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 .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .snagfilms import SnagFilmsEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
64 class GenericIE(InfoExtractor):
65 IE_DESC = 'Generic downloader that works on some sites'
69 # Direct link to a video
71 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
72 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
77 'upload_date': '20100513',
80 # Direct link to media delivered compressed (until Accept-Encoding is *)
82 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
83 'md5': '128c42e68b13950268b648275386fc74',
85 'id': 'FictionJunction-Parallel_Hearts',
87 'title': 'FictionJunction-Parallel_Hearts',
88 'upload_date': '20140522',
90 'expected_warnings': [
91 'URL could be a direct video link, returning it as such.'
94 # Direct download with broken HEAD
96 'url': 'http://ai-radio.org:8000/radio.opus',
103 'skip_download': True, # infinite live stream
105 'expected_warnings': [
106 r'501.*Not Implemented'
109 # Direct link with incorrect MIME type
111 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
112 'md5': '4ccbebe5f36706d85221f204d7eb5913',
114 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
115 'id': '5_Lennart_Poettering_-_Systemd',
117 'title': '5_Lennart_Poettering_-_Systemd',
118 'upload_date': '20141120',
120 'expected_warnings': [
121 'URL could be a direct video link, returning it as such.'
126 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
128 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
129 'title': 'Zero Punctuation',
130 'description': 're:.*groundbreaking video review series.*'
132 'playlist_mincount': 11,
134 # RSS feed with enclosure
136 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
138 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
140 'upload_date': '20150228',
141 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
144 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
146 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
150 'title': 'Automatics, robotics and biocybernetics',
151 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
152 'upload_date': '20130627',
153 'formats': 'mincount:16',
154 'subtitles': 'mincount:1',
157 'force_generic_extractor': True,
158 'skip_download': True,
161 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
163 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
168 'formats': 'mincount:1',
171 'skip_download': True,
174 # SMIL from https://www.restudy.dk/video/play/id/1637
176 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
180 'title': 'video_1637',
181 'formats': 'mincount:3',
184 'skip_download': True,
187 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
189 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
191 'id': 'smil-service',
193 'title': 'smil-service',
194 'formats': 'mincount:1',
197 'skip_download': True,
200 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
202 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
206 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
207 'formats': 'mincount:3',
210 'skip_download': True,
213 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
215 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
217 'id': 'mZlp2ctYIUEB',
219 'title': 'Tikibad ontruimd wegens brand',
220 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
221 'thumbnail': 're:^https?://.*\.jpg$',
225 'skip_download': True,
228 # MPD from http://dash-mse-test.appspot.com/media.html
230 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
231 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
233 'id': 'car-20120827-manifest',
235 'title': 'car-20120827-manifest',
236 'formats': 'mincount:9',
239 'format': 'bestvideo',
242 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
244 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
249 'formats': 'mincount:8',
253 'skip_download': True,
256 # m3u8 served with Content-Type: text/plain
258 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
263 'upload_date': '20140720',
264 'formats': 'mincount:11',
268 'skip_download': True,
273 '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',
277 'upload_date': '20130224',
278 'uploader_id': 'TheVerge',
279 'description': 're:^Chris Ziegler takes a look at the\.*',
280 'uploader': 'The Verge',
281 'title': 'First Firefox OS phones side-by-side',
284 'skip_download': False,
288 # redirect in Refresh HTTP header
289 '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',
293 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
294 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
295 'upload_date': '20150917',
296 'uploader_id': 'brtvofficial',
297 'uploader': 'Boiler Room',
300 'skip_download': False,
304 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
305 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
307 'id': '13601338388002',
309 'uploader': 'www.hodiho.fr',
310 'title': 'R\u00e9gis plante sa Jeep',
313 # bandcamp page with custom domain
315 'add_ie': ['Bandcamp'],
316 'url': 'http://bronyrock.com/track/the-pony-mash',
320 'title': 'The Pony Mash',
321 'uploader': 'M_Pallante',
323 'skip': 'There is a limit of 200 free downloads / month for the test song',
325 # embedded brightcove video
326 # it also tests brightcove videos that need to set the 'Referer' in the
329 'add_ie': ['BrightcoveLegacy'],
330 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
332 'id': '2765128793001',
334 'title': 'Le cours de bourse : l’analyse technique',
335 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
336 'uploader': 'BFM BUSINESS',
339 'skip_download': True,
343 # https://github.com/rg3/youtube-dl/issues/2253
344 'url': 'http://bcove.me/i6nfkrc3',
345 'md5': '0ba9446db037002366bab3b3eb30c88c',
