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
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
66 class GenericIE(InfoExtractor):
67 IE_DESC = 'Generic downloader that works on some sites'
71 # Direct link to a video
73 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
74 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
79 'upload_date': '20100513',
82 # Direct link to media delivered compressed (until Accept-Encoding is *)
84 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
85 'md5': '128c42e68b13950268b648275386fc74',
87 'id': 'FictionJunction-Parallel_Hearts',
89 'title': 'FictionJunction-Parallel_Hearts',
90 'upload_date': '20140522',
92 'expected_warnings': [
93 'URL could be a direct video link, returning it as such.'
96 # Direct download with broken HEAD
98 'url': 'http://ai-radio.org:8000/radio.opus',
105 'skip_download': True, # infinite live stream
107 'expected_warnings': [
108 r'501.*Not Implemented',
112 # Direct link with incorrect MIME type
114 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
115 'md5': '4ccbebe5f36706d85221f204d7eb5913',
117 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
118 'id': '5_Lennart_Poettering_-_Systemd',
120 'title': '5_Lennart_Poettering_-_Systemd',
121 'upload_date': '20141120',
123 'expected_warnings': [
124 'URL could be a direct video link, returning it as such.'
129 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
131 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
132 'title': 'Zero Punctuation',
133 'description': 're:.*groundbreaking video review series.*'
135 'playlist_mincount': 11,
137 # RSS feed with enclosure
139 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
141 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
143 'upload_date': '20150228',
144 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
147 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
149 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
153 'title': 'Automatics, robotics and biocybernetics',
154 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
155 'upload_date': '20130627',
156 'formats': 'mincount:16',
157 'subtitles': 'mincount:1',
160 'force_generic_extractor': True,
161 'skip_download': True,
164 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
166 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
171 'formats': 'mincount:1',
174 'skip_download': True,
177 # SMIL from https://www.restudy.dk/video/play/id/1637
179 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
183 'title': 'video_1637',
184 'formats': 'mincount:3',
187 'skip_download': True,
190 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
192 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
194 'id': 'smil-service',
196 'title': 'smil-service',
197 'formats': 'mincount:1',
200 'skip_download': True,
203 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
205 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
209 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
210 'formats': 'mincount:3',
213 'skip_download': True,
216 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
218 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
220 'id': 'mZlp2ctYIUEB',
222 'title': 'Tikibad ontruimd wegens brand',
223 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
224 'thumbnail': 're:^https?://.*\.jpg$',
228 'skip_download': True,
231 # MPD from http://dash-mse-test.appspot.com/media.html
233 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
234 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
236 'id': 'car-20120827-manifest',
238 'title': 'car-20120827-manifest',
239 'formats': 'mincount:9',
242 'format': 'bestvideo',
245 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
247 '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',
252 'formats': 'mincount:8',
256 'skip_download': True,
259 # m3u8 served with Content-Type: text/plain
261 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
266 'upload_date': '20140720',
267 'formats': 'mincount:11',
271 'skip_download': True,
276 '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',
280 'upload_date': '20130224',
281 'uploader_id': 'TheVerge',
282 'description': 're:^Chris Ziegler takes a look at the\.*',
283 'uploader': 'The Verge',
284 'title': 'First Firefox OS phones side-by-side',
287 'skip_download': False,
291 # redirect in Refresh HTTP header
292 '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',
296 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
297 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
298 'upload_date': '20150917',
299 'uploader_id': 'brtvofficial',
300 'uploader': 'Boiler Room',
303 'skip_download': False,
307 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
308 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
310 'id': '13601338388002',
312 'uploader': 'www.hodiho.fr',
313 'title': 'R\u00e9gis plante sa Jeep',
316 # bandcamp page with custom domain
318 'add_ie': ['Bandcamp'],
319 'url': 'http://bronyrock.com/track/the-pony-mash',
323 'title': 'The Pony Mash',
324 'uploader': 'M_Pallante',
326 'skip': 'There is a limit of 200 free downloads / month for the test song',
328 # embedded brightcove video
329 # it also tests brightcove videos that need to set the 'Referer' in the
332 'add_ie': ['BrightcoveLegacy'],
333 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
335 'id': '2765128793001',
337 'title': 'Le cours de bourse : l’analyse technique',
338 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
339 'uploader': 'BFM BUSINESS',
342 'skip_download': True,
346 # https://github.com/rg3/youtube-dl/issues/2253
347 'url': 'http://bcove.me/i6nfkrc3',
348 'md5': '0ba9446db037002366bab3b3eb30c88c',
350 'id': '3101154703001',
352 'title': 'Still no power',
353 'uploader': 'thestar.com',
354 '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.',
356 'add_ie': ['BrightcoveLegacy'],
359 'url': 'http://www.championat.com/video/football/v/87/87499.html',
