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,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .vimeo import VimeoIE
51 from .dailymotion import (
55 from .onionstudios import OnionStudiosIE
56 from .viewlift import ViewLiftEmbedIE
57 from .screenwavemedia import ScreenwaveMediaIE
58 from .mtv import MTVServicesEmbeddedIE
59 from .pladform import PladformIE
60 from .videomore import VideomoreIE
61 from .googledrive import GoogleDriveIE
62 from .jwplatform import JWPlatformIE
63 from .digiteka import DigitekaIE
64 from .arkena import ArkenaIE
65 from .instagram import InstagramIE
66 from .liveleak import LiveLeakIE
67 from .threeqsdn import ThreeQSDNIE
68 from .theplatform import ThePlatformIE
69 from .vessel import VesselIE
70 from .kaltura import KalturaIE
71 from .eagleplatform import EaglePlatformIE
72 from .facebook import FacebookIE
73 from .soundcloud import SoundcloudIE
74 from .vbox7 import Vbox7IE
75 from .dbtv import DBTVIE
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.'
107 'skip': 'URL invalid',
109 # Direct download with broken HEAD
111 'url': 'http://ai-radio.org:8000/radio.opus',
118 'skip_download': True, # infinite live stream
120 'expected_warnings': [
121 r'501.*Not Implemented',
125 # Direct link with incorrect MIME type
127 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
128 'md5': '4ccbebe5f36706d85221f204d7eb5913',
130 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
131 'id': '5_Lennart_Poettering_-_Systemd',
133 'title': '5_Lennart_Poettering_-_Systemd',
134 'upload_date': '20141120',
136 'expected_warnings': [
137 'URL could be a direct video link, returning it as such.'
142 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
144 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
145 'title': 'Zero Punctuation',
146 'description': 're:.*groundbreaking video review series.*'
148 'playlist_mincount': 11,
150 # RSS feed with enclosure
152 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
154 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
156 'upload_date': '20150228',
157 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
160 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
162 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
166 'title': 'Automatics, robotics and biocybernetics',
167 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
168 'upload_date': '20130627',
169 'formats': 'mincount:16',
170 'subtitles': 'mincount:1',
173 'force_generic_extractor': True,
174 'skip_download': True,
177 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
179 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
184 'formats': 'mincount:1',
187 'skip_download': True,
190 # SMIL from https://www.restudy.dk/video/play/id/1637
192 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
196 'title': 'video_1637',
197 'formats': 'mincount:3',
200 'skip_download': True,
203 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
205 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
207 'id': 'smil-service',
209 'title': 'smil-service',
210 'formats': 'mincount:1',
213 'skip_download': True,
216 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
218 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
222 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
223 'formats': 'mincount:3',
226 'skip_download': True,
229 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
231 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
233 'id': 'mZlp2ctYIUEB',
235 'title': 'Tikibad ontruimd wegens brand',
236 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
237 'thumbnail': 're:^https?://.*\.jpg$',
241 'skip_download': True,
244 # MPD from http://dash-mse-test.appspot.com/media.html
246 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
247 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
249 'id': 'car-20120827-manifest',
251 'title': 'car-20120827-manifest',
252 'formats': 'mincount:9',
253 'upload_date': '20130904',
256 'format': 'bestvideo',
259 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
261 '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',
266 'formats': 'mincount:8',
270 'skip_download': True,
272 'skip': 'video gone',
274 # m3u8 served with Content-Type: text/plain
276 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
281 'upload_date': '20140720',
282 'formats': 'mincount:11',
286 'skip_download': True,
288 'skip': 'video gone',
292 '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',
296 'upload_date': '20130224',
297 'uploader_id': 'TheVerge',
298 'description': 're:^Chris Ziegler takes a look at the\.*',
299 'uploader': 'The Verge',
300 'title': 'First Firefox OS phones side-by-side',
303 'skip_download': False,
307 # redirect in Refresh HTTP header
308 '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',
312 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
313 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
314 'upload_date': '20150917',
315 'uploader_id': 'brtvofficial',
316 'uploader': 'Boiler Room',
319 'skip_download': False,
323 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
324 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
326 'id': '13601338388002',
328 'uploader': 'www.hodiho.fr',
329 'title': 'R\u00e9gis plante sa Jeep',
332 # bandcamp page with custom domain
334 'add_ie': ['Bandcamp'],
335 'url': 'http://bronyrock.com/track/the-pony-mash',
339 'title': 'The Pony Mash',
340 'uploader': 'M_Pallante',
342 'skip': 'There is a limit of 200 free downloads / month for the test song',
344 # embedded brightcove video
345 # it also tests brightcove videos that need to set the 'Referer' in the
348 'add_ie': ['BrightcoveLegacy'],
349 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
351 'id': '2765128793001',
353 'title': 'Le cours de bourse : l’analyse technique',
354 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
355 'uploader': 'BFM BUSINESS',
358 'skip_download': True,
362 # https://github.com/rg3/youtube-dl/issues/2253
363 'url': 'http://bcove.me/i6nfkrc3',
364 'md5': '0ba9446db037002366bab3b3eb30c88c',
366 'id': '3101154703001',
368 'title': 'Still no power',
369 'uploader': 'thestar.com',
370 '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.',
372 'add_ie': ['BrightcoveLegacy'],
373 'skip': 'video gone',
376 'url': 'http://www.championat.com/video/football/v/87/87499.html',
377 'md5': 'fb973ecf6e4a78a67453647444222983',
379 'id': '3414141473001',
381 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
382 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
383 'uploader': 'Championat',
387 # https://github.com/rg3/youtube-dl/issues/3541
388 'add_ie': ['BrightcoveLegacy'],
389 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
391 'id': '3866516442001',
393 'title': 'Leer mij vrouwen kennen: Aflevering 1',
394 'description': 'Leer mij vrouwen kennen: Aflevering 1',
395 'uploader': 'SBS Broadcasting',
397 'skip': 'Restricted to Netherlands',
