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
96 class GenericIE(InfoExtractor):
97 IE_DESC = 'Generic downloader that works on some sites'
101 # Direct link to a video
103 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
104 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
109 'upload_date': '20100513',
112 # Direct link to media delivered compressed (until Accept-Encoding is *)
114 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
115 'md5': '128c42e68b13950268b648275386fc74',
117 'id': 'FictionJunction-Parallel_Hearts',
119 'title': 'FictionJunction-Parallel_Hearts',
120 'upload_date': '20140522',
122 'expected_warnings': [
123 'URL could be a direct video link, returning it as such.'
125 'skip': 'URL invalid',
127 # Direct download with broken HEAD
129 'url': 'http://ai-radio.org:8000/radio.opus',
136 'skip_download': True, # infinite live stream
138 'expected_warnings': [
139 r'501.*Not Implemented',
143 # Direct link with incorrect MIME type
145 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
146 'md5': '4ccbebe5f36706d85221f204d7eb5913',
148 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
149 'id': '5_Lennart_Poettering_-_Systemd',
151 'title': '5_Lennart_Poettering_-_Systemd',
152 'upload_date': '20141120',
154 'expected_warnings': [
155 'URL could be a direct video link, returning it as such.'
160 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
162 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
163 'title': 'Zero Punctuation',
164 'description': 're:.*groundbreaking video review series.*'
166 'playlist_mincount': 11,
168 # RSS feed with enclosure
170 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
172 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
174 'upload_date': '20150228',
175 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
178 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
180 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
184 'title': 'Automatics, robotics and biocybernetics',
185 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
186 'upload_date': '20130627',
187 'formats': 'mincount:16',
188 'subtitles': 'mincount:1',
191 'force_generic_extractor': True,
192 'skip_download': True,
195 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
197 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
202 'formats': 'mincount:1',
205 'skip_download': True,
208 # SMIL from https://www.restudy.dk/video/play/id/1637
210 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
214 'title': 'video_1637',
215 'formats': 'mincount:3',
218 'skip_download': True,
221 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
223 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
225 'id': 'smil-service',
227 'title': 'smil-service',
228 'formats': 'mincount:1',
231 'skip_download': True,
234 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
236 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
240 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
241 'formats': 'mincount:3',
244 'skip_download': True,
247 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
249 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
251 'id': 'mZlp2ctYIUEB',
253 'title': 'Tikibad ontruimd wegens brand',
254 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
255 'thumbnail': r're:^https?://.*\.jpg$',
259 'skip_download': True,
262 # MPD from http://dash-mse-test.appspot.com/media.html
264 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
265 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
267 'id': 'car-20120827-manifest',
269 'title': 'car-20120827-manifest',
270 'formats': 'mincount:9',
271 'upload_date': '20130904',
274 'format': 'bestvideo',
277 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
279 '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',
284 'formats': 'mincount:8',
288 'skip_download': True,
290 'skip': 'video gone',
292 # m3u8 served with Content-Type: text/plain
294 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
299 'upload_date': '20140720',
300 'formats': 'mincount:11',
304 'skip_download': True,
306 'skip': 'video gone',
310 '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',
314 'upload_date': '20130224',
315 'uploader_id': 'TheVerge',
316 'description': r're:^Chris Ziegler takes a look at the\.*',
317 'uploader': 'The Verge',
318 'title': 'First Firefox OS phones side-by-side',
321 'skip_download': False,
325 # redirect in Refresh HTTP header
326 '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',
330 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
331 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
332 'upload_date': '20150917',
333 'uploader_id': 'brtvofficial',
334 'uploader': 'Boiler Room',
337 'skip_download': False,
341 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
342 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
344 'id': '13601338388002',
346 'uploader': 'www.hodiho.fr',
347 'title': 'R\u00e9gis plante sa Jeep',
350 # bandcamp page with custom domain
352 'add_ie': ['Bandcamp'],
353 'url': 'http://bronyrock.com/track/the-pony-mash',
357 'title': 'The Pony Mash',
358 'uploader': 'M_Pallante',
360 'skip': 'There is a limit of 200 free downloads / month for the test song',
363 # embedded brightcove video
364 # it also tests brightcove videos that need to set the 'Referer'
365 # in the http requests
366 'add_ie': ['BrightcoveLegacy'],
367 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
369 'id': '2765128793001',
371 'title': 'Le cours de bourse : l’analyse technique',
372 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
373 'uploader': 'BFM BUSINESS',
376 'skip_download': True,
380 # embedded with itemprop embedURL and video id spelled as `idVideo`
381 'add_id': ['BrightcoveLegacy'],
382 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
384 'id': '5255628253001',
386 'title': 'md5:37c519b1128915607601e75a87995fc0',
387 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
388 'uploader': 'BFM BUSINESS',
389 'uploader_id': '876450612001',
390 'timestamp': 1482255315,
391 'upload_date': '20161220',
394 'skip_download': True,
398 # https://github.com/rg3/youtube-dl/issues/2253
399 'url': 'http://bcove.me/i6nfkrc3',
400 'md5': '0ba9446db037002366bab3b3eb30c88c',
402 'id': '3101154703001',
404 'title': 'Still no power',
405 'uploader': 'thestar.com',
406 '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.',
408 'add_ie': ['BrightcoveLegacy'],
409 'skip': 'video gone',
412 'url': 'http://www.championat.com/video/football/v/87/87499.html',
413 'md5': 'fb973ecf6e4a78a67453647444222983',
415 'id': '3414141473001',
417 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
418 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
419 'uploader': 'Championat',
423 # https://github.com/rg3/youtube-dl/issues/3541
424 'add_ie': ['BrightcoveLegacy'],
425 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
427 'id': '3866516442001',
429 'title': 'Leer mij vrouwen kennen: Aflevering 1',
430 'description': 'Leer mij vrouwen kennen: Aflevering 1',
431 'uploader': 'SBS Broadcasting',
433 'skip': 'Restricted to Netherlands',
435 'skip_download': True, # m3u8 download
439 # Brightcove video in <iframe>
440 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
441 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
443 'id': '5360463607001',
445 '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',
446 '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。',
447 'uploader': 'United Nations',
448 'uploader_id': '1362235914001',
449 'timestamp': 1489593889,
450 'upload_date': '20170315',
452 'add_ie': ['BrightcoveLegacy'],
455 # Brightcove with alternative playerID key
456 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
458 'id': 'nmeth.2062_SV1',
459 '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',
463 'id': '2228375078001',
465 'title': 'nmeth.2062-sv1',
466 'description': 'nmeth.2062-sv1',
467 'timestamp': 1363357591,
468 'upload_date': '20130315',
469 'uploader': 'Nature Publishing Group',
470 'uploader_id': '1964492299001',
475 # Brightcove with UUID in videoPlayer
476 'url': 'http://www8.hp.com/cn/zh/home.html',
478 'id': '5255815316001',
480 'title': 'Sprocket Video - China',
481 'description': 'Sprocket Video - China',
482 'uploader': 'HP-Video Gallery',
483 'timestamp': 1482263210,
484 'upload_date': '20161220',
485 'uploader_id': '1107601872001',
488 'skip_download': True, # m3u8 download
490 'skip': 'video rotates...weekly?',
493 # Brightcove:new type [2].
