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'
111 # Direct link with incorrect MIME type
113 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
114 'md5': '4ccbebe5f36706d85221f204d7eb5913',
116 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
117 'id': '5_Lennart_Poettering_-_Systemd',
119 'title': '5_Lennart_Poettering_-_Systemd',
120 'upload_date': '20141120',
122 'expected_warnings': [
123 'URL could be a direct video link, returning it as such.'
128 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
130 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
131 'title': 'Zero Punctuation',
132 'description': 're:.*groundbreaking video review series.*'
134 'playlist_mincount': 11,
136 # RSS feed with enclosure
138 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
140 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
142 'upload_date': '20150228',
143 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
146 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
148 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
152 'title': 'Automatics, robotics and biocybernetics',
153 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
154 'upload_date': '20130627',
155 'formats': 'mincount:16',
156 'subtitles': 'mincount:1',
159 'force_generic_extractor': True,
160 'skip_download': True,
163 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
165 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
170 'formats': 'mincount:1',
173 'skip_download': True,
176 # SMIL from https://www.restudy.dk/video/play/id/1637
178 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
182 'title': 'video_1637',
183 'formats': 'mincount:3',
186 'skip_download': True,
189 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
191 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
193 'id': 'smil-service',
195 'title': 'smil-service',
196 'formats': 'mincount:1',
199 'skip_download': True,
202 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
204 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
208 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
209 'formats': 'mincount:3',
212 'skip_download': True,
215 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
217 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
219 'id': 'mZlp2ctYIUEB',
221 'title': 'Tikibad ontruimd wegens brand',
222 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
223 'thumbnail': 're:^https?://.*\.jpg$',
227 'skip_download': True,
230 # MPD from http://dash-mse-test.appspot.com/media.html
232 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
233 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
235 'id': 'car-20120827-manifest',
237 'title': 'car-20120827-manifest',
238 'formats': 'mincount:9',
241 'format': 'bestvideo',
244 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
246 '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',
251 'formats': 'mincount:8',
255 'skip_download': True,
258 # m3u8 served with Content-Type: text/plain
260 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
265 'upload_date': '20140720',
266 'formats': 'mincount:11',
270 'skip_download': True,
275 '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',
279 'upload_date': '20130224',
280 'uploader_id': 'TheVerge',
281 'description': 're:^Chris Ziegler takes a look at the\.*',
282 'uploader': 'The Verge',
283 'title': 'First Firefox OS phones side-by-side',
286 'skip_download': False,
290 # redirect in Refresh HTTP header
291 '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',
295 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
296 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
297 'upload_date': '20150917',
298 'uploader_id': 'brtvofficial',
299 'uploader': 'Boiler Room',
302 'skip_download': False,
306 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
307 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
309 'id': '13601338388002',
311 'uploader': 'www.hodiho.fr',
312 'title': 'R\u00e9gis plante sa Jeep',
315 # bandcamp page with custom domain
317 'add_ie': ['Bandcamp'],
318 'url': 'http://bronyrock.com/track/the-pony-mash',
322 'title': 'The Pony Mash',
323 'uploader': 'M_Pallante',
325 'skip': 'There is a limit of 200 free downloads / month for the test song',
327 # embedded brightcove video
328 # it also tests brightcove videos that need to set the 'Referer' in the
331 'add_ie': ['BrightcoveLegacy'],
332 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
334 'id': '2765128793001',
336 'title': 'Le cours de bourse : l’analyse technique',
337 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
338 'uploader': 'BFM BUSINESS',
341 'skip_download': True,
345 # https://github.com/rg3/youtube-dl/issues/2253
346 'url': 'http://bcove.me/i6nfkrc3',
347 'md5': '0ba9446db037002366bab3b3eb30c88c',
349 'id': '3101154703001',
351 'title': 'Still no power',
352 'uploader': 'thestar.com',
353 '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.',
355 'add_ie': ['BrightcoveLegacy'],
358 'url': 'http://www.championat.com/video/football/v/87/87499.html',
359 'md5': 'fb973ecf6e4a78a67453647444222983',
361 'id': '3414141473001',
363 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
364 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
365 'uploader': 'Championat',
369 # https://github.com/rg3/youtube-dl/issues/3541
370 'add_ie': ['BrightcoveLegacy'],
371 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
373 'id': '3866516442001',
375 'title': 'Leer mij vrouwen kennen: Aflevering 1',
376 'description': 'Leer mij vrouwen kennen: Aflevering 1',
377 'uploader': 'SBS Broadcasting',
379 'skip': 'Restricted to Netherlands',
381 'skip_download': True, # m3u8 download
386 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
