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',
244 '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',
248 'upload_date': '20130224',
249 'uploader_id': 'TheVerge',
250 'description': 're:^Chris Ziegler takes a look at the\.*',
251 'uploader': 'The Verge',
252 'title': 'First Firefox OS phones side-by-side',
255 'skip_download': False,
259 # redirect in Refresh HTTP header
260 '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',
264 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
265 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
266 'upload_date': '20150917',
267 'uploader_id': 'brtvofficial',
268 'uploader': 'Boiler Room',
271 'skip_download': False,
275 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
276 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
278 'id': '13601338388002',
280 'uploader': 'www.hodiho.fr',
281 'title': 'R\u00e9gis plante sa Jeep',
284 # bandcamp page with custom domain
286 'add_ie': ['Bandcamp'],
287 'url': 'http://bronyrock.com/track/the-pony-mash',
291 'title': 'The Pony Mash',
292 'uploader': 'M_Pallante',
294 'skip': 'There is a limit of 200 free downloads / month for the test song',
296 # embedded brightcove video
297 # it also tests brightcove videos that need to set the 'Referer' in the
300 'add_ie': ['BrightcoveLegacy'],
301 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
303 'id': '2765128793001',
305 'title': 'Le cours de bourse : l’analyse technique',
306 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
307 'uploader': 'BFM BUSINESS',
310 'skip_download': True,
314 # https://github.com/rg3/youtube-dl/issues/2253
315 'url': 'http://bcove.me/i6nfkrc3',
316 'md5': '0ba9446db037002366bab3b3eb30c88c',
318 'id': '3101154703001',
320 'title': 'Still no power',
321 'uploader': 'thestar.com',
322 '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.',
324 'add_ie': ['BrightcoveLegacy'],
327 'url': 'http://www.championat.com/video/football/v/87/87499.html',
328 'md5': 'fb973ecf6e4a78a67453647444222983',
330 'id': '3414141473001',
332 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
333 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
334 'uploader': 'Championat',
338 # https://github.com/rg3/youtube-dl/issues/3541
339 'add_ie': ['BrightcoveLegacy'],
340 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
342 'id': '3866516442001',
344 'title': 'Leer mij vrouwen kennen: Aflevering 1',
345 'description': 'Leer mij vrouwen kennen: Aflevering 1',
346 'uploader': 'SBS Broadcasting',
348 'skip': 'Restricted to Netherlands',
350 'skip_download': True, # m3u8 download
355 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
356 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
358 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
360 'title': '2cc213299525360.mov', # that's what we get
363 'add_ie': ['Ooyala'],
366 # ooyala video embedded with http://player.ooyala.com/iframe.js
367 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
369 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
371 'title': '"Steve Jobs: Man in the Machine" trailer',
372 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
376 'skip_download': True,
379 # multiple ooyala embeds on SBN network websites
381 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
383 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
384 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
386 'playlist_mincount': 3,
388 'skip_download': True,
390 'add_ie': ['Ooyala'],
394 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
398 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
399 'upload_date': '20140225',
400 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
401 'uploader': 'Tested',
402 'uploader_id': 'testedcom',
404 # No need to test YoutubeIE here
406 'skip_download': True,
411 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
415 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
416 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
421 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
425 'title': 'Охотское море стало целиком российским',
426 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
430 'skip_download': True,
435 '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/',
439 'title': 'Дошкольное воспитание',
444 'url': 'http://www.vestifinance.ru/articles/25753',
447 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
452 'title': 'Госзаказ. День 3',
458 'title': 'Госзаказ. День 2',
464 'title': 'Госзаказ. День 1',
470 'skip_download': True,
475 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
477 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
479 'title': 'Ужастики, русский трейлер (2015)',
480 'thumbnail': 're:^https?://.*\.jpg$',
486 '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',
489 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
491 'playlist_mincount': 7,
495 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
496 'md5': '65fdff94098e4a607385a60c5177c638',
500 'title': 'Hidden miracles of the natural world',
501 'uploader': 'Louie Schwartzberg',
502 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
505 # Embedded Ustream video
507 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
508 'md5': '27b99cdb639c9b12a79bca876a073417',
512 'uploader': 'AU SPA: The NSA and Privacy',
513 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
516 # nowvideo embed hidden behind percent encoding
518 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
