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,
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .spankwire import SpankwireIE
64 from .vimeo import VimeoIE
65 from .dailymotion import DailymotionIE
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudEmbedIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
101 from .vzaar import VzaarIE
102 from .channel9 import Channel9IE
103 from .vshare import VShareIE
104 from .mediasite import MediasiteIE
105 from .springboardplatform import SpringboardPlatformIE
106 from .yapfiles import YapFilesIE
107 from .vice import ViceIE
108 from .xfileshare import XFileShareIE
109 from .cloudflarestream import CloudflareStreamIE
110 from .peertube import PeerTubeIE
111 from .teachable import TeachableIE
112 from .indavideo import IndavideoEmbedIE
113 from .apa import APAIE
114 from .foxnews import FoxNewsIE
115 from .viqeo import ViqeoIE
116 from .expressen import ExpressenIE
117 from .zype import ZypeIE
118 from .odnoklassniki import OdnoklassnikiIE
119 from .kinja import KinjaEmbedIE
122 class GenericIE(InfoExtractor):
123 IE_DESC = 'Generic downloader that works on some sites'
127 # Direct link to a video
129 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
130 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
135 'upload_date': '20100513',
138 # Direct link to media delivered compressed (until Accept-Encoding is *)
140 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
141 'md5': '128c42e68b13950268b648275386fc74',
143 'id': 'FictionJunction-Parallel_Hearts',
145 'title': 'FictionJunction-Parallel_Hearts',
146 'upload_date': '20140522',
148 'expected_warnings': [
149 'URL could be a direct video link, returning it as such.'
151 'skip': 'URL invalid',
153 # Direct download with broken HEAD
155 'url': 'http://ai-radio.org:8000/radio.opus',
162 'skip_download': True, # infinite live stream
164 'expected_warnings': [
165 r'501.*Not Implemented',
169 # Direct link with incorrect MIME type
171 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
172 'md5': '4ccbebe5f36706d85221f204d7eb5913',
174 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
175 'id': '5_Lennart_Poettering_-_Systemd',
177 'title': '5_Lennart_Poettering_-_Systemd',
178 'upload_date': '20141120',
180 'expected_warnings': [
181 'URL could be a direct video link, returning it as such.'
186 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
188 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
189 'title': 'Zero Punctuation',
190 'description': 're:.*groundbreaking video review series.*'
192 'playlist_mincount': 11,
194 # RSS feed with enclosure
196 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
198 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
200 'upload_date': '20150228',
201 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
204 # RSS feed with enclosures and unsupported link URLs
206 'url': 'http://www.hellointernet.fm/podcast?format=rss',
208 'id': 'http://www.hellointernet.fm/podcast?format=rss',
209 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
210 'title': 'Hello Internet',
212 'playlist_mincount': 100,
214 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
216 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
220 'title': 'Automatics, robotics and biocybernetics',
221 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
222 'upload_date': '20130627',
223 'formats': 'mincount:16',
224 'subtitles': 'mincount:1',
227 'force_generic_extractor': True,
228 'skip_download': True,
231 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
233 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
238 'formats': 'mincount:1',
241 'skip_download': True,
244 # SMIL from https://www.restudy.dk/video/play/id/1637
246 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
250 'title': 'video_1637',
251 'formats': 'mincount:3',
254 'skip_download': True,
257 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
259 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
261 'id': 'smil-service',
263 'title': 'smil-service',
264 'formats': 'mincount:1',
267 'skip_download': True,
270 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
272 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
276 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
277 'formats': 'mincount:3',
280 'skip_download': True,
283 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
285 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
287 'id': 'mZlp2ctYIUEB',
289 'title': 'Tikibad ontruimd wegens brand',
290 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
291 'thumbnail': r're:^https?://.*\.jpg$',
295 'skip_download': True,
298 # MPD from http://dash-mse-test.appspot.com/media.html
300 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
301 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
303 'id': 'car-20120827-manifest',
305 'title': 'car-20120827-manifest',
306 'formats': 'mincount:9',
307 'upload_date': '20130904',
310 'format': 'bestvideo',
313 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
315 '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',
320 'formats': 'mincount:8',
324 'skip_download': True,
326 'skip': 'video gone',
328 # m3u8 served with Content-Type: text/plain
330 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
335 'upload_date': '20140720',
336 'formats': 'mincount:11',
340 'skip_download': True,
342 'skip': 'video gone',
346 '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',
350 'upload_date': '20130224',
351 'uploader_id': 'TheVerge',
352 'description': r're:^Chris Ziegler takes a look at the\.*',
353 'uploader': 'The Verge',
354 'title': 'First Firefox OS phones side-by-side',
357 'skip_download': False,
361 # redirect in Refresh HTTP header
362 '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',
366 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
367 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
368 'upload_date': '20150917',
369 'uploader_id': 'brtvofficial',
370 'uploader': 'Boiler Room',
373 'skip_download': False,
377 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
378 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
380 'id': '13601338388002',
382 'uploader': 'www.hodiho.fr',
383 'title': 'R\u00e9gis plante sa Jeep',
386 # bandcamp page with custom domain
388 'add_ie': ['Bandcamp'],
389 'url': 'http://bronyrock.com/track/the-pony-mash',
393 'title': 'The Pony Mash',
394 'uploader': 'M_Pallante',
396 'skip': 'There is a limit of 200 free downloads / month for the test song',
399 # embedded brightcove video
400 # it also tests brightcove videos that need to set the 'Referer'
401 # in the http requests
402 'add_ie': ['BrightcoveLegacy'],
403 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
405 'id': '2765128793001',
407 'title': 'Le cours de bourse : l’analyse technique',
408 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
409 'uploader': 'BFM BUSINESS',
412 'skip_download': True,
416 # embedded with itemprop embedURL and video id spelled as `idVideo`
417 'add_id': ['BrightcoveLegacy'],
418 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
420 'id': '5255628253001',
422 'title': 'md5:37c519b1128915607601e75a87995fc0',
423 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
424 'uploader': 'BFM BUSINESS',
425 'uploader_id': '876450612001',
426 'timestamp': 1482255315,
427 'upload_date': '20161220',
430 'skip_download': True,
434 # https://github.com/ytdl-org/youtube-dl/issues/2253
435 'url': 'http://bcove.me/i6nfkrc3',
436 'md5': '0ba9446db037002366bab3b3eb30c88c',
438 'id': '3101154703001',
440 'title': 'Still no power',
441 'uploader': 'thestar.com',
442 '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.',
444 'add_ie': ['BrightcoveLegacy'],
445 'skip': 'video gone',
448 'url': 'http://www.championat.com/video/football/v/87/87499.html',
449 'md5': 'fb973ecf6e4a78a67453647444222983',
451 'id': '3414141473001',
453 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
454 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
455 'uploader': 'Championat',
459 # https://github.com/ytdl-org/youtube-dl/issues/3541
460 'add_ie': ['BrightcoveLegacy'],
461 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
463 'id': '3866516442001',
465 'title': 'Leer mij vrouwen kennen: Aflevering 1',
466 'description': 'Leer mij vrouwen kennen: Aflevering 1',
467 'uploader': 'SBS Broadcasting',
469 'skip': 'Restricted to Netherlands',
471 'skip_download': True, # m3u8 download
475 # Brightcove video in <iframe>
476 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
477 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
479 'id': '5360463607001',
481 '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',
482 '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。',
483 'uploader': 'United Nations',
484 'uploader_id': '1362235914001',
485 'timestamp': 1489593889,
486 'upload_date': '20170315',
488 'add_ie': ['BrightcoveLegacy'],
491 # Brightcove with alternative playerID key
492 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
494 'id': 'nmeth.2062_SV1',
495 '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',
499 'id': '2228375078001',
501 'title': 'nmeth.2062-sv1',
502 'description': 'nmeth.2062-sv1',
503 'timestamp': 1363357591,
504 'upload_date': '20130315',
505 'uploader': 'Nature Publishing Group',
506 'uploader_id': '1964492299001',
511 # Brightcove with UUID in videoPlayer
512 'url': 'http://www8.hp.com/cn/zh/home.html',
514 'id': '5255815316001',
516 'title': 'Sprocket Video - China',
517 'description': 'Sprocket Video - China',
518 'uploader': 'HP-Video Gallery',
519 'timestamp': 1482263210,
520 'upload_date': '20161220',
521 'uploader_id': '1107601872001',
524 'skip_download': True, # m3u8 download
526 'skip': 'video rotates...weekly?',
529 # Brightcove:new type [2].