399 'skip_download': True, # m3u8 download
404 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
405 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
407 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
409 'title': '2cc213299525360.mov', # that's what we get
412 'add_ie': ['Ooyala'],
415 # ooyala video embedded with http://player.ooyala.com/iframe.js
416 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
418 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
420 'title': '"Steve Jobs: Man in the Machine" trailer',
421 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
425 'skip_download': True,
427 'skip': 'movie expired',
431 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
435 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
436 'upload_date': '20140225',
437 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
438 'uploader': 'Tested',
439 'uploader_id': 'testedcom',
441 # No need to test YoutubeIE here
443 'skip_download': True,
448 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
452 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
453 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
455 # HEAD requests lead to endless 301, while GET is OK
456 'expected_warnings': ['301'],
460 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
464 'title': 'Охотское море стало целиком российским',
465 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
469 'skip_download': True,
474 '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/',
478 'title': 'Дошкольное воспитание',
483 'url': 'http://www.vestifinance.ru/articles/25753',
486 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
491 'title': 'Госзаказ. День 3',
497 'title': 'Госзаказ. День 2',
503 'title': 'Госзаказ. День 1',
509 'skip_download': True,
514 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
516 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
518 'title': 'Ужастики, русский трейлер (2015)',
519 'thumbnail': 're:^https?://.*\.jpg$',
525 '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',
528 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
530 'playlist_mincount': 7,
531 # This forum does not allow <iframe> syntaxes anymore
532 # Now HTML tags are displayed as-is
533 'skip': 'No videos on this page',
537 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
538 'md5': '65fdff94098e4a607385a60c5177c638',
542 'title': 'Hidden miracles of the natural world',
543 'uploader': 'Louie Schwartzberg',
544 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
547 # Embedded Ustream video
549 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
550 'md5': '27b99cdb639c9b12a79bca876a073417',
554 'uploader': 'AU SPA: The NSA and Privacy',
555 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
558 # nowvideo embed hidden behind percent encoding
560 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
561 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
563 'id': '06e53103ca9aa',
565 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
566 'description': 'No description',
571 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
572 'md5': '7653032cbb25bf6c80d80f217055fa43',
574 'id': '048195-004_PLUS7-F',
577 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
578 'upload_date': '20140320',
581 'skip_download': 'Requires rtmpdump'
583 'skip': 'video gone',
587 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
591 'title': 'Alcaline, le concert avec Calogero',
592 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
593 'upload_date': '20150226',
594 'timestamp': 1424989860,
599 'skip_download': True,
601 'expected_warnings': [
607 'url': 'http://www.wired.com/2014/04/honda-asimo/',
608 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
610 'id': '53501be369702d3275860000',
612 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
617 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
618 'md5': '441aeeb82eb72c422c7f14ec533999cd',
620 'id': 'k2mm4bCdJ6CQ2i7c8o2',
622 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
623 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
625 'uploader_id': 'xgditw',
626 'upload_date': '20140425',
627 'timestamp': 1398441542,
629 'add_ie': ['Dailymotion'],
633 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
637 'title': 'The NBL Auction 2014',
638 'uploader': 'BADMINTON England',
639 'uploader_id': 'BADMINTONEvents',
640 'upload_date': '20140603',
641 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
643 'add_ie': ['Youtube'],
645 'skip_download': True,
650 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
651 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
653 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
655 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
656 'description': 'Two valets share their love for movie star Liam Neesons.',
657 'timestamp': 1349922600,
658 'upload_date': '20121011',
661 # YouTube embed via <data-embed-url="">
663 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
667 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
668 'uploader': 'Gameloft',
669 'uploader_id': 'gameloft',
670 'upload_date': '20140828',
671 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
674 'skip_download': True,
679 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
681 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
683 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
684 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
689 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
691 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
692 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
698 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
703 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
704 'md5': '9d65602bf31c6e20014319c7d07fba27',
706 'id': '5123ea6d5e5a7',
709 'uploader': 'www.handjobhub.com',
710 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
713 # Multiple brightcove videos
714 # https://github.com/rg3/youtube-dl/issues/2283
716 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
718 'id': 'always-never',
719 'title': 'Always / Never - The New Yorker',
723 'extract_flat': False,
724 'skip_download': True,
729 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
730 'md5': '96f09a37e44da40dd083e12d9a683327',
734 'title': 'Ump changes call to ball',
735 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
737 'timestamp': 1401537900,
738 'upload_date': '20140531',
739 'thumbnail': 're:^https?://.*\.jpg$',
744 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
745 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
749 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
750 'description': 'a Paywall Videos video from Remilon',
752 'uploader': 'study.com',
753 'timestamp': 1459678540,
754 'upload_date': '20160403',
755 'filesize': 24687186,
759 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