494 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
495 'md5': '2b35148fcf48da41c9fb4591650784f3',
497 'id': '5348741021001',
499 'upload_date': '20170306',
500 'uploader_id': '4191638492001',
501 'timestamp': 1488769918,
502 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
507 # Alternative brightcove <video> attributes
508 '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/',
510 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
511 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
514 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
516 'id': '5311302538001',
518 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
519 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
520 'timestamp': 1486321708,
521 'upload_date': '20170205',
522 'uploader_id': '800000640001',
524 'only_matching': True,
528 # Brightcove with UUID in videoPlayer
529 'url': 'http://www8.hp.com/cn/zh/home.html',
531 'id': '5255815316001',
533 'title': 'Sprocket Video - China',
534 'description': 'Sprocket Video - China',
535 'uploader': 'HP-Video Gallery',
536 'timestamp': 1482263210,
537 'upload_date': '20161220',
538 'uploader_id': '1107601872001',
541 'skip_download': True, # m3u8 download
546 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
547 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
549 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
551 'title': '2cc213299525360.mov', # that's what we get
554 'add_ie': ['Ooyala'],
557 # ooyala video embedded with http://player.ooyala.com/iframe.js
558 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
560 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
562 'title': '"Steve Jobs: Man in the Machine" trailer',
563 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
567 'skip_download': True,
569 'skip': 'movie expired',
573 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
577 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
578 'upload_date': '20140225',
579 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
580 'uploader': 'Tested',
581 'uploader_id': 'testedcom',
583 # No need to test YoutubeIE here
585 'skip_download': True,
590 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
594 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
595 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
597 # HEAD requests lead to endless 301, while GET is OK
598 'expected_warnings': ['301'],
602 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
606 'title': 'Охотское море стало целиком российским',
607 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
611 'skip_download': True,
616 '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/',
620 'title': 'Дошкольное воспитание',
625 'url': 'http://www.vestifinance.ru/articles/25753',
628 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
633 'title': 'Госзаказ. День 3',
639 'title': 'Госзаказ. День 2',
645 'title': 'Госзаказ. День 1',
651 'skip_download': True,
656 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
658 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
660 'title': 'Ужастики, русский трейлер (2015)',
661 'thumbnail': r're:^https?://.*\.jpg$',
667 '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',
670 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
672 'playlist_mincount': 7,
673 # This forum does not allow <iframe> syntaxes anymore
674 # Now HTML tags are displayed as-is
675 'skip': 'No videos on this page',
679 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
680 'md5': '65fdff94098e4a607385a60c5177c638',
684 'title': 'Hidden miracles of the natural world',
685 'uploader': 'Louie Schwartzberg',
686 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
689 # nowvideo embed hidden behind percent encoding
691 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
692 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
694 'id': '06e53103ca9aa',
696 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
697 'description': 'No description',
702 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
703 'md5': '7653032cbb25bf6c80d80f217055fa43',
705 'id': '048195-004_PLUS7-F',
708 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
709 'upload_date': '20140320',
712 'skip_download': 'Requires rtmpdump'
714 'skip': 'video gone',
718 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
722 'title': 'Alcaline, le concert avec Calogero',
723 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
724 'upload_date': '20150226',
725 'timestamp': 1424989860,
730 'skip_download': True,
732 'expected_warnings': [
738 'url': 'http://www.wired.com/2014/04/honda-asimo/',
739 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
741 'id': '53501be369702d3275860000',
743 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
748 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
749 'md5': '441aeeb82eb72c422c7f14ec533999cd',
751 'id': 'k2mm4bCdJ6CQ2i7c8o2',
753 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
754 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
756 'uploader_id': 'xgditw',
757 'upload_date': '20140425',
758 'timestamp': 1398441542,
760 'add_ie': ['Dailymotion'],
764 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
768 'title': 'The NBL Auction 2014',
769 'uploader': 'BADMINTON England',
770 'uploader_id': 'BADMINTONEvents',
771 'upload_date': '20140603',
772 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
774 'add_ie': ['Youtube'],
776 'skip_download': True,
781 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
782 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
784 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
786 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
787 'description': 'Two valets share their love for movie star Liam Neesons.',
788 'timestamp': 1349922600,
789 'upload_date': '20121011',
792 # YouTube embed via <data-embed-url="">
794 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
798 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
799 'uploader': 'Gameloft',
800 'uploader_id': 'gameloft',
801 'upload_date': '20140828',
802 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
805 'skip_download': True,
808 # YouTube <object> embed
810 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
811 'md5': '516718101ec834f74318df76259fb3cc',
815 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
816 'upload_date': '20080526',
817 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
818 'uploader': 'Christopher Sykes',
819 'uploader_id': 'ChristopherJSykes',
821 'add_ie': ['Youtube'],
825 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
827 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
829 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
830 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
835 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
837 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
838 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
844 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
849 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
850 'md5': '9d65602bf31c6e20014319c7d07fba27',
852 'id': '5123ea6d5e5a7',
855 'uploader': 'www.handjobhub.com',
856 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
859 # Multiple brightcove videos
860 # https://github.com/rg3/youtube-dl/issues/2283
862 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
864 'id': 'always-never',
865 'title': 'Always / Never - The New Yorker',
869 'extract_flat': False,
870 'skip_download': True,
875 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
876 'md5': '96f09a37e44da40dd083e12d9a683327',
880 'title': 'Ump changes call to ball',
881 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
883 'timestamp': 1401537900,
884 'upload_date': '20140531',
885 'thumbnail': r're:^https?://.*\.jpg$',
890 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
891 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
895 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
896 'description': 'a Paywall Videos video from Remilon',
898 'uploader': 'study.com',
899 'timestamp': 1459678540,
900 'upload_date': '20160403',
901 'filesize': 24687186,
905 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
906 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
910 'title': 'Conversation about Hexagonal Rails Part 1',
911 'description': 'a Martin Fowler video from ThoughtWorks',
913 'uploader': 'thoughtworks.wistia.com',
914 'timestamp': 1401832161,
915 'upload_date': '20140603',
918 # Wistia standard embed (async)
920 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
924 'title': 'Drip Brennan Dunn Workshop',
925 'description': 'a JV Webinars video from getdrip-1',
927 'timestamp': 1463607249,
928 'upload_date': '20160518',
931 'skip_download': True,
936 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
