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 (
56 from .onionstudios import OnionStudiosIE
57 from .viewlift import ViewLiftEmbedIE
58 from .screenwavemedia import ScreenwaveMediaIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .googledrive import GoogleDriveIE
63 from .jwplatform import JWPlatformIE
64 from .digiteka import DigitekaIE
65 from .arkena import ArkenaIE
66 from .instagram import InstagramIE
67 from .liveleak import LiveLeakIE
68 from .threeqsdn import ThreeQSDNIE
69 from .theplatform import ThePlatformIE
70 from .vessel import VesselIE
71 from .kaltura import KalturaIE
72 from .eagleplatform import EaglePlatformIE
73 from .facebook import FacebookIE
74 from .soundcloud import SoundcloudIE
75 from .vbox7 import Vbox7IE
78 class GenericIE(InfoExtractor):
79 IE_DESC = 'Generic downloader that works on some sites'
83 # Direct link to a video
85 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
86 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
91 'upload_date': '20100513',
94 # Direct link to media delivered compressed (until Accept-Encoding is *)
96 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
97 'md5': '128c42e68b13950268b648275386fc74',
99 'id': 'FictionJunction-Parallel_Hearts',
101 'title': 'FictionJunction-Parallel_Hearts',
102 'upload_date': '20140522',
104 'expected_warnings': [
105 'URL could be a direct video link, returning it as such.'
108 # Direct download with broken HEAD
110 'url': 'http://ai-radio.org:8000/radio.opus',
117 'skip_download': True, # infinite live stream
119 'expected_warnings': [
120 r'501.*Not Implemented',
124 # Direct link with incorrect MIME type
126 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
127 'md5': '4ccbebe5f36706d85221f204d7eb5913',
129 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
130 'id': '5_Lennart_Poettering_-_Systemd',
132 'title': '5_Lennart_Poettering_-_Systemd',
133 'upload_date': '20141120',
135 'expected_warnings': [
136 'URL could be a direct video link, returning it as such.'
141 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
143 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
144 'title': 'Zero Punctuation',
145 'description': 're:.*groundbreaking video review series.*'
147 'playlist_mincount': 11,
149 # RSS feed with enclosure
151 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
153 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
155 'upload_date': '20150228',
156 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
159 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
161 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
165 'title': 'Automatics, robotics and biocybernetics',
166 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
167 'upload_date': '20130627',
168 'formats': 'mincount:16',
169 'subtitles': 'mincount:1',
172 'force_generic_extractor': True,
173 'skip_download': True,
176 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
178 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
183 'formats': 'mincount:1',
186 'skip_download': True,
189 # SMIL from https://www.restudy.dk/video/play/id/1637
191 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
195 'title': 'video_1637',
196 'formats': 'mincount:3',
199 'skip_download': True,
202 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
204 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
206 'id': 'smil-service',
208 'title': 'smil-service',
209 'formats': 'mincount:1',
212 'skip_download': True,
215 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
217 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
221 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
222 'formats': 'mincount:3',
225 'skip_download': True,
228 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
230 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
232 'id': 'mZlp2ctYIUEB',
234 'title': 'Tikibad ontruimd wegens brand',
235 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
236 'thumbnail': 're:^https?://.*\.jpg$',
240 'skip_download': True,
243 # MPD from http://dash-mse-test.appspot.com/media.html
245 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
246 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
248 'id': 'car-20120827-manifest',
250 'title': 'car-20120827-manifest',
251 'formats': 'mincount:9',
252 'upload_date': '20130904',
255 'format': 'bestvideo',
258 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
260 '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',
265 'formats': 'mincount:8',
269 'skip_download': True,
272 # m3u8 served with Content-Type: text/plain
274 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
279 'upload_date': '20140720',
280 'formats': 'mincount:11',
284 'skip_download': True,
289 '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',
293 'upload_date': '20130224',
294 'uploader_id': 'TheVerge',
295 'description': 're:^Chris Ziegler takes a look at the\.*',
296 'uploader': 'The Verge',
297 'title': 'First Firefox OS phones side-by-side',
300 'skip_download': False,
304 # redirect in Refresh HTTP header
305 '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',
309 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
310 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
311 'upload_date': '20150917',
312 'uploader_id': 'brtvofficial',
313 'uploader': 'Boiler Room',
316 'skip_download': False,
320 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
321 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
323 'id': '13601338388002',
325 'uploader': 'www.hodiho.fr',
326 'title': 'R\u00e9gis plante sa Jeep',
329 # bandcamp page with custom domain
331 'add_ie': ['Bandcamp'],
332 'url': 'http://bronyrock.com/track/the-pony-mash',
336 'title': 'The Pony Mash',
337 'uploader': 'M_Pallante',
339 'skip': 'There is a limit of 200 free downloads / month for the test song',
341 # embedded brightcove video
342 # it also tests brightcove videos that need to set the 'Referer' in the
345 'add_ie': ['BrightcoveLegacy'],
346 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
348 'id': '2765128793001',
350 'title': 'Le cours de bourse : l’analyse technique',
351 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
352 'uploader': 'BFM BUSINESS',
355 'skip_download': True,
359 # https://github.com/rg3/youtube-dl/issues/2253
360 'url': 'http://bcove.me/i6nfkrc3',
361 'md5': '0ba9446db037002366bab3b3eb30c88c',
363 'id': '3101154703001',
365 'title': 'Still no power',
366 'uploader': 'thestar.com',
367 '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.',
369 'add_ie': ['BrightcoveLegacy'],
372 'url': 'http://www.championat.com/video/football/v/87/87499.html',
373 'md5': 'fb973ecf6e4a78a67453647444222983',
375 'id': '3414141473001',
377 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
378 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
