3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
39 from .nbc import NBCSportsVPlayerIE
40 from .ooyala import OoyalaIE
41 from .rutv import RUTVIE
42 from .tvc import TVCIE
43 from .sportbox import SportBoxEmbedIE
44 from .smotri import SmotriIE
45 from .myvi import MyviIE
46 from .condenast import CondeNastIE
47 from .udn import UDNEmbedIE
48 from .senateisvp import SenateISVPIE
49 from .svt import SVTIE
50 from .pornhub import PornHubIE
51 from .xhamster import XHamsterEmbedIE
52 from .tnaflix import TNAFlixNetworkEmbedIE
53 from .drtuber import DrTuberIE
54 from .redtube import RedTubeIE
55 from .vimeo import VimeoIE
56 from .dailymotion import (
60 from .onionstudios import OnionStudiosIE
61 from .viewlift import ViewLiftEmbedIE
62 from .mtv import MTVServicesEmbeddedIE
63 from .pladform import PladformIE
64 from .videomore import VideomoreIE
65 from .webcaster import WebcasterFeedIE
66 from .googledrive import GoogleDriveIE
67 from .jwplatform import JWPlatformIE
68 from .digiteka import DigitekaIE
69 from .arkena import ArkenaIE
70 from .instagram import InstagramIE
71 from .liveleak import LiveLeakIE
72 from .threeqsdn import ThreeQSDNIE
73 from .theplatform import ThePlatformIE
74 from .vessel import VesselIE
75 from .kaltura import KalturaIE
76 from .eagleplatform import EaglePlatformIE
77 from .facebook import FacebookIE
78 from .soundcloud import SoundcloudIE
79 from .tunein import TuneInBaseIE
80 from .vbox7 import Vbox7IE
81 from .dbtv import DBTVIE
82 from .piksel import PikselIE
83 from .videa import VideaIE
84 from .twentymin import TwentyMinutenIE
85 from .ustream import UstreamIE
86 from .openload import OpenloadIE
87 from .videopress import VideoPressIE
88 from .rutube import RutubeIE
89 from .limelight import LimelightBaseIE
90 from .anvato import AnvatoIE
91 from .washingtonpost import WashingtonPostIE
92 from .wistia import WistiaIE
93 from .mediaset import MediasetIE
94 from .joj import JojIE
97 class GenericIE(InfoExtractor):
98 IE_DESC = 'Generic downloader that works on some sites'
102 # Direct link to a video
104 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
105 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
110 'upload_date': '20100513',
113 # Direct link to media delivered compressed (until Accept-Encoding is *)
115 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
116 'md5': '128c42e68b13950268b648275386fc74',
118 'id': 'FictionJunction-Parallel_Hearts',
120 'title': 'FictionJunction-Parallel_Hearts',
121 'upload_date': '20140522',
123 'expected_warnings': [
124 'URL could be a direct video link, returning it as such.'
126 'skip': 'URL invalid',
128 # Direct download with broken HEAD
130 'url': 'http://ai-radio.org:8000/radio.opus',
137 'skip_download': True, # infinite live stream
139 'expected_warnings': [
140 r'501.*Not Implemented',
144 # Direct link with incorrect MIME type
146 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
147 'md5': '4ccbebe5f36706d85221f204d7eb5913',
149 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
150 'id': '5_Lennart_Poettering_-_Systemd',
152 'title': '5_Lennart_Poettering_-_Systemd',
153 'upload_date': '20141120',
155 'expected_warnings': [
156 'URL could be a direct video link, returning it as such.'
161 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
163 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
164 'title': 'Zero Punctuation',
165 'description': 're:.*groundbreaking video review series.*'
167 'playlist_mincount': 11,
169 # RSS feed with enclosure
171 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
173 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
175 'upload_date': '20150228',
176 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
179 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
181 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
185 'title': 'Automatics, robotics and biocybernetics',
186 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
187 'upload_date': '20130627',
188 'formats': 'mincount:16',
189 'subtitles': 'mincount:1',
192 'force_generic_extractor': True,
193 'skip_download': True,
196 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
198 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
203 'formats': 'mincount:1',
206 'skip_download': True,
209 # SMIL from https://www.restudy.dk/video/play/id/1637
211 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
215 'title': 'video_1637',
216 'formats': 'mincount:3',
219 'skip_download': True,
222 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
224 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
226 'id': 'smil-service',
228 'title': 'smil-service',
229 'formats': 'mincount:1',
232 'skip_download': True,
235 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
237 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
241 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
242 'formats': 'mincount:3',
245 'skip_download': True,
248 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
250 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
252 'id': 'mZlp2ctYIUEB',
254 'title': 'Tikibad ontruimd wegens brand',
255 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
256 'thumbnail': r're:^https?://.*\.jpg$',
260 'skip_download': True,
263 # MPD from http://dash-mse-test.appspot.com/media.html
265 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
266 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
268 'id': 'car-20120827-manifest',
270 'title': 'car-20120827-manifest',
271 'formats': 'mincount:9',
272 'upload_date': '20130904',
275 'format': 'bestvideo',
278 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
280 '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',
285 'formats': 'mincount:8',
289 'skip_download': True,
291 'skip': 'video gone',
293 # m3u8 served with Content-Type: text/plain
295 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
300 'upload_date': '20140720',
301 'formats': 'mincount:11',
305 'skip_download': True,
307 'skip': 'video gone',
311 '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',
315 'upload_date': '20130224',
316 'uploader_id': 'TheVerge',
317 'description': r're:^Chris Ziegler takes a look at the\.*',
318 'uploader': 'The Verge',
319 'title': 'First Firefox OS phones side-by-side',
322 'skip_download': False,
326 # redirect in Refresh HTTP header
327 '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',
331 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
332 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
333 'upload_date': '20150917',
334 'uploader_id': 'brtvofficial',
335 'uploader': 'Boiler Room',
338 'skip_download': False,
342 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
343 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
345 'id': '13601338388002',
347 'uploader': 'www.hodiho.fr',
348 'title': 'R\u00e9gis plante sa Jeep',
351 # bandcamp page with custom domain
353 'add_ie': ['Bandcamp'],
354 'url': 'http://bronyrock.com/track/the-pony-mash',
358 'title': 'The Pony Mash',
359 'uploader': 'M_Pallante',
361 'skip': 'There is a limit of 200 free downloads / month for the test song',
364 # embedded brightcove video
365 # it also tests brightcove videos that need to set the 'Referer'
366 # in the http requests
367 'add_ie': ['BrightcoveLegacy'],
368 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
370 'id': '2765128793001',
372 'title': 'Le cours de bourse : l’analyse technique',
373 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
374 'uploader': 'BFM BUSINESS',
377 'skip_download': True,
381 # embedded with itemprop embedURL and video id spelled as `idVideo`
382 'add_id': ['BrightcoveLegacy'],
383 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
385 'id': '5255628253001',
387 'title': 'md5:37c519b1128915607601e75a87995fc0',
388 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
389 'uploader': 'BFM BUSINESS',
390 'uploader_id': '876450612001',
391 'timestamp': 1482255315,
392 'upload_date': '20161220',
395 'skip_download': True,
399 # https://github.com/rg3/youtube-dl/issues/2253
400 'url': 'http://bcove.me/i6nfkrc3',
401 'md5': '0ba9446db037002366bab3b3eb30c88c',
403 'id': '3101154703001',
405 'title': 'Still no power',
406 'uploader': 'thestar.com',
407 '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.',
409 'add_ie': ['BrightcoveLegacy'],
410 'skip': 'video gone',
413 'url': 'http://www.championat.com/video/football/v/87/87499.html',
414 'md5': 'fb973ecf6e4a78a67453647444222983',
416 'id': '3414141473001',
418 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
419 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
420 'uploader': 'Championat',
424 # https://github.com/rg3/youtube-dl/issues/3541
425 'add_ie': ['BrightcoveLegacy'],
426 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
428 'id': '3866516442001',
430 'title': 'Leer mij vrouwen kennen: Aflevering 1',
431 'description': 'Leer mij vrouwen kennen: Aflevering 1',
432 'uploader': 'SBS Broadcasting',
434 'skip': 'Restricted to Netherlands',
436 'skip_download': True, # m3u8 download
440 # Brightcove video in <iframe>
441 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
442 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
444 'id': '5360463607001',
446 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
