3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
11 compat_urllib_parse_unquote,
12 compat_urllib_request,
14 compat_xml_parse_error,
32 from .brightcove import BrightcoveIE
33 from .nbc import NBCSportsVPlayerIE
34 from .ooyala import OoyalaIE
35 from .rutv import RUTVIE
36 from .tvc import TVCIE
37 from .sportbox import SportBoxEmbedIE
38 from .smotri import SmotriIE
39 from .myvi import MyviIE
40 from .condenast import CondeNastIE
41 from .udn import UDNEmbedIE
42 from .senateisvp import SenateISVPIE
43 from .bliptv import BlipTVIE
44 from .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
49 from .onionstudios import OnionStudiosIE
50 from .snagfilms import SnagFilmsEmbedIE
53 class GenericIE(InfoExtractor):
54 IE_DESC = 'Generic downloader that works on some sites'
58 # Direct link to a video
60 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
61 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
66 'upload_date': '20100513',
69 # Direct link to media delivered compressed (until Accept-Encoding is *)
71 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
72 'md5': '128c42e68b13950268b648275386fc74',
74 'id': 'FictionJunction-Parallel_Hearts',
76 'title': 'FictionJunction-Parallel_Hearts',
77 'upload_date': '20140522',
79 'expected_warnings': [
80 'URL could be a direct video link, returning it as such.'
83 # Direct download with broken HEAD
85 'url': 'http://ai-radio.org:8000/radio.opus',
92 'skip_download': True, # infinite live stream
94 'expected_warnings': [
95 r'501.*Not Implemented'
98 # Direct link with incorrect MIME type
100 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
101 'md5': '4ccbebe5f36706d85221f204d7eb5913',
103 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
104 'id': '5_Lennart_Poettering_-_Systemd',
106 'title': '5_Lennart_Poettering_-_Systemd',
107 'upload_date': '20141120',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
115 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
117 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'title': 'Zero Punctuation',
119 'description': 're:.*groundbreaking video review series.*'
121 'playlist_mincount': 11,
123 # RSS feed with enclosure
125 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
127 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
129 'upload_date': '20150228',
130 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
133 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
135 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
139 'title': 'Automatics, robotics and biocybernetics',
140 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
141 'formats': 'mincount:16',
142 'subtitles': 'mincount:1',
145 'force_generic_extractor': True,
146 'skip_download': True,
149 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
151 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
156 'formats': 'mincount:1',
159 'skip_download': True,
162 # SMIL from https://www.restudy.dk/video/play/id/1637
164 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
168 'title': 'video_1637',
169 'formats': 'mincount:3',
172 'skip_download': True,
175 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
177 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
179 'id': 'smil-service',
181 'title': 'smil-service',
182 'formats': 'mincount:1',
185 'skip_download': True,
188 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
190 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
194 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
195 'formats': 'mincount:3',
198 'skip_download': True,
203 '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',
207 'upload_date': '20130224',
208 'uploader_id': 'TheVerge',
209 'description': 're:^Chris Ziegler takes a look at the\.*',
210 'uploader': 'The Verge',
211 'title': 'First Firefox OS phones side-by-side',
214 'skip_download': False,
218 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
219 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
221 'id': '13601338388002',
223 'uploader': 'www.hodiho.fr',
224 'title': 'R\u00e9gis plante sa Jeep',
227 # bandcamp page with custom domain
229 'add_ie': ['Bandcamp'],
230 'url': 'http://bronyrock.com/track/the-pony-mash',
234 'title': 'The Pony Mash',
235 'uploader': 'M_Pallante',
237 'skip': 'There is a limit of 200 free downloads / month for the test song',
239 # embedded brightcove video
240 # it also tests brightcove videos that need to set the 'Referer' in the
243 'add_ie': ['Brightcove'],
244 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
246 'id': '2765128793001',
248 'title': 'Le cours de bourse : l’analyse technique',
249 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
250 'uploader': 'BFM BUSINESS',
253 'skip_download': True,
257 # https://github.com/rg3/youtube-dl/issues/2253
258 'url': 'http://bcove.me/i6nfkrc3',
259 'md5': '0ba9446db037002366bab3b3eb30c88c',
261 'id': '3101154703001',
263 'title': 'Still no power',
264 'uploader': 'thestar.com',
265 '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.',
267 'add_ie': ['Brightcove'],
270 'url': 'http://www.championat.com/video/football/v/87/87499.html',
271 'md5': 'fb973ecf6e4a78a67453647444222983',