379 'uploader': 'Championat',
383 # https://github.com/rg3/youtube-dl/issues/3541
384 'add_ie': ['BrightcoveLegacy'],
385 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
387 'id': '3866516442001',
389 'title': 'Leer mij vrouwen kennen: Aflevering 1',
390 'description': 'Leer mij vrouwen kennen: Aflevering 1',
391 'uploader': 'SBS Broadcasting',
393 'skip': 'Restricted to Netherlands',
395 'skip_download': True, # m3u8 download
400 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
401 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
403 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
405 'title': '2cc213299525360.mov', # that's what we get
408 'add_ie': ['Ooyala'],
411 # ooyala video embedded with http://player.ooyala.com/iframe.js
412 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
414 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
416 'title': '"Steve Jobs: Man in the Machine" trailer',
417 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
421 'skip_download': True,
426 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
430 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
431 'upload_date': '20140225',
432 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
433 'uploader': 'Tested',
434 'uploader_id': 'testedcom',
436 # No need to test YoutubeIE here
438 'skip_download': True,
443 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
447 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
448 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
453 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
457 'title': 'Охотское море стало целиком российским',
458 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
462 'skip_download': True,
467 '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/',
471 'title': 'Дошкольное воспитание',
476 'url': 'http://www.vestifinance.ru/articles/25753',
479 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
484 'title': 'Госзаказ. День 3',
490 'title': 'Госзаказ. День 2',
496 'title': 'Госзаказ. День 1',
502 'skip_download': True,
507 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
509 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
511 'title': 'Ужастики, русский трейлер (2015)',
512 'thumbnail': 're:^https?://.*\.jpg$',
518 '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',
521 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
523 'playlist_mincount': 7,
527 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
528 'md5': '65fdff94098e4a607385a60c5177c638',
532 'title': 'Hidden miracles of the natural world',
533 'uploader': 'Louie Schwartzberg',
534 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
537 # Embedded Ustream video
539 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
540 'md5': '27b99cdb639c9b12a79bca876a073417',
544 'uploader': 'AU SPA: The NSA and Privacy',
545 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
548 # nowvideo embed hidden behind percent encoding
550 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
551 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
553 'id': '06e53103ca9aa',
555 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
556 'description': 'No description',
561 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
562 'md5': '7653032cbb25bf6c80d80f217055fa43',
564 'id': '048195-004_PLUS7-F',
567 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
568 'upload_date': '20140320',
571 'skip_download': 'Requires rtmpdump'
576 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
580 'title': 'Alcaline, le concert avec Calogero',
581 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
582 'upload_date': '20150226',
583 'timestamp': 1424989860,
588 'skip_download': True,
590 'expected_warnings': [
596 'url': 'http://www.wired.com/2014/04/honda-asimo/',
597 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
599 'id': '53501be369702d3275860000',
601 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
606 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
607 'md5': '441aeeb82eb72c422c7f14ec533999cd',
609 'id': 'k2mm4bCdJ6CQ2i7c8o2',
611 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
612 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
614 'uploader_id': 'xgditw',
615 'upload_date': '20140425',
616 'timestamp': 1398441542,
618 'add_ie': ['Dailymotion'],
622 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
626 'title': 'The NBL Auction 2014',
627 'uploader': 'BADMINTON England',
628 'uploader_id': 'BADMINTONEvents',
629 'upload_date': '20140603',
630 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
632 'add_ie': ['Youtube'],
634 'skip_download': True,
639 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
640 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
642 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
644 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
645 'description': 'Two valets share their love for movie star Liam Neesons.',
646 'timestamp': 1349922600,
647 'upload_date': '20121011',
650 # YouTube embed via <data-embed-url="">
652 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
656 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
657 'uploader': 'Gameloft',
658 'uploader_id': 'gameloft',
659 'upload_date': '20140828',
660 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
663 'skip_download': True,
668 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
670 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
672 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
673 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
678 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
680 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
681 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
687 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
692 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
693 'md5': '9d65602bf31c6e20014319c7d07fba27',
695 'id': '5123ea6d5e5a7',
698 'uploader': 'www.handjobhub.com',
699 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
702 # Multiple brightcove videos
703 # https://github.com/rg3/youtube-dl/issues/2283
705 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
707 'id': 'always-never',
708 'title': 'Always / Never - The New Yorker',
712 'extract_flat': False,
713 'skip_download': True,
718 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
719 'md5': '96f09a37e44da40dd083e12d9a683327',
723 'title': 'Ump changes call to ball',
724 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
726 'timestamp': 1401537900,
727 'upload_date': '20140531',
728 'thumbnail': 're:^https?://.*\.jpg$',
733 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
734 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
738 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
739 'description': 'a Paywall Videos video from Remilon',