760 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
764 'title': 'Conversation about Hexagonal Rails Part 1',
765 'description': 'a Martin Fowler video from ThoughtWorks',
767 'uploader': 'thoughtworks.wistia.com',
768 'timestamp': 1401832161,
769 'upload_date': '20140603',
772 # Wistia standard embed (async)
774 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
778 'title': 'Drip Brennan Dunn Workshop',
779 'description': 'a JV Webinars video from getdrip-1',
781 'timestamp': 1463607249,
782 'upload_date': '20160518',
785 'skip_download': True,
790 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
794 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
795 'uploader': 'Sophos Security',
796 'title': 'Chet Chat 171 - Oct 29, 2014',
797 'upload_date': '20141029',
800 # Soundcloud multiple embeds
802 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
805 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
807 'playlist_mincount': 7,
811 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
815 'upload_date': '20141112',
816 'title': 'Rosetta #CometLanding webcast HL 10',
819 # Another Livestream embed, without 'new.' in URL
821 'url': 'https://www.freespeech.org/',
825 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
829 'skip_download': True,
834 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
837 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
839 'playlist_mincount': 2,
843 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
847 'upload_date': '20141126',
848 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
853 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
855 'id': '730m_DandD_1901_512k',
857 'uploader': 'www.abc.net.au',
858 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
861 # embedded viddler video
863 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
867 'uploader': 'deadspin',
868 'title': 'WALL-TO-GORTAT',
869 'timestamp': 1422285291,
870 'upload_date': '20150126',
872 'add_ie': ['Viddler'],
876 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
880 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
881 'description': 'md5:601cb790edd05908957dae8aaa866465',
882 'upload_date': '20150220',
884 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
888 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
892 'upload_date': '20150212',
893 'uploader': 'The National Archives UK',
894 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
895 'uploader_id': 'NationalArchives08',
896 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
901 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
902 'playlist_mincount': 5,
904 'id': 'aanslagen-kopenhagen',
905 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
910 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
914 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
917 # Kaltura embed (different embed code)
919 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
923 'upload_date': '20150127',
924 'uploader_id': 'PremierMedia',
926 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
929 # Kaltura embed protected with referrer
931 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
935 'title': 'Violetta - Achter De Schermen - Ruggero',
936 'description': 'Achter de schermen met Ruggero',
937 'timestamp': 1435133761,
938 'upload_date': '20150624',
939 'uploader_id': 'echojecka',
942 # Kaltura embed with single quotes
944 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
949 'timestamp': 1355743100,
950 'upload_date': '20121217',
951 'uploader_id': 'batchUser',
953 'add_ie': ['Kaltura'],
956 # Kaltura embedded via quoted entry_id
957 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
961 'title': '06_matthew_brender_raj_dutt',
962 'timestamp': 1466638791,
963 'upload_date': '20160622',
965 'add_ie': ['Kaltura'],
966 'expected_warnings': [
967 'Could not send HEAD request'
970 'skip_download': True,
973 # Eagle.Platform embed (generic URL)
975 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
976 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
980 'title': 'Навальный вышел на свободу',
981 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
982 'thumbnail': 're:^https?://.*\.jpg$',
988 # ClipYou (Eagle.Platform) embed (custom URL)
990 'url': 'http://muz-tv.ru/play/7129/',
991 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
995 'title': "'O Sole Mio",
996 'thumbnail': 're:^https?://.*\.jpg$',
1003 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1007 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1008 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1009 'thumbnail': 're:^https?://.*\.jpg$',
1016 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1020 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1021 'thumbnail': 're:^https?://.*\.png$',
1027 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1028 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1032 'title': 'Facebook Creates "On This Day" | Crunch Report',
1037 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1041 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1046 # Crooks and Liars embed
1048 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1052 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1053 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1054 'timestamp': 1428207000,
1055 'upload_date': '20150405',
1056 'uploader': 'Heather',
1059 # Crooks and Liars external embed
1061 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1063 'id': 'MTE3MjUtMzQ2MzA',
1065 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1066 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1067 'timestamp': 1265032391,
1068 'upload_date': '20100201',
1069 'uploader': 'Heather',
1072 # NBC Sports vplayer embed
1074 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1076 'id': 'ln7x1qSThw4k',
1078 'title': "PFT Live: New leader in the 'new-look' defense",
1079 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1080 'uploader': 'NBCU-SPORTS',
1081 'upload_date': '20140107',
1082 'timestamp': 1389118457,
1087 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1088 'md5': '1aa589c675898ae6d37a17913cf68d66',
1090 'id': '701714499682',
1092 'title': 'PREVIEW: On Assignment: David Letterman',
1093 '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.',
1098 'url': 'https://video.udn.com/news/300346',
1099 'md5': 'fd2060e988c326991037b9aff9df21a6',
1103 'title': '中一中男師變性 全校師生力挺',
1104 'thumbnail': 're:^https?://.*\.jpg$',
1108 'skip_download': True,
1113 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1115 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1117 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1118 'title': 'This is what separates the Excel masters from the wannabes',
1119 'duration': 191.933,
1123 'skip_download': True,
1126 # Brightcove URL in single quotes
1128 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1129 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1131 'id': '4255764656001',
