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 .youporn import YouPornIE
65 from .vimeo import VimeoIE
66 from .dailymotion import DailymotionIE
67 from .dailymail import DailyMailIE
68 from .onionstudios import OnionStudiosIE
69 from .viewlift import ViewLiftEmbedIE
70 from .mtv import MTVServicesEmbeddedIE
71 from .pladform import PladformIE
72 from .videomore import VideomoreIE
73 from .webcaster import WebcasterFeedIE
74 from .googledrive import GoogleDriveIE
75 from .jwplatform import JWPlatformIE
76 from .digiteka import DigitekaIE
77 from .arkena import ArkenaIE
78 from .instagram import InstagramIE
79 from .liveleak import LiveLeakIE
80 from .threeqsdn import ThreeQSDNIE
81 from .theplatform import ThePlatformIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudEmbedIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
111 from .peertube import PeerTubeIE
112 from .teachable import TeachableIE
113 from .indavideo import IndavideoEmbedIE
114 from .apa import APAIE
115 from .foxnews import FoxNewsIE
116 from .viqeo import ViqeoIE
117 from .expressen import ExpressenIE
118 from .zype import ZypeIE
119 from .odnoklassniki import OdnoklassnikiIE
120 from .kinja import KinjaEmbedIE
123 class GenericIE(InfoExtractor):
124 IE_DESC = 'Generic downloader that works on some sites'
128 # Direct link to a video
130 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
131 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
136 'upload_date': '20100513',
139 # Direct link to media delivered compressed (until Accept-Encoding is *)
141 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
142 'md5': '128c42e68b13950268b648275386fc74',
144 'id': 'FictionJunction-Parallel_Hearts',
146 'title': 'FictionJunction-Parallel_Hearts',
147 'upload_date': '20140522',
149 'expected_warnings': [
150 'URL could be a direct video link, returning it as such.'
152 'skip': 'URL invalid',
154 # Direct download with broken HEAD
156 'url': 'http://ai-radio.org:8000/radio.opus',
163 'skip_download': True, # infinite live stream
165 'expected_warnings': [
166 r'501.*Not Implemented',
170 # Direct link with incorrect MIME type
172 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
173 'md5': '4ccbebe5f36706d85221f204d7eb5913',
175 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
176 'id': '5_Lennart_Poettering_-_Systemd',
178 'title': '5_Lennart_Poettering_-_Systemd',
179 'upload_date': '20141120',
181 'expected_warnings': [
182 'URL could be a direct video link, returning it as such.'
187 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
189 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
190 'title': 'Zero Punctuation',
191 'description': 're:.*groundbreaking video review series.*'
193 'playlist_mincount': 11,
195 # RSS feed with enclosure
197 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
199 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 'upload_date': '20150228',
202 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
205 # RSS feed with enclosures and unsupported link URLs
207 'url': 'http://www.hellointernet.fm/podcast?format=rss',
209 'id': 'http://www.hellointernet.fm/podcast?format=rss',
210 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
211 'title': 'Hello Internet',
213 'playlist_mincount': 100,
215 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
217 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
221 'title': 'Automatics, robotics and biocybernetics',
222 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
223 'upload_date': '20130627',
224 'formats': 'mincount:16',
225 'subtitles': 'mincount:1',
228 'force_generic_extractor': True,
229 'skip_download': True,
232 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
234 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
239 'formats': 'mincount:1',
242 'skip_download': True,
245 # SMIL from https://www.restudy.dk/video/play/id/1637
247 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
251 'title': 'video_1637',
252 'formats': 'mincount:3',
255 'skip_download': True,
258 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
260 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
262 'id': 'smil-service',
264 'title': 'smil-service',
265 'formats': 'mincount:1',
268 'skip_download': True,
271 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
273 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
277 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
278 'formats': 'mincount:3',
281 'skip_download': True,
284 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
286 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
288 'id': 'mZlp2ctYIUEB',
290 'title': 'Tikibad ontruimd wegens brand',
291 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
292 'thumbnail': r're:^https?://.*\.jpg$',
296 'skip_download': True,
299 # MPD from http://dash-mse-test.appspot.com/media.html
301 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
302 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
304 'id': 'car-20120827-manifest',
306 'title': 'car-20120827-manifest',
307 'formats': 'mincount:9',
308 'upload_date': '20130904',
311 'format': 'bestvideo',
314 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
316 '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',
321 'formats': 'mincount:8',
325 'skip_download': True,
327 'skip': 'video gone',
329 # m3u8 served with Content-Type: text/plain
331 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
336 'upload_date': '20140720',
337 'formats': 'mincount:11',
341 'skip_download': True,
343 'skip': 'video gone',
347 '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',
351 'upload_date': '20130224',
352 'uploader_id': 'TheVerge',
353 'description': r're:^Chris Ziegler takes a look at the\.*',
354 'uploader': 'The Verge',
355 'title': 'First Firefox OS phones side-by-side',
358 'skip_download': False,
362 # redirect in Refresh HTTP header
363 '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',
367 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
368 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
369 'upload_date': '20150917',
370 'uploader_id': 'brtvofficial',
371 'uploader': 'Boiler Room',
374 'skip_download': False,
378 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
379 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
381 'id': '13601338388002',
383 'uploader': 'www.hodiho.fr',
384 'title': 'R\u00e9gis plante sa Jeep',
387 # bandcamp page with custom domain
389 'add_ie': ['Bandcamp'],
390 'url': 'http://bronyrock.com/track/the-pony-mash',
394 'title': 'The Pony Mash',
395 'uploader': 'M_Pallante',
397 'skip': 'There is a limit of 200 free downloads / month for the test song',
400 # embedded brightcove video
401 # it also tests brightcove videos that need to set the 'Referer'
402 # in the http requests