741 'uploader': 'study.com',
742 'timestamp': 1459678540,
743 'upload_date': '20160403',
744 'filesize': 24687186,
748 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
749 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
753 'title': 'Conversation about Hexagonal Rails Part 1',
754 'description': 'a Martin Fowler video from ThoughtWorks',
756 'uploader': 'thoughtworks.wistia.com',
757 'timestamp': 1401832161,
758 'upload_date': '20140603',
761 # Wistia standard embed (async)
763 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
767 'title': 'Drip Brennan Dunn Workshop',
768 'description': 'a JV Webinars video from getdrip-1',
770 'timestamp': 1463607249,
771 'upload_date': '20160518',
774 'skip_download': True,
779 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
783 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
784 'uploader': 'Sophos Security',
785 'title': 'Chet Chat 171 - Oct 29, 2014',
786 'upload_date': '20141029',
789 # Soundcloud multiple embeds
791 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
794 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
796 'playlist_mincount': 7,
800 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
804 'upload_date': '20141112',
805 'title': 'Rosetta #CometLanding webcast HL 10',
808 # Another Livestream embed, without 'new.' in URL
810 'url': 'https://www.freespeech.org/',
814 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
818 'skip_download': True,
823 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
826 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
828 'playlist_mincount': 2,
832 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
836 'upload_date': '20141126',
837 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
842 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
844 'id': '730m_DandD_1901_512k',
846 'uploader': 'www.abc.net.au',
847 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
850 # embedded viddler video
852 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
856 'uploader': 'deadspin',
857 'title': 'WALL-TO-GORTAT',
858 'timestamp': 1422285291,
859 'upload_date': '20150126',
861 'add_ie': ['Viddler'],
865 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
869 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
870 'description': 'md5:601cb790edd05908957dae8aaa866465',
871 'upload_date': '20150220',
873 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
877 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
881 'upload_date': '20150212',
882 'uploader': 'The National Archives UK',
883 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
884 'uploader_id': 'NationalArchives08',
885 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
890 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
891 'playlist_mincount': 5,
893 'id': 'aanslagen-kopenhagen',
894 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
899 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
903 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
906 # Kaltura embed (different embed code)
908 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
912 'upload_date': '20150127',
913 'uploader_id': 'PremierMedia',
915 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
918 # Kaltura embed protected with referrer
920 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
924 'title': 'Violetta - Achter De Schermen - Ruggero',
925 'description': 'Achter de schermen met Ruggero',
926 'timestamp': 1435133761,
927 'upload_date': '20150624',
928 'uploader_id': 'echojecka',
931 # Kaltura embed with single quotes
933 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
938 'timestamp': 1355743100,
939 'upload_date': '20121217',
940 'uploader_id': 'batchUser',
942 'add_ie': ['Kaltura'],
945 # Kaltura embedded via quoted entry_id
946 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
950 'title': '06_matthew_brender_raj_dutt',
951 'timestamp': 1466638791,
952 'upload_date': '20160622',
954 'add_ie': ['Kaltura'],
955 'expected_warnings': [
956 'Could not send HEAD request'
959 'skip_download': True,
962 # Eagle.Platform embed (generic URL)
964 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
965 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
969 'title': 'Навальный вышел на свободу',
970 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
971 'thumbnail': 're:^https?://.*\.jpg$',
977 # ClipYou (Eagle.Platform) embed (custom URL)
979 'url': 'http://muz-tv.ru/play/7129/',
980 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
984 'title': "'O Sole Mio",
985 'thumbnail': 're:^https?://.*\.jpg$',
992 'url': 'http://muz-tv.ru/kinozal/view/7400/',
996 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
997 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
998 'thumbnail': 're:^https?://.*\.jpg$',
1005 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1009 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1010 'thumbnail': 're:^https?://.*\.png$',
1016 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1017 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1021 'title': 'Facebook Creates "On This Day" | Crunch Report',
1026 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1030 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1035 # Crooks and Liars embed
1037 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1041 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1042 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1043 'timestamp': 1428207000,
1044 'upload_date': '20150405',
1045 'uploader': 'Heather',
1048 # Crooks and Liars external embed
1050 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1052 'id': 'MTE3MjUtMzQ2MzA',
1054 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1055 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1056 'timestamp': 1265032391,
1057 'upload_date': '20100201',
1058 'uploader': 'Heather',
1061 # NBC Sports vplayer embed
1063 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1065 'id': 'ln7x1qSThw4k',
1067 'title': "PFT Live: New leader in the 'new-look' defense",
1068 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1069 'uploader': 'NBCU-SPORTS',
1070 'upload_date': '20140107',
1071 'timestamp': 1389118457,
1076 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1077 'md5': '1aa589c675898ae6d37a17913cf68d66',
1079 'id': '701714499682',
1081 'title': 'PREVIEW: On Assignment: David Letterman',
1082 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1087 'url': 'https://video.udn.com/news/300346',
1088 'md5': 'fd2060e988c326991037b9aff9df21a6',
1092 'title': '中一中男師變性 全校師生力挺',
1093 'thumbnail': 're:^https?://.*\.jpg$',
1097 'skip_download': True,
1102 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1104 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1106 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1107 'title': 'This is what separates the Excel masters from the wannabes',