940 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
941 'uploader': 'Sophos Security',
942 'title': 'Chet Chat 171 - Oct 29, 2014',
943 'upload_date': '20141029',
946 # Soundcloud multiple embeds
948 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
951 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
953 'playlist_mincount': 7,
955 # TuneIn station embed
957 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
962 'location': 'Paris, France',
967 'skip_download': True,
972 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
976 'upload_date': '20141112',
977 'title': 'Rosetta #CometLanding webcast HL 10',
980 # Another Livestream embed, without 'new.' in URL
982 'url': 'https://www.freespeech.org/',
986 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
990 'skip_download': True,
995 'url': 'https://skiplagged.com/',
998 'title': 'Skiplagged: The smart way to find cheap flights',
1000 'playlist_mincount': 1,
1001 'add_ie': ['Youtube'],
1005 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1009 'upload_date': '20141126',
1010 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1015 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1017 'id': '730m_DandD_1901_512k',
1019 'uploader': 'www.abc.net.au',
1020 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1023 # embedded viddler video
1025 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1029 'uploader': 'deadspin',
1030 'title': 'WALL-TO-GORTAT',
1031 'timestamp': 1422285291,
1032 'upload_date': '20150126',
1034 'add_ie': ['Viddler'],
1038 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1042 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1043 'description': 'md5:601cb790edd05908957dae8aaa866465',
1044 'upload_date': '20150220',
1046 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1050 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1052 'id': 'Mrj4DVp2zeA',
1054 'upload_date': '20150212',
1055 'uploader': 'The National Archives UK',
1056 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1057 'uploader_id': 'NationalArchives08',
1058 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1063 'url': 'http://www.suffolk.edu/sjc/',
1067 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1068 'uploader': 'www.suffolk.edu',
1071 'skip_download': True,
1076 'url': 'http://www.indiedb.com/games/king-machine/videos',
1080 'title': 'king machine trailer 1',
1081 'thumbnail': r're:^https?://.*\.jpg$',
1085 # JWPlayer config passed as variable
1086 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1090 'title': 'ARIELE | Tube Cup',
1091 'uploader': 'www.txxx.com',
1095 'skip_download': True,
1100 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1101 'playlist_mincount': 5,
1103 'id': 'aanslagen-kopenhagen',
1104 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1109 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1113 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1116 # Kaltura embed (different embed code)
1118 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1122 'upload_date': '20150127',
1123 'uploader_id': 'PremierMedia',
1125 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1128 # Kaltura embed with single quotes
1130 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1135 'timestamp': 1355743100,
1136 'upload_date': '20121217',
1137 'uploader_id': 'batchUser',
1139 'add_ie': ['Kaltura'],
1142 # Kaltura embedded via quoted entry_id
1143 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1147 'title': '06_matthew_brender_raj_dutt',
1148 'timestamp': 1466638791,
1149 'upload_date': '20160622',
1151 'add_ie': ['Kaltura'],
1152 'expected_warnings': [
1153 'Could not send HEAD request'
1156 'skip_download': True,
1160 # Kaltura embedded, some fileExt broken (#11480)
1161 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1165 'title': 'Our "Standard Models" of particle physics and cosmology',
1166 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1167 'timestamp': 1321158993,
1168 'upload_date': '20111113',
1169 'uploader_id': 'kps1',
1171 'add_ie': ['Kaltura'],
1174 # Kaltura iframe embed
1175 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1176 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1180 'title': 'I. M. Pei: A Centennial Celebration',
1181 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1182 'upload_date': '20170403',
1183 'uploader_id': 'batchUser',
1184 'timestamp': 1491232186,
1186 'add_ie': ['Kaltura'],
1188 # EaglePlatform embed (generic URL)
1190 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1191 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1195 'title': 'Навальный вышел на свободу',
1196 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1197 'thumbnail': r're:^https?://.*\.jpg$',
1203 'skip_download': True,
1206 # referrer protected EaglePlatform embed
1208 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1212 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1213 'thumbnail': r're:^https?://.*\.jpg$',
1218 'skip_download': True,
1221 # ClipYou (EaglePlatform) embed (custom URL)
1223 'url': 'http://muz-tv.ru/play/7129/',
1224 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1228 'title': "'O Sole Mio",
1229 'thumbnail': r're:^https?://.*\.jpg$',
1234 'skip_download': True,
1239 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1243 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1244 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1245 'thumbnail': r're:^https?://.*\.jpg$',
1252 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1256 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1257 'thumbnail': r're:^https?://.*\.png$',
1263 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1264 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1268 'title': 'Facebook Creates "On This Day" | Crunch Report',
1273 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1277 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1282 # Crooks and Liars embed
1284 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1288 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1289 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1290 'timestamp': 1428207000,
1291 'upload_date': '20150405',
1292 'uploader': 'Heather',
1295 # Crooks and Liars external embed
1297 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1299 'id': 'MTE3MjUtMzQ2MzA',
1301 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1302 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1303 'timestamp': 1265032391,
1304 'upload_date': '20100201',
1305 'uploader': 'Heather',
1308 # NBC Sports vplayer embed
1310 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1312 'id': 'ln7x1qSThw4k',
1314 'title': "PFT Live: New leader in the 'new-look' defense",
1315 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1316 'uploader': 'NBCU-SPORTS',
1317 'upload_date': '20140107',
1318 'timestamp': 1389118457,
1323 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1324 'md5': '1aa589c675898ae6d37a17913cf68d66',
1326 'id': '701714499682',
1328 'title': 'PREVIEW: On Assignment: David Letterman',
1329 '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.',
1334 'url': 'https://video.udn.com/news/300346',
1335 'md5': 'fd2060e988c326991037b9aff9df21a6',
1339 'title': '中一中男師變性 全校師生力挺',
1340 'thumbnail': r're:^https?://.*\.jpg$',
1344 'skip_download': True,
1349 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1351 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1353 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1354 'title': 'This is what separates the Excel masters from the wannabes',
1355 'duration': 191.933,
1359 'skip_download': True,
1362 # Brightcove URL in single quotes
1364 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1365 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1367 'id': '4255764656001',
1369 'title': 'SN Presents: Russell Martin, World Citizen',
1370 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1371 'uploader': 'Rogers Sportsnet',
1372 'uploader_id': '1704050871',
1373 'upload_date': '20150525',
1374 'timestamp': 1432570283,
1377 # Dailymotion Cloud video
1379 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1380 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1384 'title': 'Sauvons les abeilles ! - Le débat',
1385 'description': 'md5:d9082128b1c5277987825d684939ca26',
1386 'thumbnail': r're:^https?://.*\.jpe?g$',
1387 'timestamp': 1434970506,
1388 'upload_date': '20150622',
1389 'uploader': 'Public Sénat',
1390 'uploader_id': 'xa9gza',
1393 # OnionStudios embed
1395 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1399 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1400 'thumbnail': r're:^https?://.*\.jpe?g$',
1401 'uploader': 'ClickHole',
1402 'uploader_id': 'clickhole',
1407 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1409 'id': '74849a00-85a9-11e1-9660-123139220831',