273 'id': '3414141473001',
275 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
276 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
277 'uploader': 'Championat',
281 # https://github.com/rg3/youtube-dl/issues/3541
282 'add_ie': ['Brightcove'],
283 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
285 'id': '3866516442001',
287 'title': 'Leer mij vrouwen kennen: Aflevering 1',
288 'description': 'Leer mij vrouwen kennen: Aflevering 1',
289 'uploader': 'SBS Broadcasting',
291 'skip': 'Restricted to Netherlands',
293 'skip_download': True, # m3u8 download
298 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
299 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
301 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
303 'title': '2cc213299525360.mov', # that's what we get
305 'add_ie': ['Ooyala'],
307 # multiple ooyala embeds on SBN network websites
309 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
311 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
312 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
314 'playlist_mincount': 3,
316 'skip_download': True,
318 'add_ie': ['Ooyala'],
322 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
326 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
327 'upload_date': '20140225',
328 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
329 'uploader': 'Tested',
330 'uploader_id': 'testedcom',
332 # No need to test YoutubeIE here
334 'skip_download': True,
339 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
343 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
344 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
349 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
353 'title': 'Охотское море стало целиком российским',
354 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
358 'skip_download': True,
363 '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/',
367 'title': 'Дошкольное воспитание',
372 'url': 'http://www.vestifinance.ru/articles/25753',
375 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
380 'title': 'Госзаказ. День 3',
386 'title': 'Госзаказ. День 2',
392 'title': 'Госзаказ. День 1',
398 'skip_download': True,
403 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
405 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
407 'title': 'Ужастики, русский трейлер (2015)',
408 'thumbnail': 're:^https?://.*\.jpg$',
414 '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',
417 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
419 'playlist_mincount': 7,
423 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
424 'md5': '65fdff94098e4a607385a60c5177c638',
428 'title': 'Hidden miracles of the natural world',
429 'uploader': 'Louie Schwartzberg',
430 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
433 # Embeded Ustream video
435 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
436 'md5': '27b99cdb639c9b12a79bca876a073417',
440 'uploader': 'AU SPA: The NSA and Privacy',
441 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
444 # nowvideo embed hidden behind percent encoding
446 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
447 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
449 'id': '06e53103ca9aa',
451 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
452 'description': 'No description',
457 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
458 'md5': '7653032cbb25bf6c80d80f217055fa43',
460 'id': '048195-004_PLUS7-F',
463 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
464 'upload_date': '20140320',
467 'skip_download': 'Requires rtmpdump'
472 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
476 'title': 'Alcaline, le concert avec Calogero',
477 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
478 'upload_date': '20150226',
479 'timestamp': 1424989860,
484 'skip_download': True,
486 'expected_warnings': [
492 'url': 'http://www.wired.com/2014/04/honda-asimo/',
493 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
495 'id': '53501be369702d3275860000',
497 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
502 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
503 'md5': '441aeeb82eb72c422c7f14ec533999cd',
505 'id': 'k2mm4bCdJ6CQ2i7c8o2',
507 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
510 'add_ie': ['Dailymotion'],
514 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
518 'title': 'The NBL Auction 2014',
519 'uploader': 'BADMINTON England',
520 'uploader_id': 'BADMINTONEvents',
521 'upload_date': '20140603',
522 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
524 'add_ie': ['Youtube'],
526 'skip_download': True,
531 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
532 'md5': '35727f82f58c76d996fc188f9755b0d5',
534 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
537 'description': 'Mario\'s life in the fast lane has never looked so good.',
540 # YouTube embed via <data-embed-url="">
542 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
546 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
547 'uploader': 'Gameloft',
548 'uploader_id': 'gameloft',
549 'upload_date': '20140828',
550 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