447 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
448 'uploader': 'United Nations',
449 'uploader_id': '1362235914001',
450 'timestamp': 1489593889,
451 'upload_date': '20170315',
453 'add_ie': ['BrightcoveLegacy'],
456 # Brightcove with alternative playerID key
457 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
459 'id': 'nmeth.2062_SV1',
460 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
464 'id': '2228375078001',
466 'title': 'nmeth.2062-sv1',
467 'description': 'nmeth.2062-sv1',
468 'timestamp': 1363357591,
469 'upload_date': '20130315',
470 'uploader': 'Nature Publishing Group',
471 'uploader_id': '1964492299001',
476 # Brightcove with UUID in videoPlayer
477 'url': 'http://www8.hp.com/cn/zh/home.html',
479 'id': '5255815316001',
481 'title': 'Sprocket Video - China',
482 'description': 'Sprocket Video - China',
483 'uploader': 'HP-Video Gallery',
484 'timestamp': 1482263210,
485 'upload_date': '20161220',
486 'uploader_id': '1107601872001',
489 'skip_download': True, # m3u8 download
491 'skip': 'video rotates...weekly?',
494 # Brightcove:new type [2].
495 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
496 'md5': '2b35148fcf48da41c9fb4591650784f3',
498 'id': '5348741021001',
500 'upload_date': '20170306',
501 'uploader_id': '4191638492001',
502 'timestamp': 1488769918,
503 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
508 # Alternative brightcove <video> attributes
509 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
511 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
512 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
515 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
517 'id': '5311302538001',
519 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
520 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
521 'timestamp': 1486321708,
522 'upload_date': '20170205',
523 'uploader_id': '800000640001',
525 'only_matching': True,
529 # Brightcove with UUID in videoPlayer
530 'url': 'http://www8.hp.com/cn/zh/home.html',
532 'id': '5255815316001',
534 'title': 'Sprocket Video - China',
535 'description': 'Sprocket Video - China',
536 'uploader': 'HP-Video Gallery',
537 'timestamp': 1482263210,
538 'upload_date': '20161220',
539 'uploader_id': '1107601872001',
542 'skip_download': True, # m3u8 download
547 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
548 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
550 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
552 'title': '2cc213299525360.mov', # that's what we get
555 'add_ie': ['Ooyala'],
558 # ooyala video embedded with http://player.ooyala.com/iframe.js
559 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
561 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
563 'title': '"Steve Jobs: Man in the Machine" trailer',
564 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
568 'skip_download': True,
570 'skip': 'movie expired',
574 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
578 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
579 'upload_date': '20140225',
580 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
581 'uploader': 'Tested',
582 'uploader_id': 'testedcom',
584 # No need to test YoutubeIE here
586 'skip_download': True,
591 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
595 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
596 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
598 # HEAD requests lead to endless 301, while GET is OK
599 'expected_warnings': ['301'],
603 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
607 'title': 'Охотское море стало целиком российским',
608 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
612 'skip_download': True,
617 '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/',
621 'title': 'Дошкольное воспитание',
626 'url': 'http://www.vestifinance.ru/articles/25753',
629 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
634 'title': 'Госзаказ. День 3',
640 'title': 'Госзаказ. День 2',
646 'title': 'Госзаказ. День 1',
652 'skip_download': True,
657 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
659 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
661 'title': 'Ужастики, русский трейлер (2015)',
662 'thumbnail': r're:^https?://.*\.jpg$',
668 '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',
671 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
673 'playlist_mincount': 7,
674 # This forum does not allow <iframe> syntaxes anymore
675 # Now HTML tags are displayed as-is
676 'skip': 'No videos on this page',
680 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
681 'md5': '65fdff94098e4a607385a60c5177c638',
685 'title': 'Hidden miracles of the natural world',
686 'uploader': 'Louie Schwartzberg',
687 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
690 # nowvideo embed hidden behind percent encoding
692 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
693 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
695 'id': '06e53103ca9aa',
697 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
698 'description': 'No description',
703 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
704 'md5': '7653032cbb25bf6c80d80f217055fa43',
706 'id': '048195-004_PLUS7-F',
709 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
710 'upload_date': '20140320',
713 'skip_download': 'Requires rtmpdump'
715 'skip': 'video gone',
719 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
723 'title': 'Alcaline, le concert avec Calogero',
724 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
725 'upload_date': '20150226',
726 'timestamp': 1424989860,
731 'skip_download': True,
733 'expected_warnings': [
739 'url': 'http://www.wired.com/2014/04/honda-asimo/',
740 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
742 'id': '53501be369702d3275860000',
744 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
749 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
750 'md5': '441aeeb82eb72c422c7f14ec533999cd',
752 'id': 'k2mm4bCdJ6CQ2i7c8o2',
754 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
755 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
757 'uploader_id': 'xgditw',
758 'upload_date': '20140425',
759 'timestamp': 1398441542,
761 'add_ie': ['Dailymotion'],
765 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
769 'title': 'The NBL Auction 2014',
770 'uploader': 'BADMINTON England',
771 'uploader_id': 'BADMINTONEvents',
772 'upload_date': '20140603',
773 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
775 'add_ie': ['Youtube'],
777 'skip_download': True,
782 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
783 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
785 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
787 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
788 'description': 'Two valets share their love for movie star Liam Neesons.',
789 'timestamp': 1349922600,
790 'upload_date': '20121011',
793 # YouTube embed via <data-embed-url="">
795 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
799 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
800 'uploader': 'Gameloft',
801 'uploader_id': 'gameloft',
802 'upload_date': '20140828',
803 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
806 'skip_download': True,
809 # YouTube <object> embed
811 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
812 'md5': '516718101ec834f74318df76259fb3cc',
816 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
817 'upload_date': '20080526',
818 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
819 'uploader': 'Christopher Sykes',
820 'uploader_id': 'ChristopherJSykes',
822 'add_ie': ['Youtube'],
826 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
828 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
830 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
831 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
836 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
838 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
839 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
845 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
850 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
851 'md5': '9d65602bf31c6e20014319c7d07fba27',
853 'id': '5123ea6d5e5a7',
856 'uploader': 'www.handjobhub.com',
857 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
860 # Multiple brightcove videos
861 # https://github.com/rg3/youtube-dl/issues/2283
863 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
865 'id': 'always-never',
866 'title': 'Always / Never - The New Yorker',
870 'extract_flat': False,
871 'skip_download': True,
876 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
877 'md5': '96f09a37e44da40dd083e12d9a683327',
881 'title': 'Ump changes call to ball',
882 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
884 'timestamp': 1401537900,
885 'upload_date': '20140531',
886 'thumbnail': r're:^https?://.*\.jpg$',
891 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
892 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
896 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
897 'description': 'a Paywall Videos video from Remilon',
899 'uploader': 'study.com',
900 'timestamp': 1459678540,
901 'upload_date': '20160403',
902 'filesize': 24687186,
906 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