530 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
531 'md5': '2b35148fcf48da41c9fb4591650784f3',
533 'id': '5348741021001',
535 'upload_date': '20170306',
536 'uploader_id': '4191638492001',
537 'timestamp': 1488769918,
538 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
543 # Alternative brightcove <video> attributes
544 '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/',
546 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
547 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
550 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
552 'id': '5311302538001',
554 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
555 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
556 'timestamp': 1486321708,
557 'upload_date': '20170205',
558 'uploader_id': '800000640001',
560 'only_matching': True,
564 # Brightcove with UUID in videoPlayer
565 'url': 'http://www8.hp.com/cn/zh/home.html',
567 'id': '5255815316001',
569 'title': 'Sprocket Video - China',
570 'description': 'Sprocket Video - China',
571 'uploader': 'HP-Video Gallery',
572 'timestamp': 1482263210,
573 'upload_date': '20161220',
574 'uploader_id': '1107601872001',
577 'skip_download': True, # m3u8 download
582 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
583 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
585 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
587 'title': '2cc213299525360.mov', # that's what we get
590 'add_ie': ['Ooyala'],
593 # ooyala video embedded with http://player.ooyala.com/iframe.js
594 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
596 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
598 'title': '"Steve Jobs: Man in the Machine" trailer',
599 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
603 'skip_download': True,
605 'skip': 'movie expired',
607 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
609 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
611 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
613 'title': 'Steampunk Fest Comes to Honesdale',
617 'skip_download': True,
622 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
626 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
627 'upload_date': '20140225',
628 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
629 'uploader': 'Tested',
630 'uploader_id': 'testedcom',
632 # No need to test YoutubeIE here
634 'skip_download': True,
639 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
643 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
644 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
646 # HEAD requests lead to endless 301, while GET is OK
647 'expected_warnings': ['301'],
651 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
655 'title': 'Охотское море стало целиком российским',
656 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
660 'skip_download': True,
665 '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/',
669 'title': 'Дошкольное воспитание',
674 'url': 'http://www.vestifinance.ru/articles/25753',
677 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
682 'title': 'Госзаказ. День 3',
688 'title': 'Госзаказ. День 2',
694 'title': 'Госзаказ. День 1',
700 'skip_download': True,
705 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
707 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
709 'title': 'Ужастики, русский трейлер (2015)',
710 'thumbnail': r're:^https?://.*\.jpg$',
716 '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',
719 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
721 'playlist_mincount': 7,
722 # This forum does not allow <iframe> syntaxes anymore
723 # Now HTML tags are displayed as-is
724 'skip': 'No videos on this page',
728 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
729 'md5': '65fdff94098e4a607385a60c5177c638',
733 'title': 'Hidden miracles of the natural world',
734 'uploader': 'Louie Schwartzberg',
735 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
738 # nowvideo embed hidden behind percent encoding
740 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
741 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
743 'id': '06e53103ca9aa',
745 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
746 'description': 'No description',
751 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
752 'md5': '7653032cbb25bf6c80d80f217055fa43',
754 'id': '048195-004_PLUS7-F',
757 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
758 'upload_date': '20140320',
761 'skip_download': 'Requires rtmpdump'
763 'skip': 'video gone',
767 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
771 'title': 'Alcaline, le concert avec Calogero',
772 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
773 'upload_date': '20150226',
774 'timestamp': 1424989860,
779 'skip_download': True,
781 'expected_warnings': [
787 'url': 'http://www.wired.com/2014/04/honda-asimo/',
788 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
790 'id': '53501be369702d3275860000',
792 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
797 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
798 'md5': '441aeeb82eb72c422c7f14ec533999cd',
800 'id': 'k2mm4bCdJ6CQ2i7c8o2',
802 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
803 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
805 'uploader_id': 'xgditw',
806 'upload_date': '20140425',
807 'timestamp': 1398441542,
809 'add_ie': ['Dailymotion'],
813 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
817 'title': 'Care worker punches elderly dementia patient in head 11 times',
818 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
820 'add_ie': ['DailyMail'],
822 'skip_download': True,
827 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
831 'title': 'The NBL Auction 2014',
832 'uploader': 'BADMINTON England',
833 'uploader_id': 'BADMINTONEvents',
834 'upload_date': '20140603',
835 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
837 'add_ie': ['Youtube'],
839 'skip_download': True,
844 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
845 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
847 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
849 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
850 'description': 'Two valets share their love for movie star Liam Neesons.',
851 'timestamp': 1349922600,
852 'upload_date': '20121011',
855 # YouTube embed via <data-embed-url="">
857 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
861 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
862 'uploader': 'Gameloft',
863 'uploader_id': 'gameloft',
864 'upload_date': '20140828',
865 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
868 'skip_download': True,
871 # YouTube <object> embed
873 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
874 'md5': '516718101ec834f74318df76259fb3cc',
878 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
879 'upload_date': '20080526',
880 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
881 'uploader': 'Christopher Sykes',
882 'uploader_id': 'ChristopherJSykes',
884 'add_ie': ['Youtube'],
888 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
890 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
892 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
893 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
898 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
900 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
901 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
907 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
912 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
913 'md5': '9d65602bf31c6e20014319c7d07fba27',
915 'id': '5123ea6d5e5a7',
918 'uploader': 'www.handjobhub.com',
919 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
922 # Multiple brightcove videos
923 # https://github.com/ytdl-org/youtube-dl/issues/2283
925 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
927 'id': 'always-never',
928 'title': 'Always / Never - The New Yorker',
932 'extract_flat': False,
933 'skip_download': True,
938 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
939 'md5': '96f09a37e44da40dd083e12d9a683327',
943 'title': 'Ump changes call to ball',
944 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
946 'timestamp': 1401537900,
947 'upload_date': '20140531',
948 'thumbnail': r're:^https?://.*\.jpg$',
953 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
954 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
958 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
959 'description': 'a Paywall Videos video from Remilon',
961 'uploader': 'study.com',
962 'timestamp': 1459678540,
963 'upload_date': '20160403',
964 'filesize': 24687186,
968 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
969 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
973 'title': 'Conversation about Hexagonal Rails Part 1',
974 'description': 'a Martin Fowler video from ThoughtWorks',
976 'uploader': 'thoughtworks.wistia.com',
977 'timestamp': 1401832161,
978 'upload_date': '20140603',
981 # Wistia standard embed (async)
983 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
987 'title': 'Drip Brennan Dunn Workshop',
988 'description': 'a JV Webinars video from getdrip-1',
990 'timestamp': 1463607249,
991 'upload_date': '20160518',
994 'skip_download': True,
999 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1003 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1004 'uploader': 'Sophos Security',
1005 'title': 'Chet Chat 171 - Oct 29, 2014',
1006 'upload_date': '20141029',
1009 # Soundcloud multiple embeds
1011 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1014 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1016 'playlist_mincount': 7,
1018 # TuneIn station embed
1020 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1025 'location': 'Paris, France',
1030 'skip_download': True,