553 'skip_download': True,
558 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
560 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
562 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
563 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
568 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
570 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
571 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
577 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
582 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
583 'md5': '9d65602bf31c6e20014319c7d07fba27',
585 'id': '5123ea6d5e5a7',
588 'uploader': 'www.handjobhub.com',
589 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
592 # Multiple brightcove videos
593 # https://github.com/rg3/youtube-dl/issues/2283
595 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
597 'id': 'always-never',
598 'title': 'Always / Never - The New Yorker',
602 'extract_flat': False,
603 'skip_download': True,
608 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
609 'md5': '96f09a37e44da40dd083e12d9a683327',
613 'title': 'Ump changes call to ball',
614 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
616 'timestamp': 1401537900,
617 'upload_date': '20140531',
618 'thumbnail': 're:^https?://.*\.jpg$',
623 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
624 'md5': '8788b683c777a5cf25621eaf286d0c23',
628 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
630 'filesize': 182808282,
631 'uploader': 'education-portal.com',
635 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
636 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
640 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
642 'uploader': 'thoughtworks.wistia.com',
647 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
651 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
652 'uploader': 'Sophos Security',
653 'title': 'Chet Chat 171 - Oct 29, 2014',
654 'upload_date': '20141029',
659 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
663 'upload_date': '20141112',
664 'title': 'Rosetta #CometLanding webcast HL 10',
669 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
672 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
674 'playlist_mincount': 2,
678 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
682 'upload_date': '20141126',
683 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
688 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
690 'id': '730m_DandD_1901_512k',
692 'uploader': 'www.abc.net.au',
693 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
696 # embedded viddler video
698 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
702 'uploader': 'deadspin',
703 'title': 'WALL-TO-GORTAT',
704 'timestamp': 1422285291,
705 'upload_date': '20150126',
707 'add_ie': ['Viddler'],
711 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
715 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
716 'description': 'md5:601cb790edd05908957dae8aaa866465',
717 'upload_date': '20150220',
722 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
726 'upload_date': '20150212',
727 'uploader': 'The National Archives UK',
728 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
729 'uploader_id': 'NationalArchives08',
730 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
735 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
736 'playlist_mincount': 5,
738 'id': 'aanslagen-kopenhagen',
739 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
744 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
748 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
753 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
757 'upload_date': '20150226',
758 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
760 'title': 'John Carlson Postgame 2/25/15',
763 # Kaltura embed (different embed code)
765 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
769 'upload_date': '20150127',
770 'uploader_id': 'PremierMedia',
772 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
775 # Eagle.Platform embed (generic URL)
777 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
781 'title': 'Навальный вышел на свободу',
782 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
783 'thumbnail': 're:^https?://.*\.jpg$',
789 # ClipYou (Eagle.Platform) embed (custom URL)
791 'url': 'http://muz-tv.ru/play/7129/',
795 'title': "'O Sole Mio",
796 'thumbnail': 're:^https?://.*\.jpg$',
803 'url': 'http://muz-tv.ru/kinozal/view/7400/',
807 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
808 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
809 'thumbnail': 're:^https?://.*\.jpg$',
816 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
820 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
821 'thumbnail': 're:^https?://.*\.png$',
827 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
828 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
832 'title': 'Facebook Creates "On This Day" | Crunch Report',
837 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
841 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
846 # Crooks and Liars embed
848 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