1108 'duration': 191.933,
1112 'skip_download': True,
1115 # Brightcove URL in single quotes
1117 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1118 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1120 'id': '4255764656001',
1122 'title': 'SN Presents: Russell Martin, World Citizen',
1123 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1124 'uploader': 'Rogers Sportsnet',
1125 'uploader_id': '1704050871',
1126 'upload_date': '20150525',
1127 'timestamp': 1432570283,
1130 # Dailymotion Cloud video
1132 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1133 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1137 'title': 'Sauvons les abeilles ! - Le débat',
1138 'description': 'md5:d9082128b1c5277987825d684939ca26',
1139 'thumbnail': 're:^https?://.*\.jpe?g$',
1140 'timestamp': 1434970506,
1141 'upload_date': '20150622',
1142 'uploader': 'Public Sénat',
1143 'uploader_id': 'xa9gza',
1146 # OnionStudios embed
1148 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1152 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1153 'thumbnail': 're:^https?://.*\.jpe?g$',
1154 'uploader': 'ClickHole',
1155 'uploader_id': 'clickhole',
1160 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1162 'id': '74849a00-85a9-11e1-9660-123139220831',
1164 'title': '#whilewewatch',
1167 # AdobeTVVideo embed
1169 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1170 'md5': '43662b577c018ad707a63766462b1e87',
1174 'title': 'New experience with Acrobat DC',
1175 'description': 'New experience with Acrobat DC',
1176 'duration': 248.667,
1179 # ScreenwaveMedia embed
1181 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1182 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1184 'id': 'cinemasnob-55d26273809dd',
1186 'title': 'cinemasnob',
1189 # BrightcoveInPageEmbed embed
1191 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1193 'id': '4238694884001',
1195 'title': 'Tabletop: Dread, Last Thoughts',
1196 'description': 'Tabletop: Dread, Last Thoughts',
1200 # JWPlayer with M3U8
1202 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1206 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1207 'uploader': 'ren.tv',
1211 'skip_download': True,
1214 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1215 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1217 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1219 'id': '4785848093001',
1221 'title': 'The Cardinal Pell Interview',
1222 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1223 'uploader': 'GlobeCast Australia - GlobeStream',
1224 'uploader_id': '2733773828001',
1225 'upload_date': '20160304',
1226 'timestamp': 1457083087,
1230 'skip_download': True,
1233 # Another form of arte.tv embed
1235 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1236 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1238 'id': '030273-562_PLUS7-F',
1240 'title': 'ARTE Reportage - Nulle part, en France',
1241 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1242 'upload_date': '20160409',
1247 'url': 'http://www.wykop.pl/link/3088787/',
1248 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1250 'id': '874_1459135191',
1252 'title': 'Man shows poor quality of new apartment building',
1253 'description': 'The wall is like a sand pile.',
1254 'uploader': 'Lake8737',
1257 # Duplicated embedded video URLs
1259 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1261 'id': '149298443_480_16c25b74_2',
1263 'title': 'vs. Blue Orange Spring Game',
1264 'uploader': 'www.hudl.com',
1267 # twitter:player:stream embed
1269 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1273 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1274 'uploader': 'www.rtl.be',
1278 'skip_download': True,
1281 # twitter:player embed
1283 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1284 'md5': 'a3e0df96369831de324f0778e126653c',
1286 'id': '4909620399001',
1288 'title': 'What Do Black Holes Sound Like?',
1289 'description': 'what do black holes sound like',
1290 'upload_date': '20160524',
1291 'uploader_id': '29913724001',
1292 'timestamp': 1464107587,
1293 'uploader': 'TheAtlantic',
1295 'add_ie': ['BrightcoveLegacy'],
1297 # Facebook <iframe> embed
1299 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1300 'md5': 'fbcde74f534176ecb015849146dd3aee',
1302 'id': '599637780109885',
1304 'title': 'Facebook video #599637780109885',
1307 # Facebook API embed
1309 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1310 'md5': 'a47372ee61b39a7b90287094d447d94e',
1312 'id': '10153467542406923',
1314 'title': 'Facebook video #10153467542406923',
1317 # Wordpress "YouTube Video Importer" plugin
1319 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1320 'md5': 'd16797741b560b485194eddda8121b48',
1322 'id': 'HNTXWDXV9Is',
1324 'title': 'Blue Devils Drumline Stanford lot 2016',
1325 'upload_date': '20160627',
1326 'uploader_id': 'GENOCIDE8GENERAL10',
1327 'uploader': 'cylus cyrus',
1331 # video stored on custom kaltura server
1332 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1333 'md5': '537617d06e64dfed891fa1593c4b30cc',
1337 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1338 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1339 'uploader_id': 'videos.expansion@el-mundo.net',
1340 'upload_date': '20150429',
1341 'timestamp': 1430303472,
1343 'add_ie': ['Kaltura'],
1346 # Non-standard Vimeo embed
1347 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1348 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1352 'title': 'Understanding the web - Teaser',
1353 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1354 'upload_date': '20151214',
1355 'uploader': 'OpenClassrooms',
1356 'uploader_id': 'openclassrooms',
1358 'add_ie': ['Vimeo'],
1361 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1362 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1364 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1366 'title': 'Big Buck Bunny',
1367 'description': 'Royalty free test video',
1368 'timestamp': 1432816365,
1369 'upload_date': '20150528',
1373 'skip_download': True,
1375 'add_ie': [ArkenaIE.ie_key()],
1378 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1382 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1385 'skip_download': True,
1387 'add_ie': [Vbox7IE.ie_key()],
1390 # # TODO: find another test
1391 # # http://schema.org/VideoObject
1392 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1393 # 'md5': '888dcf08b7ea671381f00fab74692755',
1395 # 'id': 'nyvTSJMKId',
1397 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1398 # 'description': '#love for cats.',
1399 # 'timestamp': 1461244995,
1400 # 'upload_date': '20160421',
1403 # 'force_generic_extractor': True,
1408 def report_following_redirect(self, new_url):
1409 """Report information extraction."""