1411 'title': '#whilewewatch',
1414 # AdobeTVVideo embed
1416 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1417 'md5': '43662b577c018ad707a63766462b1e87',
1421 'title': 'New experience with Acrobat DC',
1422 'description': 'New experience with Acrobat DC',
1423 'duration': 248.667,
1426 # BrightcoveInPageEmbed embed
1428 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1430 'id': '4238694884001',
1432 'title': 'Tabletop: Dread, Last Thoughts',
1433 'description': 'Tabletop: Dread, Last Thoughts',
1437 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1438 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1440 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1442 'id': '4785848093001',
1444 'title': 'The Cardinal Pell Interview',
1445 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1446 'uploader': 'GlobeCast Australia - GlobeStream',
1447 'uploader_id': '2733773828001',
1448 'upload_date': '20160304',
1449 'timestamp': 1457083087,
1453 'skip_download': True,
1457 # Brightcove embed with whitespace around attribute names
1458 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1460 'id': '3167554373001',
1462 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1463 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1464 'uploader_id': '1079349493',
1465 'upload_date': '20140207',
1466 'timestamp': 1391810548,
1469 'skip_download': True,
1472 # Another form of arte.tv embed
1474 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1475 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1477 'id': '030273-562_PLUS7-F',
1479 'title': 'ARTE Reportage - Nulle part, en France',
1480 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1481 'upload_date': '20160409',
1486 'url': 'http://www.wykop.pl/link/3088787/',
1487 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1489 'id': '874_1459135191',
1491 'title': 'Man shows poor quality of new apartment building',
1492 'description': 'The wall is like a sand pile.',
1493 'uploader': 'Lake8737',
1496 # Duplicated embedded video URLs
1498 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1500 'id': '149298443_480_16c25b74_2',
1502 'title': 'vs. Blue Orange Spring Game',
1503 'uploader': 'www.hudl.com',
1506 # twitter:player:stream embed
1508 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1512 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1513 'uploader': 'www.rtl.be',
1517 'skip_download': True,
1520 # twitter:player embed
1522 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1523 'md5': 'a3e0df96369831de324f0778e126653c',
1525 'id': '4909620399001',
1527 'title': 'What Do Black Holes Sound Like?',
1528 'description': 'what do black holes sound like',
1529 'upload_date': '20160524',
1530 'uploader_id': '29913724001',
1531 'timestamp': 1464107587,
1532 'uploader': 'TheAtlantic',
1534 'add_ie': ['BrightcoveLegacy'],
1536 # Facebook <iframe> embed
1538 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1539 'md5': 'fbcde74f534176ecb015849146dd3aee',
1541 'id': '599637780109885',
1543 'title': 'Facebook video #599637780109885',
1546 # Facebook <iframe> embed, plugin video
1548 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1550 'id': '1754168231264132',
1552 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1553 'uploader': 'Tariq Ramadan (official)',
1554 'timestamp': 1496758379,
1555 'upload_date': '20170606',
1558 'skip_download': True,
1561 # Facebook API embed
1563 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1564 'md5': 'a47372ee61b39a7b90287094d447d94e',
1566 'id': '10153467542406923',
1568 'title': 'Facebook video #10153467542406923',
1571 # Wordpress "YouTube Video Importer" plugin
1573 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1574 'md5': 'd16797741b560b485194eddda8121b48',
1576 'id': 'HNTXWDXV9Is',
1578 'title': 'Blue Devils Drumline Stanford lot 2016',
1579 'upload_date': '20160627',
1580 'uploader_id': 'GENOCIDE8GENERAL10',
1581 'uploader': 'cylus cyrus',
1585 # video stored on custom kaltura server
1586 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1587 'md5': '537617d06e64dfed891fa1593c4b30cc',
1591 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1592 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1593 'uploader_id': 'videos.expansion@el-mundo.net',
1594 'upload_date': '20150429',
1595 'timestamp': 1430303472,
1597 'add_ie': ['Kaltura'],
1600 # Non-standard Vimeo embed
1601 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1602 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1606 'title': 'Understanding the web - Teaser',
1607 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1608 'upload_date': '20151214',
1609 'uploader': 'OpenClassrooms',
1610 'uploader_id': 'openclassrooms',
1612 'add_ie': ['Vimeo'],
1615 # generic vimeo embed that requires original URL passed as Referer
1616 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1617 'only_matching': True,
1620 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1621 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1623 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1625 'title': 'Big Buck Bunny',
1626 'description': 'Royalty free test video',
1627 'timestamp': 1432816365,
1628 'upload_date': '20150528',
1632 'skip_download': True,
1634 'add_ie': [ArkenaIE.ie_key()],
1637 '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/',
1641 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1644 'skip_download': True,
1646 'add_ie': [Vbox7IE.ie_key()],
1650 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1653 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1655 'playlist_mincount': 3,
1659 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1661 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1662 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1664 'playlist_mincount': 2,
1668 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1672 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1673 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1676 'skip_download': True,
1678 'add_ie': [TwentyMinutenIE.ie_key()],
1682 'url': 'https://en.support.wordpress.com/videopress/',
1686 'title': 'IMG_5786',
1687 'timestamp': 1435711927,
1688 'upload_date': '20150701',
1691 'skip_download': True,
1693 'add_ie': [VideoPressIE.ie_key()],
1697 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1699 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1701 'title': 'Магаззино: Казань 2',
1702 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1703 'uploader': 'Магаззино',
1704 'upload_date': '20170228',
1705 'uploader_id': '996642',
1708 'skip_download': True,
1710 'add_ie': [RutubeIE.ie_key()],
1713 # ThePlatform embedded with whitespaces in URLs
1714 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1715 'only_matching': True,
1718 # Senate ISVP iframe https
1719 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1720 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1722 'id': 'govtaff020316',
1724 'title': 'Integrated Senate Video Player',
1726 'add_ie': [SenateISVPIE.ie_key()],
1729 # Limelight embeds (1 channel embed + 4 media embeds)
1730 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1732 'id': 'FacilitatorTraining2017',
1733 'title': 'Facilitator Training 2017',
1735 'playlist_mincount': 5,
1738 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1740 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1741 'title': 'Standoff with Walnut Creek murder suspect ends',
1742 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1744 'playlist_mincount': 4,
1747 # WashingtonPost embed
1748 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1750 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1752 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1753 '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.',
1754 'timestamp': 1455216756,
1755 'uploader': 'The Washington Post',
1756 'upload_date': '20160211',
1758 'add_ie': [WashingtonPostIE.ie_key()],
1762 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1766 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1769 'skip_download': True,
1771 'add_ie': [MediasetIE.ie_key()],
1774 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1775 'url': 'https://tvrain.ru/amp/418921/',
1776 'md5': 'cc00413936695987e8de148b67d14f1d',
1780 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1784 # # TODO: find another test
1785 # # http://schema.org/VideoObject
1786 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1787 # 'md5': '888dcf08b7ea671381f00fab74692755',
1789 # 'id': 'nyvTSJMKId',
1791 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1792 # 'description': '#love for cats.',
1793 # 'timestamp': 1461244995,
1794 # 'upload_date': '20160421',
1797 # 'force_generic_extractor': True,
1802 def report_following_redirect(self, new_url):
1803 """Report information extraction."""