852 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
853 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
854 'timestamp': 1428207000,
855 'upload_date': '20150405',
856 'uploader': 'Heather',
859 # Crooks and Liars external embed
861 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
863 'id': 'MTE3MjUtMzQ2MzA',
865 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
866 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
867 'timestamp': 1265032391,
868 'upload_date': '20100201',
869 'uploader': 'Heather',
872 # NBC Sports vplayer embed
874 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
876 'id': 'ln7x1qSThw4k',
878 'title': "PFT Live: New leader in the 'new-look' defense",
879 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
884 'url': 'http://www.udn.com/news/story/7314/822787',
885 'md5': 'fd2060e988c326991037b9aff9df21a6',
889 'title': '中一中男師變性 全校師生力挺',
890 'thumbnail': 're:^https?://.*\.jpg$',
895 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
897 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
899 'description': 'VIDEO: Index/Match versus VLOOKUP.',
900 'title': 'This is what separates the Excel masters from the wannabes',
904 'skip_download': True,
907 # Contains a SMIL manifest
909 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
913 'title': '+ Football: Lottery Champions League Europe',
914 'uploader': 'www.telewebion.com',
918 'skip_download': True,
921 # Brightcove URL in single quotes
923 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
924 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
926 'id': '4255764656001',
928 'title': 'SN Presents: Russell Martin, World Citizen',
929 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
930 'uploader': 'Rogers Sportsnet',
933 # Dailymotion Cloud video
935 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
936 'md5': '49444254273501a64675a7e68c502681',
938 'id': '5585de919473990de4bee11b',
941 'thumbnail': 're:^https?://.*\.jpe?g$',
946 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
950 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
951 'thumbnail': 're:^https?://.*\.jpe?g$',
952 'uploader': 'ClickHole',
953 'uploader_id': 'clickhole',
958 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
960 'id': '74849a00-85a9-11e1-9660-123139220831',
962 'title': '#whilewewatch',
967 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
968 'md5': '43662b577c018ad707a63766462b1e87',
972 'title': 'New experience with Acrobat DC',
973 'description': 'New experience with Acrobat DC',
979 def report_following_redirect(self, new_url):
980 """Report information extraction."""
981 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
983 def _extract_rss(self, url, video_id, doc):
984 playlist_title = doc.find('./channel/title').text
985 playlist_desc_el = doc.find('./channel/description')
986 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
989 for it in doc.findall('./channel/item'):
990 next_url = xpath_text(it, 'link', fatal=False)
992 enclosure_nodes = it.findall('./enclosure')
993 for e in enclosure_nodes:
994 next_url = e.attrib.get('url')
1004 'title': it.find('title').text,
1008 '_type': 'playlist',
1010 'title': playlist_title,
1011 'description': playlist_desc,
1015 def _extract_camtasia(self, url, video_id, webpage):
1016 """ Returns None if no camtasia video can be found. """
1018 camtasia_cfg = self._search_regex(
1019 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1020 webpage, 'camtasia configuration file', default=None)
1021 if camtasia_cfg is None:
1024 title = self._html_search_meta('DC.title', webpage, fatal=True)
1026 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1027 camtasia_cfg = self._download_xml(
1028 camtasia_url, video_id,
1029 note='Downloading camtasia configuration',
1030 errnote='Failed to download camtasia configuration')
1031 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1034 for n in fileset_node.getchildren():
1035 url_n = n.find('./uri')
1040 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1041 'title': '%s - %s' % (title, n.tag),
1042 'url': compat_urlparse.urljoin(url, url_n.text),
1043 'duration': float_or_none(n.find('./duration').text),
1047 '_type': 'playlist',
1052 def _real_extract(self, url):
1053 if url.startswith('//'):
1056 'url': self.http_scheme() + url,
1059 parsed_url = compat_urlparse.urlparse(url)
1060 if not parsed_url.scheme:
1061 default_search = self._downloader.params.get('default_search')
1062 if default_search is None:
1063 default_search = 'fixup_error'
1065 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1067 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1068 return self.url_result('http://' + url)
1069 elif default_search != 'fixup_error':
1070 if default_search == 'auto_warning':
1071 if re.match(r'^(?:url|URL)$', url):
1072 raise ExtractorError(
1073 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1076 self._downloader.report_warning(
1077 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1078 return self.url_result('ytsearch:' + url)
1080 if default_search in ('error', 'fixup_error'):
1081 raise ExtractorError(
1082 '%r is not a valid URL. '