360 'md5': 'fb973ecf6e4a78a67453647444222983',
362 'id': '3414141473001',
364 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
365 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
366 'uploader': 'Championat',
370 # https://github.com/rg3/youtube-dl/issues/3541
371 'add_ie': ['BrightcoveLegacy'],
372 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
374 'id': '3866516442001',
376 'title': 'Leer mij vrouwen kennen: Aflevering 1',
377 'description': 'Leer mij vrouwen kennen: Aflevering 1',
378 'uploader': 'SBS Broadcasting',
380 'skip': 'Restricted to Netherlands',
382 'skip_download': True, # m3u8 download
387 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
388 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
390 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
392 'title': '2cc213299525360.mov', # that's what we get
395 'add_ie': ['Ooyala'],
398 # ooyala video embedded with http://player.ooyala.com/iframe.js
399 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
401 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
403 'title': '"Steve Jobs: Man in the Machine" trailer',
404 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
408 'skip_download': True,
413 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
417 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
418 'upload_date': '20140225',
419 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
420 'uploader': 'Tested',
421 'uploader_id': 'testedcom',
423 # No need to test YoutubeIE here
425 'skip_download': True,
430 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
434 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
435 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
440 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
444 'title': 'Охотское море стало целиком российским',
445 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
449 'skip_download': True,
454 '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/',
458 'title': 'Дошкольное воспитание',
463 'url': 'http://www.vestifinance.ru/articles/25753',
466 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
471 'title': 'Госзаказ. День 3',
477 'title': 'Госзаказ. День 2',
483 'title': 'Госзаказ. День 1',
489 'skip_download': True,
494 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
496 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
498 'title': 'Ужастики, русский трейлер (2015)',
499 'thumbnail': 're:^https?://.*\.jpg$',
505 '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',
508 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
510 'playlist_mincount': 7,
514 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
515 'md5': '65fdff94098e4a607385a60c5177c638',
519 'title': 'Hidden miracles of the natural world',
520 'uploader': 'Louie Schwartzberg',
521 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
524 # Embedded Ustream video
526 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
527 'md5': '27b99cdb639c9b12a79bca876a073417',
531 'uploader': 'AU SPA: The NSA and Privacy',
532 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
535 # nowvideo embed hidden behind percent encoding
537 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
538 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
540 'id': '06e53103ca9aa',
542 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
543 'description': 'No description',
548 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
549 'md5': '7653032cbb25bf6c80d80f217055fa43',
551 'id': '048195-004_PLUS7-F',
554 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
555 'upload_date': '20140320',
558 'skip_download': 'Requires rtmpdump'
563 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
567 'title': 'Alcaline, le concert avec Calogero',
568 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
569 'upload_date': '20150226',
570 'timestamp': 1424989860,
575 'skip_download': True,
577 'expected_warnings': [
583 'url': 'http://www.wired.com/2014/04/honda-asimo/',
584 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
586 'id': '53501be369702d3275860000',
588 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
593 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
594 'md5': '441aeeb82eb72c422c7f14ec533999cd',
596 'id': 'k2mm4bCdJ6CQ2i7c8o2',
598 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
601 'add_ie': ['Dailymotion'],
605 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
609 'title': 'The NBL Auction 2014',
610 'uploader': 'BADMINTON England',
611 'uploader_id': 'BADMINTONEvents',
612 'upload_date': '20140603',
613 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
615 'add_ie': ['Youtube'],
617 'skip_download': True,
622 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
623 'md5': '35727f82f58c76d996fc188f9755b0d5',
625 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
628 'description': 'Mario\'s life in the fast lane has never looked so good.',
631 # YouTube embed via <data-embed-url="">
633 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
637 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
638 'uploader': 'Gameloft',
639 'uploader_id': 'gameloft',
640 'upload_date': '20140828',
641 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
644 'skip_download': True,
649 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
651 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
653 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
654 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
659 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
661 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
662 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
668 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
673 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
674 'md5': '9d65602bf31c6e20014319c7d07fba27',
676 'id': '5123ea6d5e5a7',
679 'uploader': 'www.handjobhub.com',