387 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
389 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
391 'title': '2cc213299525360.mov', # that's what we get
394 'add_ie': ['Ooyala'],
397 # ooyala video embedded with http://player.ooyala.com/iframe.js
398 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
400 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
402 'title': '"Steve Jobs: Man in the Machine" trailer',
403 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
407 'skip_download': True,
412 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
416 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
417 'upload_date': '20140225',
418 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
419 'uploader': 'Tested',
420 'uploader_id': 'testedcom',
422 # No need to test YoutubeIE here
424 'skip_download': True,
429 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
433 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
434 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
439 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
443 'title': 'Охотское море стало целиком российским',
444 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
448 'skip_download': True,
453 '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/',
457 'title': 'Дошкольное воспитание',
462 'url': 'http://www.vestifinance.ru/articles/25753',
465 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
470 'title': 'Госзаказ. День 3',
476 'title': 'Госзаказ. День 2',
482 'title': 'Госзаказ. День 1',
488 'skip_download': True,
493 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
495 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
497 'title': 'Ужастики, русский трейлер (2015)',
498 'thumbnail': 're:^https?://.*\.jpg$',
504 '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',
507 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
509 'playlist_mincount': 7,
513 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
514 'md5': '65fdff94098e4a607385a60c5177c638',
518 'title': 'Hidden miracles of the natural world',
519 'uploader': 'Louie Schwartzberg',
520 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
523 # Embedded Ustream video
525 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
526 'md5': '27b99cdb639c9b12a79bca876a073417',
530 'uploader': 'AU SPA: The NSA and Privacy',
531 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
534 # nowvideo embed hidden behind percent encoding
536 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
537 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
539 'id': '06e53103ca9aa',
541 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
542 'description': 'No description',
547 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
548 'md5': '7653032cbb25bf6c80d80f217055fa43',
550 'id': '048195-004_PLUS7-F',
553 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
554 'upload_date': '20140320',
557 'skip_download': 'Requires rtmpdump'
562 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
566 'title': 'Alcaline, le concert avec Calogero',
567 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
568 'upload_date': '20150226',
569 'timestamp': 1424989860,
574 'skip_download': True,
576 'expected_warnings': [
582 'url': 'http://www.wired.com/2014/04/honda-asimo/',
583 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
585 'id': '53501be369702d3275860000',
587 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
592 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
593 'md5': '441aeeb82eb72c422c7f14ec533999cd',
595 'id': 'k2mm4bCdJ6CQ2i7c8o2',
597 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
600 'add_ie': ['Dailymotion'],
604 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
608 'title': 'The NBL Auction 2014',
609 'uploader': 'BADMINTON England',
610 'uploader_id': 'BADMINTONEvents',
611 'upload_date': '20140603',
612 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
614 'add_ie': ['Youtube'],
616 'skip_download': True,
621 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
622 'md5': '35727f82f58c76d996fc188f9755b0d5',
624 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
627 'description': 'Mario\'s life in the fast lane has never looked so good.',
630 # YouTube embed via <data-embed-url="">
632 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
636 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
637 'uploader': 'Gameloft',
638 'uploader_id': 'gameloft',
639 'upload_date': '20140828',
640 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
643 'skip_download': True,
648 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
650 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
652 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
653 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
658 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
660 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
661 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
667 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
672 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
673 'md5': '9d65602bf31c6e20014319c7d07fba27',
675 'id': '5123ea6d5e5a7',
678 'uploader': 'www.handjobhub.com',
679 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
682 # Multiple brightcove videos
683 # https://github.com/rg3/youtube-dl/issues/2283
685 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
687 'id': 'always-never',
688 'title': 'Always / Never - The New Yorker',
692 'extract_flat': False,
693 'skip_download': True,
698 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
699 'md5': '96f09a37e44da40dd083e12d9a683327',
703 'title': 'Ump changes call to ball',
704 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
706 'timestamp': 1401537900,