1804 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1806 def _extract_rss(self, url, video_id, doc):
1807 playlist_title = doc.find('./channel/title').text
1808 playlist_desc_el = doc.find('./channel/description')
1809 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1812 for it in doc.findall('./channel/item'):
1813 next_url = xpath_text(it, 'link', fatal=False)
1815 enclosure_nodes = it.findall('./enclosure')
1816 for e in enclosure_nodes:
1817 next_url = e.attrib.get('url')
1825 '_type': 'url_transparent',
1827 'title': it.find('title').text,
1831 '_type': 'playlist',
1833 'title': playlist_title,
1834 'description': playlist_desc,
1838 def _extract_camtasia(self, url, video_id, webpage):
1839 """ Returns None if no camtasia video can be found. """
1841 camtasia_cfg = self._search_regex(
1842 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1843 webpage, 'camtasia configuration file', default=None)
1844 if camtasia_cfg is None:
1847 title = self._html_search_meta('DC.title', webpage, fatal=True)
1849 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1850 camtasia_cfg = self._download_xml(
1851 camtasia_url, video_id,
1852 note='Downloading camtasia configuration',
1853 errnote='Failed to download camtasia configuration')
1854 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1857 for n in fileset_node.getchildren():
1858 url_n = n.find('./uri')
1863 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1864 'title': '%s - %s' % (title, n.tag),
1865 'url': compat_urlparse.urljoin(url, url_n.text),
1866 'duration': float_or_none(n.find('./duration').text),
1870 '_type': 'playlist',
1875 def _real_extract(self, url):
1876 if url.startswith('//'):
1879 'url': self.http_scheme() + url,
1882 parsed_url = compat_urlparse.urlparse(url)
1883 if not parsed_url.scheme:
1884 default_search = self._downloader.params.get('default_search')
1885 if default_search is None:
1886 default_search = 'fixup_error'
1888 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1890 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1891 return self.url_result('http://' + url)
1892 elif default_search != 'fixup_error':
1893 if default_search == 'auto_warning':
1894 if re.match(r'^(?:url|URL)$', url):
1895 raise ExtractorError(
1896 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1899 self._downloader.report_warning(
1900 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1901 return self.url_result('ytsearch:' + url)
1903 if default_search in ('error', 'fixup_error'):
1904 raise ExtractorError(
1905 '%r is not a valid URL. '
1906 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1907 % (url, url), expected=True)
1909 if ':' not in default_search:
1910 default_search += ':'
1911 return self.url_result(default_search + url)
1913 url, smuggled_data = unsmuggle_url(url)
1914 force_videoid = None
1915 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1916 if smuggled_data and 'force_videoid' in smuggled_data:
1917 force_videoid = smuggled_data['force_videoid']
1918 video_id = force_videoid
1920 video_id = self._generic_id(url)
1922 self.to_screen('%s: Requesting header' % video_id)
1924 head_req = HEADRequest(url)
1925 head_response = self._request_webpage(
1927 note=False, errnote='Could not send HEAD request to %s' % url,
1930 if head_response is not False:
1931 # Check for redirect
1932 new_url = head_response.geturl()
1934 self.report_following_redirect(new_url)
1936 new_url = smuggle_url(
1937 new_url, {'force_videoid': force_videoid})
1938 return self.url_result(new_url)
1940 full_response = None
1941 if head_response is False:
1942 request = sanitized_Request(url)
1943 request.add_header('Accept-Encoding', '*')
1944 full_response = self._request_webpage(request, video_id)
1945 head_response = full_response
1949 'title': self._generic_title(url),
1950 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1953 # Check for direct link to a video
1954 content_type = head_response.headers.get('Content-Type', '').lower()
1955 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1957 format_id = compat_str(m.group('format_id'))
1958 if format_id.endswith('mpegurl'):
1959 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1960 elif format_id == 'f4m':
1961 formats = self._extract_f4m_formats(url, video_id)
1964 'format_id': format_id,
1966 'vcodec': 'none' if m.group('type') == 'audio' else None
1968 info_dict['direct'] = True
1969 self._sort_formats(formats)
1970 info_dict['formats'] = formats
1973 if not self._downloader.params.get('test', False) and not is_intentional:
1974 force = self._downloader.params.get('force_generic_extractor', False)
1975 self._downloader.report_warning(
1976 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1978 if not full_response:
1979 request = sanitized_Request(url)
1980 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1981 # making it impossible to download only chunk of the file (yet we need only 512kB to
1982 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1983 # that will always result in downloading the whole file that is not desirable.
1984 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1985 # to accept raw bytes and being able to download only a chunk.
1986 # It may probably better to solve this by checking Content-Type for application/octet-stream
1987 # after HEAD request finishes, but not sure if we can rely on this.
1988 request.add_header('Accept-Encoding', '*')
1989 full_response = self._request_webpage(request, video_id)
1991 first_bytes = full_response.read(512)
1993 # Is it an M3U playlist?
1994 if first_bytes.startswith(b'#EXTM3U'):
1995 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1996 self._sort_formats(info_dict['formats'])
1999 # Maybe it's a direct link to a video?
2000 # Be careful not to download the whole thing!
2001 if not is_html(first_bytes):
2002 self._downloader.report_warning(
2003 'URL could be a direct video link, returning it as such.')
2010 webpage = self._webpage_read_content(
2011 full_response, url, video_id, prefix=first_bytes)
2013 self.report_extraction(video_id)
2015 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2017 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2018 if doc.tag == 'rss':
2019 return self._extract_rss(url, video_id, doc)
2020 elif doc.tag == 'SmoothStreamingMedia':
2021 info_dict['formats'] = self._parse_ism_formats(doc, url)
2022 self._sort_formats(info_dict['formats'])
2024 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2025 smil = self._parse_smil(doc, url, video_id)
2026 self._sort_formats(smil['formats'])
2028 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2029 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2030 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2031 info_dict['formats'] = self._parse_mpd_formats(
2033 mpd_base_url=full_response.geturl().rpartition('/')[0],
2035 self._sort_formats(info_dict['formats'])
2037 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2038 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2039 self._sort_formats(info_dict['formats'])
2041 except compat_xml_parse_error:
2044 # Is it a Camtasia project?