1083 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1084 % (url, url), expected=True)
1086 if ':' not in default_search:
1087 default_search += ':'
1088 return self.url_result(default_search + url)
1090 url, smuggled_data = unsmuggle_url(url)
1091 force_videoid = None
1092 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1093 if smuggled_data and 'force_videoid' in smuggled_data:
1094 force_videoid = smuggled_data['force_videoid']
1095 video_id = force_videoid
1097 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1099 self.to_screen('%s: Requesting header' % video_id)
1101 head_req = HEADRequest(url)
1102 head_response = self._request_webpage(
1104 note=False, errnote='Could not send HEAD request to %s' % url,
1107 if head_response is not False:
1108 # Check for redirect
1109 new_url = head_response.geturl()
1111 self.report_following_redirect(new_url)
1113 new_url = smuggle_url(
1114 new_url, {'force_videoid': force_videoid})
1115 return self.url_result(new_url)
1117 full_response = None
1118 if head_response is False:
1119 request = compat_urllib_request.Request(url)
1120 request.add_header('Accept-Encoding', '*')
1121 full_response = self._request_webpage(request, video_id)
1122 head_response = full_response
1124 # Check for direct link to a video
1125 content_type = head_response.headers.get('Content-Type', '')
1126 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1128 upload_date = unified_strdate(
1129 head_response.headers.get('Last-Modified'))
1132 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1135 'format_id': m.group('format_id'),
1137 'vcodec': 'none' if m.group('type') == 'audio' else None
1139 'upload_date': upload_date,
1142 if not self._downloader.params.get('test', False) and not is_intentional:
1143 force = self._downloader.params.get('force_generic_extractor', False)
1144 self._downloader.report_warning(
1145 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1147 if not full_response:
1148 request = compat_urllib_request.Request(url)
1149 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1150 # making it impossible to download only chunk of the file (yet we need only 512kB to
1151 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1152 # that will always result in downloading the whole file that is not desirable.
1153 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1154 # to accept raw bytes and being able to download only a chunk.
1155 # It may probably better to solve this by checking Content-Type for application/octet-stream
1156 # after HEAD request finishes, but not sure if we can rely on this.
1157 request.add_header('Accept-Encoding', '*')
1158 full_response = self._request_webpage(request, video_id)
1160 # Maybe it's a direct link to a video?
1161 # Be careful not to download the whole thing!
1162 first_bytes = full_response.read(512)
1163 if not is_html(first_bytes):
1164 self._downloader.report_warning(
1165 'URL could be a direct video link, returning it as such.')
1166 upload_date = unified_strdate(
1167 head_response.headers.get('Last-Modified'))
1170 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1173 'upload_date': upload_date,
1176 webpage = self._webpage_read_content(
1177 full_response, url, video_id, prefix=first_bytes)
1179 self.report_extraction(video_id)
1181 # Is it an RSS feed or a SMIL file?
1183 doc = parse_xml(webpage)
1184 if doc.tag == 'rss':
1185 return self._extract_rss(url, video_id, doc)
1186 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1187 return self._parse_smil(doc, url, video_id)
1188 except compat_xml_parse_error:
1191 # Is it a Camtasia project?
1192 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1193 if camtasia_res is not None:
1196 # Sometimes embedded video player is hidden behind percent encoding
1197 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1198 # Unescaping the whole page allows to handle those cases in a generic way
1199 webpage = compat_urllib_parse_unquote(webpage)
1201 # it's tempting to parse this further, but you would
1202 # have to take into account all the variations like
1203 # Video Title - Site Name
1204 # Site Name | Video Title
1205 # Video Title - Tagline | Site Name
1206 # and so on and so forth; it's just not practical
1207 video_title = self._html_search_regex(
1208 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1211 # Try to detect age limit automatically
1212 age_limit = self._rta_search(webpage)
1213 # And then there are the jokers who advertise that they use RTA,
1214 # but actually don't.
1215 AGE_LIMIT_MARKERS = [
1216 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1218 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1221 # video uploader is domain name
1222 video_uploader = self._search_regex(
1223 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1226 def _playlist_from_matches(matches, getter=None, ie=None):
1228 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1230 return self.playlist_result(
1231 urlrs, playlist_id=video_id, playlist_title=video_title)
1233 # Look for BrightCove:
1234 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1236 self.to_screen('Brightcove video detected.')