1410 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1412 def _extract_rss(self, url, video_id, doc):
1413 playlist_title = doc.find('./channel/title').text
1414 playlist_desc_el = doc.find('./channel/description')
1415 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1418 for it in doc.findall('./channel/item'):
1419 next_url = xpath_text(it, 'link', fatal=False)
1421 enclosure_nodes = it.findall('./enclosure')
1422 for e in enclosure_nodes:
1423 next_url = e.attrib.get('url')
1433 'title': it.find('title').text,
1437 '_type': 'playlist',
1439 'title': playlist_title,
1440 'description': playlist_desc,
1444 def _extract_camtasia(self, url, video_id, webpage):
1445 """ Returns None if no camtasia video can be found. """
1447 camtasia_cfg = self._search_regex(
1448 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1449 webpage, 'camtasia configuration file', default=None)
1450 if camtasia_cfg is None:
1453 title = self._html_search_meta('DC.title', webpage, fatal=True)
1455 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1456 camtasia_cfg = self._download_xml(
1457 camtasia_url, video_id,
1458 note='Downloading camtasia configuration',
1459 errnote='Failed to download camtasia configuration')
1460 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1463 for n in fileset_node.getchildren():
1464 url_n = n.find('./uri')
1469 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1470 'title': '%s - %s' % (title, n.tag),
1471 'url': compat_urlparse.urljoin(url, url_n.text),
1472 'duration': float_or_none(n.find('./duration').text),
1476 '_type': 'playlist',
1481 def _real_extract(self, url):
1482 if url.startswith('//'):
1485 'url': self.http_scheme() + url,
1488 parsed_url = compat_urlparse.urlparse(url)
1489 if not parsed_url.scheme:
1490 default_search = self._downloader.params.get('default_search')
1491 if default_search is None:
1492 default_search = 'fixup_error'
1494 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1496 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1497 return self.url_result('http://' + url)
1498 elif default_search != 'fixup_error':
1499 if default_search == 'auto_warning':
1500 if re.match(r'^(?:url|URL)$', url):
1501 raise ExtractorError(
1502 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1505 self._downloader.report_warning(
1506 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1507 return self.url_result('ytsearch:' + url)
1509 if default_search in ('error', 'fixup_error'):
1510 raise ExtractorError(
1511 '%r is not a valid URL. '
1512 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1513 % (url, url), expected=True)
1515 if ':' not in default_search:
1516 default_search += ':'
1517 return self.url_result(default_search + url)
1519 url, smuggled_data = unsmuggle_url(url)
1520 force_videoid = None
1521 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1522 if smuggled_data and 'force_videoid' in smuggled_data:
1523 force_videoid = smuggled_data['force_videoid']
1524 video_id = force_videoid
1526 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1528 self.to_screen('%s: Requesting header' % video_id)
1530 head_req = HEADRequest(url)
1531 head_response = self._request_webpage(
1533 note=False, errnote='Could not send HEAD request to %s' % url,
1536 if head_response is not False:
1537 # Check for redirect
1538 new_url = head_response.geturl()
1540 self.report_following_redirect(new_url)
1542 new_url = smuggle_url(
1543 new_url, {'force_videoid': force_videoid})
1544 return self.url_result(new_url)
1546 full_response = None
1547 if head_response is False:
1548 request = sanitized_Request(url)
1549 request.add_header('Accept-Encoding', '*')
1550 full_response = self._request_webpage(request, video_id)
1551 head_response = full_response
1555 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1556 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1559 # Check for direct link to a video
1560 content_type = head_response.headers.get('Content-Type', '').lower()
1561 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1563 format_id = m.group('format_id')
1564 if format_id.endswith('mpegurl'):
1565 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1566 elif format_id == 'f4m':
1567 formats = self._extract_f4m_formats(url, video_id)
1570 'format_id': m.group('format_id'),
1572 'vcodec': 'none' if m.group('type') == 'audio' else None
1574 info_dict['direct'] = True
1575 self._sort_formats(formats)
1576 info_dict['formats'] = formats
1579 if not self._downloader.params.get('test', False) and not is_intentional:
1580 force = self._downloader.params.get('force_generic_extractor', False)
1581 self._downloader.report_warning(
1582 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1584 if not full_response:
1585 request = sanitized_Request(url)
1586 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1587 # making it impossible to download only chunk of the file (yet we need only 512kB to
1588 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1589 # that will always result in downloading the whole file that is not desirable.
1590 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1591 # to accept raw bytes and being able to download only a chunk.
1592 # It may probably better to solve this by checking Content-Type for application/octet-stream
1593 # after HEAD request finishes, but not sure if we can rely on this.
1594 request.add_header('Accept-Encoding', '*')
1595 full_response = self._request_webpage(request, video_id)
1597 first_bytes = full_response.read(512)
1599 # Is it an M3U playlist?
1600 if first_bytes.startswith(b'#EXTM3U'):
1601 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1602 self._sort_formats(info_dict['formats'])
1605 # Maybe it's a direct link to a video?
1606 # Be careful not to download the whole thing!
1607 if not is_html(first_bytes):
1608 self._downloader.report_warning(
1609 'URL could be a direct video link, returning it as such.')
1616 webpage = self._webpage_read_content(
1617 full_response, url, video_id, prefix=first_bytes)
1619 self.report_extraction(video_id)
1621 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1623 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1624 if doc.tag == 'rss':
1625 return self._extract_rss(url, video_id, doc)
1626 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1627 smil = self._parse_smil(doc, url, video_id)
1628 self._sort_formats(smil['formats'])
1630 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1631 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1632 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1633 info_dict['formats'] = self._parse_mpd_formats(
1634 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1635 self._sort_formats(info_dict['formats'])
1637 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1638 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1639 self._sort_formats(info_dict['formats'])
1641 except compat_xml_parse_error:
1644 # Is it a Camtasia project?