1035 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1039 'upload_date': '20141112',
1040 'title': 'Rosetta #CometLanding webcast HL 10',
1043 # Another Livestream embed, without 'new.' in URL
1045 'url': 'https://www.freespeech.org/',
1049 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1053 'skip_download': True,
1058 'url': 'https://skiplagged.com/',
1061 'title': 'Skiplagged: The smart way to find cheap flights',
1063 'playlist_mincount': 1,
1064 'add_ie': ['Youtube'],
1068 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1072 'upload_date': '20141126',
1073 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1078 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1080 'id': '730m_DandD_1901_512k',
1082 'uploader': 'www.abc.net.au',
1083 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1086 # embedded viddler video
1088 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1092 'uploader': 'deadspin',
1093 'title': 'WALL-TO-GORTAT',
1094 'timestamp': 1422285291,
1095 'upload_date': '20150126',
1097 'add_ie': ['Viddler'],
1101 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1105 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1106 'description': 'md5:601cb790edd05908957dae8aaa866465',
1107 'upload_date': '20150220',
1109 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1113 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1115 'id': 'Mrj4DVp2zeA',
1117 'upload_date': '20150212',
1118 'uploader': 'The National Archives UK',
1119 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1120 'uploader_id': 'NationalArchives08',
1121 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1126 'url': 'http://www.suffolk.edu/sjc/live.php',
1130 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1131 'uploader': 'www.suffolk.edu',
1134 'skip_download': True,
1136 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1140 'url': 'http://www.indiedb.com/games/king-machine/videos',
1144 'title': 'king machine trailer 1',
1145 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1146 'thumbnail': r're:^https?://.*\.jpg$',
1150 # JWPlayer config passed as variable
1151 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1155 'title': 'ARIELE | Tube Cup',
1156 'uploader': 'www.txxx.com',
1160 'skip_download': True,
1165 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1166 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1170 'upload_date': '20171122',
1171 'timestamp': 1511366290,
1172 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1174 'add_ie': [JWPlatformIE.ie_key()],
1177 # Video.js embed, multiple formats
1178 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1180 'id': 'yygqldloqIk',
1182 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1183 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1184 'upload_date': '20130314',
1185 'uploader': 'PROстое3D',
1186 'uploader_id': 'PROstoe3D',
1189 'skip_download': True,
1193 # Video.js embed, single format
1194 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1198 'title': 'Step 1 - Good Foundation',
1199 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1202 'skip_download': True,
1207 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1208 'playlist_mincount': 5,
1210 'id': 'aanslagen-kopenhagen',
1211 'title': 'Aanslagen Kopenhagen',
1216 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1220 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1223 # Kaltura embed (different embed code)
1225 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1229 'upload_date': '20150127',
1230 'uploader_id': 'PremierMedia',
1232 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1235 # Kaltura embed with single quotes
1237 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1242 'timestamp': 1355743100,
1243 'upload_date': '20121217',
1244 'uploader_id': 'cplapp@learn360.com',
1246 'add_ie': ['Kaltura'],
1249 # Kaltura embedded via quoted entry_id
1250 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1254 'title': '06_matthew_brender_raj_dutt',
1255 'timestamp': 1466638791,
1256 'upload_date': '20160622',
1258 'add_ie': ['Kaltura'],
1259 'expected_warnings': [
1260 'Could not send HEAD request'
1263 'skip_download': True,
1267 # Kaltura embedded, some fileExt broken (#11480)
1268 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1272 'title': 'Our "Standard Models" of particle physics and cosmology',
1273 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1274 'timestamp': 1321158993,
1275 'upload_date': '20111113',
1276 'uploader_id': 'kps1',
1278 'add_ie': ['Kaltura'],
1281 # Kaltura iframe embed
1282 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1283 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1287 'title': 'I. M. Pei: A Centennial Celebration',
1288 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1289 'upload_date': '20170403',
1290 'uploader_id': 'batchUser',
1291 'timestamp': 1491232186,
1293 'add_ie': ['Kaltura'],
1296 # Kaltura iframe embed, more sophisticated
1297 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1301 'title': 'lecture-05sep2017',
1302 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1303 'upload_date': '20170913',
1304 'uploader_id': 'eps2',
1305 'timestamp': 1505340777,
1308 'skip_download': True,
1310 'add_ie': ['Kaltura'],
1313 # meta twitter:player
1314 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1318 'title': 'Main Twerk (Video)',
1319 'upload_date': '20171208',
1320 'uploader_id': 'sebastian.salinas@thechive.com',
1321 'timestamp': 1512713057,
1324 'skip_download': True,
1326 'add_ie': ['Kaltura'],
1328 # referrer protected EaglePlatform embed
1330 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1334 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1335 'thumbnail': r're:^https?://.*\.jpg$',
1340 'skip_download': True,
1343 # ClipYou (EaglePlatform) embed (custom URL)
1345 'url': 'http://muz-tv.ru/play/7129/',
1346 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1350 'title': "'O Sole Mio",
1351 'thumbnail': r're:^https?://.*\.jpg$',
1356 'skip_download': True,
1358 'skip': 'This video is unavailable.',
1362 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1366 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1367 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1368 'thumbnail': r're:^https?://.*\.jpg$',
1372 'skip': 'HTTP Error 404: Not Found',
1376 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1380 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1381 'thumbnail': r're:^https?://.*\.png$',
1387 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1388 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1392 'title': 'Facebook Creates "On This Day" | Crunch Report',
1393 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1394 'timestamp': 1427237531,
1395 'uploader': 'Crunch Report',
1396 'upload_date': '20150324',
1400 'skip_download': True,
1403 # Crooks and Liars embed
1405 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1409 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1410 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1411 'timestamp': 1428207000,
1412 'upload_date': '20150405',
1413 'uploader': 'Heather',
1416 # Crooks and Liars external embed
1418 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1420 'id': 'MTE3MjUtMzQ2MzA',
1422 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1423 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1424 'timestamp': 1265032391,
1425 'upload_date': '20100201',
1426 'uploader': 'Heather',
1429 # NBC Sports vplayer embed
1431 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1433 'id': 'ln7x1qSThw4k',
1435 'title': "PFT Live: New leader in the 'new-look' defense",
1436 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1437 'uploader': 'NBCU-SPORTS',
1438 'upload_date': '20140107',
1439 'timestamp': 1389118457,
1441 'skip': 'Invalid Page URL',
1445 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1446 'md5': '1aa589c675898ae6d37a17913cf68d66',
1448 'id': 'x_dtl_oa_LettermanliftPR_160608',
1450 'title': 'David Letterman: A Preview',
1451 '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.',
1452 'upload_date': '20160609',
1453 'timestamp': 1465431544,
1454 'uploader': 'NBCU-NEWS',
1459 'url': 'https://video.udn.com/news/300346',
1460 'md5': 'fd2060e988c326991037b9aff9df21a6',
1464 'title': '中一中男師變性 全校師生力挺',
1465 'thumbnail': r're:^https?://.*\.jpg$',
1469 'skip_download': True,
1471 'expected_warnings': ['Failed to parse JSON Expecting value'],
1473 # Brightcove URL in single quotes
1475 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1476 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1478 'id': '4255764656001',
1480 'title': 'SN Presents: Russell Martin, World Citizen',
1481 '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.',
1482 'uploader': 'Rogers Sportsnet',
1483 'uploader_id': '1704050871',
1484 'upload_date': '20150525',
1485 'timestamp': 1432570283,
1490 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1494 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1495 'description': 'Migrated from OnionStudios',
1496 'thumbnail': r're:^https?://.*\.jpe?g$',
1497 'uploader': 'clickhole',
1498 'upload_date': '20150527',
1499 'timestamp': 1432744860,
1504 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1506 'id': '74849a00-85a9-11e1-9660-123139220831',
1508 'title': '#whilewewatch',
1511 # AdobeTVVideo embed
1513 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1514 'md5': '43662b577c018ad707a63766462b1e87',
1518 'title': 'New experience with Acrobat DC',
1519 'description': 'New experience with Acrobat DC',
1520 'duration': 248.667,
1523 # BrightcoveInPageEmbed embed
1525 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1527 'id': '4238694884001',
1529 'title': 'Tabletop: Dread, Last Thoughts',
1530 'description': 'Tabletop: Dread, Last Thoughts',