519 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
521 'id': '06e53103ca9aa',
523 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
524 'description': 'No description',
529 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
530 'md5': '7653032cbb25bf6c80d80f217055fa43',
532 'id': '048195-004_PLUS7-F',
535 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
536 'upload_date': '20140320',
539 'skip_download': 'Requires rtmpdump'
544 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
548 'title': 'Alcaline, le concert avec Calogero',
549 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
550 'upload_date': '20150226',
551 'timestamp': 1424989860,
556 'skip_download': True,
558 'expected_warnings': [
564 'url': 'http://www.wired.com/2014/04/honda-asimo/',
565 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
567 'id': '53501be369702d3275860000',
569 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
574 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
575 'md5': '441aeeb82eb72c422c7f14ec533999cd',
577 'id': 'k2mm4bCdJ6CQ2i7c8o2',
579 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
582 'add_ie': ['Dailymotion'],
586 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
590 'title': 'The NBL Auction 2014',
591 'uploader': 'BADMINTON England',
592 'uploader_id': 'BADMINTONEvents',
593 'upload_date': '20140603',
594 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
596 'add_ie': ['Youtube'],
598 'skip_download': True,
603 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
604 'md5': '35727f82f58c76d996fc188f9755b0d5',
606 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
609 'description': 'Mario\'s life in the fast lane has never looked so good.',
612 # YouTube embed via <data-embed-url="">
614 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
618 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
619 'uploader': 'Gameloft',
620 'uploader_id': 'gameloft',
621 'upload_date': '20140828',
622 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
625 'skip_download': True,
630 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
632 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
634 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
635 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
640 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
642 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
643 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
649 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
654 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
655 'md5': '9d65602bf31c6e20014319c7d07fba27',
657 'id': '5123ea6d5e5a7',
660 'uploader': 'www.handjobhub.com',
661 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
664 # Multiple brightcove videos
665 # https://github.com/rg3/youtube-dl/issues/2283
667 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
669 'id': 'always-never',
670 'title': 'Always / Never - The New Yorker',
674 'extract_flat': False,
675 'skip_download': True,
680 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
681 'md5': '96f09a37e44da40dd083e12d9a683327',
685 'title': 'Ump changes call to ball',
686 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
688 'timestamp': 1401537900,
689 'upload_date': '20140531',
690 'thumbnail': 're:^https?://.*\.jpg$',
695 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
696 'md5': '8788b683c777a5cf25621eaf286d0c23',
700 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
702 'filesize': 182808282,
703 'uploader': 'education-portal.com',
707 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
708 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
712 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
714 'uploader': 'thoughtworks.wistia.com',
719 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
723 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
724 'uploader': 'Sophos Security',
725 'title': 'Chet Chat 171 - Oct 29, 2014',
726 'upload_date': '20141029',
731 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
735 'upload_date': '20141112',
736 'title': 'Rosetta #CometLanding webcast HL 10',
741 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
744 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
746 'playlist_mincount': 2,
750 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
754 'upload_date': '20141126',
755 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
760 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
762 'id': '730m_DandD_1901_512k',
764 'uploader': 'www.abc.net.au',
765 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
768 # embedded viddler video
770 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
774 'uploader': 'deadspin',
775 'title': 'WALL-TO-GORTAT',
776 'timestamp': 1422285291,
777 'upload_date': '20150126',
779 'add_ie': ['Viddler'],
783 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
787 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
788 'description': 'md5:601cb790edd05908957dae8aaa866465',
789 'upload_date': '20150220',
794 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
798 'upload_date': '20150212',
799 'uploader': 'The National Archives UK',
800 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
801 'uploader_id': 'NationalArchives08',
802 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
807 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
808 'playlist_mincount': 5,
810 'id': 'aanslagen-kopenhagen',