347 'id': '3101154703001',
349 'title': 'Still no power',
350 'uploader': 'thestar.com',
351 '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.',
353 'add_ie': ['BrightcoveLegacy'],
356 'url': 'http://www.championat.com/video/football/v/87/87499.html',
357 'md5': 'fb973ecf6e4a78a67453647444222983',
359 'id': '3414141473001',
361 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
362 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
363 'uploader': 'Championat',
367 # https://github.com/rg3/youtube-dl/issues/3541
368 'add_ie': ['BrightcoveLegacy'],
369 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
371 'id': '3866516442001',
373 'title': 'Leer mij vrouwen kennen: Aflevering 1',
374 'description': 'Leer mij vrouwen kennen: Aflevering 1',
375 'uploader': 'SBS Broadcasting',
377 'skip': 'Restricted to Netherlands',
379 'skip_download': True, # m3u8 download
384 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
385 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
387 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
389 'title': '2cc213299525360.mov', # that's what we get
392 'add_ie': ['Ooyala'],
395 # ooyala video embedded with http://player.ooyala.com/iframe.js
396 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
398 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
400 'title': '"Steve Jobs: Man in the Machine" trailer',
401 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
405 'skip_download': True,
408 # multiple ooyala embeds on SBN network websites
410 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
412 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
413 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
415 'playlist_mincount': 3,
417 'skip_download': True,
419 'add_ie': ['Ooyala'],
423 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
427 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
428 'upload_date': '20140225',
429 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
430 'uploader': 'Tested',
431 'uploader_id': 'testedcom',
433 # No need to test YoutubeIE here
435 'skip_download': True,
440 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
444 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
445 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
450 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
454 'title': 'Охотское море стало целиком российским',
455 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
459 'skip_download': True,
464 '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/',
468 'title': 'Дошкольное воспитание',
473 'url': 'http://www.vestifinance.ru/articles/25753',
476 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
481 'title': 'Госзаказ. День 3',
487 'title': 'Госзаказ. День 2',
493 'title': 'Госзаказ. День 1',
499 'skip_download': True,
504 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
506 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
508 'title': 'Ужастики, русский трейлер (2015)',
509 'thumbnail': 're:^https?://.*\.jpg$',
515 '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',
518 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
520 'playlist_mincount': 7,
524 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
525 'md5': '65fdff94098e4a607385a60c5177c638',
529 'title': 'Hidden miracles of the natural world',
530 'uploader': 'Louie Schwartzberg',
531 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
534 # Embedded Ustream video
536 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
537 'md5': '27b99cdb639c9b12a79bca876a073417',
541 'uploader': 'AU SPA: The NSA and Privacy',
542 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
545 # nowvideo embed hidden behind percent encoding
547 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
548 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
550 'id': '06e53103ca9aa',
552 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
553 'description': 'No description',
558 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
559 'md5': '7653032cbb25bf6c80d80f217055fa43',
561 'id': '048195-004_PLUS7-F',
564 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
565 'upload_date': '20140320',
568 'skip_download': 'Requires rtmpdump'
573 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
577 'title': 'Alcaline, le concert avec Calogero',
578 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
579 'upload_date': '20150226',
580 'timestamp': 1424989860,
585 'skip_download': True,
587 'expected_warnings': [
593 'url': 'http://www.wired.com/2014/04/honda-asimo/',
594 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
596 'id': '53501be369702d3275860000',
598 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
603 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
604 'md5': '441aeeb82eb72c422c7f14ec533999cd',
606 'id': 'k2mm4bCdJ6CQ2i7c8o2',
608 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
611 'add_ie': ['Dailymotion'],
615 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
619 'title': 'The NBL Auction 2014',
620 'uploader': 'BADMINTON England',
621 'uploader_id': 'BADMINTONEvents',
622 'upload_date': '20140603',
623 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
625 'add_ie': ['Youtube'],
627 'skip_download': True,
632 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
633 'md5': '35727f82f58c76d996fc188f9755b0d5',
635 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
638 'description': 'Mario\'s life in the fast lane has never looked so good.',
641 # YouTube embed via <data-embed-url="">
643 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
647 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
648 'uploader': 'Gameloft',
649 'uploader_id': 'gameloft',
650 'upload_date': '20140828',