907 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
911 'title': 'Conversation about Hexagonal Rails Part 1',
912 'description': 'a Martin Fowler video from ThoughtWorks',
914 'uploader': 'thoughtworks.wistia.com',
915 'timestamp': 1401832161,
916 'upload_date': '20140603',
919 # Wistia standard embed (async)
921 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
925 'title': 'Drip Brennan Dunn Workshop',
926 'description': 'a JV Webinars video from getdrip-1',
928 'timestamp': 1463607249,
929 'upload_date': '20160518',
932 'skip_download': True,
937 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
941 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
942 'uploader': 'Sophos Security',
943 'title': 'Chet Chat 171 - Oct 29, 2014',
944 'upload_date': '20141029',
947 # Soundcloud multiple embeds
949 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
952 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
954 'playlist_mincount': 7,
956 # TuneIn station embed
958 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
963 'location': 'Paris, France',
968 'skip_download': True,
973 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
977 'upload_date': '20141112',
978 'title': 'Rosetta #CometLanding webcast HL 10',
981 # Another Livestream embed, without 'new.' in URL
983 'url': 'https://www.freespeech.org/',
987 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
991 'skip_download': True,
996 'url': 'https://skiplagged.com/',
999 'title': 'Skiplagged: The smart way to find cheap flights',
1001 'playlist_mincount': 1,
1002 'add_ie': ['Youtube'],
1006 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1010 'upload_date': '20141126',
1011 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1016 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1018 'id': '730m_DandD_1901_512k',
1020 'uploader': 'www.abc.net.au',
1021 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1024 # embedded viddler video
1026 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1030 'uploader': 'deadspin',
1031 'title': 'WALL-TO-GORTAT',
1032 'timestamp': 1422285291,
1033 'upload_date': '20150126',
1035 'add_ie': ['Viddler'],
1039 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1043 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1044 'description': 'md5:601cb790edd05908957dae8aaa866465',
1045 'upload_date': '20150220',
1047 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1051 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1053 'id': 'Mrj4DVp2zeA',
1055 'upload_date': '20150212',
1056 'uploader': 'The National Archives UK',
1057 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1058 'uploader_id': 'NationalArchives08',
1059 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1064 'url': 'http://www.suffolk.edu/sjc/',
1068 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1069 'uploader': 'www.suffolk.edu',
1072 'skip_download': True,
1077 'url': 'http://www.indiedb.com/games/king-machine/videos',
1081 'title': 'king machine trailer 1',
1082 'thumbnail': r're:^https?://.*\.jpg$',
1086 # JWPlayer config passed as variable
1087 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1091 'title': 'ARIELE | Tube Cup',
1092 'uploader': 'www.txxx.com',
1096 'skip_download': True,
1101 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1102 'playlist_mincount': 5,
1104 'id': 'aanslagen-kopenhagen',
1105 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1110 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1114 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1117 # Kaltura embed (different embed code)
1119 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1123 'upload_date': '20150127',
1124 'uploader_id': 'PremierMedia',
1126 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1129 # Kaltura embed with single quotes
1131 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1136 'timestamp': 1355743100,
1137 'upload_date': '20121217',
1138 'uploader_id': 'batchUser',
1140 'add_ie': ['Kaltura'],
1143 # Kaltura embedded via quoted entry_id
1144 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1148 'title': '06_matthew_brender_raj_dutt',
1149 'timestamp': 1466638791,
1150 'upload_date': '20160622',
1152 'add_ie': ['Kaltura'],
1153 'expected_warnings': [
1154 'Could not send HEAD request'
1157 'skip_download': True,
1161 # Kaltura embedded, some fileExt broken (#11480)
1162 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1166 'title': 'Our "Standard Models" of particle physics and cosmology',
1167 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1168 'timestamp': 1321158993,
1169 'upload_date': '20111113',
1170 'uploader_id': 'kps1',
1172 'add_ie': ['Kaltura'],
1175 # Kaltura iframe embed
1176 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1177 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1181 'title': 'I. M. Pei: A Centennial Celebration',
1182 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1183 'upload_date': '20170403',
1184 'uploader_id': 'batchUser',
1185 'timestamp': 1491232186,
1187 'add_ie': ['Kaltura'],
1189 # EaglePlatform embed (generic URL)
1191 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1192 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1196 'title': 'Навальный вышел на свободу',
1197 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1198 'thumbnail': r're:^https?://.*\.jpg$',
1204 'skip_download': True,
1207 # referrer protected EaglePlatform embed
1209 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1213 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1214 'thumbnail': r're:^https?://.*\.jpg$',
1219 'skip_download': True,
1222 # ClipYou (EaglePlatform) embed (custom URL)
1224 'url': 'http://muz-tv.ru/play/7129/',
1225 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1229 'title': "'O Sole Mio",
1230 'thumbnail': r're:^https?://.*\.jpg$',
1235 'skip_download': True,
1240 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1244 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1245 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1246 'thumbnail': r're:^https?://.*\.jpg$',
1253 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1257 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1258 'thumbnail': r're:^https?://.*\.png$',
1264 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1265 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1269 'title': 'Facebook Creates "On This Day" | Crunch Report',
1274 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1278 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1283 # Crooks and Liars embed
1285 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1289 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1290 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1291 'timestamp': 1428207000,
1292 'upload_date': '20150405',
1293 'uploader': 'Heather',
1296 # Crooks and Liars external embed
1298 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1300 'id': 'MTE3MjUtMzQ2MzA',
1302 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1303 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1304 'timestamp': 1265032391,
1305 'upload_date': '20100201',
1306 'uploader': 'Heather',
1309 # NBC Sports vplayer embed
1311 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1313 'id': 'ln7x1qSThw4k',
1315 'title': "PFT Live: New leader in the 'new-look' defense",
1316 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1317 'uploader': 'NBCU-SPORTS',
1318 'upload_date': '20140107',
1319 'timestamp': 1389118457,
1324 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1325 'md5': '1aa589c675898ae6d37a17913cf68d66',
1327 'id': '701714499682',
1329 'title': 'PREVIEW: On Assignment: David Letterman',
1330 '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.',
1335 'url': 'https://video.udn.com/news/300346',
1336 'md5': 'fd2060e988c326991037b9aff9df21a6',
1340 'title': '中一中男師變性 全校師生力挺',
1341 'thumbnail': r're:^https?://.*\.jpg$',
1345 'skip_download': True,
1350 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1352 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1354 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1355 'title': 'This is what separates the Excel masters from the wannabes',
1356 'duration': 191.933,
1360 'skip_download': True,
1363 # Brightcove URL in single quotes
1365 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1366 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1368 'id': '4255764656001',
1370 'title': 'SN Presents: Russell Martin, World Citizen',
1371 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1372 'uploader': 'Rogers Sportsnet',
1373 'uploader_id': '1704050871',
1374 'upload_date': '20150525',
1375 'timestamp': 1432570283,
1378 # Dailymotion Cloud video
1380 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1381 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1385 'title': 'Sauvons les abeilles ! - Le débat',
1386 'description': 'md5:d9082128b1c5277987825d684939ca26',
1387 'thumbnail': r're:^https?://.*\.jpe?g$',
1388 'timestamp': 1434970506,
1389 'upload_date': '20150622',
1390 'uploader': 'Public Sénat',
1391 'uploader_id': 'xa9gza',
1394 # OnionStudios embed
1396 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1400 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1401 'thumbnail': r're:^https?://.*\.jpe?g$',