680 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
683 # Multiple brightcove videos
684 # https://github.com/rg3/youtube-dl/issues/2283
686 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
688 'id': 'always-never',
689 'title': 'Always / Never - The New Yorker',
693 'extract_flat': False,
694 'skip_download': True,
699 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
700 'md5': '96f09a37e44da40dd083e12d9a683327',
704 'title': 'Ump changes call to ball',
705 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
707 'timestamp': 1401537900,
708 'upload_date': '20140531',
709 'thumbnail': 're:^https?://.*\.jpg$',
714 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
715 'md5': '8788b683c777a5cf25621eaf286d0c23',
719 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
721 'filesize': 182808282,
722 'uploader': 'education-portal.com',
726 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
727 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
731 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
733 'uploader': 'thoughtworks.wistia.com',
738 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
742 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
743 'uploader': 'Sophos Security',
744 'title': 'Chet Chat 171 - Oct 29, 2014',
745 'upload_date': '20141029',
750 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
754 'upload_date': '20141112',
755 'title': 'Rosetta #CometLanding webcast HL 10',
760 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
763 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
765 'playlist_mincount': 2,
769 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
773 'upload_date': '20141126',
774 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
779 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
781 'id': '730m_DandD_1901_512k',
783 'uploader': 'www.abc.net.au',
784 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
787 # embedded viddler video
789 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
793 'uploader': 'deadspin',
794 'title': 'WALL-TO-GORTAT',
795 'timestamp': 1422285291,
796 'upload_date': '20150126',
798 'add_ie': ['Viddler'],
802 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
806 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
807 'description': 'md5:601cb790edd05908957dae8aaa866465',
808 'upload_date': '20150220',
813 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
817 'upload_date': '20150212',
818 'uploader': 'The National Archives UK',
819 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
820 'uploader_id': 'NationalArchives08',
821 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
826 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
827 'playlist_mincount': 5,
829 'id': 'aanslagen-kopenhagen',
830 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
835 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
839 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
844 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
848 'upload_date': '20150226',
849 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
851 'title': 'John Carlson Postgame 2/25/15',
854 # Kaltura embed (different embed code)
856 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
860 'upload_date': '20150127',
861 'uploader_id': 'PremierMedia',
863 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
866 # Kaltura embed protected with referrer
868 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
872 'title': 'Violetta - Achter De Schermen - Ruggero',
873 'description': 'Achter de schermen met Ruggero',
874 'timestamp': 1435133761,
875 'upload_date': '20150624',
876 'uploader_id': 'echojecka',
879 # Eagle.Platform embed (generic URL)
881 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
885 'title': 'Навальный вышел на свободу',
886 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
887 'thumbnail': 're:^https?://.*\.jpg$',
893 # ClipYou (Eagle.Platform) embed (custom URL)
895 'url': 'http://muz-tv.ru/play/7129/',
899 'title': "'O Sole Mio",
900 'thumbnail': 're:^https?://.*\.jpg$',
907 'url': 'http://muz-tv.ru/kinozal/view/7400/',
911 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
912 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
913 'thumbnail': 're:^https?://.*\.jpg$',
920 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
924 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
925 'thumbnail': 're:^https?://.*\.png$',
931 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
932 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
936 'title': 'Facebook Creates "On This Day" | Crunch Report',
941 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
945 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
950 # Crooks and Liars embed
952 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
956 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
957 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
958 'timestamp': 1428207000,
959 'upload_date': '20150405',
960 'uploader': 'Heather',
963 # Crooks and Liars external embed
965 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
967 'id': 'MTE3MjUtMzQ2MzA',
969 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
970 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
971 'timestamp': 1265032391,
972 'upload_date': '20100201',
973 'uploader': 'Heather',
976 # NBC Sports vplayer embed
978 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
980 'id': 'ln7x1qSThw4k',
982 'title': "PFT Live: New leader in the 'new-look' defense",
983 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
988 'url': 'http://www.udn.com/news/story/7314/822787',
989 'md5': 'fd2060e988c326991037b9aff9df21a6',
993 'title': '中一中男師變性 全校師生力挺',
994 'thumbnail': 're:^https?://.*\.jpg$',
999 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1001 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1003 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1004 'title': 'This is what separates the Excel masters from the wannabes',