651 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
654 'skip_download': True,
659 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
661 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
663 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
664 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
669 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
671 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
672 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
678 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
683 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
684 'md5': '9d65602bf31c6e20014319c7d07fba27',
686 'id': '5123ea6d5e5a7',
689 'uploader': 'www.handjobhub.com',
690 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
693 # Multiple brightcove videos
694 # https://github.com/rg3/youtube-dl/issues/2283
696 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
698 'id': 'always-never',
699 'title': 'Always / Never - The New Yorker',
703 'extract_flat': False,
704 'skip_download': True,
709 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
710 'md5': '96f09a37e44da40dd083e12d9a683327',
714 'title': 'Ump changes call to ball',
715 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
717 'timestamp': 1401537900,
718 'upload_date': '20140531',
719 'thumbnail': 're:^https?://.*\.jpg$',
724 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
725 'md5': '8788b683c777a5cf25621eaf286d0c23',
729 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
731 'filesize': 182808282,
732 'uploader': 'education-portal.com',
736 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
737 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
741 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
743 'uploader': 'thoughtworks.wistia.com',
748 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
752 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
753 'uploader': 'Sophos Security',
754 'title': 'Chet Chat 171 - Oct 29, 2014',
755 'upload_date': '20141029',
760 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
764 'upload_date': '20141112',
765 'title': 'Rosetta #CometLanding webcast HL 10',
770 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
773 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
775 'playlist_mincount': 2,
779 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
783 'upload_date': '20141126',
784 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
789 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
791 'id': '730m_DandD_1901_512k',
793 'uploader': 'www.abc.net.au',
794 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
797 # embedded viddler video
799 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
803 'uploader': 'deadspin',
804 'title': 'WALL-TO-GORTAT',
805 'timestamp': 1422285291,
806 'upload_date': '20150126',
808 'add_ie': ['Viddler'],
812 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
816 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
817 'description': 'md5:601cb790edd05908957dae8aaa866465',
818 'upload_date': '20150220',
823 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
827 'upload_date': '20150212',
828 'uploader': 'The National Archives UK',
829 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
830 'uploader_id': 'NationalArchives08',
831 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
836 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
837 'playlist_mincount': 5,
839 'id': 'aanslagen-kopenhagen',
840 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
845 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
849 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
854 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
858 'upload_date': '20150226',
859 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
861 'title': 'John Carlson Postgame 2/25/15',
864 # Kaltura embed (different embed code)
866 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
870 'upload_date': '20150127',
871 'uploader_id': 'PremierMedia',
873 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
876 # Kaltura embed protected with referrer
878 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
882 'title': 'Violetta - Achter De Schermen - Ruggero',
883 'description': 'Achter de schermen met Ruggero',
884 'timestamp': 1435133761,
885 'upload_date': '20150624',
886 'uploader_id': 'echojecka',
889 # Eagle.Platform embed (generic URL)
891 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
895 'title': 'Навальный вышел на свободу',
896 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
897 'thumbnail': 're:^https?://.*\.jpg$',
903 # ClipYou (Eagle.Platform) embed (custom URL)
905 'url': 'http://muz-tv.ru/play/7129/',
909 'title': "'O Sole Mio",
910 'thumbnail': 're:^https?://.*\.jpg$',
917 'url': 'http://muz-tv.ru/kinozal/view/7400/',
921 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
922 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
923 'thumbnail': 're:^https?://.*\.jpg$',
930 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
934 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
935 'thumbnail': 're:^https?://.*\.png$',
941 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
942 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
946 'title': 'Facebook Creates "On This Day" | Crunch Report',
951 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
955 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
960 # Crooks and Liars embed
962 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
966 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
967 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
968 'timestamp': 1428207000,
969 'upload_date': '20150405',
970 'uploader': 'Heather',
973 # Crooks and Liars external embed