1402 'uploader': 'ClickHole',
1403 'uploader_id': 'clickhole',
1408 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1410 'id': '74849a00-85a9-11e1-9660-123139220831',
1412 'title': '#whilewewatch',
1415 # AdobeTVVideo embed
1417 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1418 'md5': '43662b577c018ad707a63766462b1e87',
1422 'title': 'New experience with Acrobat DC',
1423 'description': 'New experience with Acrobat DC',
1424 'duration': 248.667,
1427 # BrightcoveInPageEmbed embed
1429 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1431 'id': '4238694884001',
1433 'title': 'Tabletop: Dread, Last Thoughts',
1434 'description': 'Tabletop: Dread, Last Thoughts',
1438 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1439 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1441 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1443 'id': '4785848093001',
1445 'title': 'The Cardinal Pell Interview',
1446 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1447 'uploader': 'GlobeCast Australia - GlobeStream',
1448 'uploader_id': '2733773828001',
1449 'upload_date': '20160304',
1450 'timestamp': 1457083087,
1454 'skip_download': True,
1458 # Brightcove embed with whitespace around attribute names
1459 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1461 'id': '3167554373001',
1463 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1464 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1465 'uploader_id': '1079349493',
1466 'upload_date': '20140207',
1467 'timestamp': 1391810548,
1470 'skip_download': True,
1473 # Another form of arte.tv embed
1475 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1476 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1478 'id': '030273-562_PLUS7-F',
1480 'title': 'ARTE Reportage - Nulle part, en France',
1481 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1482 'upload_date': '20160409',
1487 'url': 'http://www.wykop.pl/link/3088787/',
1488 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1490 'id': '874_1459135191',
1492 'title': 'Man shows poor quality of new apartment building',
1493 'description': 'The wall is like a sand pile.',
1494 'uploader': 'Lake8737',
1497 # Duplicated embedded video URLs
1499 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1501 'id': '149298443_480_16c25b74_2',
1503 'title': 'vs. Blue Orange Spring Game',
1504 'uploader': 'www.hudl.com',
1507 # twitter:player:stream embed
1509 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1513 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1514 'uploader': 'www.rtl.be',
1518 'skip_download': True,
1521 # twitter:player embed
1523 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1524 'md5': 'a3e0df96369831de324f0778e126653c',
1526 'id': '4909620399001',
1528 'title': 'What Do Black Holes Sound Like?',
1529 'description': 'what do black holes sound like',
1530 'upload_date': '20160524',
1531 'uploader_id': '29913724001',
1532 'timestamp': 1464107587,
1533 'uploader': 'TheAtlantic',
1535 'add_ie': ['BrightcoveLegacy'],
1537 # Facebook <iframe> embed
1539 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1540 'md5': 'fbcde74f534176ecb015849146dd3aee',
1542 'id': '599637780109885',
1544 'title': 'Facebook video #599637780109885',
1547 # Facebook <iframe> embed, plugin video
1549 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1551 'id': '1754168231264132',
1553 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1554 'uploader': 'Tariq Ramadan (official)',
1555 'timestamp': 1496758379,
1556 'upload_date': '20170606',
1559 'skip_download': True,
1562 # Facebook API embed
1564 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1565 'md5': 'a47372ee61b39a7b90287094d447d94e',
1567 'id': '10153467542406923',
1569 'title': 'Facebook video #10153467542406923',
1572 # Wordpress "YouTube Video Importer" plugin
1574 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1575 'md5': 'd16797741b560b485194eddda8121b48',
1577 'id': 'HNTXWDXV9Is',
1579 'title': 'Blue Devils Drumline Stanford lot 2016',
1580 'upload_date': '20160627',
1581 'uploader_id': 'GENOCIDE8GENERAL10',
1582 'uploader': 'cylus cyrus',
1586 # video stored on custom kaltura server
1587 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1588 'md5': '537617d06e64dfed891fa1593c4b30cc',
1592 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1593 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1594 'uploader_id': 'videos.expansion@el-mundo.net',
1595 'upload_date': '20150429',
1596 'timestamp': 1430303472,
1598 'add_ie': ['Kaltura'],
1601 # Non-standard Vimeo embed
1602 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1603 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1607 'title': 'Understanding the web - Teaser',
1608 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1609 'upload_date': '20151214',
1610 'uploader': 'OpenClassrooms',
1611 'uploader_id': 'openclassrooms',
1613 'add_ie': ['Vimeo'],
1616 # generic vimeo embed that requires original URL passed as Referer
1617 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1618 'only_matching': True,
1621 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1622 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1624 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1626 'title': 'Big Buck Bunny',
1627 'description': 'Royalty free test video',
1628 'timestamp': 1432816365,
1629 'upload_date': '20150528',
1633 'skip_download': True,
1635 'add_ie': [ArkenaIE.ie_key()],
1638 '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/',
1642 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1645 'skip_download': True,
1647 'add_ie': [Vbox7IE.ie_key()],
1651 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1654 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1656 'playlist_mincount': 3,
1660 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1662 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1663 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1665 'playlist_mincount': 2,
1669 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1673 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1674 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1677 'skip_download': True,
1679 'add_ie': [TwentyMinutenIE.ie_key()],
1683 'url': 'https://en.support.wordpress.com/videopress/',
1687 'title': 'IMG_5786',
1688 'timestamp': 1435711927,
1689 'upload_date': '20150701',
1692 'skip_download': True,
1694 'add_ie': [VideoPressIE.ie_key()],
1698 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1700 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1702 'title': 'Магаззино: Казань 2',
1703 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1704 'uploader': 'Магаззино',
1705 'upload_date': '20170228',
1706 'uploader_id': '996642',
1709 'skip_download': True,
1711 'add_ie': [RutubeIE.ie_key()],
1714 # ThePlatform embedded with whitespaces in URLs
1715 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1716 'only_matching': True,
1719 # Senate ISVP iframe https
1720 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1721 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1723 'id': 'govtaff020316',
1725 'title': 'Integrated Senate Video Player',
1727 'add_ie': [SenateISVPIE.ie_key()],
1730 # Limelight embeds (1 channel embed + 4 media embeds)
1731 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1733 'id': 'FacilitatorTraining2017',
1734 'title': 'Facilitator Training 2017',
1736 'playlist_mincount': 5,
1739 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1741 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1742 'title': 'Standoff with Walnut Creek murder suspect ends',
1743 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1745 'playlist_mincount': 4,
1748 # WashingtonPost embed
1749 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1751 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1753 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1754 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1755 'timestamp': 1455216756,
1756 'uploader': 'The Washington Post',
1757 'upload_date': '20160211',
1759 'add_ie': [WashingtonPostIE.ie_key()],
1763 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1767 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1770 'skip_download': True,
1772 'add_ie': [MediasetIE.ie_key()],
1776 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1778 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1779 'title': 'Slovenskom sa prehnala vlna silných búrok',
1781 'playlist_mincount': 5,
1782 'add_ie': [JojIE.ie_key()],
1785 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1786 'url': 'https://tvrain.ru/amp/418921/',
1787 'md5': 'cc00413936695987e8de148b67d14f1d',
1791 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1795 # # TODO: find another test
1796 # # http://schema.org/VideoObject
1797 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1798 # 'md5': '888dcf08b7ea671381f00fab74692755',
1800 # 'id': 'nyvTSJMKId',
1802 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1803 # 'description': '#love for cats.',
1804 # 'timestamp': 1461244995,
1805 # 'upload_date': '20160421',
1808 # 'force_generic_extractor': True,
1813 def report_following_redirect(self, new_url):
1814 """Report information extraction."""