1534 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1535 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1537 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1539 'id': '4785848093001',
1541 'title': 'The Cardinal Pell Interview',
1542 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1543 'uploader': 'GlobeCast Australia - GlobeStream',
1544 'uploader_id': '2733773828001',
1545 'upload_date': '20160304',
1546 'timestamp': 1457083087,
1550 'skip_download': True,
1554 # Brightcove embed with whitespace around attribute names
1555 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1557 'id': '3167554373001',
1559 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1560 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1561 'uploader_id': '1079349493',
1562 'upload_date': '20140207',
1563 'timestamp': 1391810548,
1566 'skip_download': True,
1569 # Another form of arte.tv embed
1571 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1572 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1574 'id': '030273-562_PLUS7-F',
1576 'title': 'ARTE Reportage - Nulle part, en France',
1577 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1578 'upload_date': '20160409',
1583 'url': 'http://www.wykop.pl/link/3088787/',
1584 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1586 'id': '874_1459135191',
1588 'title': 'Man shows poor quality of new apartment building',
1589 'description': 'The wall is like a sand pile.',
1590 'uploader': 'Lake8737',
1592 'add_ie': [LiveLeakIE.ie_key()],
1594 # Another LiveLeak embed pattern (#13336)
1596 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1598 'id': '2eb_1496309988',
1600 'title': 'Thief robs place where everyone was armed',
1601 'description': 'md5:694d73ee79e535953cf2488562288eee',
1602 'uploader': 'brazilwtf',
1604 'add_ie': [LiveLeakIE.ie_key()],
1606 # Duplicated embedded video URLs
1608 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1610 'id': '149298443_480_16c25b74_2',
1612 'title': 'vs. Blue Orange Spring Game',
1613 'uploader': 'www.hudl.com',
1616 # twitter:player:stream embed
1618 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1622 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1623 'uploader': 'www.rtl.be',
1627 'skip_download': True,
1630 # twitter:player embed
1632 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1633 'md5': 'a3e0df96369831de324f0778e126653c',
1635 'id': '4909620399001',
1637 'title': 'What Do Black Holes Sound Like?',
1638 'description': 'what do black holes sound like',
1639 'upload_date': '20160524',
1640 'uploader_id': '29913724001',
1641 'timestamp': 1464107587,
1642 'uploader': 'TheAtlantic',
1644 'add_ie': ['BrightcoveLegacy'],
1646 # Facebook <iframe> embed
1648 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1649 'md5': 'fbcde74f534176ecb015849146dd3aee',
1651 'id': '599637780109885',
1653 'title': 'Facebook video #599637780109885',
1656 # Facebook <iframe> embed, plugin video
1658 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1660 'id': '1754168231264132',
1662 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1663 'uploader': 'Tariq Ramadan (official)',
1664 'timestamp': 1496758379,
1665 'upload_date': '20170606',
1668 'skip_download': True,
1671 # Facebook API embed
1673 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1674 'md5': 'a47372ee61b39a7b90287094d447d94e',
1676 'id': '10153467542406923',
1678 'title': 'Facebook video #10153467542406923',
1681 # Wordpress "YouTube Video Importer" plugin
1683 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1684 'md5': 'd16797741b560b485194eddda8121b48',
1686 'id': 'HNTXWDXV9Is',
1688 'title': 'Blue Devils Drumline Stanford lot 2016',
1689 'upload_date': '20160627',
1690 'uploader_id': 'GENOCIDE8GENERAL10',
1691 'uploader': 'cylus cyrus',
1695 # video stored on custom kaltura server
1696 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1697 'md5': '537617d06e64dfed891fa1593c4b30cc',
1701 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1702 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1703 'uploader_id': 'videos.expansion@el-mundo.net',
1704 'upload_date': '20150429',
1705 'timestamp': 1430303472,
1707 'add_ie': ['Kaltura'],
1710 # Non-standard Vimeo embed
1711 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1712 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1716 'title': 'Understanding the web - Teaser',
1717 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1718 'upload_date': '20151214',
1719 'uploader': 'OpenClassrooms',
1720 'uploader_id': 'openclassrooms',
1722 'add_ie': ['Vimeo'],
1725 # generic vimeo embed that requires original URL passed as Referer
1726 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1727 'only_matching': True,
1730 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1731 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1733 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1735 'title': 'Big Buck Bunny',
1736 'description': 'Royalty free test video',
1737 'timestamp': 1432816365,
1738 'upload_date': '20150528',
1742 'skip_download': True,
1744 'add_ie': [ArkenaIE.ie_key()],
1747 '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/',
1751 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1754 'skip_download': True,
1756 'add_ie': [Vbox7IE.ie_key()],
1760 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1763 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1765 'playlist_mincount': 3,
1769 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1771 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1772 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1774 'playlist_mincount': 2,
1778 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1782 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1783 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1786 'skip_download': True,
1788 'add_ie': [TwentyMinutenIE.ie_key()],
1792 'url': 'https://en.support.wordpress.com/videopress/',
1796 'title': 'IMG_5786',
1797 'timestamp': 1435711927,
1798 'upload_date': '20150701',
1801 'skip_download': True,
1803 'add_ie': [VideoPressIE.ie_key()],
1807 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1809 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1811 'title': 'Магаззино: Казань 2',
1812 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1813 'uploader': 'Магаззино',
1814 'upload_date': '20170228',
1815 'uploader_id': '996642',
1818 'skip_download': True,
1820 'add_ie': [RutubeIE.ie_key()],
1823 # ThePlatform embedded with whitespaces in URLs
1824 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1825 'only_matching': True,
1828 # Senate ISVP iframe https
1829 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1830 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1832 'id': 'govtaff020316',
1834 'title': 'Integrated Senate Video Player',
1836 'add_ie': [SenateISVPIE.ie_key()],
1839 # Limelight embeds (1 channel embed + 4 media embeds)
1840 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1842 'id': 'FacilitatorTraining2017',
1843 'title': 'Facilitator Training 2017',
1845 'playlist_mincount': 5,
1848 # Limelight embed (LimelightPlayerUtil.embed)
1849 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1851 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1853 'title': '07448641',
1854 'timestamp': 1499890639,
1855 'upload_date': '20170712',
1858 'skip_download': True,
1860 'add_ie': ['LimelightMedia'],
1863 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1865 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1866 'title': 'Standoff with Walnut Creek murder suspect ends',
1867 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1869 'playlist_mincount': 4,
1872 # WashingtonPost embed
1873 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1875 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1877 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1878 '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.',
1879 'timestamp': 1455216756,
1880 'uploader': 'The Washington Post',
1881 'upload_date': '20160211',
1883 'add_ie': [WashingtonPostIE.ie_key()],
1887 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1891 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1894 'skip_download': True,
1896 'add_ie': [MediasetIE.ie_key()],
1900 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1902 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'title': 'Slovenskom sa prehnala vlna silných búrok',
1905 'playlist_mincount': 5,
1906 'add_ie': [JojIE.ie_key()],
1909 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1910 'url': 'https://tvrain.ru/amp/418921/',
1911 'md5': 'cc00413936695987e8de148b67d14f1d',
1915 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1920 'url': 'http://help.vzaar.com/article/165-embedding-video',
1921 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1925 'title': 'Building A Business Online: Principal Chairs Q & A',
1929 # multiple HTML5 videos on one page
1930 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1932 'id': 'keyscenarios',
1933 'title': 'Rescue Kit 14 Free Edition - Getting started',
1935 'playlist_count': 4,
1939 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1940 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1943 'title': 'vl14062007715967',
1948 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1949 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1951 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1953 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1954 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1955 'timestamp': 1474354800,
1956 'upload_date': '20160920',
1960 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1964 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1965 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1966 'timestamp': 1516100691,