975 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
977 'id': 'MTE3MjUtMzQ2MzA',
979 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
980 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
981 'timestamp': 1265032391,
982 'upload_date': '20100201',
983 'uploader': 'Heather',
986 # NBC Sports vplayer embed
988 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
990 'id': 'ln7x1qSThw4k',
992 'title': "PFT Live: New leader in the 'new-look' defense",
993 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
998 'url': 'http://www.udn.com/news/story/7314/822787',
999 'md5': 'fd2060e988c326991037b9aff9df21a6',
1003 'title': '中一中男師變性 全校師生力挺',
1004 'thumbnail': 're:^https?://.*\.jpg$',
1009 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1011 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1013 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1014 'title': 'This is what separates the Excel masters from the wannabes',
1015 'duration': 191.933,
1019 'skip_download': True,
1022 # Contains a SMIL manifest
1024 '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',
1028 'title': '+ Football: Lottery Champions League Europe',
1029 'uploader': 'www.telewebion.com',
1033 'skip_download': True,
1036 # Brightcove URL in single quotes
1038 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1039 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1041 'id': '4255764656001',
1043 'title': 'SN Presents: Russell Martin, World Citizen',
1044 '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.',
1045 'uploader': 'Rogers Sportsnet',
1048 # Dailymotion Cloud video
1050 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1051 'md5': '49444254273501a64675a7e68c502681',
1053 'id': '5585de919473990de4bee11b',
1055 'title': 'Le débat',
1056 'thumbnail': 're:^https?://.*\.jpe?g$',
1059 # OnionStudios embed
1061 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1065 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1066 'thumbnail': 're:^https?://.*\.jpe?g$',
1067 'uploader': 'ClickHole',
1068 'uploader_id': 'clickhole',
1073 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1075 'id': '74849a00-85a9-11e1-9660-123139220831',
1077 'title': '#whilewewatch',
1080 # AdobeTVVideo embed
1082 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1083 'md5': '43662b577c018ad707a63766462b1e87',
1087 'title': 'New experience with Acrobat DC',
1088 'description': 'New experience with Acrobat DC',
1089 'duration': 248.667,
1092 # ScreenwaveMedia embed
1094 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1095 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1097 'id': 'cinemasnob-55d26273809dd',
1099 'title': 'cinemasnob',
1102 # BrightcoveInPageEmbed embed
1104 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1106 'id': '4238694884001',
1108 'title': 'Tabletop: Dread, Last Thoughts',
1109 'description': 'Tabletop: Dread, Last Thoughts',
1113 # JWPlayer with M3U8
1115 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1119 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1120 'uploader': 'ren.tv',
1124 'skip_download': True,
1129 def report_following_redirect(self, new_url):
1130 """Report information extraction."""
1131 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1133 def _extract_rss(self, url, video_id, doc):
1134 playlist_title = doc.find('./channel/title').text
1135 playlist_desc_el = doc.find('./channel/description')
1136 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1139 for it in doc.findall('./channel/item'):
1140 next_url = xpath_text(it, 'link', fatal=False)
1142 enclosure_nodes = it.findall('./enclosure')
1143 for e in enclosure_nodes:
1144 next_url = e.attrib.get('url')
1154 'title': it.find('title').text,
1158 '_type': 'playlist',
1160 'title': playlist_title,
1161 'description': playlist_desc,
1165 def _extract_camtasia(self, url, video_id, webpage):
1166 """ Returns None if no camtasia video can be found. """
1168 camtasia_cfg = self._search_regex(
1169 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1170 webpage, 'camtasia configuration file', default=None)
1171 if camtasia_cfg is None:
1174 title = self._html_search_meta('DC.title', webpage, fatal=True)
1176 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1177 camtasia_cfg = self._download_xml(
1178 camtasia_url, video_id,
1179 note='Downloading camtasia configuration',
1180 errnote='Failed to download camtasia configuration')
1181 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1184 for n in fileset_node.getchildren():
1185 url_n = n.find('./uri')
1190 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1191 'title': '%s - %s' % (title, n.tag),
1192 'url': compat_urlparse.urljoin(url, url_n.text),
1193 'duration': float_or_none(n.find('./duration').text),
1197 '_type': 'playlist',
1202 def _real_extract(self, url):
1203 if url.startswith('//'):
1206 'url': self.http_scheme() + url,
1209 parsed_url = compat_urlparse.urlparse(url)
1210 if not parsed_url.scheme:
1211 default_search = self._downloader.params.get('default_search')
1212 if default_search is None:
1213 default_search = 'fixup_error'
1215 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1217 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1218 return self.url_result('http://' + url)
1219 elif default_search != 'fixup_error':
1220 if default_search == 'auto_warning':
1221 if re.match(r'^(?:url|URL)$', url):
1222 raise ExtractorError(
1223 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1226 self._downloader.report_warning(
1227 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1228 return self.url_result('ytsearch:' + url)
1230 if default_search in ('error', 'fixup_error'):
1231 raise ExtractorError(
1232 '%r is not a valid URL. '