1239 'url': smuggle_url(bc_url, {'Referer': url}),
1240 'ie_key': 'Brightcove'
1241 } for bc_url in bc_urls]
1244 '_type': 'playlist',
1245 'title': video_title,
1250 # Look for embedded rtl.nl player
1251 matches = re.findall(
1252 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1255 return _playlist_from_matches(matches, ie='RtlNl')
1257 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1258 if vimeo_url is not None:
1259 return self.url_result(vimeo_url)
1261 vid_me_embed_url = self._search_regex(
1262 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1263 webpage, 'vid.me embed', default=None)
1264 if vid_me_embed_url is not None:
1265 return self.url_result(vid_me_embed_url, 'Vidme')
1267 # Look for embedded YouTube player
1268 matches = re.findall(r'''(?x)
1277 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1281 return _playlist_from_matches(
1282 matches, lambda m: unescapeHTML(m[1]))
1284 # Look for lazyYT YouTube embed
1285 matches = re.findall(
1286 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1288 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1290 # Look for embedded Dailymotion player
1291 matches = re.findall(
1292 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1294 return _playlist_from_matches(
1295 matches, lambda m: unescapeHTML(m[1]))
1297 # Look for embedded Dailymotion playlist player (#3822)
1299 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1301 playlists = re.findall(
1302 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1304 return _playlist_from_matches(
1305 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1307 # Look for embedded Wistia player
1309 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1311 embed_url = self._proto_relative_url(
1312 unescapeHTML(match.group('url')))
1314 '_type': 'url_transparent',
1317 'uploader': video_uploader,
1318 'title': video_title,
1322 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1325 '_type': 'url_transparent',
1326 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1328 'uploader': video_uploader,
1329 'title': video_title,
1330 'id': match.group('id')
1333 # Look for embedded blip.tv player
1334 bliptv_url = BlipTVIE._extract_url(webpage)
1336 return self.url_result(bliptv_url, 'BlipTV')
1338 # Look for SVT player
1339 svt_url = SVTIE._extract_url(webpage)
1341 return self.url_result(svt_url, 'SVT')
1343 # Look for embedded condenast player
1344 matches = re.findall(
1345 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1349 '_type': 'playlist',
1352 'ie_key': 'CondeNast',
1354 } for ma in matches],
1355 'title': video_title,
1359 # Look for Bandcamp pages with custom domain
1360 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1361 if mobj is not None:
1362 burl = unescapeHTML(mobj.group(1))
1363 # Don't set the extractor because it can be a track url or an album
1364 return self.url_result(burl)
1366 # Look for embedded Vevo player
1368 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1369 if mobj is not None:
1370 return self.url_result(mobj.group('url'))
1372 # Look for embedded Viddler player
1374 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1376 if mobj is not None:
1377 return self.url_result(mobj.group('url'))
1379 # Look for NYTimes player
1381 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1383 if mobj is not None:
1384 return self.url_result(mobj.group('url'))
1386 # Look for Libsyn player
1388 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1389 if mobj is not None:
1390 return self.url_result(mobj.group('url'))
1392 # Look for Ooyala videos
1393 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1394 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1395 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1396 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1397 if mobj is not None:
1398 return OoyalaIE._build_url_result(mobj.group('ec'))
1400 # Look for multiple Ooyala embeds on SBN network websites
1401 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1402 if mobj is not None:
1403 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1405 return _playlist_from_matches(
1406 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1408 # Look for Aparat videos
1409 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1410 if mobj is not None:
1411 return self.url_result(mobj.group(1), 'Aparat')
1413 # Look for MPORA videos
1414 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1415 if mobj is not None:
1416 return self.url_result(mobj.group(1), 'Mpora')
1418 # Look for embedded NovaMov-based player
1420 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1421 (?P<url>http://(?:(?:embed|www)\.)?