1815 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1817 def _extract_rss(self, url, video_id, doc):
1818 playlist_title = doc.find('./channel/title').text
1819 playlist_desc_el = doc.find('./channel/description')
1820 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1823 for it in doc.findall('./channel/item'):
1824 next_url = xpath_text(it, 'link', fatal=False)
1826 enclosure_nodes = it.findall('./enclosure')
1827 for e in enclosure_nodes:
1828 next_url = e.attrib.get('url')
1836 '_type': 'url_transparent',
1838 'title': it.find('title').text,
1842 '_type': 'playlist',
1844 'title': playlist_title,
1845 'description': playlist_desc,
1849 def _extract_camtasia(self, url, video_id, webpage):
1850 """ Returns None if no camtasia video can be found. """
1852 camtasia_cfg = self._search_regex(
1853 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1854 webpage, 'camtasia configuration file', default=None)
1855 if camtasia_cfg is None:
1858 title = self._html_search_meta('DC.title', webpage, fatal=True)
1860 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1861 camtasia_cfg = self._download_xml(
1862 camtasia_url, video_id,
1863 note='Downloading camtasia configuration',
1864 errnote='Failed to download camtasia configuration')
1865 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1868 for n in fileset_node.getchildren():
1869 url_n = n.find('./uri')
1874 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1875 'title': '%s - %s' % (title, n.tag),
1876 'url': compat_urlparse.urljoin(url, url_n.text),
1877 'duration': float_or_none(n.find('./duration').text),
1881 '_type': 'playlist',
1886 def _real_extract(self, url):
1887 if url.startswith('//'):
1890 'url': self.http_scheme() + url,
1893 parsed_url = compat_urlparse.urlparse(url)
1894 if not parsed_url.scheme:
1895 default_search = self._downloader.params.get('default_search')
1896 if default_search is None:
1897 default_search = 'fixup_error'
1899 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1901 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1902 return self.url_result('http://' + url)
1903 elif default_search != 'fixup_error':
1904 if default_search == 'auto_warning':
1905 if re.match(r'^(?:url|URL)$', url):
1906 raise ExtractorError(
1907 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1910 self._downloader.report_warning(
1911 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1912 return self.url_result('ytsearch:' + url)
1914 if default_search in ('error', 'fixup_error'):
1915 raise ExtractorError(
1916 '%r is not a valid URL. '
1917 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1918 % (url, url), expected=True)
1920 if ':' not in default_search:
1921 default_search += ':'
1922 return self.url_result(default_search + url)
1924 url, smuggled_data = unsmuggle_url(url)
1925 force_videoid = None
1926 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1927 if smuggled_data and 'force_videoid' in smuggled_data:
1928 force_videoid = smuggled_data['force_videoid']
1929 video_id = force_videoid
1931 video_id = self._generic_id(url)
1933 self.to_screen('%s: Requesting header' % video_id)
1935 head_req = HEADRequest(url)
1936 head_response = self._request_webpage(
1938 note=False, errnote='Could not send HEAD request to %s' % url,
1941 if head_response is not False:
1942 # Check for redirect
1943 new_url = head_response.geturl()
1945 self.report_following_redirect(new_url)
1947 new_url = smuggle_url(
1948 new_url, {'force_videoid': force_videoid})
1949 return self.url_result(new_url)
1951 full_response = None
1952 if head_response is False:
1953 request = sanitized_Request(url)
1954 request.add_header('Accept-Encoding', '*')
1955 full_response = self._request_webpage(request, video_id)
1956 head_response = full_response
1960 'title': self._generic_title(url),
1961 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1964 # Check for direct link to a video
1965 content_type = head_response.headers.get('Content-Type', '').lower()
1966 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1968 format_id = compat_str(m.group('format_id'))
1969 if format_id.endswith('mpegurl'):
1970 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1971 elif format_id == 'f4m':
1972 formats = self._extract_f4m_formats(url, video_id)
1975 'format_id': format_id,
1977 'vcodec': 'none' if m.group('type') == 'audio' else None
1979 info_dict['direct'] = True
1980 self._sort_formats(formats)
1981 info_dict['formats'] = formats
1984 if not self._downloader.params.get('test', False) and not is_intentional:
1985 force = self._downloader.params.get('force_generic_extractor', False)
1986 self._downloader.report_warning(
1987 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1989 if not full_response:
1990 request = sanitized_Request(url)
1991 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1992 # making it impossible to download only chunk of the file (yet we need only 512kB to
1993 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1994 # that will always result in downloading the whole file that is not desirable.
1995 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1996 # to accept raw bytes and being able to download only a chunk.
1997 # It may probably better to solve this by checking Content-Type for application/octet-stream
1998 # after HEAD request finishes, but not sure if we can rely on this.
1999 request.add_header('Accept-Encoding', '*')
2000 full_response = self._request_webpage(request, video_id)
2002 first_bytes = full_response.read(512)
2004 # Is it an M3U playlist?