1133 'title': 'SN Presents: Russell Martin, World Citizen',
1134 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1135 'uploader': 'Rogers Sportsnet',
1136 'uploader_id': '1704050871',
1137 'upload_date': '20150525',
1138 'timestamp': 1432570283,
1141 # Dailymotion Cloud video
1143 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1144 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1148 'title': 'Sauvons les abeilles ! - Le débat',
1149 'description': 'md5:d9082128b1c5277987825d684939ca26',
1150 'thumbnail': 're:^https?://.*\.jpe?g$',
1151 'timestamp': 1434970506,
1152 'upload_date': '20150622',
1153 'uploader': 'Public Sénat',
1154 'uploader_id': 'xa9gza',
1157 # OnionStudios embed
1159 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1163 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1164 'thumbnail': 're:^https?://.*\.jpe?g$',
1165 'uploader': 'ClickHole',
1166 'uploader_id': 'clickhole',
1171 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1173 'id': '74849a00-85a9-11e1-9660-123139220831',
1175 'title': '#whilewewatch',
1178 # AdobeTVVideo embed
1180 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1181 'md5': '43662b577c018ad707a63766462b1e87',
1185 'title': 'New experience with Acrobat DC',
1186 'description': 'New experience with Acrobat DC',
1187 'duration': 248.667,
1190 # ScreenwaveMedia embed
1192 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1193 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1195 'id': 'cinemasnob-55d26273809dd',
1197 'title': 'cinemasnob',
1200 # BrightcoveInPageEmbed embed
1202 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1204 'id': '4238694884001',
1206 'title': 'Tabletop: Dread, Last Thoughts',
1207 'description': 'Tabletop: Dread, Last Thoughts',
1211 # JWPlayer with M3U8
1213 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1217 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1218 'uploader': 'ren.tv',
1222 'skip_download': True,
1225 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1226 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1228 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1230 'id': '4785848093001',
1232 'title': 'The Cardinal Pell Interview',
1233 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1234 'uploader': 'GlobeCast Australia - GlobeStream',
1235 'uploader_id': '2733773828001',
1236 'upload_date': '20160304',
1237 'timestamp': 1457083087,
1241 'skip_download': True,
1244 # Another form of arte.tv embed
1246 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1247 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1249 'id': '030273-562_PLUS7-F',
1251 'title': 'ARTE Reportage - Nulle part, en France',
1252 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1253 'upload_date': '20160409',
1258 'url': 'http://www.wykop.pl/link/3088787/',
1259 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1261 'id': '874_1459135191',
1263 'title': 'Man shows poor quality of new apartment building',
1264 'description': 'The wall is like a sand pile.',
1265 'uploader': 'Lake8737',
1268 # Duplicated embedded video URLs
1270 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1272 'id': '149298443_480_16c25b74_2',
1274 'title': 'vs. Blue Orange Spring Game',
1275 'uploader': 'www.hudl.com',
1278 # twitter:player:stream embed
1280 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1284 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1285 'uploader': 'www.rtl.be',
1289 'skip_download': True,
1292 # twitter:player embed
1294 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1295 'md5': 'a3e0df96369831de324f0778e126653c',
1297 'id': '4909620399001',
1299 'title': 'What Do Black Holes Sound Like?',
1300 'description': 'what do black holes sound like',
1301 'upload_date': '20160524',
1302 'uploader_id': '29913724001',
1303 'timestamp': 1464107587,
1304 'uploader': 'TheAtlantic',
1306 'add_ie': ['BrightcoveLegacy'],
1308 # Facebook <iframe> embed
1310 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1311 'md5': 'fbcde74f534176ecb015849146dd3aee',
1313 'id': '599637780109885',
1315 'title': 'Facebook video #599637780109885',
1318 # Facebook API embed
1320 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1321 'md5': 'a47372ee61b39a7b90287094d447d94e',
1323 'id': '10153467542406923',
1325 'title': 'Facebook video #10153467542406923',
1328 # Wordpress "YouTube Video Importer" plugin
1330 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1331 'md5': 'd16797741b560b485194eddda8121b48',
1333 'id': 'HNTXWDXV9Is',
1335 'title': 'Blue Devils Drumline Stanford lot 2016',
1336 'upload_date': '20160627',
1337 'uploader_id': 'GENOCIDE8GENERAL10',
1338 'uploader': 'cylus cyrus',
1342 # video stored on custom kaltura server
1343 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1344 'md5': '537617d06e64dfed891fa1593c4b30cc',
1348 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1349 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1350 'uploader_id': 'videos.expansion@el-mundo.net',
1351 'upload_date': '20150429',
1352 'timestamp': 1430303472,
1354 'add_ie': ['Kaltura'],
1357 # Non-standard Vimeo embed
1358 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1359 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1363 'title': 'Understanding the web - Teaser',
1364 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1365 'upload_date': '20151214',
1366 'uploader': 'OpenClassrooms',
1367 'uploader_id': 'openclassrooms',
1369 'add_ie': ['Vimeo'],
1372 # generic vimeo embed that requires original URL passed as Referer
1373 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1374 'only_matching': True,
1377 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1378 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1380 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1382 'title': 'Big Buck Bunny',
1383 'description': 'Royalty free test video',
1384 'timestamp': 1432816365,
1385 'upload_date': '20150528',
1389 'skip_download': True,
1391 'add_ie': [ArkenaIE.ie_key()],
1394 '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/',
1398 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1401 'skip_download': True,
1403 'add_ie': [Vbox7IE.ie_key()],
1407 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1410 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1412 'playlist_mincount': 3,
1415 # # TODO: find another test
1416 # # http://schema.org/VideoObject
1417 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1418 # 'md5': '888dcf08b7ea671381f00fab74692755',
1420 # 'id': 'nyvTSJMKId',
1422 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1423 # 'description': '#love for cats.',
1424 # 'timestamp': 1461244995,
1425 # 'upload_date': '20160421',
1428 # 'force_generic_extractor': True,
1433 def report_following_redirect(self, new_url):
1434 """Report information extraction."""