1423 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1424 videoweed\.(?:es|com)|
1425 movshare\.(?:net|sx|ag)|
1426 divxstage\.(?:eu|net|ch|co|at|ag))
1427 /embed\.php.+?)\1''', webpage)
1428 if mobj is not None:
1429 return self.url_result(mobj.group('url'))
1431 # Look for embedded Facebook player
1433 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1434 if mobj is not None:
1435 return self.url_result(mobj.group('url'), 'Facebook')
1437 # Look for embedded VK player
1438 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1439 if mobj is not None:
1440 return self.url_result(mobj.group('url'), 'VK')
1442 # Look for embedded ivi player
1443 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1444 if mobj is not None:
1445 return self.url_result(mobj.group('url'), 'Ivi')
1447 # Look for embedded Huffington Post player
1449 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1450 if mobj is not None:
1451 return self.url_result(mobj.group('url'), 'HuffPost')
1454 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1455 if mobj is not None:
1456 return self.url_result(mobj.group('url'))
1457 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1458 if mobj is not None:
1459 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1461 # Look for funnyordie embed
1462 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1464 return _playlist_from_matches(
1465 matches, getter=unescapeHTML, ie='FunnyOrDie')
1467 # Look for BBC iPlayer embed
1468 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1470 return _playlist_from_matches(matches, ie='BBCCoUk')
1472 # Look for embedded RUTV player
1473 rutv_url = RUTVIE._extract_url(webpage)
1475 return self.url_result(rutv_url, 'RUTV')
1477 # Look for embedded TVC player
1478 tvc_url = TVCIE._extract_url(webpage)
1480 return self.url_result(tvc_url, 'TVC')
1482 # Look for embedded SportBox player
1483 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1485 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1487 # Look for embedded PornHub player
1488 pornhub_url = PornHubIE._extract_url(webpage)
1490 return self.url_result(pornhub_url, 'PornHub')
1492 # Look for embedded XHamster player
1493 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1495 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1497 # Look for embedded Tvigle player
1499 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1500 if mobj is not None:
1501 return self.url_result(mobj.group('url'), 'Tvigle')
1503 # Look for embedded TED player
1505 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1506 if mobj is not None:
1507 return self.url_result(mobj.group('url'), 'TED')
1509 # Look for embedded Ustream videos
1511 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1512 if mobj is not None:
1513 return self.url_result(mobj.group('url'), 'Ustream')
1515 # Look for embedded arte.tv player
1517 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1519 if mobj is not None:
1520 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1522 # Look for embedded francetv player
1524 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1526 if mobj is not None:
1527 return self.url_result(mobj.group('url'))
1529 # Look for embedded smotri.com player
1530 smotri_url = SmotriIE._extract_url(webpage)
1532 return self.url_result(smotri_url, 'Smotri')
1534 # Look for embedded Myvi.ru player
1535 myvi_url = MyviIE._extract_url(webpage)
1537 return self.url_result(myvi_url)
1539 # Look for embeded soundcloud player
1541 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1543 if mobj is not None:
1544 url = unescapeHTML(mobj.group('url'))
1545 return self.url_result(url)
1547 # Look for embedded vulture.com player
1549 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1551 if mobj is not None:
1552 url = unescapeHTML(mobj.group('url'))
1553 return self.url_result(url, ie='Vulture')
1555 # Look for embedded mtvservices player
1557 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1559 if mobj is not None:
1560 url = unescapeHTML(mobj.group('url'))
1561 return self.url_result(url, ie='MTVServicesEmbedded')
1563 # Look for embedded yahoo player
1565 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1567 if mobj is not None:
1568 return self.url_result(mobj.group('url'), 'Yahoo')
1570 # Look for embedded sbs.com.au player
1574 <meta\s+property="og:video"\s+content=|
1577 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1579 if mobj is not None:
1580 return self.url_result(mobj.group('url'), 'SBS')
1582 # Look for embedded Cinchcast player
1584 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1586 if mobj is not None:
1587 return self.url_result(mobj.group('url'), 'Cinchcast')
1590 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1594 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1596 if mobj is not None:
1597 return self.url_result(mobj.group('url'), 'MLB')
1600 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1602 if mobj is not None:
1603 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1606 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1608 if mobj is not None:
1609 return self.url_result(mobj.group('url'), 'Livestream')
1611 # Look for Zapiks embed
1613 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1614 if mobj is not None:
1615 return self.url_result(mobj.group('url'), 'Zapiks')
1617 # Look for Kaltura embeds