1645 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1646 if camtasia_res is not None:
1649 # Sometimes embedded video player is hidden behind percent encoding
1650 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1651 # Unescaping the whole page allows to handle those cases in a generic way
1652 webpage = compat_urllib_parse_unquote(webpage)
1654 # it's tempting to parse this further, but you would
1655 # have to take into account all the variations like
1656 # Video Title - Site Name
1657 # Site Name | Video Title
1658 # Video Title - Tagline | Site Name
1659 # and so on and so forth; it's just not practical
1660 video_title = self._og_search_title(
1661 webpage, default=None) or self._html_search_regex(
1662 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1665 # Try to detect age limit automatically
1666 age_limit = self._rta_search(webpage)
1667 # And then there are the jokers who advertise that they use RTA,
1668 # but actually don't.
1669 AGE_LIMIT_MARKERS = [
1670 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1672 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1675 # video uploader is domain name
1676 video_uploader = self._search_regex(
1677 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1679 video_description = self._og_search_description(webpage, default=None)
1680 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1683 def _playlist_from_matches(matches, getter=None, ie=None):
1685 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1687 return self.playlist_result(
1688 urlrs, playlist_id=video_id, playlist_title=video_title)
1690 # Look for Brightcove Legacy Studio embeds
1691 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1693 self.to_screen('Brightcove video detected.')
1696 'url': smuggle_url(bc_url, {'Referer': url}),
1697 'ie_key': 'BrightcoveLegacy'
1698 } for bc_url in bc_urls]
1701 '_type': 'playlist',
1702 'title': video_title,
1707 # Look for Brightcove New Studio embeds
1708 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1710 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1712 # Look for ThePlatform embeds
1713 tp_urls = ThePlatformIE._extract_urls(webpage)
1715 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1717 # Look for Vessel embeds
1718 vessel_urls = VesselIE._extract_urls(webpage)
1720 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1722 # Look for embedded rtl.nl player
1723 matches = re.findall(
1724 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1727 return _playlist_from_matches(matches, ie='RtlNl')
1729 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1730 if vimeo_url is not None:
1731 return self.url_result(vimeo_url)
1733 vid_me_embed_url = self._search_regex(
1734 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1735 webpage, 'vid.me embed', default=None)
1736 if vid_me_embed_url is not None:
1737 return self.url_result(vid_me_embed_url, 'Vidme')
1739 # Look for embedded YouTube player
1740 matches = re.findall(r'''(?x)
1749 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1753 return _playlist_from_matches(
1754 matches, lambda m: unescapeHTML(m[1]))
1756 # Look for lazyYT YouTube embed
1757 matches = re.findall(
1758 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1760 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1762 # Look for Wordpress "YouTube Video Importer" plugin
1763 matches = re.findall(r'''(?x)<div[^>]+
1764 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1765 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1767 return _playlist_from_matches(matches, lambda m: m[-1])
1769 matches = DailymotionIE._extract_urls(webpage)
1771 return _playlist_from_matches(matches)
1773 # Look for embedded Dailymotion playlist player (#3822)
1775 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1777 playlists = re.findall(
1778 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1780 return _playlist_from_matches(
1781 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1783 # Look for embedded Wistia player
1785 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1787 embed_url = self._proto_relative_url(
1788 unescapeHTML(match.group('url')))
1790 '_type': 'url_transparent',
1793 'uploader': video_uploader,
1796 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1799 '_type': 'url_transparent',
1800 'url': 'wistia:%s' % match.group('id'),
1802 'uploader': video_uploader,
1807 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1808 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1811 return self.url_result(self._proto_relative_url(
1812 'wistia:%s' % match.group('id')), 'Wistia')
1814 # Look for SVT player
1815 svt_url = SVTIE._extract_url(webpage)
1817 return self.url_result(svt_url, 'SVT')
1819 # Look for embedded condenast player
1820 matches = re.findall(
1821 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1825 '_type': 'playlist',
1828 'ie_key': 'CondeNast',
1830 } for ma in matches],
1831 'title': video_title,
1835 # Look for Bandcamp pages with custom domain
1836 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1837 if mobj is not None:
1838 burl = unescapeHTML(mobj.group(1))
1839 # Don't set the extractor because it can be a track url or an album
1840 return self.url_result(burl)
1842 # Look for embedded Vevo player
1844 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1845 if mobj is not None:
1846 return self.url_result(mobj.group('url'))
1848 # Look for embedded Viddler player
1850 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1852 if mobj is not None:
1853 return self.url_result(mobj.group('url'))
1855 # Look for NYTimes player
1857 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1859 if mobj is not None:
1860 return self.url_result(mobj.group('url'))
1862 # Look for Libsyn player
1864 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1865 if mobj is not None:
1866 return self.url_result(mobj.group('url'))
1868 # Look for Ooyala videos
1869 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1870 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1871 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1872 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1873 if mobj is not None:
1874 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1876 # Look for multiple Ooyala embeds on SBN network websites
1877 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1878 if mobj is not None:
1879 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1881 return _playlist_from_matches(
1882 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1884 # Look for Aparat videos
1885 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1886 if mobj is not None:
1887 return self.url_result(mobj.group(1), 'Aparat')
1889 # Look for MPORA videos
1890 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1891 if mobj is not None:
1892 return self.url_result(mobj.group(1), 'Mpora')
1894 # Look for embedded NovaMov-based player
1896 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1897 (?P<url>http://(?:(?:embed|www)\.)?