811 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
816 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
820 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
825 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
829 'upload_date': '20150226',
830 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
832 'title': 'John Carlson Postgame 2/25/15',
835 # Kaltura embed (different embed code)
837 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
841 'upload_date': '20150127',
842 'uploader_id': 'PremierMedia',
844 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
847 # Kaltura embed protected with referrer
849 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
853 'title': 'Violetta - Achter De Schermen - Ruggero',
854 'description': 'Achter de schermen met Ruggero',
855 'timestamp': 1435133761,
856 'upload_date': '20150624',
857 'uploader_id': 'echojecka',
860 # Eagle.Platform embed (generic URL)
862 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
866 'title': 'Навальный вышел на свободу',
867 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
868 'thumbnail': 're:^https?://.*\.jpg$',
874 # ClipYou (Eagle.Platform) embed (custom URL)
876 'url': 'http://muz-tv.ru/play/7129/',
880 'title': "'O Sole Mio",
881 'thumbnail': 're:^https?://.*\.jpg$',
888 'url': 'http://muz-tv.ru/kinozal/view/7400/',
892 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
893 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
894 'thumbnail': 're:^https?://.*\.jpg$',
901 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
905 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
906 'thumbnail': 're:^https?://.*\.png$',
912 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
913 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
917 'title': 'Facebook Creates "On This Day" | Crunch Report',
922 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
926 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
931 # Crooks and Liars embed
933 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
937 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
938 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
939 'timestamp': 1428207000,
940 'upload_date': '20150405',
941 'uploader': 'Heather',
944 # Crooks and Liars external embed
946 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
948 'id': 'MTE3MjUtMzQ2MzA',
950 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
951 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
952 'timestamp': 1265032391,
953 'upload_date': '20100201',
954 'uploader': 'Heather',
957 # NBC Sports vplayer embed
959 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
961 'id': 'ln7x1qSThw4k',
963 'title': "PFT Live: New leader in the 'new-look' defense",
964 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
969 'url': 'http://www.udn.com/news/story/7314/822787',
970 'md5': 'fd2060e988c326991037b9aff9df21a6',
974 'title': '中一中男師變性 全校師生力挺',
975 'thumbnail': 're:^https?://.*\.jpg$',
980 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
982 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
984 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
985 'title': 'This is what separates the Excel masters from the wannabes',
990 'skip_download': True,
993 # Contains a SMIL manifest
995 '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',
999 'title': '+ Football: Lottery Champions League Europe',
1000 'uploader': 'www.telewebion.com',
1004 'skip_download': True,
1007 # Brightcove URL in single quotes
1009 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1010 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1012 'id': '4255764656001',
1014 'title': 'SN Presents: Russell Martin, World Citizen',
1015 '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.',
1016 'uploader': 'Rogers Sportsnet',
1019 # Dailymotion Cloud video
1021 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1022 'md5': '49444254273501a64675a7e68c502681',
1024 'id': '5585de919473990de4bee11b',
1026 'title': 'Le débat',
1027 'thumbnail': 're:^https?://.*\.jpe?g$',
1030 # OnionStudios embed
1032 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1036 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1037 'thumbnail': 're:^https?://.*\.jpe?g$',
1038 'uploader': 'ClickHole',
1039 'uploader_id': 'clickhole',
1044 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1046 'id': '74849a00-85a9-11e1-9660-123139220831',
1048 'title': '#whilewewatch',
1051 # AdobeTVVideo embed
1053 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1054 'md5': '43662b577c018ad707a63766462b1e87',
1058 'title': 'New experience with Acrobat DC',
1059 'description': 'New experience with Acrobat DC',
1060 'duration': 248.667,
1063 # ScreenwaveMedia embed
1065 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1066 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1068 'id': 'cinemasnob-55d26273809dd',
1070 'title': 'cinemasnob',
1073 # BrightcoveInPageEmbed embed
1075 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1077 'id': '4238694884001',
1079 'title': 'Tabletop: Dread, Last Thoughts',
1080 'description': 'Tabletop: Dread, Last Thoughts',
1084 # JWPlayer with M3U8
1086 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1090 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1091 'uploader': 'ren.tv',
1095 'skip_download': True,
1100 def report_following_redirect(self, new_url):
1101 """Report information extraction."""