1005 'duration': 191.933,
1009 'skip_download': True,
1012 # Contains a SMIL manifest
1014 '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',
1018 'title': '+ Football: Lottery Champions League Europe',
1019 'uploader': 'www.telewebion.com',
1023 'skip_download': True,
1026 # Brightcove URL in single quotes
1028 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1029 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1031 'id': '4255764656001',
1033 'title': 'SN Presents: Russell Martin, World Citizen',
1034 '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.',
1035 'uploader': 'Rogers Sportsnet',
1038 # Dailymotion Cloud video
1040 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1041 'md5': '49444254273501a64675a7e68c502681',
1043 'id': '5585de919473990de4bee11b',
1045 'title': 'Le débat',
1046 'thumbnail': 're:^https?://.*\.jpe?g$',
1049 # OnionStudios embed
1051 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1055 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1056 'thumbnail': 're:^https?://.*\.jpe?g$',
1057 'uploader': 'ClickHole',
1058 'uploader_id': 'clickhole',
1063 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1065 'id': '74849a00-85a9-11e1-9660-123139220831',
1067 'title': '#whilewewatch',
1070 # AdobeTVVideo embed
1072 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1073 'md5': '43662b577c018ad707a63766462b1e87',
1077 'title': 'New experience with Acrobat DC',
1078 'description': 'New experience with Acrobat DC',
1079 'duration': 248.667,
1082 # ScreenwaveMedia embed
1084 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1085 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1087 'id': 'cinemasnob-55d26273809dd',
1089 'title': 'cinemasnob',
1092 # BrightcoveInPageEmbed embed
1094 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1096 'id': '4238694884001',
1098 'title': 'Tabletop: Dread, Last Thoughts',
1099 'description': 'Tabletop: Dread, Last Thoughts',
1103 # JWPlayer with M3U8
1105 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1109 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1110 'uploader': 'ren.tv',
1114 'skip_download': True,
1117 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1118 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1120 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1122 'id': '4785848093001',
1124 'title': 'The Cardinal Pell Interview',
1125 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1126 'uploader': 'GlobeCast Australia - GlobeStream',
1130 'skip_download': True,
1133 # Another form of arte.tv embed
1135 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1136 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1138 'id': '030273-562_PLUS7-F',
1140 'title': 'ARTE Reportage - Nulle part, en France',
1141 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1142 'upload_date': '20160409',
1147 'url': 'http://www.wykop.pl/link/3088787/',
1148 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1150 'id': '874_1459135191',
1152 'title': 'Man shows poor quality of new apartment building',
1153 'description': 'The wall is like a sand pile.',
1154 'uploader': 'Lake8737',
1159 def report_following_redirect(self, new_url):
1160 """Report information extraction."""
1161 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1163 def _extract_rss(self, url, video_id, doc):
1164 playlist_title = doc.find('./channel/title').text
1165 playlist_desc_el = doc.find('./channel/description')
1166 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1169 for it in doc.findall('./channel/item'):
1170 next_url = xpath_text(it, 'link', fatal=False)
1172 enclosure_nodes = it.findall('./enclosure')
1173 for e in enclosure_nodes:
1174 next_url = e.attrib.get('url')
1184 'title': it.find('title').text,
1188 '_type': 'playlist',
1190 'title': playlist_title,
1191 'description': playlist_desc,
1195 def _extract_camtasia(self, url, video_id, webpage):
1196 """ Returns None if no camtasia video can be found. """
1198 camtasia_cfg = self._search_regex(
1199 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1200 webpage, 'camtasia configuration file', default=None)
1201 if camtasia_cfg is None:
1204 title = self._html_search_meta('DC.title', webpage, fatal=True)
1206 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1207 camtasia_cfg = self._download_xml(
1208 camtasia_url, video_id,
1209 note='Downloading camtasia configuration',
1210 errnote='Failed to download camtasia configuration')
1211 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1214 for n in fileset_node.getchildren():
1215 url_n = n.find('./uri')
1220 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1221 'title': '%s - %s' % (title, n.tag),
1222 'url': compat_urlparse.urljoin(url, url_n.text),
1223 'duration': float_or_none(n.find('./duration').text),
1227 '_type': 'playlist',
1232 def _real_extract(self, url):
1233 if url.startswith('//'):
1236 'url': self.http_scheme() + url,
1239 parsed_url = compat_urlparse.urlparse(url)
1240 if not parsed_url.scheme:
1241 default_search = self._downloader.params.get('default_search')
1242 if default_search is None:
1243 default_search = 'fixup_error'
1245 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1247 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1248 return self.url_result('http://' + url)
1249 elif default_search != 'fixup_error':
1250 if default_search == 'auto_warning':
1251 if re.match(r'^(?:url|URL)$', url):
1252 raise ExtractorError(
1253 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1256 self._downloader.report_warning(
1257 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1258 return self.url_result('ytsearch:' + url)
1260 if default_search in ('error', 'fixup_error'):
1261 raise ExtractorError(
1262 '%r is not a valid URL. '
1263 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1264 % (url, url), expected=True)