1233 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1234 % (url, url), expected=True)
1236 if ':' not in default_search:
1237 default_search += ':'
1238 return self.url_result(default_search + url)
1240 url, smuggled_data = unsmuggle_url(url)
1241 force_videoid = None
1242 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1243 if smuggled_data and 'force_videoid' in smuggled_data:
1244 force_videoid = smuggled_data['force_videoid']
1245 video_id = force_videoid
1247 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1249 self.to_screen('%s: Requesting header' % video_id)
1251 head_req = HEADRequest(url)
1252 head_response = self._request_webpage(
1254 note=False, errnote='Could not send HEAD request to %s' % url,
1257 if head_response is not False:
1258 # Check for redirect
1259 new_url = head_response.geturl()
1261 self.report_following_redirect(new_url)
1263 new_url = smuggle_url(
1264 new_url, {'force_videoid': force_videoid})
1265 return self.url_result(new_url)
1267 full_response = None
1268 if head_response is False:
1269 request = sanitized_Request(url)
1270 request.add_header('Accept-Encoding', '*')
1271 full_response = self._request_webpage(request, video_id)
1272 head_response = full_response
1276 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1277 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1280 # Check for direct link to a video
1281 content_type = head_response.headers.get('Content-Type', '').lower()
1282 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1284 format_id = m.group('format_id')
1285 if format_id.endswith('mpegurl'):
1286 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1287 elif format_id == 'f4m':
1288 formats = self._extract_f4m_formats(url, video_id)
1291 'format_id': m.group('format_id'),
1293 'vcodec': 'none' if m.group('type') == 'audio' else None
1295 info_dict['direct'] = True
1296 info_dict['formats'] = formats
1299 if not self._downloader.params.get('test', False) and not is_intentional:
1300 force = self._downloader.params.get('force_generic_extractor', False)
1301 self._downloader.report_warning(
1302 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1304 if not full_response:
1305 request = sanitized_Request(url)
1306 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1307 # making it impossible to download only chunk of the file (yet we need only 512kB to
1308 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1309 # that will always result in downloading the whole file that is not desirable.
1310 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1311 # to accept raw bytes and being able to download only a chunk.
1312 # It may probably better to solve this by checking Content-Type for application/octet-stream
1313 # after HEAD request finishes, but not sure if we can rely on this.
1314 request.add_header('Accept-Encoding', '*')
1315 full_response = self._request_webpage(request, video_id)
1317 first_bytes = full_response.read(512)
1319 # Is it an M3U playlist?
1320 if first_bytes.startswith(b'#EXTM3U'):
1321 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1324 # Maybe it's a direct link to a video?
1325 # Be careful not to download the whole thing!
1326 if not is_html(first_bytes):
1327 self._downloader.report_warning(
1328 'URL could be a direct video link, returning it as such.')
1335 webpage = self._webpage_read_content(
1336 full_response, url, video_id, prefix=first_bytes)
1338 self.report_extraction(video_id)
1340 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1342 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1343 if doc.tag == 'rss':
1344 return self._extract_rss(url, video_id, doc)
1345 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1346 return self._parse_smil(doc, url, video_id)
1347 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1348 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1349 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1350 info_dict['formats'] = self._parse_mpd_formats(
1351 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1353 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1354 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1356 except compat_xml_parse_error:
1359 # Is it a Camtasia project?
1360 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1361 if camtasia_res is not None:
1364 # Sometimes embedded video player is hidden behind percent encoding
1365 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1366 # Unescaping the whole page allows to handle those cases in a generic way
1367 webpage = compat_urllib_parse_unquote(webpage)
1369 # it's tempting to parse this further, but you would
1370 # have to take into account all the variations like
1371 # Video Title - Site Name
1372 # Site Name | Video Title
1373 # Video Title - Tagline | Site Name
1374 # and so on and so forth; it's just not practical
1375 video_title = self._html_search_regex(
1376 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1379 # Try to detect age limit automatically
1380 age_limit = self._rta_search(webpage)
1381 # And then there are the jokers who advertise that they use RTA,
1382 # but actually don't.
1383 AGE_LIMIT_MARKERS = [
1384 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1386 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1389 # video uploader is domain name
1390 video_uploader = self._search_regex(
1391 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1394 def _playlist_from_matches(matches, getter=None, ie=None):
1396 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1398 return self.playlist_result(
1399 urlrs, playlist_id=video_id, playlist_title=video_title)
1401 # Look for Brightcove Legacy Studio embeds
1402 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1404 self.to_screen('Brightcove video detected.')