707 'upload_date': '20140531',
708 'thumbnail': 're:^https?://.*\.jpg$',
713 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
714 'md5': '8788b683c777a5cf25621eaf286d0c23',
718 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
720 'filesize': 182808282,
721 'uploader': 'education-portal.com',
725 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
726 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
730 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
732 'uploader': 'thoughtworks.wistia.com',
737 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
741 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
742 'uploader': 'Sophos Security',
743 'title': 'Chet Chat 171 - Oct 29, 2014',
744 'upload_date': '20141029',
749 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
753 'upload_date': '20141112',
754 'title': 'Rosetta #CometLanding webcast HL 10',
759 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
762 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
764 'playlist_mincount': 2,
768 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
772 'upload_date': '20141126',
773 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
778 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
780 'id': '730m_DandD_1901_512k',
782 'uploader': 'www.abc.net.au',
783 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
786 # embedded viddler video
788 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
792 'uploader': 'deadspin',
793 'title': 'WALL-TO-GORTAT',
794 'timestamp': 1422285291,
795 'upload_date': '20150126',
797 'add_ie': ['Viddler'],
801 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
805 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
806 'description': 'md5:601cb790edd05908957dae8aaa866465',
807 'upload_date': '20150220',
812 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
816 'upload_date': '20150212',
817 'uploader': 'The National Archives UK',
818 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
819 'uploader_id': 'NationalArchives08',
820 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
825 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
826 'playlist_mincount': 5,
828 'id': 'aanslagen-kopenhagen',
829 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
834 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
838 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
843 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
847 'upload_date': '20150226',
848 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
850 'title': 'John Carlson Postgame 2/25/15',
853 # Kaltura embed (different embed code)
855 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
859 'upload_date': '20150127',
860 'uploader_id': 'PremierMedia',
862 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
865 # Kaltura embed protected with referrer
867 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
871 'title': 'Violetta - Achter De Schermen - Ruggero',
872 'description': 'Achter de schermen met Ruggero',
873 'timestamp': 1435133761,
874 'upload_date': '20150624',
875 'uploader_id': 'echojecka',
878 # Eagle.Platform embed (generic URL)
880 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
884 'title': 'Навальный вышел на свободу',
885 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
886 'thumbnail': 're:^https?://.*\.jpg$',
892 # ClipYou (Eagle.Platform) embed (custom URL)
894 'url': 'http://muz-tv.ru/play/7129/',
898 'title': "'O Sole Mio",
899 'thumbnail': 're:^https?://.*\.jpg$',
906 'url': 'http://muz-tv.ru/kinozal/view/7400/',
910 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
911 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
912 'thumbnail': 're:^https?://.*\.jpg$',
919 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
923 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
924 'thumbnail': 're:^https?://.*\.png$',
930 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
931 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
935 'title': 'Facebook Creates "On This Day" | Crunch Report',
940 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
944 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
949 # Crooks and Liars embed
951 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
955 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
956 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
957 'timestamp': 1428207000,
958 'upload_date': '20150405',
959 'uploader': 'Heather',
962 # Crooks and Liars external embed
964 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
966 'id': 'MTE3MjUtMzQ2MzA',
968 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
969 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
970 'timestamp': 1265032391,
971 'upload_date': '20100201',
972 'uploader': 'Heather',
975 # NBC Sports vplayer embed
977 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
979 'id': 'ln7x1qSThw4k',
981 'title': "PFT Live: New leader in the 'new-look' defense",
982 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
987 'url': 'http://www.udn.com/news/story/7314/822787',
988 'md5': 'fd2060e988c326991037b9aff9df21a6',
992 'title': '中一中男師變性 全校師生力挺',
993 'thumbnail': 're:^https?://.*\.jpg$',
998 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1000 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1002 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1003 'title': 'This is what separates the Excel masters from the wannabes',
1004 'duration': 191.933,
1008 'skip_download': True,
1011 # Contains a SMIL manifest
1013 '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',
1017 'title': '+ Football: Lottery Champions League Europe',
1018 'uploader': 'www.telewebion.com',
1022 'skip_download': True,