1435 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1437 def _extract_rss(self, url, video_id, doc):
1438 playlist_title = doc.find('./channel/title').text
1439 playlist_desc_el = doc.find('./channel/description')
1440 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1443 for it in doc.findall('./channel/item'):
1444 next_url = xpath_text(it, 'link', fatal=False)
1446 enclosure_nodes = it.findall('./enclosure')
1447 for e in enclosure_nodes:
1448 next_url = e.attrib.get('url')
1458 'title': it.find('title').text,
1462 '_type': 'playlist',
1464 'title': playlist_title,
1465 'description': playlist_desc,
1469 def _extract_camtasia(self, url, video_id, webpage):
1470 """ Returns None if no camtasia video can be found. """
1472 camtasia_cfg = self._search_regex(
1473 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1474 webpage, 'camtasia configuration file', default=None)
1475 if camtasia_cfg is None:
1478 title = self._html_search_meta('DC.title', webpage, fatal=True)
1480 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1481 camtasia_cfg = self._download_xml(
1482 camtasia_url, video_id,
1483 note='Downloading camtasia configuration',
1484 errnote='Failed to download camtasia configuration')
1485 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1488 for n in fileset_node.getchildren():
1489 url_n = n.find('./uri')
1494 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1495 'title': '%s - %s' % (title, n.tag),
1496 'url': compat_urlparse.urljoin(url, url_n.text),
1497 'duration': float_or_none(n.find('./duration').text),
1501 '_type': 'playlist',
1506 def _real_extract(self, url):
1507 if url.startswith('//'):
1510 'url': self.http_scheme() + url,
1513 parsed_url = compat_urlparse.urlparse(url)
1514 if not parsed_url.scheme:
1515 default_search = self._downloader.params.get('default_search')
1516 if default_search is None:
1517 default_search = 'fixup_error'
1519 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1521 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1522 return self.url_result('http://' + url)
1523 elif default_search != 'fixup_error':
1524 if default_search == 'auto_warning':
1525 if re.match(r'^(?:url|URL)$', url):
1526 raise ExtractorError(
1527 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1530 self._downloader.report_warning(
1531 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1532 return self.url_result('ytsearch:' + url)
1534 if default_search in ('error', 'fixup_error'):
1535 raise ExtractorError(
1536 '%r is not a valid URL. '
1537 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1538 % (url, url), expected=True)
1540 if ':' not in default_search:
1541 default_search += ':'
1542 return self.url_result(default_search + url)
1544 url, smuggled_data = unsmuggle_url(url)
1545 force_videoid = None
1546 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1547 if smuggled_data and 'force_videoid' in smuggled_data:
1548 force_videoid = smuggled_data['force_videoid']
1549 video_id = force_videoid
1551 video_id = self._generic_id(url)
1553 self.to_screen('%s: Requesting header' % video_id)
1555 head_req = HEADRequest(url)
1556 head_response = self._request_webpage(
1558 note=False, errnote='Could not send HEAD request to %s' % url,
1561 if head_response is not False:
1562 # Check for redirect
1563 new_url = head_response.geturl()
1565 self.report_following_redirect(new_url)
1567 new_url = smuggle_url(
1568 new_url, {'force_videoid': force_videoid})
1569 return self.url_result(new_url)
1571 full_response = None
1572 if head_response is False:
1573 request = sanitized_Request(url)
1574 request.add_header('Accept-Encoding', '*')
1575 full_response = self._request_webpage(request, video_id)
1576 head_response = full_response
1580 'title': self._generic_title(url),
1581 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1584 # Check for direct link to a video
1585 content_type = head_response.headers.get('Content-Type', '').lower()
1586 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1588 format_id = m.group('format_id')
1589 if format_id.endswith('mpegurl'):
1590 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1591 elif format_id == 'f4m':
1592 formats = self._extract_f4m_formats(url, video_id)
1595 'format_id': m.group('format_id'),
1597 'vcodec': 'none' if m.group('type') == 'audio' else None
1599 info_dict['direct'] = True
1600 self._sort_formats(formats)
1601 info_dict['formats'] = formats
1604 if not self._downloader.params.get('test', False) and not is_intentional:
1605 force = self._downloader.params.get('force_generic_extractor', False)
1606 self._downloader.report_warning(
1607 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1609 if not full_response:
1610 request = sanitized_Request(url)
1611 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1612 # making it impossible to download only chunk of the file (yet we need only 512kB to
1613 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1614 # that will always result in downloading the whole file that is not desirable.
1615 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1616 # to accept raw bytes and being able to download only a chunk.
1617 # It may probably better to solve this by checking Content-Type for application/octet-stream
1618 # after HEAD request finishes, but not sure if we can rely on this.
1619 request.add_header('Accept-Encoding', '*')
1620 full_response = self._request_webpage(request, video_id)
1622 first_bytes = full_response.read(512)
1624 # Is it an M3U playlist?
1625 if first_bytes.startswith(b'#EXTM3U'):
1626 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1627 self._sort_formats(info_dict['formats'])
1630 # Maybe it's a direct link to a video?
1631 # Be careful not to download the whole thing!
1632 if not is_html(first_bytes):
1633 self._downloader.report_warning(
1634 'URL could be a direct video link, returning it as such.')
1641 webpage = self._webpage_read_content(
1642 full_response, url, video_id, prefix=first_bytes)
1644 self.report_extraction(video_id)
1646 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1648 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1649 if doc.tag == 'rss':
1650 return self._extract_rss(url, video_id, doc)
1651 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1652 smil = self._parse_smil(doc, url, video_id)
1653 self._sort_formats(smil['formats'])
1655 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1656 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1657 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1658 info_dict['formats'] = self._parse_mpd_formats(
1660 mpd_base_url=full_response.geturl().rpartition('/')[0],
1662 self._sort_formats(info_dict['formats'])
1664 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1665 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1666 self._sort_formats(info_dict['formats'])
1668 except compat_xml_parse_error:
1671 # Is it a Camtasia project?
1672 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1673 if camtasia_res is not None:
1676 # Sometimes embedded video player is hidden behind percent encoding
1677 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1678 # Unescaping the whole page allows to handle those cases in a generic way
1679 webpage = compat_urllib_parse_unquote(webpage)
1681 # it's tempting to parse this further, but you would
1682 # have to take into account all the variations like
1683 # Video Title - Site Name
1684 # Site Name | Video Title
1685 # Video Title - Tagline | Site Name
1686 # and so on and so forth; it's just not practical
1687 video_title = self._og_search_title(
1688 webpage, default=None) or self._html_search_regex(
1689 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1692 # Try to detect age limit automatically
1693 age_limit = self._rta_search(webpage)
1694 # And then there are the jokers who advertise that they use RTA,
1695 # but actually don't.