1266 if ':' not in default_search:
1267 default_search += ':'
1268 return self.url_result(default_search + url)
1270 url, smuggled_data = unsmuggle_url(url)
1271 force_videoid = None
1272 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1273 if smuggled_data and 'force_videoid' in smuggled_data:
1274 force_videoid = smuggled_data['force_videoid']
1275 video_id = force_videoid
1277 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1279 self.to_screen('%s: Requesting header' % video_id)
1281 head_req = HEADRequest(url)
1282 head_response = self._request_webpage(
1284 note=False, errnote='Could not send HEAD request to %s' % url,
1287 if head_response is not False:
1288 # Check for redirect
1289 new_url = head_response.geturl()
1291 self.report_following_redirect(new_url)
1293 new_url = smuggle_url(
1294 new_url, {'force_videoid': force_videoid})
1295 return self.url_result(new_url)
1297 full_response = None
1298 if head_response is False:
1299 request = sanitized_Request(url)
1300 request.add_header('Accept-Encoding', '*')
1301 full_response = self._request_webpage(request, video_id)
1302 head_response = full_response
1306 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1307 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1310 # Check for direct link to a video
1311 content_type = head_response.headers.get('Content-Type', '').lower()
1312 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1314 format_id = m.group('format_id')
1315 if format_id.endswith('mpegurl'):
1316 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1317 elif format_id == 'f4m':
1318 formats = self._extract_f4m_formats(url, video_id)
1321 'format_id': m.group('format_id'),
1323 'vcodec': 'none' if m.group('type') == 'audio' else None
1325 info_dict['direct'] = True
1326 self._sort_formats(formats)
1327 info_dict['formats'] = formats
1330 if not self._downloader.params.get('test', False) and not is_intentional:
1331 force = self._downloader.params.get('force_generic_extractor', False)
1332 self._downloader.report_warning(
1333 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1335 if not full_response:
1336 request = sanitized_Request(url)
1337 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1338 # making it impossible to download only chunk of the file (yet we need only 512kB to
1339 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1340 # that will always result in downloading the whole file that is not desirable.
1341 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1342 # to accept raw bytes and being able to download only a chunk.
1343 # It may probably better to solve this by checking Content-Type for application/octet-stream
1344 # after HEAD request finishes, but not sure if we can rely on this.
1345 request.add_header('Accept-Encoding', '*')
1346 full_response = self._request_webpage(request, video_id)
1348 first_bytes = full_response.read(512)
1350 # Is it an M3U playlist?
1351 if first_bytes.startswith(b'#EXTM3U'):
1352 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1353 self._sort_formats(info_dict['formats'])
1356 # Maybe it's a direct link to a video?
1357 # Be careful not to download the whole thing!
1358 if not is_html(first_bytes):
1359 self._downloader.report_warning(
1360 'URL could be a direct video link, returning it as such.')
1367 webpage = self._webpage_read_content(
1368 full_response, url, video_id, prefix=first_bytes)
1370 self.report_extraction(video_id)
1372 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1374 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1375 if doc.tag == 'rss':
1376 return self._extract_rss(url, video_id, doc)
1377 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1378 smil = self._parse_smil(doc, url, video_id)
1379 self._sort_formats(smil['formats'])
1381 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1382 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1383 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1384 info_dict['formats'] = self._parse_mpd_formats(
1385 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1386 self._sort_formats(info_dict['formats'])
1388 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1389 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1390 self._sort_formats(info_dict['formats'])
1392 except compat_xml_parse_error:
1395 # Is it a Camtasia project?
1396 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1397 if camtasia_res is not None:
1400 # Sometimes embedded video player is hidden behind percent encoding
1401 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1402 # Unescaping the whole page allows to handle those cases in a generic way
1403 webpage = compat_urllib_parse_unquote(webpage)
1405 # it's tempting to parse this further, but you would
1406 # have to take into account all the variations like
1407 # Video Title - Site Name
1408 # Site Name | Video Title
1409 # Video Title - Tagline | Site Name
1410 # and so on and so forth; it's just not practical
1411 video_title = self._html_search_regex(
1412 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1415 # Try to detect age limit automatically
1416 age_limit = self._rta_search(webpage)
1417 # And then there are the jokers who advertise that they use RTA,
1418 # but actually don't.
1419 AGE_LIMIT_MARKERS = [
1420 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1422 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1425 # video uploader is domain name
1426 video_uploader = self._search_regex(
1427 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1430 def _playlist_from_matches(matches, getter=None, ie=None):
1432 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1434 return self.playlist_result(
1435 urlrs, playlist_id=video_id, playlist_title=video_title)
1437 # Look for Brightcove Legacy Studio embeds
1438 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1440 self.to_screen('Brightcove video detected.')
