaltura')
1743 # Look for Eagle.Platform embeds
1745 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1746 if mobj is not None:
1747 return self.url_result(mobj.group('url'), 'EaglePlatform')
1749 # Look for ClipYou (uses Eagle.Platform) embeds
1751 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1752 if mobj is not None:
1753 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1755 # Look for Pladform embeds
1756 pladform_url = PladformIE._extract_url(webpage)
1758 return self.url_result(pladform_url)
1760 # Look for Videomore embeds
1761 videomore_url = VideomoreIE._extract_url(webpage)
1763 return self.url_result(videomore_url)
1765 # Look for Playwire embeds
1767 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'))
1771 # Look for 5min embeds
1773 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1774 if mobj is not None:
1775 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1777 # Look for Crooks and Liars embeds
1779 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1780 if mobj is not None:
1781 return self.url_result(mobj.group('url'))
1783 # Look for NBC Sports VPlayer embeds
1784 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1786 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1788 # Look for Google Drive embeds
1789 google_drive_url = GoogleDriveIE._extract_url(webpage)
1790 if google_drive_url:
1791 return self.url_result(google_drive_url, 'GoogleDrive')
1793 # Look for UDN embeds
1795 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1796 if mobj is not None:
1797 return self.url_result(
1798 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1800 # Look for Senate ISVP iframe
1801 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1803 return self.url_result(senate_isvp_url, 'SenateISVP')
1805 # Look for Dailymotion Cloud videos
1806 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1808 return self.url_result(dmcloud_url, 'DailymotionCloud')
1810 # Look for OnionStudios embeds
1811 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1812 if onionstudios_url:
1813 return self.url_result(onionstudios_url)
1815 # Look for SnagFilms embeds
1816 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1818 return self.url_result(snagfilms_url)
1820 # Look for JWPlatform embeds
1821 jwplatform_url = JWPlatformIE._extract_url(webpage)
1823 return self.url_result(jwplatform_url, 'JWPlatform')
1825 # Look for ScreenwaveMedia embeds
1826 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1827 if mobj is not None:
1828 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1830 # Look for Digiteka embeds
1831 digiteka_url = DigitekaIE._extract_url(webpage)
1833 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1835 # Look for Limelight embeds
1836 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1840 'Channel': 'channel',
1841 'ChannelList': 'channel_list',
1843 return self.url_result('limelight:%s:%s' % (
1844 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1846 # Look for AdobeTVVideo embeds
1848 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1850 if mobj is not None:
1851 return self.url_result(
1852 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1855 def check_video(vurl):
1856 if YoutubeIE.suitable(vurl):
1858 vpath = compat_urlparse.urlparse(vurl).path
1859 vext = determine_ext(vpath)
1860 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1862 def filter_video(urls):
1863 return list(filter(check_video, urls))
1865 # Start with something easy: JW Player in SWFObject
1866 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1868 # Look for gorilla-vid style embedding
1869 found = filter_video(re.findall(r'''(?sx)
1873 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1876 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1878 # Broaden the search a little bit
1879 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1881 # Broaden the findall a little bit: JWPlayer JS loader
1882 found = filter_video(re.findall(
1883 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1886 found = filter_video(re.findall(r'''(?xs)
1887 flowplayer\("[^"]+",\s*
1889 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1890 ["']?url["']?\s*:\s*["']([^"']+)["']
1895 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1897 # Try to find twitter cards info
1898 found = filter_video(re.findall(
1899 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1901 # We look for Open Graph info:
1902 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1903 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1904 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1905 if m_video_type is not None:
1906 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1909 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1911 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1913 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1914 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1917 # Look also in Refresh HTTP header
1918 refresh_header = head_response.headers.get('Refresh')
1920 # In python 2 response HTTP headers are bytestrings
1921 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1922 refresh_header = refresh_header.decode('iso-8859-1')
1923 found = re.search(REDIRECT_REGEX, refresh_header)
1925 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1926 self.report_following_redirect(new_url)
1932 raise UnsupportedError(url)
1935 for video_url in found:
1936 video_url = video_url.replace('\\/', '/')
1937 video_url = compat_urlparse.urljoin(url, video_url)
1938 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1940 # Sometimes, jwplayer extraction will result in a YouTube URL
1941 if YoutubeIE.suitable(video_url):
1942 entries.append(self.url_result(video_url, 'Youtube'))
1945 # here's a fun little line of code for you:
1946 video_id = os.path.splitext(video_id)[0]
1950 'uploader': video_uploader,
1951 'title': video_title,
1952 'age_limit': age_limit,
1955 ext = determine_ext(video_url)
1957 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1959 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1961 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1963 entry_info_dict['url'] = video_url
1965 entries.append(entry_info_dict)
1967 if len(entries) == 1:
1970 for num, e in enumerate(entries, start=1):
1971 # 'url' results don't have a title
1972 if e.get('title') is not None:
1973 e['title'] = '%s (%d)' % (e['title'], num)
1975 '_type': 'playlist',