1967 'upload_date': '20180116',
1970 'skip_download': True,
1972 'add_ie': [SpringboardPlatformIE.ie_key()],
1975 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1977 'id': 'uPDB5I9wfp8',
1979 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1980 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1981 'upload_date': '20160219',
1982 'uploader': 'Pocoyo - Português (BR)',
1983 'uploader_id': 'PocoyoBrazil',
1985 'add_ie': [YoutubeIE.ie_key()],
1987 'skip_download': True,
1991 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1993 'id': 'vMDE4NzI1Mjgt690b',
1997 'add_ie': [YapFilesIE.ie_key()],
1999 'skip_download': True,
2003 # CloudflareStream embed
2004 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2006 'id': '31c9291ab41fac05471db4e73aa11717',
2008 'title': '31c9291ab41fac05471db4e73aa11717',
2010 'add_ie': [CloudflareStreamIE.ie_key()],
2012 'skip_download': True,
2017 'url': 'https://joinpeertube.org/fr/home/',
2020 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2022 'playlist_count': 2,
2026 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2030 'title': 'Így kell otthon hamburgert sütni',
2031 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2032 'timestamp': 1426330212,
2033 'upload_date': '20150314',
2034 'uploader': 'StreetKitchen',
2035 'uploader_id': '546363',
2037 'add_ie': [IndavideoEmbedIE.ie_key()],
2039 'skip_download': True,
2043 # APA embed via JWPlatform embed
2044 'url': 'http://www.vol.at/blue-man-group/5593454',
2048 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2049 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2050 'thumbnail': r're:^https?://.*\.jpg$',
2052 'timestamp': 1519211149,
2053 'upload_date': '20180221',
2056 'skip_download': True,
2060 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2061 'md5': 'b68d276de422ab07ee1d49388103f457',
2064 'title': 'Lock up and get excited',
2067 'skip': 'TODO: fix nested playlists processing in tests',
2071 'url': 'https://viqeo.tv/',
2074 'title': 'All-new video platform',
2076 'playlist_count': 6,
2079 # Squarespace video embed, 2019-08-28
2080 'url': 'http://ootboxford.com',
2082 'id': 'Tc7b_JGdZfw',
2083 'title': 'Out of the Blue, at Childish Things 10',
2085 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2086 'uploader_id': 'helendouglashouse',
2087 'uploader': 'Helen & Douglas House',
2088 'upload_date': '20140328',
2091 'skip_download': True,
2096 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2098 'id': '5b400b834b32992a310622b9',
2100 'title': 'Smoky Barbecue Favorites',
2101 'thumbnail': r're:^https?://.*\.jpe?g',
2102 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2103 'upload_date': '20170909',
2104 'timestamp': 1504915200,
2106 'add_ie': [ZypeIE.ie_key()],
2108 'skip_download': True,
2113 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2117 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2118 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2119 'thumbnail': r're:^https?://.*\.jpg$',
2122 'skip_download': True,
2124 'expected_warnings': ['Failed to download MPD manifest'],
2127 # DailyMotion embed with DM.player
2128 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2130 'id': 'k6aKkGHd9FJs4mtJN39',
2132 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2133 'description': 'This video is private.',
2134 'uploader_id': 'x1jf30l',
2135 'uploader': 'beIN SPORTS USA',
2136 'upload_date': '20190528',
2137 'timestamp': 1559062971,
2140 'skip_download': True,
2144 # # TODO: find another test
2145 # # http://schema.org/VideoObject
2146 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2147 # 'md5': '888dcf08b7ea671381f00fab74692755',
2149 # 'id': 'nyvTSJMKId',
2151 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2152 # 'description': '#love for cats.',
2153 # 'timestamp': 1461244995,
2154 # 'upload_date': '20160421',
2157 # 'force_generic_extractor': True,
2162 def report_following_redirect(self, new_url):
2163 """Report information extraction."""
2164 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2166 def _extract_rss(self, url, video_id, doc):
2167 playlist_title = doc.find('./channel/title').text
2168 playlist_desc_el = doc.find('./channel/description')
2169 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2172 for it in doc.findall('./channel/item'):
2174 enclosure_nodes = it.findall('./enclosure')
2175 for e in enclosure_nodes:
2176 next_url = e.attrib.get('url')
2181 next_url = xpath_text(it, 'link', fatal=False)
2187 '_type': 'url_transparent',
2189 'title': it.find('title').text,
2193 '_type': 'playlist',
2195 'title': playlist_title,
2196 'description': playlist_desc,
2200 def _extract_camtasia(self, url, video_id, webpage):
2201 """ Returns None if no camtasia video can be found. """
2203 camtasia_cfg = self._search_regex(
2204 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2205 webpage, 'camtasia configuration file', default=None)
2206 if camtasia_cfg is None:
2209 title = self._html_search_meta('DC.title', webpage, fatal=True)
2211 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2212 camtasia_cfg = self._download_xml(
2213 camtasia_url, video_id,
2214 note='Downloading camtasia configuration',
2215 errnote='Failed to download camtasia configuration')
2216 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2219 for n in fileset_node.getchildren():
2220 url_n = n.find('./uri')
2225 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2226 'title': '%s - %s' % (title, n.tag),
2227 'url': compat_urlparse.urljoin(url, url_n.text),
2228 'duration': float_or_none(n.find('./duration').text),
2232 '_type': 'playlist',
2237 def _real_extract(self, url):
2238 if url.startswith('//'):
2239 return self.url_result(self.http_scheme() + url)
2241 parsed_url = compat_urlparse.urlparse(url)
2242 if not parsed_url.scheme:
2243 default_search = self._downloader.params.get('default_search')
2244 if default_search is None:
2245 default_search = 'fixup_error'
2247 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2248 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2249 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2250 return self.url_result('http://' + url)
2251 elif default_search != 'fixup_error':
2252 if default_search == 'auto_warning':
2253 if re.match(r'^(?:url|URL)$', url):
2254 raise ExtractorError(
2255 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2258 self._downloader.report_warning(
2259 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2260 return self.url_result('ytsearch:' + url)
2262 if default_search in ('error', 'fixup_error'):
2263 raise ExtractorError(
2264 '%r is not a valid URL. '
2265 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2266 % (url, url), expected=True)
2268 if ':' not in default_search:
2269 default_search += ':'
2270 return self.url_result(default_search + url)
2272 url, smuggled_data = unsmuggle_url(url)
2273 force_videoid = None
2274 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2275 if smuggled_data and 'force_videoid' in smuggled_data:
2276 force_videoid = smuggled_data['force_videoid']
2277 video_id = force_videoid
2279 video_id = self._generic_id(url)
2281 self.to_screen('%s: Requesting header' % video_id)
2283 head_req = HEADRequest(url)
2284 head_response = self._request_webpage(
2286 note=False, errnote='Could not send HEAD request to %s' % url,
2289 if head_response is not False:
2290 # Check for redirect
2291 new_url = head_response.geturl()
2293 self.report_following_redirect(new_url)
2295 new_url = smuggle_url(
2296 new_url, {'force_videoid': force_videoid})
2297 return self.url_result(new_url)
2299 full_response = None
2300 if head_response is False:
2301 request = sanitized_Request(url)
2302 request.add_header('Accept-Encoding', '*')
2303 full_response = self._request_webpage(request, video_id)
2304 head_response = full_response
2308 'title': self._generic_title(url),
2309 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2312 # Check for direct link to a video
2313 content_type = head_response.headers.get('Content-Type', '').lower()
2314 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2316 format_id = compat_str(m.group('format_id'))
2317 if format_id.endswith('mpegurl'):
2318 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2319 elif format_id == 'f4m':
2320 formats = self._extract_f4m_formats(url, video_id)
2323 'format_id': format_id,
2325 'vcodec': 'none' if m.group('type') == 'audio' else None
2327 info_dict['direct'] = True
2328 self._sort_formats(formats)
2329 info_dict['formats'] = formats
2332 if not self._downloader.params.get('test', False) and not is_intentional:
2333 force = self._downloader.params.get('force_generic_extractor', False)
2334 self._downloader.report_warning(
2335 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2337 if not full_response:
2338 request = sanitized_Request(url)
2339 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2340 # making it impossible to download only chunk of the file (yet we need only 512kB to
2341 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2342 # that will always result in downloading the whole file that is not desirable.
2343 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2344 # to accept raw bytes and being able to download only a chunk.
2345 # It may probably better to solve this by checking Content-Type for application/octet-stream
2346 # after HEAD request finishes, but not sure if we can rely on this.
2347 request.add_header('Accept-Encoding', '*')
2348 full_response = self._request_webpage(request, video_id)
2350 first_bytes = full_response.read(512)
2352 # Is it an M3U playlist?
2353 if first_bytes.startswith(b'#EXTM3U'):
2354 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2355 self._sort_formats(info_dict['formats'])
2358 # Maybe it's a direct link to a video?
2359 # Be careful not to download the whole thing!