2005 if first_bytes.startswith(b'#EXTM3U'):
2006 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2007 self._sort_formats(info_dict['formats'])
2010 # Maybe it's a direct link to a video?
2011 # Be careful not to download the whole thing!
2012 if not is_html(first_bytes):
2013 self._downloader.report_warning(
2014 'URL could be a direct video link, returning it as such.')
2021 webpage = self._webpage_read_content(
2022 full_response, url, video_id, prefix=first_bytes)
2024 self.report_extraction(video_id)
2026 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2028 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2029 if doc.tag == 'rss':
2030 return self._extract_rss(url, video_id, doc)
2031 elif doc.tag == 'SmoothStreamingMedia':
2032 info_dict['formats'] = self._parse_ism_formats(doc, url)
2033 self._sort_formats(info_dict['formats'])
2035 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2036 smil = self._parse_smil(doc, url, video_id)
2037 self._sort_formats(smil['formats'])
2039 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2040 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2041 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2042 info_dict['formats'] = self._parse_mpd_formats(
2044 mpd_base_url=full_response.geturl().rpartition('/')[0],
2046 self._sort_formats(info_dict['formats'])
2048 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2049 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2050 self._sort_formats(info_dict['formats'])
2052 except compat_xml_parse_error:
2055 # Is it a Camtasia project?
2056 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2057 if camtasia_res is not None:
2060 # Sometimes embedded video player is hidden behind percent encoding
2061 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2062 # Unescaping the whole page allows to handle those cases in a generic way
2063 webpage = compat_urllib_parse_unquote(webpage)
2065 # it's tempting to parse this further, but you would
2066 # have to take into account all the variations like
2067 # Video Title - Site Name
2068 # Site Name | Video Title
2069 # Video Title - Tagline | Site Name
2070 # and so on and so forth; it's just not practical
2071 video_title = self._og_search_title(
2072 webpage, default=None) or self._html_search_regex(
2073 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2076 # Try to detect age limit automatically
2077 age_limit = self._rta_search(webpage)
2078 # And then there are the jokers who advertise that they use RTA,
2079 # but actually don't.
2080 AGE_LIMIT_MARKERS = [
2081 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2083 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2086 # video uploader is domain name
2087 video_uploader = self._search_regex(
2088 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2090 video_description = self._og_search_description(webpage, default=None)
2091 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2094 'title': video_title,
2095 'description': video_description,
2096 'thumbnail': video_thumbnail,
2097 'age_limit': age_limit,
2100 # Look for Brightcove Legacy Studio embeds
2101 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2105 'url': smuggle_url(bc_url, {'Referer': url}),
2106 'ie_key': 'BrightcoveLegacy'
2107 } for bc_url in bc_urls]
2110 '_type': 'playlist',
2111 'title': video_title,
2116 # Look for Brightcove New Studio embeds
2117 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2119 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2121 # Look for ThePlatform embeds
2122 tp_urls = ThePlatformIE._extract_urls(webpage)
2124 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2126 # Look for Vessel embeds
2127 vessel_urls = VesselIE._extract_urls(webpage)
2129 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2131 # Look for embedded rtl.nl player
2132 matches = re.findall(
2133 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2136 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2138 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2140 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2142 vid_me_embed_url = self._search_regex(
2143 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2144 webpage, 'vid.me embed', default=None)
2145 if vid_me_embed_url is not None:
2146 return self.url_result(vid_me_embed_url, 'Vidme')
2148 # Look for embedded YouTube player
2149 matches = re.findall(r'''(?x)
2159 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2163 return self.playlist_from_matches(
2164 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2166 # Look for lazyYT YouTube embed
2167 matches = re.findall(
2168 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2170 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2172 # Look for Wordpress "YouTube Video Importer" plugin
2173 matches = re.findall(r'''(?x)<div[^>]+
2174 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2175 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2177 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2179 matches = DailymotionIE._extract_urls(webpage)
2181 return self.playlist_from_matches(matches, video_id, video_title)
2183 # Look for embedded Dailymotion playlist player (#3822)
2185 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2187 playlists = re.findall(
2188 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2190 return self.playlist_from_matches(
2191 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2193 # Look for embedded Wistia player
2194 wistia_url = WistiaIE._extract_url(webpage)
2197 '_type': 'url_transparent',
2198 'url': self._proto_relative_url(wistia_url),
2199 'ie_key': WistiaIE.ie_key(),
2200 'uploader': video_uploader,
2203 # Look for SVT player
2204 svt_url = SVTIE._extract_url(webpage)
2206 return self.url_result(svt_url, 'SVT')
2208 # Look for Bandcamp pages with custom domain
2209 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2210 if mobj is not None:
2211 burl = unescapeHTML(mobj.group(1))
2212 # Don't set the extractor because it can be a track url or an album
2213 return self.url_result(burl)
2215 # Look for embedded Vevo player
2217 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2218 if mobj is not None:
2219 return self.url_result(mobj.group('url'))
2221 # Look for embedded Viddler player
2223 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2225 if mobj is not None:
2226 return self.url_result(mobj.group('url'))
2228 # Look for NYTimes player
2230 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2232 if mobj is not None:
2233 return self.url_result(mobj.group('url'))
2235 # Look for Libsyn player
2237 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2238 if mobj is not None:
2239 return self.url_result(mobj.group('url'))
2241 # Look for Ooyala videos
2242 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2243 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2244 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2245 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2246 if mobj is not None:
2247 embed_token = self._search_regex(
2248 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2249 webpage, 'ooyala embed token', default=None)
2250 return OoyalaIE._build_url_result(smuggle_url(
2253 'embed_token': embed_token,
2256 # Look for multiple Ooyala embeds on SBN network websites
2257 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2258 if mobj is not None:
2259 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2261 return self.playlist_from_matches(
2262 embeds, video_id, video_title,
2263 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2265 # Look for Aparat videos
2266 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2267 if mobj is not None:
2268 return self.url_result(mobj.group(1), 'Aparat')
2270 # Look for MPORA videos
2271 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2272 if mobj is not None:
2273 return self.url_result(mobj.group(1), 'Mpora')
2275 # Look for embedded NovaMov-based player
2277 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2278 (?P<url>http://(?:(?:embed|www)\.)?