1696 AGE_LIMIT_MARKERS = [
1697 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1699 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1702 # video uploader is domain name
1703 video_uploader = self._search_regex(
1704 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1706 video_description = self._og_search_description(webpage, default=None)
1707 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1710 def _playlist_from_matches(matches, getter=None, ie=None):
1712 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1714 return self.playlist_result(
1715 urlrs, playlist_id=video_id, playlist_title=video_title)
1717 # Look for Brightcove Legacy Studio embeds
1718 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1720 self.to_screen('Brightcove video detected.')
1723 'url': smuggle_url(bc_url, {'Referer': url}),
1724 'ie_key': 'BrightcoveLegacy'
1725 } for bc_url in bc_urls]
1728 '_type': 'playlist',
1729 'title': video_title,
1734 # Look for Brightcove New Studio embeds
1735 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1737 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1739 # Look for ThePlatform embeds
1740 tp_urls = ThePlatformIE._extract_urls(webpage)
1742 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1744 # Look for Vessel embeds
1745 vessel_urls = VesselIE._extract_urls(webpage)
1747 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1749 # Look for embedded rtl.nl player
1750 matches = re.findall(
1751 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1754 return _playlist_from_matches(matches, ie='RtlNl')
1756 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1758 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1760 vid_me_embed_url = self._search_regex(
1761 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1762 webpage, 'vid.me embed', default=None)
1763 if vid_me_embed_url is not None:
1764 return self.url_result(vid_me_embed_url, 'Vidme')
1766 # Look for embedded YouTube player
1767 matches = re.findall(r'''(?x)
1776 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1780 return _playlist_from_matches(
1781 matches, lambda m: unescapeHTML(m[1]))
1783 # Look for lazyYT YouTube embed
1784 matches = re.findall(
1785 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1787 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1789 # Look for Wordpress "YouTube Video Importer" plugin
1790 matches = re.findall(r'''(?x)<div[^>]+
1791 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1792 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1794 return _playlist_from_matches(matches, lambda m: m[-1])
1796 matches = DailymotionIE._extract_urls(webpage)
1798 return _playlist_from_matches(matches)
1800 # Look for embedded Dailymotion playlist player (#3822)
1802 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1804 playlists = re.findall(
1805 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1807 return _playlist_from_matches(
1808 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1810 # Look for embedded Wistia player
1812 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1814 embed_url = self._proto_relative_url(
1815 unescapeHTML(match.group('url')))
1817 '_type': 'url_transparent',
1820 'uploader': video_uploader,
1823 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1826 '_type': 'url_transparent',
1827 'url': 'wistia:%s' % match.group('id'),
1829 'uploader': video_uploader,
1834 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1835 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1838 return self.url_result(self._proto_relative_url(
1839 'wistia:%s' % match.group('id')), 'Wistia')
1841 # Look for SVT player
1842 svt_url = SVTIE._extract_url(webpage)
1844 return self.url_result(svt_url, 'SVT')
1846 # Look for embedded condenast player
1847 matches = re.findall(
1848 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1852 '_type': 'playlist',
1855 'ie_key': 'CondeNast',
1857 } for ma in matches],
1858 'title': video_title,
1862 # Look for Bandcamp pages with custom domain
1863 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1864 if mobj is not None:
1865 burl = unescapeHTML(mobj.group(1))
1866 # Don't set the extractor because it can be a track url or an album
1867 return self.url_result(burl)
1869 # Look for embedded Vevo player
1871 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1872 if mobj is not None:
1873 return self.url_result(mobj.group('url'))
1875 # Look for embedded Viddler player
1877 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1879 if mobj is not None:
1880 return self.url_result(mobj.group('url'))
1882 # Look for NYTimes player
1884 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1886 if mobj is not None:
1887 return self.url_result(mobj.group('url'))
1889 # Look for Libsyn player
1891 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1892 if mobj is not None:
1893 return self.url_result(mobj.group('url'))
1895 # Look for Ooyala videos
1896 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1897 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1898 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1899 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1900 if mobj is not None:
1901 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1903 # Look for multiple Ooyala embeds on SBN network websites
1904 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1905 if mobj is not None:
1906 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1908 return _playlist_from_matches(
1909 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1911 # Look for Aparat videos
1912 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1913 if mobj is not None:
1914 return self.url_result(mobj.group(1), 'Aparat')
1916 # Look for MPORA videos
1917 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1918 if mobj is not None:
1919 return self.url_result(mobj.group(1), 'Mpora')
1921 # Look for embedded NovaMov-based player
1923 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1924 (?P<url>http://(?:(?:embed|www)\.)?