2360 if not is_html(first_bytes):
2361 self._downloader.report_warning(
2362 'URL could be a direct video link, returning it as such.')
2369 webpage = self._webpage_read_content(
2370 full_response, url, video_id, prefix=first_bytes)
2372 self.report_extraction(video_id)
2374 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2376 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2377 if doc.tag == 'rss':
2378 return self._extract_rss(url, video_id, doc)
2379 elif doc.tag == 'SmoothStreamingMedia':
2380 info_dict['formats'] = self._parse_ism_formats(doc, url)
2381 self._sort_formats(info_dict['formats'])
2383 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2384 smil = self._parse_smil(doc, url, video_id)
2385 self._sort_formats(smil['formats'])
2387 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2388 return self.playlist_result(
2390 doc, video_id, xspf_url=url,
2391 xspf_base_url=full_response.geturl()),
2393 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2394 info_dict['formats'] = self._parse_mpd_formats(
2396 mpd_base_url=full_response.geturl().rpartition('/')[0],
2398 self._sort_formats(info_dict['formats'])
2400 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2401 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2402 self._sort_formats(info_dict['formats'])
2404 except compat_xml_parse_error:
2407 # Is it a Camtasia project?
2408 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2409 if camtasia_res is not None:
2412 # Sometimes embedded video player is hidden behind percent encoding
2413 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2414 # Unescaping the whole page allows to handle those cases in a generic way
2415 webpage = compat_urllib_parse_unquote(webpage)
2417 # Unescape squarespace embeds to be detected by generic extractor,
2418 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2420 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2421 lambda x: unescapeHTML(x.group(0)), webpage)
2423 # it's tempting to parse this further, but you would
2424 # have to take into account all the variations like
2425 # Video Title - Site Name
2426 # Site Name | Video Title
2427 # Video Title - Tagline | Site Name
2428 # and so on and so forth; it's just not practical
2429 video_title = self._og_search_title(
2430 webpage, default=None) or self._html_search_regex(
2431 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2434 # Try to detect age limit automatically
2435 age_limit = self._rta_search(webpage)
2436 # And then there are the jokers who advertise that they use RTA,
2437 # but actually don't.
2438 AGE_LIMIT_MARKERS = [
2439 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2441 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2444 # video uploader is domain name
2445 video_uploader = self._search_regex(
2446 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2448 video_description = self._og_search_description(webpage, default=None)
2449 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2452 'title': video_title,
2453 'description': video_description,
2454 'thumbnail': video_thumbnail,
2455 'age_limit': age_limit,
2458 # Look for Brightcove Legacy Studio embeds
2459 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2463 'url': smuggle_url(bc_url, {'Referer': url}),
2464 'ie_key': 'BrightcoveLegacy'
2465 } for bc_url in bc_urls]
2468 '_type': 'playlist',
2469 'title': video_title,
2474 # Look for Brightcove New Studio embeds
2475 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2477 return self.playlist_from_matches(
2478 bc_urls, video_id, video_title,
2479 getter=lambda x: smuggle_url(x, {'referrer': url}),
2482 # Look for Nexx embeds
2483 nexx_urls = NexxIE._extract_urls(webpage)
2485 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2487 # Look for Nexx iFrame embeds
2488 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2490 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2492 # Look for ThePlatform embeds
2493 tp_urls = ThePlatformIE._extract_urls(webpage)
2495 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2497 # Look for embedded rtl.nl player
2498 matches = re.findall(
2499 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2502 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2504 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2506 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2508 vid_me_embed_url = self._search_regex(
2509 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2510 webpage, 'vid.me embed', default=None)
2511 if vid_me_embed_url is not None:
2512 return self.url_result(vid_me_embed_url, 'Vidme')
2514 # Look for YouTube embeds
2515 youtube_urls = YoutubeIE._extract_urls(webpage)
2517 return self.playlist_from_matches(
2518 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2520 matches = DailymotionIE._extract_urls(webpage)
2522 return self.playlist_from_matches(matches, video_id, video_title)
2524 # Look for embedded Dailymotion playlist player (#3822)
2526 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2528 playlists = re.findall(
2529 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2531 return self.playlist_from_matches(
2532 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2534 # Look for DailyMail embeds
2535 dailymail_urls = DailyMailIE._extract_urls(webpage)
2537 return self.playlist_from_matches(
2538 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2540 # Look for Teachable embeds, must be before Wistia
2541 teachable_url = TeachableIE._extract_url(webpage, url)
2543 return self.url_result(teachable_url)
2545 # Look for embedded Wistia player
2546 wistia_urls = WistiaIE._extract_urls(webpage)
2548 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2549 for entry in playlist['entries']:
2551 '_type': 'url_transparent',
2552 'uploader': video_uploader,
2556 # Look for SVT player
2557 svt_url = SVTIE._extract_url(webpage)
2559 return self.url_result(svt_url, 'SVT')
2561 # Look for Bandcamp pages with custom domain
2562 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2563 if mobj is not None:
2564 burl = unescapeHTML(mobj.group(1))
2565 # Don't set the extractor because it can be a track url or an album
2566 return self.url_result(burl)
2568 # Look for embedded Vevo player
2570 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2571 if mobj is not None:
2572 return self.url_result(mobj.group('url'))
2574 # Look for embedded Viddler player
2576 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2578 if mobj is not None:
2579 return self.url_result(mobj.group('url'))
2581 # Look for NYTimes player
2583 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2585 if mobj is not None:
2586 return self.url_result(mobj.group('url'))
2588 # Look for Libsyn player
2590 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2591 if mobj is not None:
2592 return self.url_result(mobj.group('url'))
2594 # Look for Ooyala videos
2595 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2596 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2597 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2598 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2599 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2600 if mobj is not None:
2601 embed_token = self._search_regex(
2602 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2603 webpage, 'ooyala embed token', default=None)
2604 return OoyalaIE._build_url_result(smuggle_url(
2607 'embed_token': embed_token,
2610 # Look for multiple Ooyala embeds on SBN network websites
2611 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2612 if mobj is not None:
2613 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2615 return self.playlist_from_matches(
2616 embeds, video_id, video_title,
2617 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2619 # Look for Aparat videos
2620 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2621 if mobj is not None:
2622 return self.url_result(mobj.group(1), 'Aparat')
2624 # Look for MPORA videos
2625 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2626 if mobj is not None:
2627 return self.url_result(mobj.group(1), 'Mpora')
2629 # Look for embedded Facebook player
2630 facebook_urls = FacebookIE._extract_urls(webpage)
2632 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2634 # Look for embedded VK player
2635 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2636 if mobj is not None:
2637 return self.url_result(mobj.group('url'), 'VK')
2639 # Look for embedded Odnoklassniki player
2640 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2641 if odnoklassniki_url:
2642 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2644 # Look for embedded ivi player
2645 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2646 if mobj is not None:
2647 return self.url_result(mobj.group('url'), 'Ivi')
2649 # Look for embedded Huffington Post player
2651 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2652 if mobj is not None:
2653 return self.url_result(mobj.group('url'), 'HuffPost')
2656 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2657 if mobj is not None:
2658 return self.url_result(mobj.group('url'))
2659 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2660 if mobj is not None:
2661 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2663 # Look for funnyordie embed
2664 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2666 return self.playlist_from_matches(
2667 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2669 # Look for BBC iPlayer embed
2670 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2672 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2674 # Look for embedded RUTV player
2675 rutv_url = RUTVIE._extract_url(webpage)
2677 return self.url_result(rutv_url, 'RUTV')
2679 # Look for embedded TVC player
2680 tvc_url = TVCIE._extract_url(webpage)
2682 return self.url_result(tvc_url, 'TVC')
2684 # Look for embedded SportBox player
2685 sportbox_urls = SportBoxIE._extract_urls(webpage)
2687 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2689 # Look for embedded XHamster player
2690 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2692 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2694 # Look for embedded TNAFlixNetwork player
2695 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2697 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2699 # Look for embedded PornHub player
2700 pornhub_urls = PornHubIE._extract_urls(webpage)