1025 # Brightcove URL in single quotes
1027 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1028 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1030 'id': '4255764656001',
1032 'title': 'SN Presents: Russell Martin, World Citizen',
1033 '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.',
1034 'uploader': 'Rogers Sportsnet',
1037 # Dailymotion Cloud video
1039 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1040 'md5': '49444254273501a64675a7e68c502681',
1042 'id': '5585de919473990de4bee11b',
1044 'title': 'Le débat',
1045 'thumbnail': 're:^https?://.*\.jpe?g$',
1048 # OnionStudios embed
1050 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1054 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1055 'thumbnail': 're:^https?://.*\.jpe?g$',
1056 'uploader': 'ClickHole',
1057 'uploader_id': 'clickhole',
1062 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1064 'id': '74849a00-85a9-11e1-9660-123139220831',
1066 'title': '#whilewewatch',
1069 # AdobeTVVideo embed
1071 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1072 'md5': '43662b577c018ad707a63766462b1e87',
1076 'title': 'New experience with Acrobat DC',
1077 'description': 'New experience with Acrobat DC',
1078 'duration': 248.667,
1081 # ScreenwaveMedia embed
1083 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1084 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1086 'id': 'cinemasnob-55d26273809dd',
1088 'title': 'cinemasnob',
1091 # BrightcoveInPageEmbed embed
1093 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1095 'id': '4238694884001',
1097 'title': 'Tabletop: Dread, Last Thoughts',
1098 'description': 'Tabletop: Dread, Last Thoughts',
1102 # JWPlayer with M3U8
1104 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1108 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1109 'uploader': 'ren.tv',
1113 'skip_download': True,
1116 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1117 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1119 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1121 'id': '4785848093001',
1123 'title': 'The Cardinal Pell Interview',
1124 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1125 'uploader': 'GlobeCast Australia - GlobeStream',
1129 'skip_download': True,
1132 # Another form of arte.tv embed
1134 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1135 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1137 'id': '030273-562_PLUS7-F',
1139 'title': 'ARTE Reportage - Nulle part, en France',
1140 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1141 'upload_date': '20160409',
1146 'url': 'http://www.wykop.pl/link/3088787/',
1147 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1149 'id': '874_1459135191',
1151 'title': 'Man shows poor quality of new apartment building',
1152 'description': 'The wall is like a sand pile.',
1153 'uploader': 'Lake8737',
1158 def report_following_redirect(self, new_url):
1159 """Report information extraction."""
1160 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1162 def _extract_rss(self, url, video_id, doc):
1163 playlist_title = doc.find('./channel/title').text
1164 playlist_desc_el = doc.find('./channel/description')
1165 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1168 for it in doc.findall('./channel/item'):
1169 next_url = xpath_text(it, 'link', fatal=False)
1171 enclosure_nodes = it.findall('./enclosure')
1172 for e in enclosure_nodes:
1173 next_url = e.attrib.get('url')
1183 'title': it.find('title').text,
1187 '_type': 'playlist',
1189 'title': playlist_title,
1190 'description': playlist_desc,
1194 def _extract_camtasia(self, url, video_id, webpage):
1195 """ Returns None if no camtasia video can be found. """
1197 camtasia_cfg = self._search_regex(
1198 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1199 webpage, 'camtasia configuration file', default=None)
1200 if camtasia_cfg is None:
1203 title = self._html_search_meta('DC.title', webpage, fatal=True)
1205 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1206 camtasia_cfg = self._download_xml(
1207 camtasia_url, video_id,
1208 note='Downloading camtasia configuration',
1209 errnote='Failed to download camtasia configuration')
1210 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1213 for n in fileset_node.getchildren():
1214 url_n = n.find('./uri')
1219 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1220 'title': '%s - %s' % (title, n.tag),
1221 'url': compat_urlparse.urljoin(url, url_n.text),
1222 'duration': float_or_none(n.find('./duration').text),
1226 '_type': 'playlist',
1231 def _real_extract(self, url):
1232 if url.startswith('//'):
1235 'url': self.http_scheme() + url,
1238 parsed_url = compat_urlparse.urlparse(url)
1239 if not parsed_url.scheme:
1240 default_search = self._downloader.params.get('default_search')
1241 if default_search is None:
1242 default_search = 'fixup_error'
1244 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1246 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1247 return self.url_result('http://' + url)
1248 elif default_search != 'fixup_error':
1249 if default_search == 'auto_warning':
1250 if re.match(r'^(?:url|URL)$', url):
1251 raise ExtractorError(
1252 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1255 self._downloader.report_warning(
1256 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1257 return self.url_result('ytsearch:' + url)
1259 if default_search in ('error', 'fixup_error'):
1260 raise ExtractorError(
1261 '%r is not a valid URL. '
1262 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1263 % (url, url), expected=True)
1265 if ':' not in default_search:
1266 default_search += ':'
1267 return self.url_result(default_search + url)
1269 url, smuggled_data = unsmuggle_url(url)