1407 'url': smuggle_url(bc_url, {'Referer': url}),
1408 'ie_key': 'BrightcoveLegacy'
1409 } for bc_url in bc_urls]
1412 '_type': 'playlist',
1413 'title': video_title,
1418 # Look for Brightcove New Studio embeds
1419 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1421 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1423 # Look for embedded rtl.nl player
1424 matches = re.findall(
1425 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1428 return _playlist_from_matches(matches, ie='RtlNl')
1430 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1431 if vimeo_url is not None:
1432 return self.url_result(vimeo_url)
1434 vid_me_embed_url = self._search_regex(
1435 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1436 webpage, 'vid.me embed', default=None)
1437 if vid_me_embed_url is not None:
1438 return self.url_result(vid_me_embed_url, 'Vidme')
1440 # Look for embedded YouTube player
1441 matches = re.findall(r'''(?x)
1450 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1454 return _playlist_from_matches(
1455 matches, lambda m: unescapeHTML(m[1]))
1457 # Look for lazyYT YouTube embed
1458 matches = re.findall(
1459 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1461 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1463 # Look for embedded Dailymotion player
1464 matches = re.findall(
1465 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1467 return _playlist_from_matches(
1468 matches, lambda m: unescapeHTML(m[1]))
1470 # Look for embedded Dailymotion playlist player (#3822)
1472 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1474 playlists = re.findall(
1475 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1477 return _playlist_from_matches(
1478 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1480 # Look for embedded Wistia player
1482 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1484 embed_url = self._proto_relative_url(
1485 unescapeHTML(match.group('url')))
1487 '_type': 'url_transparent',
1490 'uploader': video_uploader,
1491 'title': video_title,
1495 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1498 '_type': 'url_transparent',
1499 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1501 'uploader': video_uploader,
1502 'title': video_title,
1503 'id': match.group('id')
1506 # Look for SVT player
1507 svt_url = SVTIE._extract_url(webpage)
1509 return self.url_result(svt_url, 'SVT')
1511 # Look for embedded condenast player
1512 matches = re.findall(
1513 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1517 '_type': 'playlist',
1520 'ie_key': 'CondeNast',
1522 } for ma in matches],
1523 'title': video_title,
1527 # Look for Bandcamp pages with custom domain
1528 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1529 if mobj is not None:
1530 burl = unescapeHTML(mobj.group(1))
1531 # Don't set the extractor because it can be a track url or an album
1532 return self.url_result(burl)
1534 # Look for embedded Vevo player
1536 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1537 if mobj is not None:
1538 return self.url_result(mobj.group('url'))
1540 # Look for embedded Viddler player
1542 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1544 if mobj is not None:
1545 return self.url_result(mobj.group('url'))
1547 # Look for NYTimes player
1549 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1551 if mobj is not None:
1552 return self.url_result(mobj.group('url'))
1554 # Look for Libsyn player
1556 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1557 if mobj is not None:
1558 return self.url_result(mobj.group('url'))
1560 # Look for Ooyala videos
1561 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1562 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1563 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1564 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1565 if mobj is not None:
1566 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1568 # Look for multiple Ooyala embeds on SBN network websites
1569 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1570 if mobj is not None:
1571 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1573 return _playlist_from_matches(
1574 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1576 # Look for Aparat videos
1577 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1578 if mobj is not None:
1579 return self.url_result(mobj.group(1), 'Aparat')
1581 # Look for MPORA videos
1582 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1583 if mobj is not None:
1584 return self.url_result(mobj.group(1), 'Mpora')
1586 # Look for embedded NovaMov-based player
1588 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1589 (?P<url>http://(?:(?:embed|www)\.)?