1102 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1104 def _extract_rss(self, url, video_id, doc):
1105 playlist_title = doc.find('./channel/title').text
1106 playlist_desc_el = doc.find('./channel/description')
1107 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1110 for it in doc.findall('./channel/item'):
1111 next_url = xpath_text(it, 'link', fatal=False)
1113 enclosure_nodes = it.findall('./enclosure')
1114 for e in enclosure_nodes:
1115 next_url = e.attrib.get('url')
1125 'title': it.find('title').text,
1129 '_type': 'playlist',
1131 'title': playlist_title,
1132 'description': playlist_desc,
1136 def _extract_camtasia(self, url, video_id, webpage):
1137 """ Returns None if no camtasia video can be found. """
1139 camtasia_cfg = self._search_regex(
1140 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1141 webpage, 'camtasia configuration file', default=None)
1142 if camtasia_cfg is None:
1145 title = self._html_search_meta('DC.title', webpage, fatal=True)
1147 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1148 camtasia_cfg = self._download_xml(
1149 camtasia_url, video_id,
1150 note='Downloading camtasia configuration',
1151 errnote='Failed to download camtasia configuration')
1152 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1155 for n in fileset_node.getchildren():
1156 url_n = n.find('./uri')
1161 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1162 'title': '%s - %s' % (title, n.tag),
1163 'url': compat_urlparse.urljoin(url, url_n.text),
1164 'duration': float_or_none(n.find('./duration').text),
1168 '_type': 'playlist',
1173 def _real_extract(self, url):
1174 if url.startswith('//'):
1177 'url': self.http_scheme() + url,
1180 parsed_url = compat_urlparse.urlparse(url)
1181 if not parsed_url.scheme:
1182 default_search = self._downloader.params.get('default_search')
1183 if default_search is None:
1184 default_search = 'fixup_error'
1186 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1188 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1189 return self.url_result('http://' + url)
1190 elif default_search != 'fixup_error':
1191 if default_search == 'auto_warning':
1192 if re.match(r'^(?:url|URL)$', url):
1193 raise ExtractorError(
1194 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1197 self._downloader.report_warning(
1198 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1199 return self.url_result('ytsearch:' + url)
1201 if default_search in ('error', 'fixup_error'):
1202 raise ExtractorError(
1203 '%r is not a valid URL. '
1204 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1205 % (url, url), expected=True)
1207 if ':' not in default_search:
1208 default_search += ':'
1209 return self.url_result(default_search + url)
1211 url, smuggled_data = unsmuggle_url(url)
1212 force_videoid = None
1213 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1214 if smuggled_data and 'force_videoid' in smuggled_data:
1215 force_videoid = smuggled_data['force_videoid']
1216 video_id = force_videoid
1218 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1220 self.to_screen('%s: Requesting header' % video_id)
1222 head_req = HEADRequest(url)
1223 head_response = self._request_webpage(
1225 note=False, errnote='Could not send HEAD request to %s' % url,
1228 if head_response is not False:
1229 # Check for redirect
1230 new_url = head_response.geturl()
1232 self.report_following_redirect(new_url)
1234 new_url = smuggle_url(
1235 new_url, {'force_videoid': force_videoid})
1236 return self.url_result(new_url)
1238 full_response = None
1239 if head_response is False:
1240 request = sanitized_Request(url)
1241 request.add_header('Accept-Encoding', '*')
1242 full_response = self._request_webpage(request, video_id)
1243 head_response = full_response
1245 # Check for direct link to a video
1246 content_type = head_response.headers.get('Content-Type', '')
1247 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
1249 upload_date = unified_strdate(
1250 head_response.headers.get('Last-Modified'))
1252 if m.group('format_id').endswith('mpegurl'):
1253 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1256 'format_id': m.group('format_id'),
1258 'vcodec': 'none' if m.group('type') == 'audio' else None
1262 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1265 'upload_date': upload_date,
1268 if not self._downloader.params.get('test', False) and not is_intentional:
1269 force = self._downloader.params.get('force_generic_extractor', False)
1270 self._downloader.report_warning(
1271 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1273 if not full_response:
1274 request = sanitized_Request(url)
1275 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1276 # making it impossible to download only chunk of the file (yet we need only 512kB to
1277 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1278 # that will always result in downloading the whole file that is not desirable.