1899 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1900 videoweed\.(?:es|com)|
1901 movshare\.(?:net|sx|ag)|
1902 divxstage\.(?:eu|net|ch|co|at|ag))
1903 /embed\.php.+?)\1''', webpage)
1904 if mobj is not None:
1905 return self.url_result(mobj.group('url'))
1907 # Look for embedded Facebook player
1908 facebook_url = FacebookIE._extract_url(webpage)
1909 if facebook_url is not None:
1910 return self.url_result(facebook_url, 'Facebook')
1912 # Look for embedded VK player
1913 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1914 if mobj is not None:
1915 return self.url_result(mobj.group('url'), 'VK')
1917 # Look for embedded Odnoklassniki player
1918 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1919 if mobj is not None:
1920 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1922 # Look for embedded ivi player
1923 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1924 if mobj is not None:
1925 return self.url_result(mobj.group('url'), 'Ivi')
1927 # Look for embedded Huffington Post player
1929 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1930 if mobj is not None:
1931 return self.url_result(mobj.group('url'), 'HuffPost')
1934 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1935 if mobj is not None:
1936 return self.url_result(mobj.group('url'))
1937 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1938 if mobj is not None:
1939 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1941 # Look for funnyordie embed
1942 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1944 return _playlist_from_matches(
1945 matches, getter=unescapeHTML, ie='FunnyOrDie')
1947 # Look for BBC iPlayer embed
1948 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1950 return _playlist_from_matches(matches, ie='BBCCoUk')
1952 # Look for embedded RUTV player
1953 rutv_url = RUTVIE._extract_url(webpage)
1955 return self.url_result(rutv_url, 'RUTV')
1957 # Look for embedded TVC player
1958 tvc_url = TVCIE._extract_url(webpage)
1960 return self.url_result(tvc_url, 'TVC')
1962 # Look for embedded SportBox player
1963 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1965 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1967 # Look for embedded PornHub player
1968 pornhub_url = PornHubIE._extract_url(webpage)
1970 return self.url_result(pornhub_url, 'PornHub')
1972 # Look for embedded XHamster player
1973 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1975 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1977 # Look for embedded TNAFlixNetwork player
1978 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1980 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1982 # Look for embedded Tvigle player
1984 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1985 if mobj is not None:
1986 return self.url_result(mobj.group('url'), 'Tvigle')
1988 # Look for embedded TED player
1990 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1991 if mobj is not None:
1992 return self.url_result(mobj.group('url'), 'TED')
1994 # Look for embedded Ustream videos
1996 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1997 if mobj is not None:
1998 return self.url_result(mobj.group('url'), 'Ustream')
2000 # Look for embedded arte.tv player
2002 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2004 if mobj is not None:
2005 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2007 # Look for embedded francetv player
2009 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2011 if mobj is not None:
2012 return self.url_result(mobj.group('url'))
2014 # Look for embedded smotri.com player
2015 smotri_url = SmotriIE._extract_url(webpage)
2017 return self.url_result(smotri_url, 'Smotri')
2019 # Look for embedded Myvi.ru player
2020 myvi_url = MyviIE._extract_url(webpage)
2022 return self.url_result(myvi_url)
2024 # Look for embedded soundcloud player
2025 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2027 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2029 # Look for embedded mtvservices player
2030 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2032 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2034 # Look for embedded yahoo player
2036 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2038 if mobj is not None:
2039 return self.url_result(mobj.group('url'), 'Yahoo')
2041 # Look for embedded sbs.com.au player
2045 <meta\s+property="og:video"\s+content=|
2048 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2050 if mobj is not None:
2051 return self.url_result(mobj.group('url'), 'SBS')
2053 # Look for embedded Cinchcast player
2055 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2057 if mobj is not None:
2058 return self.url_result(mobj.group('url'), 'Cinchcast')
2061 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2065 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2067 if mobj is not None:
2068 return self.url_result(mobj.group('url'), 'MLB')
2071 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2073 if mobj is not None:
2074 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2077 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2079 if mobj is not None:
2080 return self.url_result(mobj.group('url'), 'Livestream')
2082 # Look for Zapiks embed
2084 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2085 if mobj is not None:
2086 return self.url_result(mobj.group('url'), 'Zapiks')
2088 # Look for Kaltura embeds
2089 kaltura_url = KalturaIE._extract_url(webpage)
2091 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2093 # Look for Eagle.Platform embeds
2094 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2095 if eagleplatform_url:
2096 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2098 # Look for ClipYou (uses Eagle.Platform) embeds
2100 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2101 if mobj is not None:
2102 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2104 # Look for Pladform embeds
2105 pladform_url = PladformIE._extract_url(webpage)
2107 return self.url_result(pladform_url)
2109 # Look for Videomore embeds
2110 videomore_url = VideomoreIE._extract_url(webpage)
2112 return self.url_result(videomore_url)
2114 # Look for Playwire embeds
2116 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2117 if mobj is not None:
2118 return self.url_result(mobj.group('url'))
2120 # Look for 5min embeds
2122 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2123 if mobj is not None:
2124 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2126 # Look for Crooks and Liars embeds
2128 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2129 if mobj is not None:
2130 return self.url_result(mobj.group('url'))
2132 # Look for NBC Sports VPlayer embeds
2133 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2135 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2137 # Look for NBC News embeds
2138 nbc_news_embed_url = re.search(
2139 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2140 if nbc_news_embed_url:
2141 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2143 # Look for Google Drive embeds
2144 google_drive_url = GoogleDriveIE._extract_url(webpage)
2145 if google_drive_url:
2146 return self.url_result(google_drive_url, 'GoogleDrive')
2148 # Look for UDN embeds
2150 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2151 if mobj is not None:
2152 return self.url_result(