2045 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2046 if camtasia_res is not None:
2049 # Sometimes embedded video player is hidden behind percent encoding
2050 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2051 # Unescaping the whole page allows to handle those cases in a generic way
2052 webpage = compat_urllib_parse_unquote(webpage)
2054 # it's tempting to parse this further, but you would
2055 # have to take into account all the variations like
2056 # Video Title - Site Name
2057 # Site Name | Video Title
2058 # Video Title - Tagline | Site Name
2059 # and so on and so forth; it's just not practical
2060 video_title = self._og_search_title(
2061 webpage, default=None) or self._html_search_regex(
2062 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2065 # Try to detect age limit automatically
2066 age_limit = self._rta_search(webpage)
2067 # And then there are the jokers who advertise that they use RTA,
2068 # but actually don't.
2069 AGE_LIMIT_MARKERS = [
2070 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2072 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2075 # video uploader is domain name
2076 video_uploader = self._search_regex(
2077 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2079 video_description = self._og_search_description(webpage, default=None)
2080 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2083 'title': video_title,
2084 'description': video_description,
2085 'thumbnail': video_thumbnail,
2086 'age_limit': age_limit,
2089 # Look for Brightcove Legacy Studio embeds
2090 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2094 'url': smuggle_url(bc_url, {'Referer': url}),
2095 'ie_key': 'BrightcoveLegacy'
2096 } for bc_url in bc_urls]
2099 '_type': 'playlist',
2100 'title': video_title,
2105 # Look for Brightcove New Studio embeds
2106 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2108 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2110 # Look for ThePlatform embeds
2111 tp_urls = ThePlatformIE._extract_urls(webpage)
2113 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2115 # Look for Vessel embeds
2116 vessel_urls = VesselIE._extract_urls(webpage)
2118 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2120 # Look for embedded rtl.nl player
2121 matches = re.findall(
2122 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2125 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2127 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2129 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2131 vid_me_embed_url = self._search_regex(
2132 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2133 webpage, 'vid.me embed', default=None)
2134 if vid_me_embed_url is not None:
2135 return self.url_result(vid_me_embed_url, 'Vidme')
2137 # Look for embedded YouTube player
2138 matches = re.findall(r'''(?x)
2148 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2152 return self.playlist_from_matches(
2153 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2155 # Look for lazyYT YouTube embed
2156 matches = re.findall(
2157 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2159 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2161 # Look for Wordpress "YouTube Video Importer" plugin
2162 matches = re.findall(r'''(?x)<div[^>]+
2163 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2164 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2166 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2168 matches = DailymotionIE._extract_urls(webpage)
2170 return self.playlist_from_matches(matches, video_id, video_title)
2172 # Look for embedded Dailymotion playlist player (#3822)
2174 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2176 playlists = re.findall(
2177 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2179 return self.playlist_from_matches(
2180 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2182 # Look for embedded Wistia player
2183 wistia_url = WistiaIE._extract_url(webpage)
2186 '_type': 'url_transparent',
2187 'url': self._proto_relative_url(wistia_url),
2188 'ie_key': WistiaIE.ie_key(),
2189 'uploader': video_uploader,
2192 # Look for SVT player
2193 svt_url = SVTIE._extract_url(webpage)
2195 return self.url_result(svt_url, 'SVT')
2197 # Look for Bandcamp pages with custom domain
2198 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2199 if mobj is not None:
2200 burl = unescapeHTML(mobj.group(1))
2201 # Don't set the extractor because it can be a track url or an album
2202 return self.url_result(burl)
2204 # Look for embedded Vevo player
2206 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2207 if mobj is not None:
2208 return self.url_result(mobj.group('url'))
2210 # Look for embedded Viddler player
2212 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2214 if mobj is not None:
2215 return self.url_result(mobj.group('url'))
2217 # Look for NYTimes player
2219 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2221 if mobj is not None:
2222 return self.url_result(mobj.group('url'))
2224 # Look for Libsyn player
2226 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2227 if mobj is not None:
2228 return self.url_result(mobj.group('url'))
2230 # Look for Ooyala videos
2231 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2232 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2233 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2234 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2235 if mobj is not None:
2236 embed_token = self._search_regex(
2237 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2238 webpage, 'ooyala embed token', default=None)
2239 return OoyalaIE._build_url_result(smuggle_url(
2242 'embed_token': embed_token,
2245 # Look for multiple Ooyala embeds on SBN network websites
2246 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2247 if mobj is not None:
2248 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2250 return self.playlist_from_matches(
2251 embeds, video_id, video_title,
2252 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2254 # Look for Aparat videos
2255 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2256 if mobj is not None:
2257 return self.url_result(mobj.group(1), 'Aparat')
2259 # Look for MPORA videos
2260 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2261 if mobj is not None:
2262 return self.url_result(mobj.group(1), 'Mpora')
2264 # Look for embedded NovaMov-based player
2266 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2267 (?P<url>http://(?:(?:embed|www)\.)?