1279 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1280 # to accept raw bytes and being able to download only a chunk.
1281 # It may probably better to solve this by checking Content-Type for application/octet-stream
1282 # after HEAD request finishes, but not sure if we can rely on this.
1283 request.add_header('Accept-Encoding', '*')
1284 full_response = self._request_webpage(request, video_id)
1286 # Maybe it's a direct link to a video?
1287 # Be careful not to download the whole thing!
1288 first_bytes = full_response.read(512)
1289 if not is_html(first_bytes):
1290 self._downloader.report_warning(
1291 'URL could be a direct video link, returning it as such.')
1292 upload_date = unified_strdate(
1293 head_response.headers.get('Last-Modified'))
1296 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1299 'upload_date': upload_date,
1302 webpage = self._webpage_read_content(
1303 full_response, url, video_id, prefix=first_bytes)
1305 self.report_extraction(video_id)
1307 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1309 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1310 if doc.tag == 'rss':
1311 return self._extract_rss(url, video_id, doc)
1312 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1313 return self._parse_smil(doc, url, video_id)
1314 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1315 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1316 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1319 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1320 'formats': self._parse_mpd_formats(
1321 doc, video_id, mpd_base_url=url.rpartition('/')[0]),
1323 except compat_xml_parse_error:
1326 # Is it a Camtasia project?
1327 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1328 if camtasia_res is not None:
1331 # Sometimes embedded video player is hidden behind percent encoding
1332 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1333 # Unescaping the whole page allows to handle those cases in a generic way
1334 webpage = compat_urllib_parse_unquote(webpage)
1336 # it's tempting to parse this further, but you would
1337 # have to take into account all the variations like
1338 # Video Title - Site Name
1339 # Site Name | Video Title
1340 # Video Title - Tagline | Site Name
1341 # and so on and so forth; it's just not practical
1342 video_title = self._html_search_regex(
1343 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1346 # Try to detect age limit automatically
1347 age_limit = self._rta_search(webpage)
1348 # And then there are the jokers who advertise that they use RTA,
1349 # but actually don't.
1350 AGE_LIMIT_MARKERS = [
1351 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1353 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1356 # video uploader is domain name
1357 video_uploader = self._search_regex(
1358 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1361 def _playlist_from_matches(matches, getter=None, ie=None):
1363 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1365 return self.playlist_result(
1366 urlrs, playlist_id=video_id, playlist_title=video_title)
1368 # Look for Brightcove Legacy Studio embeds
1369 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1371 self.to_screen('Brightcove video detected.')