2153 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2155 # Look for Senate ISVP iframe
2156 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2158 return self.url_result(senate_isvp_url, 'SenateISVP')
2160 # Look for Dailymotion Cloud videos
2161 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2163 return self.url_result(dmcloud_url, 'DailymotionCloud')
2165 # Look for OnionStudios embeds
2166 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2167 if onionstudios_url:
2168 return self.url_result(onionstudios_url)
2170 # Look for ViewLift embeds
2171 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2173 return self.url_result(viewlift_url)
2175 # Look for JWPlatform embeds
2176 jwplatform_url = JWPlatformIE._extract_url(webpage)
2178 return self.url_result(jwplatform_url, 'JWPlatform')
2180 # Look for ScreenwaveMedia embeds
2181 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2182 if mobj is not None:
2183 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2185 # Look for Digiteka embeds
2186 digiteka_url = DigitekaIE._extract_url(webpage)
2188 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2190 # Look for Arkena embeds
2191 arkena_url = ArkenaIE._extract_url(webpage)
2193 return self.url_result(arkena_url, ArkenaIE.ie_key())
2195 # Look for Limelight embeds
2196 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2200 'Channel': 'channel',
2201 'ChannelList': 'channel_list',
2203 return self.url_result('limelight:%s:%s' % (
2204 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2206 # Look for AdobeTVVideo embeds
2208 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2210 if mobj is not None:
2211 return self.url_result(
2212 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2215 # Look for Vine embeds
2217 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2219 if mobj is not None:
2220 return self.url_result(
2221 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2223 # Look for VODPlatform embeds
2225 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
2227 if mobj is not None:
2228 return self.url_result(
2229 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
2231 # Look for Instagram embeds
2232 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2233 if instagram_embed_url is not None:
2234 return self.url_result(
2235 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2237 # Look for LiveLeak embeds
2238 liveleak_url = LiveLeakIE._extract_url(webpage)
2240 return self.url_result(liveleak_url, 'LiveLeak')
2242 # Look for 3Q SDN embeds
2243 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2246 '_type': 'url_transparent',
2247 'ie_key': ThreeQSDNIE.ie_key(),
2248 'url': self._proto_relative_url(threeqsdn_url),
2249 'title': video_title,
2250 'description': video_description,
2251 'thumbnail': video_thumbnail,
2252 'uploader': video_uploader,
2255 # Look for VBOX7 embeds
2256 vbox7_url = Vbox7IE._extract_url(webpage)
2258 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2260 # Looking for http://schema.org/VideoObject
2261 json_ld = self._search_json_ld(
2262 webpage, video_id, default={}, expected_type='VideoObject')
2263 if json_ld.get('url'):
2265 'title': video_title or info_dict['title'],
2266 'description': video_description,
2267 'thumbnail': video_thumbnail,
2268 'age_limit': age_limit
2270 info_dict.update(json_ld)
2273 def check_video(vurl):
2274 if YoutubeIE.suitable(vurl):
2276 vpath = compat_urlparse.urlparse(vurl).path
2277 vext = determine_ext(vpath)
2278 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2280 def filter_video(urls):
2281 return list(filter(check_video, urls))
2283 # Start with something easy: JW Player in SWFObject
2284 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2286 # Look for gorilla-vid style embedding
2287 found = filter_video(re.findall(r'''(?sx)
2291 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2294 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2296 # Broaden the search a little bit
2297 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2299 # Broaden the findall a little bit: JWPlayer JS loader
2300 found = filter_video(re.findall(
2301 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2304 found = filter_video(re.findall(r'''(?xs)
2305 flowplayer\("[^"]+",\s*
2307 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2308 ["']?url["']?\s*:\s*["']([^"']+)["']
2313 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2315 # Try to find twitter cards info
2316 # twitter:player:stream should be checked before twitter:player since
2317 # it is expected to contain a raw stream (see
2318 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2319 found = filter_video(re.findall(
2320 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2322 # We look for Open Graph info:
2323 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2324 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2325 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2326 if m_video_type is not None:
2327 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2330 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2332 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2334 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2335 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2338 # Look also in Refresh HTTP header
2339 refresh_header = head_response.headers.get('Refresh')
2341 # In python 2 response HTTP headers are bytestrings
2342 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2343 refresh_header = refresh_header.decode('iso-8859-1')
2344 found = re.search(REDIRECT_REGEX, refresh_header)
2346 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2347 self.report_following_redirect(new_url)
2354 # twitter:player is a https URL to iframe player that may or may not
2355 # be supported by youtube-dl thus this is checked the very last (see
2356 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2357 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2359 return self.url_result(embed_url)
2362 raise UnsupportedError(url)
2365 for video_url in orderedSet(found):
2366 video_url = unescapeHTML(video_url)
2367 video_url = video_url.replace('\\/', '/')
2368 video_url = compat_urlparse.urljoin(url, video_url)
2369 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2371 # Sometimes, jwplayer extraction will result in a YouTube URL
2372 if YoutubeIE.suitable(video_url):
2373 entries.append(self.url_result(video_url, 'Youtube'))
2376 # here's a fun little line of code for you:
2377 video_id = os.path.splitext(video_id)[0]
2381 'uploader': video_uploader,
2382 'title': video_title,
2383 'age_limit': age_limit,
2386 ext = determine_ext(video_url)
2388 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2390 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2392 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2394 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2396 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2398 entry_info_dict['url'] = video_url
2400 if entry_info_dict.get('formats'):
2401 self._sort_formats(entry_info_dict['formats'])
2403 entries.append(entry_info_dict)
2405 if len(entries) == 1:
2408 for num, e in enumerate(entries, start=1):
2409 # 'url' results don't have a title
2410 if e.get('title') is not None:
2411 e['title'] = '%s (%d)' % (e['title'], num)
2413 '_type': 'playlist',