1270 force_videoid = None
1271 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1272 if smuggled_data and 'force_videoid' in smuggled_data:
1273 force_videoid = smuggled_data['force_videoid']
1274 video_id = force_videoid
1276 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1278 self.to_screen('%s: Requesting header' % video_id)
1280 head_req = HEADRequest(url)
1281 head_response = self._request_webpage(
1283 note=False, errnote='Could not send HEAD request to %s' % url,
1286 if head_response is not False:
1287 # Check for redirect
1288 new_url = head_response.geturl()
1290 self.report_following_redirect(new_url)
1292 new_url = smuggle_url(
1293 new_url, {'force_videoid': force_videoid})
1294 return self.url_result(new_url)
1296 full_response = None
1297 if head_response is False:
1298 request = sanitized_Request(url)
1299 request.add_header('Accept-Encoding', '*')
1300 full_response = self._request_webpage(request, video_id)
1301 head_response = full_response
1305 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1306 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1309 # Check for direct link to a video
1310 content_type = head_response.headers.get('Content-Type', '').lower()
1311 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1313 format_id = m.group('format_id')
1314 if format_id.endswith('mpegurl'):
1315 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1316 elif format_id == 'f4m':
1317 formats = self._extract_f4m_formats(url, video_id)
1320 'format_id': m.group('format_id'),
1322 'vcodec': 'none' if m.group('type') == 'audio' else None
1324 info_dict['direct'] = True
1325 self._sort_formats(formats)
1326 info_dict['formats'] = formats
1329 if not self._downloader.params.get('test', False) and not is_intentional:
1330 force = self._downloader.params.get('force_generic_extractor', False)
1331 self._downloader.report_warning(
1332 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1334 if not full_response:
1335 request = sanitized_Request(url)
1336 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1337 # making it impossible to download only chunk of the file (yet we need only 512kB to
1338 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1339 # that will always result in downloading the whole file that is not desirable.
1340 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1341 # to accept raw bytes and being able to download only a chunk.
1342 # It may probably better to solve this by checking Content-Type for application/octet-stream
1343 # after HEAD request finishes, but not sure if we can rely on this.
1344 request.add_header('Accept-Encoding', '*')
1345 full_response = self._request_webpage(request, video_id)
1347 first_bytes = full_response.read(512)
1349 # Is it an M3U playlist?
1350 if first_bytes.startswith(b'#EXTM3U'):
1351 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1352 self._sort_formats(info_dict['formats'])
1355 # Maybe it's a direct link to a video?
1356 # Be careful not to download the whole thing!
1357 if not is_html(first_bytes):
1358 self._downloader.report_warning(
1359 'URL could be a direct video link, returning it as such.')
1366 webpage = self._webpage_read_content(
1367 full_response, url, video_id, prefix=first_bytes)
1369 self.report_extraction(video_id)
1371 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1373 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1374 if doc.tag == 'rss':
1375 return self._extract_rss(url, video_id, doc)
1376 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1377 smil = self._parse_smil(doc, url, video_id)
1378 self._sort_formats(smil['formats'])
1380 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1381 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1382 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1383 info_dict['formats'] = self._parse_mpd_formats(
1384 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1385 self._sort_formats(info_dict['formats'])
1387 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1388 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1389 self._sort_formats(info_dict['formats'])
1391 except compat_xml_parse_error:
1394 # Is it a Camtasia project?
1395 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1396 if camtasia_res is not None:
1399 # Sometimes embedded video player is hidden behind percent encoding
1400 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1401 # Unescaping the whole page allows to handle those cases in a generic way
1402 webpage = compat_urllib_parse_unquote(webpage)
1404 # it's tempting to parse this further, but you would
1405 # have to take into account all the variations like
1406 # Video Title - Site Name
1407 # Site Name | Video Title
1408 # Video Title - Tagline | Site Name
1409 # and so on and so forth; it's just not practical
1410 video_title = self._html_search_regex(
1411 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1414 # Try to detect age limit automatically
1415 age_limit = self._rta_search(webpage)
1416 # And then there are the jokers who advertise that they use RTA,
1417 # but actually don't.
1418 AGE_LIMIT_MARKERS = [
1419 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1421 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1424 # video uploader is domain name
1425 video_uploader = self._search_regex(
1426 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1429 def _playlist_from_matches(matches, getter=None, ie=None):
1431 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1433 return self.playlist_result(
1434 urlrs, playlist_id=video_id, playlist_title=video_title)
1436 # Look for Brightcove Legacy Studio embeds
1437 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1439 self.to_screen('Brightcove video detected.')