1443 'url': smuggle_url(bc_url, {'Referer': url}),
1444 'ie_key': 'BrightcoveLegacy'
1445 } for bc_url in bc_urls]
1448 '_type': 'playlist',
1449 'title': video_title,
1454 # Look for Brightcove New Studio embeds
1455 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1457 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1459 # Look for embedded rtl.nl player
1460 matches = re.findall(
1461 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1464 return _playlist_from_matches(matches, ie='RtlNl')
1466 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1467 if vimeo_url is not None:
1468 return self.url_result(vimeo_url)
1470 vid_me_embed_url = self._search_regex(
1471 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1472 webpage, 'vid.me embed', default=None)
1473 if vid_me_embed_url is not None:
1474 return self.url_result(vid_me_embed_url, 'Vidme')
1476 # Look for embedded YouTube player
1477 matches = re.findall(r'''(?x)
1486 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1490 return _playlist_from_matches(
1491 matches, lambda m: unescapeHTML(m[1]))
1493 # Look for lazyYT YouTube embed
1494 matches = re.findall(
1495 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1497 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1499 # Look for embedded Dailymotion player
1500 matches = re.findall(
1501 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1503 return _playlist_from_matches(
1504 matches, lambda m: unescapeHTML(m[1]))
1506 # Look for embedded Dailymotion playlist player (#3822)
1508 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1510 playlists = re.findall(
1511 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1513 return _playlist_from_matches(
1514 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1516 # Look for embedded Wistia player
1518 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1520 embed_url = self._proto_relative_url(
1521 unescapeHTML(match.group('url')))
1523 '_type': 'url_transparent',
1526 'uploader': video_uploader,
1527 'title': video_title,
1531 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1534 '_type': 'url_transparent',
1535 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1537 'uploader': video_uploader,
1538 'title': video_title,
1539 'id': match.group('id')
1542 # Look for SVT player
1543 svt_url = SVTIE._extract_url(webpage)
1545 return self.url_result(svt_url, 'SVT')
1547 # Look for embedded condenast player
1548 matches = re.findall(
1549 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1553 '_type': 'playlist',
1556 'ie_key': 'CondeNast',
1558 } for ma in matches],
1559 'title': video_title,
1563 # Look for Bandcamp pages with custom domain
1564 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1565 if mobj is not None:
1566 burl = unescapeHTML(mobj.group(1))
1567 # Don't set the extractor because it can be a track url or an album
1568 return self.url_result(burl)
1570 # Look for embedded Vevo player
1572 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1573 if mobj is not None:
1574 return self.url_result(mobj.group('url'))
1576 # Look for embedded Viddler player
1578 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1580 if mobj is not None:
1581 return self.url_result(mobj.group('url'))
1583 # Look for NYTimes player
1585 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1587 if mobj is not None:
1588 return self.url_result(mobj.group('url'))
1590 # Look for Libsyn player
1592 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1593 if mobj is not None:
1594 return self.url_result(mobj.group('url'))
1596 # Look for Ooyala videos
1597 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1598 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1599 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1600 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1601 if mobj is not None:
1602 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1604 # Look for multiple Ooyala embeds on SBN network websites
1605 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1606 if mobj is not None:
1607 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1609 return _playlist_from_matches(
1610 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1612 # Look for Aparat videos
1613 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1614 if mobj is not None:
1615 return self.url_result(mobj.group(1), 'Aparat')
1617 # Look for MPORA videos
1618 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1619 if mobj is not None:
1620 return self.url_result(mobj.group(1), 'Mpora')
1622 # Look for embedded NovaMov-based player
1624 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1625 (?P<url>http://(?:(?:embed|www)\.)?