2702 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2704 # Look for embedded DrTuber player
2705 drtuber_urls = DrTuberIE._extract_urls(webpage)
2707 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2709 # Look for embedded RedTube player
2710 redtube_urls = RedTubeIE._extract_urls(webpage)
2712 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2714 # Look for embedded Tube8 player
2715 tube8_urls = Tube8IE._extract_urls(webpage)
2717 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2719 # Look for embedded Spankwire player
2720 spankwire_urls = SpankwireIE._extract_urls(webpage)
2722 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2724 # Look for embedded Tvigle player
2726 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2727 if mobj is not None:
2728 return self.url_result(mobj.group('url'), 'Tvigle')
2730 # Look for embedded TED player
2732 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2733 if mobj is not None:
2734 return self.url_result(mobj.group('url'), 'TED')
2736 # Look for embedded Ustream videos
2737 ustream_url = UstreamIE._extract_url(webpage)
2739 return self.url_result(ustream_url, UstreamIE.ie_key())
2741 # Look for embedded arte.tv player
2743 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2745 if mobj is not None:
2746 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2748 # Look for embedded francetv player
2750 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2752 if mobj is not None:
2753 return self.url_result(mobj.group('url'))
2755 # Look for embedded smotri.com player
2756 smotri_url = SmotriIE._extract_url(webpage)
2758 return self.url_result(smotri_url, 'Smotri')
2760 # Look for embedded Myvi.ru player
2761 myvi_url = MyviIE._extract_url(webpage)
2763 return self.url_result(myvi_url)
2765 # Look for embedded soundcloud player
2766 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2768 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2770 # Look for tunein player
2771 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2773 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2775 # Look for embedded mtvservices player
2776 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2778 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2780 # Look for embedded yahoo player
2782 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2784 if mobj is not None:
2785 return self.url_result(mobj.group('url'), 'Yahoo')
2787 # Look for embedded sbs.com.au player
2791 <meta\s+property="og:video"\s+content=|
2794 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2796 if mobj is not None:
2797 return self.url_result(mobj.group('url'), 'SBS')
2799 # Look for embedded Cinchcast player
2801 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2803 if mobj is not None:
2804 return self.url_result(mobj.group('url'), 'Cinchcast')
2807 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2811 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2813 if mobj is not None:
2814 return self.url_result(mobj.group('url'), 'MLB')
2817 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2819 if mobj is not None:
2820 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2823 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2825 if mobj is not None:
2826 return self.url_result(mobj.group('url'), 'Livestream')
2828 # Look for Zapiks embed
2830 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2831 if mobj is not None:
2832 return self.url_result(mobj.group('url'), 'Zapiks')
2834 # Look for Kaltura embeds
2835 kaltura_url = KalturaIE._extract_url(webpage)
2837 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2839 # Look for EaglePlatform embeds
2840 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2841 if eagleplatform_url:
2842 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2844 # Look for ClipYou (uses EaglePlatform) embeds
2846 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2847 if mobj is not None:
2848 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2850 # Look for Pladform embeds
2851 pladform_url = PladformIE._extract_url(webpage)
2853 return self.url_result(pladform_url)
2855 # Look for Videomore embeds
2856 videomore_url = VideomoreIE._extract_url(webpage)
2858 return self.url_result(videomore_url)
2860 # Look for Webcaster embeds
2861 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2863 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2865 # Look for Playwire embeds
2867 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2868 if mobj is not None:
2869 return self.url_result(mobj.group('url'))
2871 # Look for 5min embeds
2873 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2874 if mobj is not None:
2875 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2877 # Look for Crooks and Liars embeds
2879 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2880 if mobj is not None:
2881 return self.url_result(mobj.group('url'))
2883 # Look for NBC Sports VPlayer embeds
2884 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2886 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2888 # Look for NBC News embeds
2889 nbc_news_embed_url = re.search(
2890 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2891 if nbc_news_embed_url:
2892 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2894 # Look for Google Drive embeds
2895 google_drive_url = GoogleDriveIE._extract_url(webpage)
2896 if google_drive_url:
2897 return self.url_result(google_drive_url, 'GoogleDrive')
2899 # Look for UDN embeds
2901 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2902 if mobj is not None:
2903 return self.url_result(
2904 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2906 # Look for Senate ISVP iframe
2907 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2909 return self.url_result(senate_isvp_url, 'SenateISVP')
2911 # Look for Kinja embeds
2912 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2913 if kinja_embed_urls:
2914 return self.playlist_from_matches(
2915 kinja_embed_urls, video_id, video_title)
2917 # Look for OnionStudios embeds
2918 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2919 if onionstudios_url:
2920 return self.url_result(onionstudios_url)
2922 # Look for ViewLift embeds
2923 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2925 return self.url_result(viewlift_url)
2927 # Look for JWPlatform embeds
2928 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2930 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2932 # Look for Digiteka embeds
2933 digiteka_url = DigitekaIE._extract_url(webpage)
2935 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2937 # Look for Arkena embeds
2938 arkena_url = ArkenaIE._extract_url(webpage)
2940 return self.url_result(arkena_url, ArkenaIE.ie_key())
2942 # Look for Piksel embeds
2943 piksel_url = PikselIE._extract_url(webpage)
2945 return self.url_result(piksel_url, PikselIE.ie_key())
2947 # Look for Limelight embeds
2948 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2950 return self.playlist_result(
2951 limelight_urls, video_id, video_title, video_description)
2953 # Look for Anvato embeds
2954 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2956 return self.playlist_result(
2957 anvato_urls, video_id, video_title, video_description)
2959 # Look for AdobeTVVideo embeds
2961 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2963 if mobj is not None:
2964 return self.url_result(
2965 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2968 # Look for Vine embeds
2970 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2972 if mobj is not None:
2973 return self.url_result(
2974 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2976 # Look for VODPlatform embeds
2978 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
2980 if mobj is not None:
2981 return self.url_result(
2982 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2984 # Look for Mangomolo embeds
2986 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
2988 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
2989 player\.mangomolo\.com/v1
2992 video\?.*?\bid=(?P<video_id>\d+)|
2993 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2994 ).+?)\1''', webpage)
2995 if mobj is not None:
2997 '_type': 'url_transparent',
2998 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2999 'title': video_title,
3000 'description': video_description,
3001 'thumbnail': video_thumbnail,
3002 'uploader': video_uploader,
3004 video_id = mobj.group('video_id')
3007 'ie_key': 'MangomoloVideo',
3012 'ie_key': 'MangomoloLive',
3013 'id': mobj.group('channel_id'),
3017 # Look for Instagram embeds
3018 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3019 if instagram_embed_url is not None:
3020 return self.url_result(
3021 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3023 # Look for LiveLeak embeds
3024 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3026 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3028 # Look for 3Q SDN embeds
3029 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3032 '_type': 'url_transparent',
3033 'ie_key': ThreeQSDNIE.ie_key(),
3034 'url': self._proto_relative_url(threeqsdn_url),
3035 'title': video_title,
3036 'description': video_description,
3037 'thumbnail': video_thumbnail,
3038 'uploader': video_uploader,
3041 # Look for VBOX7 embeds
3042 vbox7_url = Vbox7IE._extract_url(webpage)
3044 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3046 # Look for DBTV embeds
3047 dbtv_urls = DBTVIE._extract_urls(webpage)
3049 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3051 # Look for Videa embeds
3052 videa_urls = VideaIE._extract_urls(webpage)
3054 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3056 # Look for 20 minuten embeds
3057 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3059 return self.playlist_from_matches(
3060 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3062 # Look for VideoPress embeds
3063 videopress_urls = VideoPressIE._extract_urls(webpage)
3065 return self.playlist_from_matches(
3066 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3068 # Look for Rutube embeds
3069 rutube_urls = RutubeIE._extract_urls(webpage)
3071 return self.playlist_from_matches(
3072 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3074 # Look for WashingtonPost embeds
3075 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3077 return self.playlist_from_matches(
3078 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3080 # Look for Mediaset embeds