1591 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1592 videoweed\.(?:es|com)|
1593 movshare\.(?:net|sx|ag)|
1594 divxstage\.(?:eu|net|ch|co|at|ag))
1595 /embed\.php.+?)\1''', webpage)
1596 if mobj is not None:
1597 return self.url_result(mobj.group('url'))
1599 # Look for embedded Facebook player
1601 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1602 if mobj is not None:
1603 return self.url_result(mobj.group('url'), 'Facebook')
1605 # Look for embedded VK player
1606 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1607 if mobj is not None:
1608 return self.url_result(mobj.group('url'), 'VK')
1610 # Look for embedded Odnoklassniki player
1611 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1612 if mobj is not None:
1613 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1615 # Look for embedded ivi player
1616 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1617 if mobj is not None:
1618 return self.url_result(mobj.group('url'), 'Ivi')
1620 # Look for embedded Huffington Post player
1622 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1623 if mobj is not None:
1624 return self.url_result(mobj.group('url'), 'HuffPost')
1627 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1628 if mobj is not None:
1629 return self.url_result(mobj.group('url'))
1630 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1631 if mobj is not None:
1632 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1634 # Look for funnyordie embed
1635 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1637 return _playlist_from_matches(
1638 matches, getter=unescapeHTML, ie='FunnyOrDie')
1640 # Look for BBC iPlayer embed
1641 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1643 return _playlist_from_matches(matches, ie='BBCCoUk')
1645 # Look for embedded RUTV player
1646 rutv_url = RUTVIE._extract_url(webpage)
1648 return self.url_result(rutv_url, 'RUTV')
1650 # Look for embedded TVC player
1651 tvc_url = TVCIE._extract_url(webpage)
1653 return self.url_result(tvc_url, 'TVC')
1655 # Look for embedded SportBox player
1656 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1658 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1660 # Look for embedded PornHub player
1661 pornhub_url = PornHubIE._extract_url(webpage)
1663 return self.url_result(pornhub_url, 'PornHub')
1665 # Look for embedded XHamster player
1666 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1668 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1670 # Look for embedded TNAFlixNetwork player
1671 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1673 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1675 # Look for embedded Tvigle player
1677 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1678 if mobj is not None:
1679 return self.url_result(mobj.group('url'), 'Tvigle')
1681 # Look for embedded TED player
1683 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1684 if mobj is not None:
1685 return self.url_result(mobj.group('url'), 'TED')
1687 # Look for embedded Ustream videos
1689 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1690 if mobj is not None:
1691 return self.url_result(mobj.group('url'), 'Ustream')
1693 # Look for embedded arte.tv player
1695 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1700 # Look for embedded francetv player
1702 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1704 if mobj is not None:
1705 return self.url_result(mobj.group('url'))
1707 # Look for embedded smotri.com player
1708 smotri_url = SmotriIE._extract_url(webpage)
1710 return self.url_result(smotri_url, 'Smotri')
1712 # Look for embedded Myvi.ru player
1713 myvi_url = MyviIE._extract_url(webpage)
1715 return self.url_result(myvi_url)
1717 # Look for embedded soundcloud player
1719 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1721 if mobj is not None:
1722 url = unescapeHTML(mobj.group('url'))
1723 return self.url_result(url)
1725 # Look for embedded vulture.com player
1727 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1729 if mobj is not None:
1730 url = unescapeHTML(mobj.group('url'))
1731 return self.url_result(url, ie='Vulture')
1733 # Look for embedded mtvservices player
1734 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1736 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1738 # Look for embedded yahoo player
1740 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1742 if mobj is not None:
1743 return self.url_result(mobj.group('url'), 'Yahoo')
1745 # Look for embedded sbs.com.au player
1749 <meta\s+property="og:video"\s+content=|
1752 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1754 if mobj is not None:
1755 return self.url_result(mobj.group('url'), 'SBS')
1757 # Look for embedded Cinchcast player
1759 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1761 if mobj is not None:
1762 return self.url_result(mobj.group('url'), 'Cinchcast')
1765 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1769 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1771 if mobj is not None:
1772 return self.url_result(mobj.group('url'), 'MLB')
1775 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1777 if mobj is not None:
1778 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1781 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1783 if mobj is not None:
1784 return self.url_result(mobj.group('url'), 'Livestream')
1786 # Look for Zapiks embed
1788 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1789 if mobj is not None:
1790 return self.url_result(mobj.group('url'), 'Zapiks')
1792 # Look for Kaltura embeds
1793 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1794 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))
1795 if mobj is not None:
1796 return self.url_result(smuggle_url(
1797 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1798 {'source_url': url}), 'Kaltura')
1800 # Look for Eagle.Platform embeds
1802 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1803 if mobj is not None:
1804 return self.url_result(mobj.group('url'), 'EaglePlatform')
1806 # Look for ClipYou (uses Eagle.Platform) embeds
1808 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1809 if mobj is not None:
1810 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1812 # Look for Pladform embeds
1813 pladform_url = PladformIE._extract_url(webpage)