1627 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1628 videoweed\.(?:es|com)|
1629 movshare\.(?:net|sx|ag)|
1630 divxstage\.(?:eu|net|ch|co|at|ag))
1631 /embed\.php.+?)\1''', webpage)
1632 if mobj is not None:
1633 return self.url_result(mobj.group('url'))
1635 # Look for embedded Facebook player
1637 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1638 if mobj is not None:
1639 return self.url_result(mobj.group('url'), 'Facebook')
1641 # Look for embedded VK player
1642 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1643 if mobj is not None:
1644 return self.url_result(mobj.group('url'), 'VK')
1646 # Look for embedded Odnoklassniki player
1647 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1648 if mobj is not None:
1649 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1651 # Look for embedded ivi player
1652 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1653 if mobj is not None:
1654 return self.url_result(mobj.group('url'), 'Ivi')
1656 # Look for embedded Huffington Post player
1658 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1659 if mobj is not None:
1660 return self.url_result(mobj.group('url'), 'HuffPost')
1663 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1664 if mobj is not None:
1665 return self.url_result(mobj.group('url'))
1666 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1667 if mobj is not None:
1668 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1670 # Look for funnyordie embed
1671 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1673 return _playlist_from_matches(
1674 matches, getter=unescapeHTML, ie='FunnyOrDie')
1676 # Look for BBC iPlayer embed
1677 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1679 return _playlist_from_matches(matches, ie='BBCCoUk')
1681 # Look for embedded RUTV player
1682 rutv_url = RUTVIE._extract_url(webpage)
1684 return self.url_result(rutv_url, 'RUTV')
1686 # Look for embedded TVC player
1687 tvc_url = TVCIE._extract_url(webpage)
1689 return self.url_result(tvc_url, 'TVC')
1691 # Look for embedded SportBox player
1692 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1694 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1696 # Look for embedded PornHub player
1697 pornhub_url = PornHubIE._extract_url(webpage)
1699 return self.url_result(pornhub_url, 'PornHub')
1701 # Look for embedded XHamster player
1702 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1704 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1706 # Look for embedded TNAFlixNetwork player
1707 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1709 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1711 # Look for embedded Tvigle player
1713 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1714 if mobj is not None:
1715 return self.url_result(mobj.group('url'), 'Tvigle')
1717 # Look for embedded TED player
1719 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1720 if mobj is not None:
1721 return self.url_result(mobj.group('url'), 'TED')
1723 # Look for embedded Ustream videos
1725 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1726 if mobj is not None:
1727 return self.url_result(mobj.group('url'), 'Ustream')
1729 # Look for embedded arte.tv player
1731 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1733 if mobj is not None:
1734 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1736 # Look for embedded francetv player
1738 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1740 if mobj is not None:
1741 return self.url_result(mobj.group('url'))
1743 # Look for embedded smotri.com player
1744 smotri_url = SmotriIE._extract_url(webpage)
1746 return self.url_result(smotri_url, 'Smotri')
1748 # Look for embedded Myvi.ru player
1749 myvi_url = MyviIE._extract_url(webpage)
1751 return self.url_result(myvi_url)
1753 # Look for embedded soundcloud player
1755 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1757 if mobj is not None:
1758 url = unescapeHTML(mobj.group('url'))
1759 return self.url_result(url)
1761 # Look for embedded vulture.com player
1763 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1765 if mobj is not None:
1766 url = unescapeHTML(mobj.group('url'))
1767 return self.url_result(url, ie='Vulture')
1769 # Look for embedded mtvservices player
1770 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1772 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1774 # Look for embedded yahoo player
1776 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1778 if mobj is not None:
1779 return self.url_result(mobj.group('url'), 'Yahoo')
1781 # Look for embedded sbs.com.au player
1785 <meta\s+property="og:video"\s+content=|
1788 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1790 if mobj is not None:
1791 return self.url_result(mobj.group('url'), 'SBS')
1793 # Look for embedded Cinchcast player
1795 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1797 if mobj is not None:
1798 return self.url_result(mobj.group('url'), 'Cinchcast')
1801 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1805 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1807 if mobj is not None:
1808 return self.url_result(mobj.group('url'), 'MLB')
1811 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1813 if mobj is not None:
1814 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1817 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1819 if mobj is not None:
1820 return self.url_result(mobj.group('url'), 'Livestream')
1822 # Look for Zapiks embed
1824 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1825 if mobj is not None:
1826 return self.url_result(mobj.group('url'), 'Zapiks')
1828 # Look for Kaltura embeds
1829 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1830 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))
1831 if mobj is not None:
1832 return self.url_result(smuggle_url(
1833 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1834 {'source_url': url}), 'Kaltura')
1836 # Look for Eagle.Platform embeds
1838 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1839 if mobj is not None:
1840 return self.url_result(mobj.group('url'), 'EaglePlatform')
1842 # Look for ClipYou (uses Eagle.Platform) embeds
1844 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1845 if mobj is not None:
1846 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1848 # Look for Pladform embeds
1849 pladform_url = PladformIE._extract_url(webpage)
1851 return self.url_result(pladform_url)
1853 # Look for Videomore embeds
1854 videomore_url = VideomoreIE._extract_url(webpage)
1856 return self.url_result(videomore_url)
1858 # Look for Playwire embeds