3081 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3083 return self.playlist_from_matches(
3084 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3086 # Look for JOJ.sk embeds
3087 joj_urls = JojIE._extract_urls(webpage)
3089 return self.playlist_from_matches(
3090 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3092 # Look for megaphone.fm embeds
3093 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3095 return self.playlist_from_matches(
3096 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3098 # Look for vzaar embeds
3099 vzaar_urls = VzaarIE._extract_urls(webpage)
3101 return self.playlist_from_matches(
3102 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3104 channel9_urls = Channel9IE._extract_urls(webpage)
3106 return self.playlist_from_matches(
3107 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3109 vshare_urls = VShareIE._extract_urls(webpage)
3111 return self.playlist_from_matches(
3112 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3114 # Look for Mediasite embeds
3115 mediasite_urls = MediasiteIE._extract_urls(webpage)
3118 self.url_result(smuggle_url(
3119 compat_urlparse.urljoin(url, mediasite_url),
3120 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3121 for mediasite_url in mediasite_urls]
3122 return self.playlist_result(entries, video_id, video_title)
3124 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3125 if springboardplatform_urls:
3126 return self.playlist_from_matches(
3127 springboardplatform_urls, video_id, video_title,
3128 ie=SpringboardPlatformIE.ie_key())
3130 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3132 return self.playlist_from_matches(
3133 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3135 vice_urls = ViceIE._extract_urls(webpage)
3137 return self.playlist_from_matches(
3138 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3140 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3142 return self.playlist_from_matches(
3143 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3145 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3146 if cloudflarestream_urls:
3147 return self.playlist_from_matches(
3148 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3150 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3152 return self.playlist_from_matches(
3153 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3155 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3157 return self.playlist_from_matches(
3158 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3160 apa_urls = APAIE._extract_urls(webpage)
3162 return self.playlist_from_matches(
3163 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3165 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3167 return self.playlist_from_matches(
3168 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3170 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3171 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3173 if sharevideos_urls:
3174 return self.playlist_from_matches(
3175 sharevideos_urls, video_id, video_title)
3177 viqeo_urls = ViqeoIE._extract_urls(webpage)
3179 return self.playlist_from_matches(
3180 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3182 expressen_urls = ExpressenIE._extract_urls(webpage)
3184 return self.playlist_from_matches(
3185 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3187 zype_urls = ZypeIE._extract_urls(webpage)
3189 return self.playlist_from_matches(
3190 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3192 # Look for HTML5 media
3193 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3195 if len(entries) == 1:
3198 'title': video_title,
3201 for num, entry in enumerate(entries, start=1):
3203 'id': '%s-%s' % (video_id, num),
3204 'title': '%s (%d)' % (video_title, num),
3206 for entry in entries:
3207 self._sort_formats(entry['formats'])
3208 return self.playlist_result(entries, video_id, video_title)
3210 jwplayer_data = self._find_jwplayer_data(
3211 webpage, video_id, transform_source=js_to_json)
3214 info = self._parse_jwplayer_data(
3215 jwplayer_data, video_id, require_title=False, base_url=url)
3216 return merge_dicts(info, info_dict)
3217 except ExtractorError:
3218 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3223 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3225 if mobj is not None:
3226 sources = self._parse_json(
3227 mobj.group(1), video_id, transform_source=js_to_json,
3229 if not isinstance(sources, list):
3232 for source in sources:
3233 src = source.get('src')
3234 if not src or not isinstance(src, compat_str):
3236 src = compat_urlparse.urljoin(url, src)
3237 src_type = source.get('type')
3238 if isinstance(src_type, compat_str):
3239 src_type = src_type.lower()
3240 ext = determine_ext(src).lower()
3241 if src_type == 'video/youtube':
3242 return self.url_result(src, YoutubeIE.ie_key())
3243 if src_type == 'application/dash+xml' or ext == 'mpd':
3244 formats.extend(self._extract_mpd_formats(
3245 src, video_id, mpd_id='dash', fatal=False))
3246 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3247 formats.extend(self._extract_m3u8_formats(
3248 src, video_id, 'mp4', entry_protocol='m3u8_native',
3249 m3u8_id='hls', fatal=False))
3253 'ext': (mimetype2ext(src_type)
3254 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3257 self._sort_formats(formats)
3258 info_dict['formats'] = formats
3261 # Looking for http://schema.org/VideoObject
3262 json_ld = self._search_json_ld(
3263 webpage, video_id, default={}, expected_type='VideoObject')
3264 if json_ld.get('url'):
3265 return merge_dicts(json_ld, info_dict)
3267 def check_video(vurl):
3268 if YoutubeIE.suitable(vurl):
3270 if RtmpIE.suitable(vurl):
3272 vpath = compat_urlparse.urlparse(vurl).path
3273 vext = determine_ext(vpath)
3274 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3276 def filter_video(urls):
3277 return list(filter(check_video, urls))
3279 # Start with something easy: JW Player in SWFObject
3280 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3282 # Look for gorilla-vid style embedding
3283 found = filter_video(re.findall(r'''(?sx)
3287 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3290 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3292 # Broaden the search a little bit
3293 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3295 # Broaden the findall a little bit: JWPlayer JS loader
3296 found = filter_video(re.findall(
3297 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3300 found = filter_video(re.findall(r'''(?xs)
3301 flowplayer\("[^"]+",\s*
3303 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3304 ["']?url["']?\s*:\s*["']([^"']+)["']
3309 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3311 # Try to find twitter cards info
3312 # twitter:player:stream should be checked before twitter:player since
3313 # it is expected to contain a raw stream (see
3314 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3315 found = filter_video(re.findall(
3316 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3318 # We look for Open Graph info:
3319 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3320 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3321 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3322 if m_video_type is not None:
3323 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3325 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3327 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3328 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3331 # Look also in Refresh HTTP header
3332 refresh_header = head_response.headers.get('Refresh')
3334 # In python 2 response HTTP headers are bytestrings
3335 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3336 refresh_header = refresh_header.decode('iso-8859-1')
3337 found = re.search(REDIRECT_REGEX, refresh_header)
3339 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3341 self.report_following_redirect(new_url)
3350 # twitter:player is a https URL to iframe player that may or may not
3351 # be supported by youtube-dl thus this is checked the very last (see
3352 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3353 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3354 if embed_url and embed_url != url:
3355 return self.url_result(embed_url)
3358 raise UnsupportedError(url)
3361 for video_url in orderedSet(found):
3362 video_url = unescapeHTML(video_url)
3363 video_url = video_url.replace('\\/', '/')
3364 video_url = compat_urlparse.urljoin(url, video_url)
3365 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3367 # Sometimes, jwplayer extraction will result in a YouTube URL
3368 if YoutubeIE.suitable(video_url):
3369 entries.append(self.url_result(video_url, 'Youtube'))
3372 # here's a fun little line of code for you:
3373 video_id = os.path.splitext(video_id)[0]
3377 'uploader': video_uploader,
3378 'title': video_title,
3379 'age_limit': age_limit,
3382 if RtmpIE.suitable(video_url):
3383 entry_info_dict.update({
3384 '_type': 'url_transparent',
3385 'ie_key': RtmpIE.ie_key(),
3388 entries.append(entry_info_dict)
3391 ext = determine_ext(video_url)
3393 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3395 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3397 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3399 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3401 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3402 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3403 # Just matching .ism/manifest is not enough to be reliably sure
3404 # whether it's actually an ISM manifest or some other streaming
3405 # manifest since there are various streaming URL formats
3406 # possible (see [1]) as well as some other shenanigans like
3407 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3409 # Thus the most reasonable way to solve this is to delegate
3410 # to generic extractor in order to look into the contents of
3411 # the manifest itself.
3412 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3413 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3414 entry_info_dict = self.url_result(
3415 smuggle_url(video_url, {'to_generic': True}),
3418 entry_info_dict['url'] = video_url
3420 if entry_info_dict.get('formats'):
3421 self._sort_formats(entry_info_dict['formats'])
3423 entries.append(entry_info_dict)
3425 if len(entries) == 1:
3428 for num, e in enumerate(entries, start=1):
3429 # 'url' results don't have a title
3430 if e.get('title') is not None:
3431 e['title'] = '%s (%d)' % (e['title'], num)
3433 '_type': 'playlist',