1442 'url': smuggle_url(bc_url, {'Referer': url}),
1443 'ie_key': 'BrightcoveLegacy'
1444 } for bc_url in bc_urls]
1447 '_type': 'playlist',
1448 'title': video_title,
1453 # Look for Brightcove New Studio embeds
1454 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1456 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1458 # Look for embedded rtl.nl player
1459 matches = re.findall(
1460 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1463 return _playlist_from_matches(matches, ie='RtlNl')
1465 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1466 if vimeo_url is not None:
1467 return self.url_result(vimeo_url)
1469 vid_me_embed_url = self._search_regex(
1470 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1471 webpage, 'vid.me embed', default=None)
1472 if vid_me_embed_url is not None:
1473 return self.url_result(vid_me_embed_url, 'Vidme')
1475 # Look for embedded YouTube player
1476 matches = re.findall(r'''(?x)
1485 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1489 return _playlist_from_matches(
1490 matches, lambda m: unescapeHTML(m[1]))
1492 # Look for lazyYT YouTube embed
1493 matches = re.findall(
1494 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1496 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1498 # Look for embedded Dailymotion player
1499 matches = re.findall(
1500 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1502 return _playlist_from_matches(
1503 matches, lambda m: unescapeHTML(m[1]))
1505 # Look for embedded Dailymotion playlist player (#3822)
1507 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1509 playlists = re.findall(
1510 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1512 return _playlist_from_matches(
1513 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1515 # Look for embedded Wistia player
1517 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1519 embed_url = self._proto_relative_url(
1520 unescapeHTML(match.group('url')))
1522 '_type': 'url_transparent',
1525 'uploader': video_uploader,
1526 'title': video_title,
1530 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1533 '_type': 'url_transparent',
1534 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1536 'uploader': video_uploader,
1537 'title': video_title,
1538 'id': match.group('id')
1541 # Look for SVT player
1542 svt_url = SVTIE._extract_url(webpage)
1544 return self.url_result(svt_url, 'SVT')
1546 # Look for embedded condenast player
1547 matches = re.findall(
1548 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1552 '_type': 'playlist',
1555 'ie_key': 'CondeNast',
1557 } for ma in matches],
1558 'title': video_title,
1562 # Look for Bandcamp pages with custom domain
1563 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1564 if mobj is not None:
1565 burl = unescapeHTML(mobj.group(1))
1566 # Don't set the extractor because it can be a track url or an album
1567 return self.url_result(burl)
1569 # Look for embedded Vevo player
1571 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1572 if mobj is not None:
1573 return self.url_result(mobj.group('url'))
1575 # Look for embedded Viddler player
1577 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1579 if mobj is not None:
1580 return self.url_result(mobj.group('url'))
1582 # Look for NYTimes player
1584 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1586 if mobj is not None:
1587 return self.url_result(mobj.group('url'))
1589 # Look for Libsyn player
1591 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1592 if mobj is not None:
1593 return self.url_result(mobj.group('url'))
1595 # Look for Ooyala videos
1596 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1597 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1598 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1599 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1600 if mobj is not None:
1601 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1603 # Look for multiple Ooyala embeds on SBN network websites
1604 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1605 if mobj is not None:
1606 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1608 return _playlist_from_matches(
1609 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1611 # Look for Aparat videos
1612 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1613 if mobj is not None:
1614 return self.url_result(mobj.group(1), 'Aparat')
1616 # Look for MPORA videos
1617 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1618 if mobj is not None:
1619 return self.url_result(mobj.group(1), 'Mpora')
1621 # Look for embedded NovaMov-based player
1623 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1624 (?P<url>http://(?:(?:embed|www)\.)?