1860 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1861 if mobj is not None:
1862 return self.url_result(mobj.group('url'))
1864 # Look for 5min embeds
1866 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1867 if mobj is not None:
1868 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1870 # Look for Crooks and Liars embeds
1872 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1873 if mobj is not None:
1874 return self.url_result(mobj.group('url'))
1876 # Look for NBC Sports VPlayer embeds
1877 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1879 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1881 # Look for Google Drive embeds
1882 google_drive_url = GoogleDriveIE._extract_url(webpage)
1883 if google_drive_url:
1884 return self.url_result(google_drive_url, 'GoogleDrive')
1886 # Look for UDN embeds
1888 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1889 if mobj is not None:
1890 return self.url_result(
1891 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1893 # Look for Senate ISVP iframe
1894 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1896 return self.url_result(senate_isvp_url, 'SenateISVP')
1898 # Look for Dailymotion Cloud videos
1899 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1901 return self.url_result(dmcloud_url, 'DailymotionCloud')
1903 # Look for OnionStudios embeds
1904 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1905 if onionstudios_url:
1906 return self.url_result(onionstudios_url)
1908 # Look for SnagFilms embeds
1909 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1911 return self.url_result(snagfilms_url)
1913 # Look for JWPlatform embeds
1914 jwplatform_url = JWPlatformIE._extract_url(webpage)
1916 return self.url_result(jwplatform_url, 'JWPlatform')
1918 # Look for ScreenwaveMedia embeds
1919 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1920 if mobj is not None:
1921 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1923 # Look for Digiteka embeds
1924 digiteka_url = DigitekaIE._extract_url(webpage)
1926 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1928 # Look for Limelight embeds
1929 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1933 'Channel': 'channel',
1934 'ChannelList': 'channel_list',
1936 return self.url_result('limelight:%s:%s' % (
1937 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1939 # Look for AdobeTVVideo embeds
1941 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1943 if mobj is not None:
1944 return self.url_result(
1945 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1948 # Look for Vine embeds
1950 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1952 if mobj is not None:
1953 return self.url_result(
1954 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1956 # Look for Instagram embeds
1957 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
1958 if instagram_embed_url is not None:
1959 return self.url_result(instagram_embed_url, InstagramIE.ie_key())
1961 # Look for LiveLeak embeds
1962 liveleak_url = LiveLeakIE._extract_url(webpage)
1964 return self.url_result(liveleak_url, 'LiveLeak')
1966 def check_video(vurl):
1967 if YoutubeIE.suitable(vurl):
1969 vpath = compat_urlparse.urlparse(vurl).path
1970 vext = determine_ext(vpath)
1971 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1973 def filter_video(urls):
1974 return list(filter(check_video, urls))
1976 # Start with something easy: JW Player in SWFObject
1977 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1979 # Look for gorilla-vid style embedding
1980 found = filter_video(re.findall(r'''(?sx)
1984 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1987 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1989 # Broaden the search a little bit
1990 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1992 # Broaden the findall a little bit: JWPlayer JS loader
1993 found = filter_video(re.findall(
1994 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1997 found = filter_video(re.findall(r'''(?xs)
1998 flowplayer\("[^"]+",\s*
2000 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2001 ["']?url["']?\s*:\s*["']([^"']+)["']
2006 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2008 # Try to find twitter cards info
2009 found = filter_video(re.findall(
2010 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2012 # We look for Open Graph info:
2013 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2014 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2015 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2016 if m_video_type is not None:
2017 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2020 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2022 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2024 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2025 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2028 # Look also in Refresh HTTP header
2029 refresh_header = head_response.headers.get('Refresh')
2031 # In python 2 response HTTP headers are bytestrings
2032 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2033 refresh_header = refresh_header.decode('iso-8859-1')
2034 found = re.search(REDIRECT_REGEX, refresh_header)
2036 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2037 self.report_following_redirect(new_url)
2043 raise UnsupportedError(url)
2046 for video_url in found:
2047 video_url = video_url.replace('\\/', '/')
2048 video_url = compat_urlparse.urljoin(url, video_url)
2049 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2051 # Sometimes, jwplayer extraction will result in a YouTube URL
2052 if YoutubeIE.suitable(video_url):
2053 entries.append(self.url_result(video_url, 'Youtube'))
2056 # here's a fun little line of code for you:
2057 video_id = os.path.splitext(video_id)[0]
2061 'uploader': video_uploader,
2062 'title': video_title,
2063 'age_limit': age_limit,
2066 ext = determine_ext(video_url)
2068 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2070 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2072 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2074 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2076 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2078 entry_info_dict['url'] = video_url
2080 if entry_info_dict.get('formats'):
2081 self._sort_formats(entry_info_dict['formats'])
2083 entries.append(entry_info_dict)
2085 if len(entries) == 1:
2088 for num, e in enumerate(entries, start=1):
2089 # 'url' results don't have a title
2090 if e.get('title') is not None:
2091 e['title'] = '%s (%d)' % (e['title'], num)
2093 '_type': 'playlist',