1926 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1927 videoweed\.(?:es|com)|
1928 movshare\.(?:net|sx|ag)|
1929 divxstage\.(?:eu|net|ch|co|at|ag))
1930 /embed\.php.+?)\1''', webpage)
1931 if mobj is not None:
1932 return self.url_result(mobj.group('url'))
1934 # Look for embedded Facebook player
1935 facebook_url = FacebookIE._extract_url(webpage)
1936 if facebook_url is not None:
1937 return self.url_result(facebook_url, 'Facebook')
1939 # Look for embedded VK player
1940 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1941 if mobj is not None:
1942 return self.url_result(mobj.group('url'), 'VK')
1944 # Look for embedded Odnoklassniki player
1945 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1946 if mobj is not None:
1947 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1949 # Look for embedded ivi player
1950 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1951 if mobj is not None:
1952 return self.url_result(mobj.group('url'), 'Ivi')
1954 # Look for embedded Huffington Post player
1956 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1957 if mobj is not None:
1958 return self.url_result(mobj.group('url'), 'HuffPost')
1961 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1962 if mobj is not None:
1963 return self.url_result(mobj.group('url'))
1964 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1965 if mobj is not None:
1966 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1968 # Look for funnyordie embed
1969 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1971 return _playlist_from_matches(
1972 matches, getter=unescapeHTML, ie='FunnyOrDie')
1974 # Look for BBC iPlayer embed
1975 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1977 return _playlist_from_matches(matches, ie='BBCCoUk')
1979 # Look for embedded RUTV player
1980 rutv_url = RUTVIE._extract_url(webpage)
1982 return self.url_result(rutv_url, 'RUTV')
1984 # Look for embedded TVC player
1985 tvc_url = TVCIE._extract_url(webpage)
1987 return self.url_result(tvc_url, 'TVC')
1989 # Look for embedded SportBox player
1990 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1992 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1994 # Look for embedded PornHub player
1995 pornhub_url = PornHubIE._extract_url(webpage)
1997 return self.url_result(pornhub_url, 'PornHub')
1999 # Look for embedded XHamster player
2000 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2002 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2004 # Look for embedded TNAFlixNetwork player
2005 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2007 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2009 # Look for embedded Tvigle player
2011 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2012 if mobj is not None:
2013 return self.url_result(mobj.group('url'), 'Tvigle')
2015 # Look for embedded TED player
2017 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2018 if mobj is not None:
2019 return self.url_result(mobj.group('url'), 'TED')
2021 # Look for embedded Ustream videos
2023 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2024 if mobj is not None:
2025 return self.url_result(mobj.group('url'), 'Ustream')
2027 # Look for embedded arte.tv player
2029 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2031 if mobj is not None:
2032 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2034 # Look for embedded francetv player
2036 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2038 if mobj is not None:
2039 return self.url_result(mobj.group('url'))
2041 # Look for embedded smotri.com player
2042 smotri_url = SmotriIE._extract_url(webpage)
2044 return self.url_result(smotri_url, 'Smotri')
2046 # Look for embedded Myvi.ru player
2047 myvi_url = MyviIE._extract_url(webpage)
2049 return self.url_result(myvi_url)
2051 # Look for embedded soundcloud player
2052 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2054 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2056 # Look for embedded mtvservices player
2057 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2059 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2061 # Look for embedded yahoo player
2063 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2065 if mobj is not None:
2066 return self.url_result(mobj.group('url'), 'Yahoo')
2068 # Look for embedded sbs.com.au player
2072 <meta\s+property="og:video"\s+content=|
2075 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2077 if mobj is not None:
2078 return self.url_result(mobj.group('url'), 'SBS')
2080 # Look for embedded Cinchcast player
2082 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2084 if mobj is not None:
2085 return self.url_result(mobj.group('url'), 'Cinchcast')
2088 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2092 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2094 if mobj is not None:
2095 return self.url_result(mobj.group('url'), 'MLB')
2098 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2100 if mobj is not None:
2101 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2104 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2106 if mobj is not None:
2107 return self.url_result(mobj.group('url'), 'Livestream')
2109 # Look for Zapiks embed
2111 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2112 if mobj is not None:
2113 return self.url_result(mobj.group('url'), 'Zapiks')
2115 # Look for Kaltura embeds
2116 kaltura_url = KalturaIE._extract_url(webpage)
2118 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2120 # Look for Eagle.Platform embeds
2121 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2122 if eagleplatform_url:
2123 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2125 # Look for ClipYou (uses Eagle.Platform) embeds
2127 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2128 if mobj is not None:
2129 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2131 # Look for Pladform embeds
2132 pladform_url = PladformIE._extract_url(webpage)
2134 return self.url_result(pladform_url)
2136 # Look for Videomore embeds
2137 videomore_url = VideomoreIE._extract_url(webpage)
2139 return self.url_result(videomore_url)
2141 # Look for Playwire embeds
2143 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2144 if mobj is not None:
2145 return self.url_result(mobj.group('url'))
2147 # Look for 5min embeds
2149 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2150 if mobj is not None:
2151 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2153 # Look for Crooks and Liars embeds
2155 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2156 if mobj is not None:
2157 return self.url_result(mobj.group('url'))
2159 # Look for NBC Sports VPlayer embeds
2160 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2162 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2164 # Look for NBC News embeds
2165 nbc_news_embed_url = re.search(
2166 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2167 if nbc_news_embed_url:
2168 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2170 # Look for Google Drive embeds
2171 google_drive_url = GoogleDriveIE._extract_url(webpage)
2172 if google_drive_url:
2173 return self.url_result(google_drive_url, 'GoogleDrive')
2175 # Look for UDN embeds
2177 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2178 if mobj is not None:
2179 return self.url_result(
2180 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2182 # Look for Senate ISVP iframe
2183 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2185 return self.url_result(senate_isvp_url, 'SenateISVP')
2187 # Look for Dailymotion Cloud videos
2188 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2190 return self.url_result(dmcloud_url, 'DailymotionCloud')
2192 # Look for OnionStudios embeds
2193 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2194 if onionstudios_url:
2195 return self.url_result(onionstudios_url)
2197 # Look for ViewLift embeds
2198 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2200 return self.url_result(viewlift_url)
2202 # Look for JWPlatform embeds
2203 jwplatform_url = JWPlatformIE._extract_url(webpage)
2205 return self.url_result(jwplatform_url, 'JWPlatform')
2207 # Look for ScreenwaveMedia embeds
2208 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2209 if mobj is not None:
2210 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2212 # Look for Digiteka embeds
2213 digiteka_url = DigitekaIE._extract_url(webpage)
2215 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2217 # Look for Arkena embeds
2218 arkena_url = ArkenaIE._extract_url(webpage)
2220 return self.url_result(arkena_url, ArkenaIE.ie_key())
2222 # Look for Limelight embeds
2223 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2227 'Channel': 'channel',
2228 'ChannelList': 'channel_list',
2230 return self.url_result('limelight:%s:%s' % (
2231 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2233 # Look for AdobeTVVideo embeds
2235 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2237 if mobj is not None:
2238 return self.url_result(
2239 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2242 # Look for Vine embeds
2244 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2246 if mobj is not None:
2247 return self.url_result(
2248 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2250 # Look for VODPlatform embeds
2252 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2254 if mobj is not None:
2255 return self.url_result(
2256 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2258 # Look for Mangomolo embeds
2260 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2262 video\?.*?\bid=(?P<video_id>\d+)|
2263 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2264 ).+?)\1''', webpage)
2265 if mobj is not None:
2267 '_type': 'url_transparent',
2268 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2269 'title': video_title,
2270 'description': video_description,
2271 'thumbnail': video_thumbnail,
2272 'uploader': video_uploader,
2274 video_id = mobj.group('video_id')
2277 'ie_key': 'MangomoloVideo',
2282 'ie_key': 'MangomoloLive',
2283 'id': mobj.group('channel_id'),
2287 # Look for Instagram embeds
2288 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2289 if instagram_embed_url is not None:
2290 return self.url_result(
2291 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2293 # Look for LiveLeak embeds
2294 liveleak_url = LiveLeakIE._extract_url(webpage)
2296 return self.url_result(liveleak_url, 'LiveLeak')
2298 # Look for 3Q SDN embeds
2299 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2302 '_type': 'url_transparent',
2303 'ie_key': ThreeQSDNIE.ie_key(),
2304 'url': self._proto_relative_url(threeqsdn_url),
2305 'title': video_title,
2306 'description': video_description,
2307 'thumbnail': video_thumbnail,
2308 'uploader': video_uploader,
2311 # Look for VBOX7 embeds
2312 vbox7_url = Vbox7IE._extract_url(webpage)
2314 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2316 # Look for DBTV embeds
2317 dbtv_urls = DBTVIE._extract_urls(webpage)
2319 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2321 # Looking for http://schema.org/VideoObject
2322 json_ld = self._search_json_ld(
2323 webpage, video_id, default={}, expected_type='VideoObject')
2324 if json_ld.get('url'):
2326 'title': video_title or info_dict['title'],
2327 'description': video_description,
2328 'thumbnail': video_thumbnail,
2329 'age_limit': age_limit
2331 info_dict.update(json_ld)
2334 # Look for HTML5 media
2335 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2337 for entry in entries:
2340 'title': video_title,
2342 self._sort_formats(entry['formats'])
2343 return self.playlist_result(entries)
2345 def check_video(vurl):
2346 if YoutubeIE.suitable(vurl):
2348 vpath = compat_urlparse.urlparse(vurl).path
2349 vext = determine_ext(vpath)
2350 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2352 def filter_video(urls):
2353 return list(filter(check_video, urls))
2355 # Start with something easy: JW Player in SWFObject
2356 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2358 # Look for gorilla-vid style embedding
2359 found = filter_video(re.findall(r'''(?sx)
2363 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2366 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2368 # Broaden the search a little bit
2369 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2371 # Broaden the findall a little bit: JWPlayer JS loader
2372 found = filter_video(re.findall(
2373 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2376 found = filter_video(re.findall(r'''(?xs)
2377 flowplayer\("[^"]+",\s*
2379 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2380 ["']?url["']?\s*:\s*["']([^"']+)["']
2385 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2387 # Try to find twitter cards info
2388 # twitter:player:stream should be checked before twitter:player since
2389 # it is expected to contain a raw stream (see
2390 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2391 found = filter_video(re.findall(
2392 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2394 # We look for Open Graph info:
2395 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2396 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2397 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2398 if m_video_type is not None:
2399 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2401 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2403 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2404 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2407 # Look also in Refresh HTTP header
2408 refresh_header = head_response.headers.get('Refresh')
2410 # In python 2 response HTTP headers are bytestrings
2411 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2412 refresh_header = refresh_header.decode('iso-8859-1')
2413 found = re.search(REDIRECT_REGEX, refresh_header)
2415 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2416 self.report_following_redirect(new_url)
2423 # twitter:player is a https URL to iframe player that may or may not
2424 # be supported by youtube-dl thus this is checked the very last (see
2425 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2426 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2428 return self.url_result(embed_url)
2431 raise UnsupportedError(url)
2434 for video_url in orderedSet(found):
2435 video_url = unescapeHTML(video_url)
2436 video_url = video_url.replace('\\/', '/')
2437 video_url = compat_urlparse.urljoin(url, video_url)
2438 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2440 # Sometimes, jwplayer extraction will result in a YouTube URL
2441 if YoutubeIE.suitable(video_url):
2442 entries.append(self.url_result(video_url, 'Youtube'))
2445 # here's a fun little line of code for you:
2446 video_id = os.path.splitext(video_id)[0]
2450 'uploader': video_uploader,
2451 'title': video_title,
2452 'age_limit': age_limit,
2455 ext = determine_ext(video_url)
2457 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2459 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2461 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2463 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2465 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2467 entry_info_dict['url'] = video_url
2469 if entry_info_dict.get('formats'):
2470 self._sort_formats(entry_info_dict['formats'])
2472 entries.append(entry_info_dict)
2474 if len(entries) == 1:
2477 for num, e in enumerate(entries, start=1):
2478 # 'url' results don't have a title
2479 if e.get('title') is not None:
2480 e['title'] = '%s (%d)' % (e['title'], num)
2482 '_type': 'playlist',