2269 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2270 videoweed\.(?:es|com)|
2271 movshare\.(?:net|sx|ag)|
2272 divxstage\.(?:eu|net|ch|co|at|ag))
2273 /embed\.php.+?)\1''', webpage)
2274 if mobj is not None:
2275 return self.url_result(mobj.group('url'))
2277 # Look for embedded Facebook player
2278 facebook_urls = FacebookIE._extract_urls(webpage)
2280 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2282 # Look for embedded VK player
2283 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2284 if mobj is not None:
2285 return self.url_result(mobj.group('url'), 'VK')
2287 # Look for embedded Odnoklassniki player
2288 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2289 if mobj is not None:
2290 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2292 # Look for embedded ivi player
2293 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2294 if mobj is not None:
2295 return self.url_result(mobj.group('url'), 'Ivi')
2297 # Look for embedded Huffington Post player
2299 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2300 if mobj is not None:
2301 return self.url_result(mobj.group('url'), 'HuffPost')
2304 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2305 if mobj is not None:
2306 return self.url_result(mobj.group('url'))
2307 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2308 if mobj is not None:
2309 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2311 # Look for funnyordie embed
2312 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2314 return self.playlist_from_matches(
2315 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2317 # Look for BBC iPlayer embed
2318 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2320 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2322 # Look for embedded RUTV player
2323 rutv_url = RUTVIE._extract_url(webpage)
2325 return self.url_result(rutv_url, 'RUTV')
2327 # Look for embedded TVC player
2328 tvc_url = TVCIE._extract_url(webpage)
2330 return self.url_result(tvc_url, 'TVC')
2332 # Look for embedded SportBox player
2333 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2335 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2337 # Look for embedded XHamster player
2338 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2340 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2342 # Look for embedded TNAFlixNetwork player
2343 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2345 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2347 # Look for embedded PornHub player
2348 pornhub_urls = PornHubIE._extract_urls(webpage)
2350 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2352 # Look for embedded DrTuber player
2353 drtuber_urls = DrTuberIE._extract_urls(webpage)
2355 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2357 # Look for embedded RedTube player
2358 redtube_urls = RedTubeIE._extract_urls(webpage)
2360 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2362 # Look for embedded Tvigle player
2364 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2365 if mobj is not None:
2366 return self.url_result(mobj.group('url'), 'Tvigle')
2368 # Look for embedded TED player
2370 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2371 if mobj is not None:
2372 return self.url_result(mobj.group('url'), 'TED')
2374 # Look for embedded Ustream videos
2375 ustream_url = UstreamIE._extract_url(webpage)
2377 return self.url_result(ustream_url, UstreamIE.ie_key())
2379 # Look for embedded arte.tv player
2381 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2383 if mobj is not None:
2384 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2386 # Look for embedded francetv player
2388 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2390 if mobj is not None:
2391 return self.url_result(mobj.group('url'))
2393 # Look for embedded smotri.com player
2394 smotri_url = SmotriIE._extract_url(webpage)
2396 return self.url_result(smotri_url, 'Smotri')
2398 # Look for embedded Myvi.ru player
2399 myvi_url = MyviIE._extract_url(webpage)
2401 return self.url_result(myvi_url)
2403 # Look for embedded soundcloud player
2404 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2406 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2408 # Look for tunein player
2409 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2411 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2413 # Look for embedded mtvservices player
2414 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2416 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2418 # Look for embedded yahoo player
2420 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2422 if mobj is not None:
2423 return self.url_result(mobj.group('url'), 'Yahoo')
2425 # Look for embedded sbs.com.au player
2429 <meta\s+property="og:video"\s+content=|
2432 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2434 if mobj is not None:
2435 return self.url_result(mobj.group('url'), 'SBS')
2437 # Look for embedded Cinchcast player
2439 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2441 if mobj is not None:
2442 return self.url_result(mobj.group('url'), 'Cinchcast')
2445 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2449 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2451 if mobj is not None:
2452 return self.url_result(mobj.group('url'), 'MLB')
2455 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2457 if mobj is not None:
2458 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2461 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2463 if mobj is not None:
2464 return self.url_result(mobj.group('url'), 'Livestream')
2466 # Look for Zapiks embed
2468 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2469 if mobj is not None:
2470 return self.url_result(mobj.group('url'), 'Zapiks')
2472 # Look for Kaltura embeds
2473 kaltura_url = KalturaIE._extract_url(webpage)
2475 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2477 # Look for EaglePlatform embeds
2478 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2479 if eagleplatform_url:
2480 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2482 # Look for ClipYou (uses EaglePlatform) embeds
2484 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2485 if mobj is not None:
2486 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2488 # Look for Pladform embeds
2489 pladform_url = PladformIE._extract_url(webpage)
2491 return self.url_result(pladform_url)
2493 # Look for Videomore embeds
2494 videomore_url = VideomoreIE._extract_url(webpage)
2496 return self.url_result(videomore_url)
2498 # Look for Webcaster embeds
2499 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2501 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2503 # Look for Playwire embeds
2505 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2506 if mobj is not None:
2507 return self.url_result(mobj.group('url'))
2509 # Look for 5min embeds
2511 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2512 if mobj is not None:
2513 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2515 # Look for Crooks and Liars embeds
2517 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2518 if mobj is not None:
2519 return self.url_result(mobj.group('url'))
2521 # Look for NBC Sports VPlayer embeds
2522 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2524 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2526 # Look for NBC News embeds
2527 nbc_news_embed_url = re.search(
2528 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2529 if nbc_news_embed_url:
2530 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2532 # Look for Google Drive embeds
2533 google_drive_url = GoogleDriveIE._extract_url(webpage)
2534 if google_drive_url:
2535 return self.url_result(google_drive_url, 'GoogleDrive')
2537 # Look for UDN embeds
2539 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2540 if mobj is not None:
2541 return self.url_result(
2542 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2544 # Look for Senate ISVP iframe
2545 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2547 return self.url_result(senate_isvp_url, 'SenateISVP')
2549 # Look for Dailymotion Cloud videos
2550 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2552 return self.url_result(dmcloud_url, 'DailymotionCloud')
2554 # Look for OnionStudios embeds
2555 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2556 if onionstudios_url:
2557 return self.url_result(onionstudios_url)
2559 # Look for ViewLift embeds
2560 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2562 return self.url_result(viewlift_url)
2564 # Look for JWPlatform embeds
2565 jwplatform_url = JWPlatformIE._extract_url(webpage)
2567 return self.url_result(jwplatform_url, 'JWPlatform')
2569 # Look for Digiteka embeds
2570 digiteka_url = DigitekaIE._extract_url(webpage)
2572 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2574 # Look for Arkena embeds
2575 arkena_url = ArkenaIE._extract_url(webpage)
2577 return self.url_result(arkena_url, ArkenaIE.ie_key())
2579 # Look for Piksel embeds
2580 piksel_url = PikselIE._extract_url(webpage)
2582 return self.url_result(piksel_url, PikselIE.ie_key())
2584 # Look for Limelight embeds
2585 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2587 return self.playlist_result(
2588 limelight_urls, video_id, video_title, video_description)
2590 # Look for Anvato embeds