1626 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1627 videoweed\.(?:es|com)|
1628 movshare\.(?:net|sx|ag)|
1629 divxstage\.(?:eu|net|ch|co|at|ag))
1630 /embed\.php.+?)\1''', webpage)
1631 if mobj is not None:
1632 return self.url_result(mobj.group('url'))
1634 # Look for embedded Facebook player
1636 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1637 if mobj is not None:
1638 return self.url_result(mobj.group('url'), 'Facebook')
1640 # Look for embedded VK player
1641 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1642 if mobj is not None:
1643 return self.url_result(mobj.group('url'), 'VK')
1645 # Look for embedded Odnoklassniki player
1646 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1647 if mobj is not None:
1648 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1650 # Look for embedded ivi player
1651 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1652 if mobj is not None:
1653 return self.url_result(mobj.group('url'), 'Ivi')
1655 # Look for embedded Huffington Post player
1657 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1658 if mobj is not None:
1659 return self.url_result(mobj.group('url'), 'HuffPost')
1662 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1663 if mobj is not None:
1664 return self.url_result(mobj.group('url'))
1665 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1666 if mobj is not None:
1667 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1669 # Look for funnyordie embed
1670 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1672 return _playlist_from_matches(
1673 matches, getter=unescapeHTML, ie='FunnyOrDie')
1675 # Look for BBC iPlayer embed
1676 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1678 return _playlist_from_matches(matches, ie='BBCCoUk')
1680 # Look for embedded RUTV player
1681 rutv_url = RUTVIE._extract_url(webpage)
1683 return self.url_result(rutv_url, 'RUTV')
1685 # Look for embedded TVC player
1686 tvc_url = TVCIE._extract_url(webpage)
1688 return self.url_result(tvc_url, 'TVC')
1690 # Look for embedded SportBox player
1691 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1693 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1695 # Look for embedded PornHub player
1696 pornhub_url = PornHubIE._extract_url(webpage)
1698 return self.url_result(pornhub_url, 'PornHub')
1700 # Look for embedded XHamster player
1701 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1703 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1705 # Look for embedded TNAFlixNetwork player
1706 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1708 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1710 # Look for embedded Tvigle player
1712 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1713 if mobj is not None:
1714 return self.url_result(mobj.group('url'), 'Tvigle')
1716 # Look for embedded TED player
1718 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1719 if mobj is not None:
1720 return self.url_result(mobj.group('url'), 'TED')
1722 # Look for embedded Ustream videos
1724 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1725 if mobj is not None:
1726 return self.url_result(mobj.group('url'), 'Ustream')
1728 # Look for embedded arte.tv player
1730 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1732 if mobj is not None:
1733 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1735 # Look for embedded francetv player
1737 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1739 if mobj is not None:
1740 return self.url_result(mobj.group('url'))
1742 # Look for embedded smotri.com player
1743 smotri_url = SmotriIE._extract_url(webpage)
1745 return self.url_result(smotri_url, 'Smotri')
1747 # Look for embedded Myvi.ru player
1748 myvi_url = MyviIE._extract_url(webpage)
1750 return self.url_result(myvi_url)
1752 # Look for embedded soundcloud player
1754 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1756 if mobj is not None:
1757 url = unescapeHTML(mobj.group('url'))
1758 return self.url_result(url)
1760 # Look for embedded vulture.com player
1762 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1764 if mobj is not None:
1765 url = unescapeHTML(mobj.group('url'))
1766 return self.url_result(url, ie='Vulture')
1768 # Look for embedded mtvservices player
1769 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1771 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1773 # Look for embedded yahoo player
1775 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1777 if mobj is not None:
1778 return self.url_result(mobj.group('url'), 'Yahoo')
1780 # Look for embedded sbs.com.au player
1784 <meta\s+property="og:video"\s+content=|
1787 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1789 if mobj is not None:
1790 return self.url_result(mobj.group('url'), 'SBS')
1792 # Look for embedded Cinchcast player
1794 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1796 if mobj is not None:
1797 return self.url_result(mobj.group('url'), 'Cinchcast')
1800 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1804 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1806 if mobj is not None:
1807 return self.url_result(mobj.group('url'), 'MLB')
1810 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1812 if mobj is not None:
1813 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1816 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1818 if mobj is not None:
1819 return self.url_result(mobj.group('url'), 'Livestream')
1821 # Look for Zapiks embed
1823 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1824 if mobj is not None:
1825 return self.url_result(mobj.group('url'), 'Zapiks')
1827 # Look for Kaltura embeds
1828 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1829 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))
1830 if mobj is not None:
1831 return self.url_result(smuggle_url(
1832 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1833 {'source_url': url}), 'Kaltura')
1835 # Look for Eagle.Platform embeds
1837 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1838 if mobj is not None:
1839 return self.url_result(mobj.group('url'), 'EaglePlatform')
1841 # Look for ClipYou (uses Eagle.Platform) embeds
1843 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1844 if mobj is not None:
1845 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1847 # Look for Pladform embeds
1848 pladform_url = PladformIE._extract_url(webpage)
1850 return self.url_result(pladform_url)
1852 # Look for Videomore embeds
1853 videomore_url = VideomoreIE._extract_url(webpage)
1855 return self.url_result(videomore_url)
1857 # Look for Playwire embeds