1374 'url': smuggle_url(bc_url, {'Referer': url}),
1375 'ie_key': 'BrightcoveLegacy'
1376 } for bc_url in bc_urls]
1379 '_type': 'playlist',
1380 'title': video_title,
1385 # Look for Brightcove New Studio embeds
1386 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1388 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1390 # Look for embedded rtl.nl player
1391 matches = re.findall(
1392 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1395 return _playlist_from_matches(matches, ie='RtlNl')
1397 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1398 if vimeo_url is not None:
1399 return self.url_result(vimeo_url)
1401 vid_me_embed_url = self._search_regex(
1402 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1403 webpage, 'vid.me embed', default=None)
1404 if vid_me_embed_url is not None:
1405 return self.url_result(vid_me_embed_url, 'Vidme')
1407 # Look for embedded YouTube player
1408 matches = re.findall(r'''(?x)
1417 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1421 return _playlist_from_matches(
1422 matches, lambda m: unescapeHTML(m[1]))
1424 # Look for lazyYT YouTube embed
1425 matches = re.findall(
1426 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1428 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1430 # Look for embedded Dailymotion player
1431 matches = re.findall(
1432 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1434 return _playlist_from_matches(
1435 matches, lambda m: unescapeHTML(m[1]))
1437 # Look for embedded Dailymotion playlist player (#3822)
1439 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1441 playlists = re.findall(
1442 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1444 return _playlist_from_matches(
1445 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1447 # Look for embedded Wistia player
1449 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1451 embed_url = self._proto_relative_url(
1452 unescapeHTML(match.group('url')))
1454 '_type': 'url_transparent',
1457 'uploader': video_uploader,
1458 'title': video_title,
1462 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1465 '_type': 'url_transparent',
1466 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1468 'uploader': video_uploader,
1469 'title': video_title,
1470 'id': match.group('id')
1473 # Look for SVT player
1474 svt_url = SVTIE._extract_url(webpage)
1476 return self.url_result(svt_url, 'SVT')
1478 # Look for embedded condenast player
1479 matches = re.findall(
1480 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1484 '_type': 'playlist',
1487 'ie_key': 'CondeNast',
1489 } for ma in matches],
1490 'title': video_title,
1494 # Look for Bandcamp pages with custom domain
1495 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1496 if mobj is not None:
1497 burl = unescapeHTML(mobj.group(1))
1498 # Don't set the extractor because it can be a track url or an album
1499 return self.url_result(burl)
1501 # Look for embedded Vevo player
1503 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1504 if mobj is not None:
1505 return self.url_result(mobj.group('url'))
1507 # Look for embedded Viddler player
1509 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1511 if mobj is not None:
1512 return self.url_result(mobj.group('url'))
1514 # Look for NYTimes player
1516 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1518 if mobj is not None:
1519 return self.url_result(mobj.group('url'))
1521 # Look for Libsyn player
1523 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1524 if mobj is not None:
1525 return self.url_result(mobj.group('url'))
1527 # Look for Ooyala videos
1528 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1529 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1530 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1531 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1532 if mobj is not None:
1533 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1535 # Look for multiple Ooyala embeds on SBN network websites
1536 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1537 if mobj is not None:
1538 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1540 return _playlist_from_matches(
1541 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1543 # Look for Aparat videos
1544 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1545 if mobj is not None:
1546 return self.url_result(mobj.group(1), 'Aparat')
1548 # Look for MPORA videos
1549 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1550 if mobj is not None:
1551 return self.url_result(mobj.group(1), 'Mpora')
1553 # Look for embedded NovaMov-based player
1555 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1556 (?P<url>http://(?:(?:embed|www)\.)?
1558 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1559 videoweed\.(?:es|com)|
1560 movshare\.(?:net|sx|ag)|
1561 divxstage\.(?:eu|net|ch|co|at|ag))
1562 /embed\.php.+?)\1''', webpage)
1563 if mobj is not None:
1564 return self.url_result(mobj.group('url'))
1566 # Look for embedded Facebook player
1568 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1569 if mobj is not None:
1570 return self.url_result(mobj.group('url'), 'Facebook')
1572 # Look for embedded VK player
1573 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1574 if mobj is not None:
1575 return self.url_result(mobj.group('url'), 'VK')
1577 # Look for embedded Odnoklassniki player
1578 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1579 if mobj is not None:
1580 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1582 # Look for embedded ivi player
1583 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1584 if mobj is not None:
1585 return self.url_result(mobj.group('url'), 'Ivi')
1587 # Look for embedded Huffington Post player