2591 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2593 return self.playlist_result(
2594 anvato_urls, video_id, video_title, video_description)
2596 # Look for AdobeTVVideo embeds
2598 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2600 if mobj is not None:
2601 return self.url_result(
2602 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2605 # Look for Vine embeds
2607 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2609 if mobj is not None:
2610 return self.url_result(
2611 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2613 # Look for VODPlatform embeds
2615 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2617 if mobj is not None:
2618 return self.url_result(
2619 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2621 # Look for Mangomolo embeds
2623 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2625 video\?.*?\bid=(?P<video_id>\d+)|
2626 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2627 ).+?)\1''', webpage)
2628 if mobj is not None:
2630 '_type': 'url_transparent',
2631 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2632 'title': video_title,
2633 'description': video_description,
2634 'thumbnail': video_thumbnail,
2635 'uploader': video_uploader,
2637 video_id = mobj.group('video_id')
2640 'ie_key': 'MangomoloVideo',
2645 'ie_key': 'MangomoloLive',
2646 'id': mobj.group('channel_id'),
2650 # Look for Instagram embeds
2651 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2652 if instagram_embed_url is not None:
2653 return self.url_result(
2654 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2656 # Look for LiveLeak embeds
2657 liveleak_url = LiveLeakIE._extract_url(webpage)
2659 return self.url_result(liveleak_url, 'LiveLeak')
2661 # Look for 3Q SDN embeds
2662 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2665 '_type': 'url_transparent',
2666 'ie_key': ThreeQSDNIE.ie_key(),
2667 'url': self._proto_relative_url(threeqsdn_url),
2668 'title': video_title,
2669 'description': video_description,
2670 'thumbnail': video_thumbnail,
2671 'uploader': video_uploader,
2674 # Look for VBOX7 embeds
2675 vbox7_url = Vbox7IE._extract_url(webpage)
2677 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2679 # Look for DBTV embeds
2680 dbtv_urls = DBTVIE._extract_urls(webpage)
2682 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2684 # Look for Videa embeds
2685 videa_urls = VideaIE._extract_urls(webpage)
2687 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2689 # Look for 20 minuten embeds
2690 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2692 return self.playlist_from_matches(
2693 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2695 # Look for Openload embeds
2696 openload_urls = OpenloadIE._extract_urls(webpage)
2698 return self.playlist_from_matches(
2699 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2701 # Look for VideoPress embeds
2702 videopress_urls = VideoPressIE._extract_urls(webpage)
2704 return self.playlist_from_matches(
2705 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2707 # Look for Rutube embeds
2708 rutube_urls = RutubeIE._extract_urls(webpage)
2710 return self.playlist_from_matches(
2711 rutube_urls, ie=RutubeIE.ie_key())
2713 # Look for WashingtonPost embeds
2714 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2716 return self.playlist_from_matches(
2717 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2719 # Look for Mediaset embeds
2720 mediaset_urls = MediasetIE._extract_urls(webpage)
2722 return self.playlist_from_matches(
2723 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2725 def merge_dicts(dict1, dict2):
2727 for k, v in dict1.items():
2730 for k, v in dict2.items():
2733 if (k not in merged or
2734 (isinstance(v, compat_str) and v and
2735 isinstance(merged[k], compat_str) and
2740 # Looking for http://schema.org/VideoObject
2741 json_ld = self._search_json_ld(
2742 webpage, video_id, default={}, expected_type='VideoObject')
2743 if json_ld.get('url'):
2744 return merge_dicts(json_ld, info_dict)
2746 # Look for HTML5 media
2747 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2749 for entry in entries:
2752 'title': video_title,
2754 self._sort_formats(entry['formats'])
2755 return self.playlist_result(entries)
2757 jwplayer_data = self._find_jwplayer_data(
2758 webpage, video_id, transform_source=js_to_json)
2760 info = self._parse_jwplayer_data(
2761 jwplayer_data, video_id, require_title=False, base_url=url)
2762 return merge_dicts(info, info_dict)
2764 def check_video(vurl):
2765 if YoutubeIE.suitable(vurl):
2767 if RtmpIE.suitable(vurl):
2769 vpath = compat_urlparse.urlparse(vurl).path
2770 vext = determine_ext(vpath)
2771 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2773 def filter_video(urls):
2774 return list(filter(check_video, urls))
2776 # Start with something easy: JW Player in SWFObject
2777 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2779 # Look for gorilla-vid style embedding
2780 found = filter_video(re.findall(r'''(?sx)
2784 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2787 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2789 # Broaden the search a little bit
2790 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2792 # Broaden the findall a little bit: JWPlayer JS loader
2793 found = filter_video(re.findall(
2794 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2797 found = filter_video(re.findall(r'''(?xs)
2798 flowplayer\("[^"]+",\s*
2800 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2801 ["']?url["']?\s*:\s*["']([^"']+)["']
2806 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2808 # Try to find twitter cards info
2809 # twitter:player:stream should be checked before twitter:player since
2810 # it is expected to contain a raw stream (see
2811 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2812 found = filter_video(re.findall(
2813 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2815 # We look for Open Graph info:
2816 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2817 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2818 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2819 if m_video_type is not None:
2820 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2822 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2824 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2825 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2828 # Look also in Refresh HTTP header
2829 refresh_header = head_response.headers.get('Refresh')
2831 # In python 2 response HTTP headers are bytestrings
2832 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2833 refresh_header = refresh_header.decode('iso-8859-1')
2834 found = re.search(REDIRECT_REGEX, refresh_header)
2836 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2838 self.report_following_redirect(new_url)
2847 # twitter:player is a https URL to iframe player that may or may not
2848 # be supported by youtube-dl thus this is checked the very last (see
2849 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2850 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2852 return self.url_result(embed_url)
2855 raise UnsupportedError(url)
2858 for video_url in orderedSet(found):
2859 video_url = unescapeHTML(video_url)
2860 video_url = video_url.replace('\\/', '/')
2861 video_url = compat_urlparse.urljoin(url, video_url)
2862 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2864 # Sometimes, jwplayer extraction will result in a YouTube URL
2865 if YoutubeIE.suitable(video_url):
2866 entries.append(self.url_result(video_url, 'Youtube'))
2869 # here's a fun little line of code for you:
2870 video_id = os.path.splitext(video_id)[0]
2874 'uploader': video_uploader,
2875 'title': video_title,
2876 'age_limit': age_limit,
2879 if RtmpIE.suitable(video_url):
2880 entry_info_dict.update({
2881 '_type': 'url_transparent',
2882 'ie_key': RtmpIE.ie_key(),
2885 entries.append(entry_info_dict)
2888 ext = determine_ext(video_url)
2890 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2892 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2894 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2896 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2898 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2899 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2900 # Just matching .ism/manifest is not enough to be reliably sure
2901 # whether it's actually an ISM manifest or some other streaming
2902 # manifest since there are various streaming URL formats
2903 # possible (see [1]) as well as some other shenanigans like
2904 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2906 # Thus the most reasonable way to solve this is to delegate
2907 # to generic extractor in order to look into the contents of
2908 # the manifest itself.
2909 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2910 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2911 entry_info_dict = self.url_result(
2912 smuggle_url(video_url, {'to_generic': True}),
2915 entry_info_dict['url'] = video_url
2917 if entry_info_dict.get('formats'):
2918 self._sort_formats(entry_info_dict['formats'])
2920 entries.append(entry_info_dict)
2922 if len(entries) == 1:
2925 for num, e in enumerate(entries, start=1):
2926 # 'url' results don't have a title
2927 if e.get('title') is not None:
2928 e['title'] = '%s (%d)' % (e['title'], num)
2930 '_type': 'playlist',