1618 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1619 re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
1620 if mobj is not None:
1621 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1623 # Look for Eagle.Platform embeds
1625 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1626 if mobj is not None:
1627 return self.url_result(mobj.group('url'), 'EaglePlatform')
1629 # Look for ClipYou (uses Eagle.Platform) embeds
1631 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1632 if mobj is not None:
1633 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1635 # Look for Pladform embeds
1637 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1638 if mobj is not None:
1639 return self.url_result(mobj.group('url'), 'Pladform')
1641 # Look for Playwire embeds
1643 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1644 if mobj is not None:
1645 return self.url_result(mobj.group('url'))
1647 # Look for 5min embeds
1649 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1650 if mobj is not None:
1651 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1653 # Look for Crooks and Liars embeds
1655 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1656 if mobj is not None:
1657 return self.url_result(mobj.group('url'))
1659 # Look for NBC Sports VPlayer embeds
1660 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1662 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1664 # Look for UDN embeds
1666 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1667 if mobj is not None:
1668 return self.url_result(
1669 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1671 # Look for Senate ISVP iframe
1672 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1674 return self.url_result(senate_isvp_url, 'SenateISVP')
1676 # Look for Dailymotion Cloud videos
1677 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1679 return self.url_result(dmcloud_url, 'DailymotionCloud')
1681 # Look for OnionStudios embeds
1682 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1683 if onionstudios_url:
1684 return self.url_result(onionstudios_url)
1686 # Look for SnagFilms embeds
1687 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1689 return self.url_result(snagfilms_url)
1691 # Look for AdobeTVVideo embeds
1693 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1695 if mobj is not None:
1696 return self.url_result(
1697 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1700 def check_video(vurl):
1701 if YoutubeIE.suitable(vurl):
1703 vpath = compat_urlparse.urlparse(vurl).path
1704 vext = determine_ext(vpath)
1705 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1707 def filter_video(urls):
1708 return list(filter(check_video, urls))
1710 # Start with something easy: JW Player in SWFObject
1711 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1713 # Look for gorilla-vid style embedding
1714 found = filter_video(re.findall(r'''(?sx)
1718 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1721 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1723 # Broaden the search a little bit
1724 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1726 # Broaden the findall a little bit: JWPlayer JS loader
1727 found = filter_video(re.findall(
1728 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1731 found = filter_video(re.findall(r'''(?xs)
1732 flowplayer\("[^"]+",\s*
1734 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1735 ["']?url["']?\s*:\s*["']([^"']+)["']
1740 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1742 # Try to find twitter cards info
1743 found = filter_video(re.findall(
1744 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1746 # We look for Open Graph info:
1747 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1748 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1749 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1750 if m_video_type is not None:
1751 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1754 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1756 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1758 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1759 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1762 # Look also in Refresh HTTP header
1763 refresh_header = head_response.headers.get('Refresh')
1765 found = re.search(REDIRECT_REGEX, refresh_header)
1767 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1768 self.report_following_redirect(new_url)
1774 raise UnsupportedError(url)
1777 for video_url in found:
1778 video_url = compat_urlparse.urljoin(url, video_url)
1779 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1781 # Sometimes, jwplayer extraction will result in a YouTube URL
1782 if YoutubeIE.suitable(video_url):
1783 entries.append(self.url_result(video_url, 'Youtube'))
1786 # here's a fun little line of code for you:
1787 video_id = os.path.splitext(video_id)[0]
1789 if determine_ext(video_url) == 'smil':
1792 'formats': self._extract_smil_formats(video_url, video_id),
1793 'uploader': video_uploader,
1794 'title': video_title,
1795 'age_limit': age_limit,
1801 'uploader': video_uploader,
1802 'title': video_title,
1803 'age_limit': age_limit,
1806 if len(entries) == 1:
1809 for num, e in enumerate(entries, start=1):
1810 # 'url' results don't have a title
1811 if e.get('title') is not None:
1812 e['title'] = '%s (%d)' % (e['title'], num)
1814 '_type': 'playlist',