1589 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1590 if mobj is not None:
1591 return self.url_result(mobj.group('url'), 'HuffPost')
1594 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1595 if mobj is not None:
1596 return self.url_result(mobj.group('url'))
1597 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1598 if mobj is not None:
1599 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1601 # Look for funnyordie embed
1602 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1604 return _playlist_from_matches(
1605 matches, getter=unescapeHTML, ie='FunnyOrDie')
1607 # Look for BBC iPlayer embed
1608 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1610 return _playlist_from_matches(matches, ie='BBCCoUk')
1612 # Look for embedded RUTV player
1613 rutv_url = RUTVIE._extract_url(webpage)
1615 return self.url_result(rutv_url, 'RUTV')
1617 # Look for embedded TVC player
1618 tvc_url = TVCIE._extract_url(webpage)
1620 return self.url_result(tvc_url, 'TVC')
1622 # Look for embedded SportBox player
1623 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1625 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1627 # Look for embedded PornHub player
1628 pornhub_url = PornHubIE._extract_url(webpage)
1630 return self.url_result(pornhub_url, 'PornHub')
1632 # Look for embedded XHamster player
1633 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1635 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1637 # Look for embedded TNAFlixNetwork player
1638 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1640 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1642 # Look for embedded Tvigle player
1644 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1645 if mobj is not None:
1646 return self.url_result(mobj.group('url'), 'Tvigle')
1648 # Look for embedded TED player
1650 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1651 if mobj is not None:
1652 return self.url_result(mobj.group('url'), 'TED')
1654 # Look for embedded Ustream videos
1656 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1657 if mobj is not None:
1658 return self.url_result(mobj.group('url'), 'Ustream')
1660 # Look for embedded arte.tv player
1662 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1664 if mobj is not None:
1665 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1667 # Look for embedded francetv player
1669 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1671 if mobj is not None:
1672 return self.url_result(mobj.group('url'))
1674 # Look for embedded smotri.com player
1675 smotri_url = SmotriIE._extract_url(webpage)
1677 return self.url_result(smotri_url, 'Smotri')
1679 # Look for embedded Myvi.ru player
1680 myvi_url = MyviIE._extract_url(webpage)
1682 return self.url_result(myvi_url)
1684 # Look for embedded soundcloud player
1686 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1688 if mobj is not None:
1689 url = unescapeHTML(mobj.group('url'))
1690 return self.url_result(url)
1692 # Look for embedded vulture.com player
1694 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1696 if mobj is not None:
1697 url = unescapeHTML(mobj.group('url'))
1698 return self.url_result(url, ie='Vulture')
1700 # Look for embedded mtvservices player
1701 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1703 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1705 # Look for embedded yahoo player
1707 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1709 if mobj is not None:
1710 return self.url_result(mobj.group('url'), 'Yahoo')
1712 # Look for embedded sbs.com.au player
1716 <meta\s+property="og:video"\s+content=|
1719 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1721 if mobj is not None:
1722 return self.url_result(mobj.group('url'), 'SBS')
1724 # Look for embedded Cinchcast player
1726 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1728 if mobj is not None:
1729 return self.url_result(mobj.group('url'), 'Cinchcast')
1732 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1736 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1738 if mobj is not None:
1739 return self.url_result(mobj.group('url'), 'MLB')
1742 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1744 if mobj is not None:
1745 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1748 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1750 if mobj is not None:
1751 return self.url_result(mobj.group('url'), 'Livestream')
1753 # Look for Zapiks embed
1755 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1756 if mobj is not None:
1757 return self.url_result(mobj.group('url'), 'Zapiks')
1759 # Look for Kaltura embeds
1760 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1761 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))
1762 if mobj is not None:
1763 return self.url_result(smuggle_url(
1764 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1765 {'source_url': url}), 'Kaltura')
1767 # Look for Eagle.Platform embeds
1769 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1770 if mobj is not None:
1771 return self.url_result(mobj.group('url'), 'EaglePlatform')
1773 # Look for ClipYou (uses Eagle.Platform) embeds
1775 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1776 if mobj is not None:
1777 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1779 # Look for Pladform embeds
1780 pladform_url = PladformIE._extract_url(webpage)
1782 return self.url_result(pladform_url)
1784 # Look for Videomore embeds
1785 videomore_url = VideomoreIE._extract_url(webpage)
1787 return self.url_result(videomore_url)
1789 # Look for Playwire embeds
1791 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1792 if mobj is not None:
1793 return self.url_result(mobj.group('url'))
1795 # Look for 5min embeds