2280 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2281 videoweed\.(?:es|com)|
2282 movshare\.(?:net|sx|ag)|
2283 divxstage\.(?:eu|net|ch|co|at|ag))
2284 /embed\.php.+?)\1''', webpage)
2285 if mobj is not None:
2286 return self.url_result(mobj.group('url'))
2288 # Look for embedded Facebook player
2289 facebook_urls = FacebookIE._extract_urls(webpage)
2291 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2293 # Look for embedded VK player
2294 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2295 if mobj is not None:
2296 return self.url_result(mobj.group('url'), 'VK')
2298 # Look for embedded Odnoklassniki player
2299 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2300 if mobj is not None:
2301 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2303 # Look for embedded ivi player
2304 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2305 if mobj is not None:
2306 return self.url_result(mobj.group('url'), 'Ivi')
2308 # Look for embedded Huffington Post player
2310 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2311 if mobj is not None:
2312 return self.url_result(mobj.group('url'), 'HuffPost')
2315 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2316 if mobj is not None:
2317 return self.url_result(mobj.group('url'))
2318 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2319 if mobj is not None:
2320 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2322 # Look for funnyordie embed
2323 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2325 return self.playlist_from_matches(
2326 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2328 # Look for BBC iPlayer embed
2329 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2331 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2333 # Look for embedded RUTV player
2334 rutv_url = RUTVIE._extract_url(webpage)
2336 return self.url_result(rutv_url, 'RUTV')
2338 # Look for embedded TVC player
2339 tvc_url = TVCIE._extract_url(webpage)
2341 return self.url_result(tvc_url, 'TVC')
2343 # Look for embedded SportBox player
2344 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2346 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2348 # Look for embedded XHamster player
2349 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2351 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2353 # Look for embedded TNAFlixNetwork player
2354 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2356 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2358 # Look for embedded PornHub player
2359 pornhub_urls = PornHubIE._extract_urls(webpage)
2361 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2363 # Look for embedded DrTuber player
2364 drtuber_urls = DrTuberIE._extract_urls(webpage)
2366 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2368 # Look for embedded RedTube player
2369 redtube_urls = RedTubeIE._extract_urls(webpage)
2371 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2373 # Look for embedded Tvigle player
2375 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2376 if mobj is not None:
2377 return self.url_result(mobj.group('url'), 'Tvigle')
2379 # Look for embedded TED player
2381 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2382 if mobj is not None:
2383 return self.url_result(mobj.group('url'), 'TED')
2385 # Look for embedded Ustream videos
2386 ustream_url = UstreamIE._extract_url(webpage)
2388 return self.url_result(ustream_url, UstreamIE.ie_key())
2390 # Look for embedded arte.tv player
2392 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2394 if mobj is not None:
2395 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2397 # Look for embedded francetv player
2399 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2401 if mobj is not None:
2402 return self.url_result(mobj.group('url'))
2404 # Look for embedded smotri.com player
2405 smotri_url = SmotriIE._extract_url(webpage)
2407 return self.url_result(smotri_url, 'Smotri')
2409 # Look for embedded Myvi.ru player
2410 myvi_url = MyviIE._extract_url(webpage)
2412 return self.url_result(myvi_url)
2414 # Look for embedded soundcloud player
2415 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2417 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2419 # Look for tunein player
2420 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2422 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2424 # Look for embedded mtvservices player
2425 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2427 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2429 # Look for embedded yahoo player
2431 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2433 if mobj is not None:
2434 return self.url_result(mobj.group('url'), 'Yahoo')
2436 # Look for embedded sbs.com.au player
2440 <meta\s+property="og:video"\s+content=|
2443 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2445 if mobj is not None:
2446 return self.url_result(mobj.group('url'), 'SBS')
2448 # Look for embedded Cinchcast player
2450 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2452 if mobj is not None:
2453 return self.url_result(mobj.group('url'), 'Cinchcast')
2456 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2460 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2462 if mobj is not None:
2463 return self.url_result(mobj.group('url'), 'MLB')
2466 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2468 if mobj is not None:
2469 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2472 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2474 if mobj is not None:
2475 return self.url_result(mobj.group('url'), 'Livestream')
2477 # Look for Zapiks embed
2479 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2480 if mobj is not None:
2481 return self.url_result(mobj.group('url'), 'Zapiks')
2483 # Look for Kaltura embeds
2484 kaltura_url = KalturaIE._extract_url(webpage)
2486 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2488 # Look for EaglePlatform embeds
2489 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2490 if eagleplatform_url:
2491 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2493 # Look for ClipYou (uses EaglePlatform) embeds
2495 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2496 if mobj is not None:
2497 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2499 # Look for Pladform embeds
2500 pladform_url = PladformIE._extract_url(webpage)
2502 return self.url_result(pladform_url)
2504 # Look for Videomore embeds
2505 videomore_url = VideomoreIE._extract_url(webpage)
2507 return self.url_result(videomore_url)
2509 # Look for Webcaster embeds
2510 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2512 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2514 # Look for Playwire embeds
2516 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2517 if mobj is not None:
2518 return self.url_result(mobj.group('url'))
2520 # Look for 5min embeds
2522 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2523 if mobj is not None:
2524 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2526 # Look for Crooks and Liars embeds
2528 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2529 if mobj is not None:
2530 return self.url_result(mobj.group('url'))
2532 # Look for NBC Sports VPlayer embeds
2533 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2535 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2537 # Look for NBC News embeds
2538 nbc_news_embed_url = re.search(
2539 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2540 if nbc_news_embed_url:
2541 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2543 # Look for Google Drive embeds
2544 google_drive_url = GoogleDriveIE._extract_url(webpage)
2545 if google_drive_url:
2546 return self.url_result(google_drive_url, 'GoogleDrive')
2548 # Look for UDN embeds
2550 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2551 if mobj is not None:
2552 return self.url_result(
2553 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2555 # Look for Senate ISVP iframe
2556 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2558 return self.url_result(senate_isvp_url, 'SenateISVP')
2560 # Look for Dailymotion Cloud videos
2561 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2563 return self.url_result(dmcloud_url, 'DailymotionCloud')
2565 # Look for OnionStudios embeds
2566 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2567 if onionstudios_url:
2568 return self.url_result(onionstudios_url)
2570 # Look for ViewLift embeds
2571 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2573 return self.url_result(viewlift_url)
2575 # Look for JWPlatform embeds
2576 jwplatform_url = JWPlatformIE._extract_url(webpage)
2578 return self.url_result(jwplatform_url, 'JWPlatform')
2580 # Look for Digiteka embeds
2581 digiteka_url = DigitekaIE._extract_url(webpage)
2583 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2585 # Look for Arkena embeds
2586 arkena_url = ArkenaIE._extract_url(webpage)
2588 return self.url_result(arkena_url, ArkenaIE.ie_key())
2590 # Look for Piksel embeds
2591 piksel_url = PikselIE._extract_url(webpage)
2593 return self.url_result(piksel_url, PikselIE.ie_key())
2595 # Look for Limelight embeds
2596 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2598 return self.playlist_result(
2599 limelight_urls, video_id, video_title, video_description)
2601 # Look for Anvato embeds
2602 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2604 return self.playlist_result(