1859 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1860 if mobj is not None:
1861 return self.url_result(mobj.group('url'))
1863 # Look for 5min embeds
1865 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1866 if mobj is not None:
1867 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1869 # Look for Crooks and Liars embeds
1871 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1872 if mobj is not None:
1873 return self.url_result(mobj.group('url'))
1875 # Look for NBC Sports VPlayer embeds
1876 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1878 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1880 # Look for Google Drive embeds
1881 google_drive_url = GoogleDriveIE._extract_url(webpage)
1882 if google_drive_url:
1883 return self.url_result(google_drive_url, 'GoogleDrive')
1885 # Look for UDN embeds
1887 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1888 if mobj is not None:
1889 return self.url_result(
1890 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1892 # Look for Senate ISVP iframe
1893 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1895 return self.url_result(senate_isvp_url, 'SenateISVP')
1897 # Look for Dailymotion Cloud videos
1898 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1900 return self.url_result(dmcloud_url, 'DailymotionCloud')
1902 # Look for OnionStudios embeds
1903 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1904 if onionstudios_url:
1905 return self.url_result(onionstudios_url)
1907 # Look for SnagFilms embeds
1908 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1910 return self.url_result(snagfilms_url)
1912 # Look for JWPlatform embeds
1913 jwplatform_url = JWPlatformIE._extract_url(webpage)
1915 return self.url_result(jwplatform_url, 'JWPlatform')
1917 # Look for ScreenwaveMedia embeds
1918 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1919 if mobj is not None:
1920 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1922 # Look for Digiteka embeds
1923 digiteka_url = DigitekaIE._extract_url(webpage)
1925 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1927 # Look for Limelight embeds
1928 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1932 'Channel': 'channel',
1933 'ChannelList': 'channel_list',
1935 return self.url_result('limelight:%s:%s' % (
1936 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1938 # Look for AdobeTVVideo embeds
1940 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1942 if mobj is not None:
1943 return self.url_result(
1944 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1947 # Look for Vine embeds
1949 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1951 if mobj is not None:
1952 return self.url_result(
1953 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1955 # Look for Instagram embeds
1956 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
1957 if instagram_embed_url is not None:
1958 return self.url_result(instagram_embed_url, InstagramIE.ie_key())
1960 # Look for LiveLeak embeds
1961 liveleak_url = LiveLeakIE._extract_url(webpage)
1963 return self.url_result(liveleak_url, 'LiveLeak')
1965 def check_video(vurl):
1966 if YoutubeIE.suitable(vurl):
1968 vpath = compat_urlparse.urlparse(vurl).path
1969 vext = determine_ext(vpath)
1970 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1972 def filter_video(urls):
1973 return list(filter(check_video, urls))
1975 # Start with something easy: JW Player in SWFObject
1976 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1978 # Look for gorilla-vid style embedding
1979 found = filter_video(re.findall(r'''(?sx)
1983 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1986 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1988 # Broaden the search a little bit
1989 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1991 # Broaden the findall a little bit: JWPlayer JS loader
1992 found = filter_video(re.findall(
1993 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1996 found = filter_video(re.findall(r'''(?xs)
1997 flowplayer\("[^"]+",\s*
1999 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2000 ["']?url["']?\s*:\s*["']([^"']+)["']
2005 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2007 # Try to find twitter cards info
2008 found = filter_video(re.findall(
2009 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2011 # We look for Open Graph info:
2012 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2013 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2014 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2015 if m_video_type is not None:
2016 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2019 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2021 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2023 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2024 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2027 # Look also in Refresh HTTP header
2028 refresh_header = head_response.headers.get('Refresh')
2030 # In python 2 response HTTP headers are bytestrings
2031 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2032 refresh_header = refresh_header.decode('iso-8859-1')
2033 found = re.search(REDIRECT_REGEX, refresh_header)
2035 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2036 self.report_following_redirect(new_url)
2042 raise UnsupportedError(url)
2045 for video_url in found:
2046 video_url = video_url.replace('\\/', '/')
2047 video_url = compat_urlparse.urljoin(url, video_url)
2048 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2050 # Sometimes, jwplayer extraction will result in a YouTube URL
2051 if YoutubeIE.suitable(video_url):
2052 entries.append(self.url_result(video_url, 'Youtube'))
2055 # here's a fun little line of code for you:
2056 video_id = os.path.splitext(video_id)[0]
2060 'uploader': video_uploader,
2061 'title': video_title,
2062 'age_limit': age_limit,
2065 ext = determine_ext(video_url)
2067 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2069 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2071 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2073 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2075 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2077 entry_info_dict['url'] = video_url
2079 if entry_info_dict.get('formats'):
2080 self._sort_formats(entry_info_dict['formats'])
2082 entries.append(entry_info_dict)
2084 if len(entries) == 1:
2087 for num, e in enumerate(entries, start=1):
2088 # 'url' results don't have a title
2089 if e.get('title') is not None:
2090 e['title'] = '%s (%d)' % (e['title'], num)
2092 '_type': 'playlist',