1797 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1798 if mobj is not None:
1799 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1801 # Look for Crooks and Liars embeds
1803 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1804 if mobj is not None:
1805 return self.url_result(mobj.group('url'))
1807 # Look for NBC Sports VPlayer embeds
1808 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1810 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1812 # Look for Google Drive embeds
1813 google_drive_url = GoogleDriveIE._extract_url(webpage)
1814 if google_drive_url:
1815 return self.url_result(google_drive_url, 'GoogleDrive')
1817 # Look for UDN embeds
1819 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1820 if mobj is not None:
1821 return self.url_result(
1822 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1824 # Look for Senate ISVP iframe
1825 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1827 return self.url_result(senate_isvp_url, 'SenateISVP')
1829 # Look for Dailymotion Cloud videos
1830 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1832 return self.url_result(dmcloud_url, 'DailymotionCloud')
1834 # Look for OnionStudios embeds
1835 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1836 if onionstudios_url:
1837 return self.url_result(onionstudios_url)
1839 # Look for SnagFilms embeds
1840 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1842 return self.url_result(snagfilms_url)
1844 # Look for JWPlatform embeds
1845 jwplatform_url = JWPlatformIE._extract_url(webpage)
1847 return self.url_result(jwplatform_url, 'JWPlatform')
1849 # Look for ScreenwaveMedia embeds
1850 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1851 if mobj is not None:
1852 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1854 # Look for Digiteka embeds
1855 digiteka_url = DigitekaIE._extract_url(webpage)
1857 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1859 # Look for Limelight embeds
1860 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1864 'Channel': 'channel',
1865 'ChannelList': 'channel_list',
1867 return self.url_result('limelight:%s:%s' % (
1868 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1870 # Look for AdobeTVVideo embeds
1872 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1874 if mobj is not None:
1875 return self.url_result(
1876 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1879 def check_video(vurl):
1880 if YoutubeIE.suitable(vurl):
1882 vpath = compat_urlparse.urlparse(vurl).path
1883 vext = determine_ext(vpath)
1884 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1886 def filter_video(urls):
1887 return list(filter(check_video, urls))
1889 # Start with something easy: JW Player in SWFObject
1890 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1892 # Look for gorilla-vid style embedding
1893 found = filter_video(re.findall(r'''(?sx)
1897 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1900 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1902 # Broaden the search a little bit
1903 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1905 # Broaden the findall a little bit: JWPlayer JS loader
1906 found = filter_video(re.findall(
1907 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1910 found = filter_video(re.findall(r'''(?xs)
1911 flowplayer\("[^"]+",\s*
1913 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1914 ["']?url["']?\s*:\s*["']([^"']+)["']
1919 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1921 # Try to find twitter cards info
1922 found = filter_video(re.findall(
1923 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1925 # We look for Open Graph info:
1926 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1927 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1928 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1929 if m_video_type is not None:
1930 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1933 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1935 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1937 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1938 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1941 # Look also in Refresh HTTP header
1942 refresh_header = head_response.headers.get('Refresh')
1944 # In python 2 response HTTP headers are bytestrings
1945 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1946 refresh_header = refresh_header.decode('iso-8859-1')
1947 found = re.search(REDIRECT_REGEX, refresh_header)
1949 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1950 self.report_following_redirect(new_url)
1956 raise UnsupportedError(url)
1959 for video_url in found:
1960 video_url = video_url.replace('\\/', '/')
1961 video_url = compat_urlparse.urljoin(url, video_url)
1962 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1964 # Sometimes, jwplayer extraction will result in a YouTube URL
1965 if YoutubeIE.suitable(video_url):
1966 entries.append(self.url_result(video_url, 'Youtube'))
1969 # here's a fun little line of code for you:
1970 video_id = os.path.splitext(video_id)[0]
1974 'uploader': video_uploader,
1975 'title': video_title,
1976 'age_limit': age_limit,
1979 ext = determine_ext(video_url)
1981 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1983 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1985 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1987 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
1989 entry_info_dict['url'] = video_url
1991 entries.append(entry_info_dict)
1993 if len(entries) == 1:
1996 for num, e in enumerate(entries, start=1):
1997 # 'url' results don't have a title
1998 if e.get('title') is not None:
1999 e['title'] = '%s (%d)' % (e['title'], num)
2001 '_type': 'playlist',