2605 anvato_urls, video_id, video_title, video_description)
2607 # Look for AdobeTVVideo embeds
2609 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2611 if mobj is not None:
2612 return self.url_result(
2613 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2616 # Look for Vine embeds
2618 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2620 if mobj is not None:
2621 return self.url_result(
2622 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2624 # Look for VODPlatform embeds
2626 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2628 if mobj is not None:
2629 return self.url_result(
2630 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2632 # Look for Mangomolo embeds
2634 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2636 video\?.*?\bid=(?P<video_id>\d+)|
2637 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2638 ).+?)\1''', webpage)
2639 if mobj is not None:
2641 '_type': 'url_transparent',
2642 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2643 'title': video_title,
2644 'description': video_description,
2645 'thumbnail': video_thumbnail,
2646 'uploader': video_uploader,
2648 video_id = mobj.group('video_id')
2651 'ie_key': 'MangomoloVideo',
2656 'ie_key': 'MangomoloLive',
2657 'id': mobj.group('channel_id'),
2661 # Look for Instagram embeds
2662 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2663 if instagram_embed_url is not None:
2664 return self.url_result(
2665 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2667 # Look for LiveLeak embeds
2668 liveleak_url = LiveLeakIE._extract_url(webpage)
2670 return self.url_result(liveleak_url, 'LiveLeak')
2672 # Look for 3Q SDN embeds
2673 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2676 '_type': 'url_transparent',
2677 'ie_key': ThreeQSDNIE.ie_key(),
2678 'url': self._proto_relative_url(threeqsdn_url),
2679 'title': video_title,
2680 'description': video_description,
2681 'thumbnail': video_thumbnail,
2682 'uploader': video_uploader,
2685 # Look for VBOX7 embeds
2686 vbox7_url = Vbox7IE._extract_url(webpage)
2688 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2690 # Look for DBTV embeds
2691 dbtv_urls = DBTVIE._extract_urls(webpage)
2693 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2695 # Look for Videa embeds
2696 videa_urls = VideaIE._extract_urls(webpage)
2698 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2700 # Look for 20 minuten embeds
2701 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2703 return self.playlist_from_matches(
2704 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2706 # Look for Openload embeds
2707 openload_urls = OpenloadIE._extract_urls(webpage)
2709 return self.playlist_from_matches(
2710 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2712 # Look for VideoPress embeds
2713 videopress_urls = VideoPressIE._extract_urls(webpage)
2715 return self.playlist_from_matches(
2716 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2718 # Look for Rutube embeds
2719 rutube_urls = RutubeIE._extract_urls(webpage)
2721 return self.playlist_from_matches(
2722 rutube_urls, ie=RutubeIE.ie_key())
2724 # Look for WashingtonPost embeds
2725 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2727 return self.playlist_from_matches(
2728 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2730 # Look for Mediaset embeds
2731 mediaset_urls = MediasetIE._extract_urls(webpage)
2733 return self.playlist_from_matches(
2734 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2736 # Look for JOJ.sk embeds
2737 joj_urls = JojIE._extract_urls(webpage)
2739 return self.playlist_from_matches(
2740 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2742 def merge_dicts(dict1, dict2):
2744 for k, v in dict1.items():
2747 for k, v in dict2.items():
2750 if (k not in merged or
2751 (isinstance(v, compat_str) and v and
2752 isinstance(merged[k], compat_str) and
2757 # Looking for http://schema.org/VideoObject
2758 json_ld = self._search_json_ld(
2759 webpage, video_id, default={}, expected_type='VideoObject')
2760 if json_ld.get('url'):
2761 return merge_dicts(json_ld, info_dict)
2763 # Look for HTML5 media
2764 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2766 for entry in entries:
2769 'title': video_title,
2771 self._sort_formats(entry['formats'])
2772 return self.playlist_result(entries)
2774 jwplayer_data = self._find_jwplayer_data(
2775 webpage, video_id, transform_source=js_to_json)
2777 info = self._parse_jwplayer_data(
2778 jwplayer_data, video_id, require_title=False, base_url=url)
2779 return merge_dicts(info, info_dict)
2781 def check_video(vurl):
2782 if YoutubeIE.suitable(vurl):
2784 if RtmpIE.suitable(vurl):
2786 vpath = compat_urlparse.urlparse(vurl).path
2787 vext = determine_ext(vpath)
2788 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2790 def filter_video(urls):
2791 return list(filter(check_video, urls))
2793 # Start with something easy: JW Player in SWFObject
2794 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2796 # Look for gorilla-vid style embedding
2797 found = filter_video(re.findall(r'''(?sx)
2801 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2804 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2806 # Broaden the search a little bit
2807 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2809 # Broaden the findall a little bit: JWPlayer JS loader
2810 found = filter_video(re.findall(
2811 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2814 found = filter_video(re.findall(r'''(?xs)
2815 flowplayer\("[^"]+",\s*
2817 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2818 ["']?url["']?\s*:\s*["']([^"']+)["']
2823 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2825 # Try to find twitter cards info
2826 # twitter:player:stream should be checked before twitter:player since
2827 # it is expected to contain a raw stream (see
2828 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2829 found = filter_video(re.findall(
2830 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2832 # We look for Open Graph info:
2833 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2834 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2835 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2836 if m_video_type is not None:
2837 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2839 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2841 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2842 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2845 # Look also in Refresh HTTP header
2846 refresh_header = head_response.headers.get('Refresh')
2848 # In python 2 response HTTP headers are bytestrings
2849 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2850 refresh_header = refresh_header.decode('iso-8859-1')
2851 found = re.search(REDIRECT_REGEX, refresh_header)
2853 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2855 self.report_following_redirect(new_url)
2864 # twitter:player is a https URL to iframe player that may or may not
2865 # be supported by youtube-dl thus this is checked the very last (see
2866 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2867 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2869 return self.url_result(embed_url)
2872 raise UnsupportedError(url)
2875 for video_url in orderedSet(found):
2876 video_url = unescapeHTML(video_url)
2877 video_url = video_url.replace('\\/', '/')
2878 video_url = compat_urlparse.urljoin(url, video_url)
2879 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2881 # Sometimes, jwplayer extraction will result in a YouTube URL
2882 if YoutubeIE.suitable(video_url):
2883 entries.append(self.url_result(video_url, 'Youtube'))
2886 # here's a fun little line of code for you:
2887 video_id = os.path.splitext(video_id)[0]
2891 'uploader': video_uploader,
2892 'title': video_title,
2893 'age_limit': age_limit,
2896 if RtmpIE.suitable(video_url):
2897 entry_info_dict.update({
2898 '_type': 'url_transparent',
2899 'ie_key': RtmpIE.ie_key(),
2902 entries.append(entry_info_dict)
2905 ext = determine_ext(video_url)
2907 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2909 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2911 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2913 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2915 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2916 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2917 # Just matching .ism/manifest is not enough to be reliably sure
2918 # whether it's actually an ISM manifest or some other streaming
2919 # manifest since there are various streaming URL formats
2920 # possible (see [1]) as well as some other shenanigans like
2921 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2923 # Thus the most reasonable way to solve this is to delegate
2924 # to generic extractor in order to look into the contents of
2925 # the manifest itself.
2926 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2927 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2928 entry_info_dict = self.url_result(
2929 smuggle_url(video_url, {'to_generic': True}),
2932 entry_info_dict['url'] = video_url
2934 if entry_info_dict.get('formats'):
2935 self._sort_formats(entry_info_dict['formats'])
2937 entries.append(entry_info_dict)
2939 if len(entries) == 1:
2942 for num, e in enumerate(entries, start=1):
2943 # 'url' results don't have a title
2944 if e.get('title') is not None:
2945 e['title'] = '%s (%d)' % (e['title'], num)
2947 '_type': 'playlist',