1815 return self.url_result(pladform_url)
1817 # Look for Videomore embeds
1818 videomore_url = VideomoreIE._extract_url(webpage)
1820 return self.url_result(videomore_url)
1822 # Look for Playwire embeds
1824 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1825 if mobj is not None:
1826 return self.url_result(mobj.group('url'))
1828 # Look for 5min embeds
1830 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1831 if mobj is not None:
1832 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1834 # Look for Crooks and Liars embeds
1836 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1837 if mobj is not None:
1838 return self.url_result(mobj.group('url'))
1840 # Look for NBC Sports VPlayer embeds
1841 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1843 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1845 # Look for Google Drive embeds
1846 google_drive_url = GoogleDriveIE._extract_url(webpage)
1847 if google_drive_url:
1848 return self.url_result(google_drive_url, 'GoogleDrive')
1850 # Look for UDN embeds
1852 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1853 if mobj is not None:
1854 return self.url_result(
1855 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1857 # Look for Senate ISVP iframe
1858 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1860 return self.url_result(senate_isvp_url, 'SenateISVP')
1862 # Look for Dailymotion Cloud videos
1863 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1865 return self.url_result(dmcloud_url, 'DailymotionCloud')
1867 # Look for OnionStudios embeds
1868 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1869 if onionstudios_url:
1870 return self.url_result(onionstudios_url)
1872 # Look for SnagFilms embeds
1873 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1875 return self.url_result(snagfilms_url)
1877 # Look for JWPlatform embeds
1878 jwplatform_url = JWPlatformIE._extract_url(webpage)
1880 return self.url_result(jwplatform_url, 'JWPlatform')
1882 # Look for ScreenwaveMedia embeds
1883 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1884 if mobj is not None:
1885 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1887 # Look for Digiteka embeds
1888 digiteka_url = DigitekaIE._extract_url(webpage)
1890 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1892 # Look for Limelight embeds
1893 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1897 'Channel': 'channel',
1898 'ChannelList': 'channel_list',
1900 return self.url_result('limelight:%s:%s' % (
1901 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1903 # Look for AdobeTVVideo embeds
1905 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1907 if mobj is not None:
1908 return self.url_result(
1909 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1912 # Look for Vine embeds
1914 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1916 if mobj is not None:
1917 return self.url_result(
1918 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1920 def check_video(vurl):
1921 if YoutubeIE.suitable(vurl):
1923 vpath = compat_urlparse.urlparse(vurl).path
1924 vext = determine_ext(vpath)
1925 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1927 def filter_video(urls):
1928 return list(filter(check_video, urls))
1930 # Start with something easy: JW Player in SWFObject
1931 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1933 # Look for gorilla-vid style embedding
1934 found = filter_video(re.findall(r'''(?sx)
1938 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1941 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1943 # Broaden the search a little bit
1944 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1946 # Broaden the findall a little bit: JWPlayer JS loader
1947 found = filter_video(re.findall(
1948 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1951 found = filter_video(re.findall(r'''(?xs)
1952 flowplayer\("[^"]+",\s*
1954 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1955 ["']?url["']?\s*:\s*["']([^"']+)["']
1960 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1962 # Try to find twitter cards info
1963 found = filter_video(re.findall(
1964 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1966 # We look for Open Graph info:
1967 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1968 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1969 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1970 if m_video_type is not None:
1971 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1974 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1976 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1978 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1979 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1982 # Look also in Refresh HTTP header
1983 refresh_header = head_response.headers.get('Refresh')
1985 # In python 2 response HTTP headers are bytestrings
1986 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1987 refresh_header = refresh_header.decode('iso-8859-1')
1988 found = re.search(REDIRECT_REGEX, refresh_header)
1990 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1991 self.report_following_redirect(new_url)
1997 raise UnsupportedError(url)
2000 for video_url in found:
2001 video_url = video_url.replace('\\/', '/')
2002 video_url = compat_urlparse.urljoin(url, video_url)
2003 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2005 # Sometimes, jwplayer extraction will result in a YouTube URL
2006 if YoutubeIE.suitable(video_url):
2007 entries.append(self.url_result(video_url, 'Youtube'))
2010 # here's a fun little line of code for you:
2011 video_id = os.path.splitext(video_id)[0]
2015 'uploader': video_uploader,
2016 'title': video_title,
2017 'age_limit': age_limit,
2020 ext = determine_ext(video_url)
2022 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2024 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2026 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2028 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2030 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2032 entry_info_dict['url'] = video_url
2034 entries.append(entry_info_dict)
2036 if len(entries) == 1:
2039 for num, e in enumerate(entries, start=1):
2040 # 'url' results don't have a title
2041 if e.get('title') is not None:
2042 e['title'] = '%s (%d)' % (e['title'], num)
2044 '_type': 'playlist',