403 'add_ie': ['BrightcoveLegacy'],
404 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
406 'id': '2765128793001',
408 'title': 'Le cours de bourse : l’analyse technique',
409 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
410 'uploader': 'BFM BUSINESS',
413 'skip_download': True,
417 # embedded with itemprop embedURL and video id spelled as `idVideo`
418 'add_id': ['BrightcoveLegacy'],
419 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
421 'id': '5255628253001',
423 'title': 'md5:37c519b1128915607601e75a87995fc0',
424 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
425 'uploader': 'BFM BUSINESS',
426 'uploader_id': '876450612001',
427 'timestamp': 1482255315,
428 'upload_date': '20161220',
431 'skip_download': True,
435 # https://github.com/ytdl-org/youtube-dl/issues/2253
436 'url': 'http://bcove.me/i6nfkrc3',
437 'md5': '0ba9446db037002366bab3b3eb30c88c',
439 'id': '3101154703001',
441 'title': 'Still no power',
442 'uploader': 'thestar.com',
443 '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.',
445 'add_ie': ['BrightcoveLegacy'],
446 'skip': 'video gone',
449 'url': 'http://www.championat.com/video/football/v/87/87499.html',
450 'md5': 'fb973ecf6e4a78a67453647444222983',
452 'id': '3414141473001',
454 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
455 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
456 'uploader': 'Championat',
460 # https://github.com/ytdl-org/youtube-dl/issues/3541
461 'add_ie': ['BrightcoveLegacy'],
462 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
464 'id': '3866516442001',
466 'title': 'Leer mij vrouwen kennen: Aflevering 1',
467 'description': 'Leer mij vrouwen kennen: Aflevering 1',
468 'uploader': 'SBS Broadcasting',
470 'skip': 'Restricted to Netherlands',
472 'skip_download': True, # m3u8 download
476 # Brightcove video in <iframe>
477 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
478 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
480 'id': '5360463607001',
482 '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',
483 '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。',
484 'uploader': 'United Nations',
485 'uploader_id': '1362235914001',
486 'timestamp': 1489593889,
487 'upload_date': '20170315',
489 'add_ie': ['BrightcoveLegacy'],
492 # Brightcove with alternative playerID key
493 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
495 'id': 'nmeth.2062_SV1',
496 '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',
500 'id': '2228375078001',
502 'title': 'nmeth.2062-sv1',
503 'description': 'nmeth.2062-sv1',
504 'timestamp': 1363357591,
505 'upload_date': '20130315',
506 'uploader': 'Nature Publishing Group',
507 'uploader_id': '1964492299001',
512 # Brightcove with UUID in videoPlayer
513 'url': 'http://www8.hp.com/cn/zh/home.html',
515 'id': '5255815316001',
517 'title': 'Sprocket Video - China',
518 'description': 'Sprocket Video - China',
519 'uploader': 'HP-Video Gallery',
520 'timestamp': 1482263210,
521 'upload_date': '20161220',
522 'uploader_id': '1107601872001',
525 'skip_download': True, # m3u8 download
527 'skip': 'video rotates...weekly?',
530 # Brightcove:new type [2].
531 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
532 'md5': '2b35148fcf48da41c9fb4591650784f3',
534 'id': '5348741021001',
536 'upload_date': '20170306',
537 'uploader_id': '4191638492001',
538 'timestamp': 1488769918,
539 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
544 # Alternative brightcove <video> attributes
545 '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/',
547 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
548 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
551 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
553 'id': '5311302538001',
555 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
556 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
557 'timestamp': 1486321708,
558 'upload_date': '20170205',
559 'uploader_id': '800000640001',
561 'only_matching': True,
565 # Brightcove with UUID in videoPlayer
566 'url': 'http://www8.hp.com/cn/zh/home.html',
568 'id': '5255815316001',
570 'title': 'Sprocket Video - China',
571 'description': 'Sprocket Video - China',
572 'uploader': 'HP-Video Gallery',
573 'timestamp': 1482263210,
574 'upload_date': '20161220',
575 'uploader_id': '1107601872001',
578 'skip_download': True, # m3u8 download
583 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
584 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
586 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
588 'title': '2cc213299525360.mov', # that's what we get
591 'add_ie': ['Ooyala'],
594 # ooyala video embedded with http://player.ooyala.com/iframe.js
595 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
597 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
599 'title': '"Steve Jobs: Man in the Machine" trailer',
600 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
604 'skip_download': True,
606 'skip': 'movie expired',
608 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
610 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
612 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
614 'title': 'Steampunk Fest Comes to Honesdale',
618 'skip_download': True,
623 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
627 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
628 'upload_date': '20140225',
629 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
630 'uploader': 'Tested',
631 'uploader_id': 'testedcom',
633 # No need to test YoutubeIE here
635 'skip_download': True,
640 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
644 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
645 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
647 # HEAD requests lead to endless 301, while GET is OK
648 'expected_warnings': ['301'],
652 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
656 'title': 'Охотское море стало целиком российским',
657 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
661 'skip_download': True,
666 '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/',
670 'title': 'Дошкольное воспитание',
675 'url': 'http://www.vestifinance.ru/articles/25753',
678 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
683 'title': 'Госзаказ. День 3',
689 'title': 'Госзаказ. День 2',
695 'title': 'Госзаказ. День 1',
701 'skip_download': True,
706 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
708 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
710 'title': 'Ужастики, русский трейлер (2015)',
711 'thumbnail': r're:^https?://.*\.jpg$',
717 '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',
720 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
722 'playlist_mincount': 7,
723 # This forum does not allow <iframe> syntaxes anymore
724 # Now HTML tags are displayed as-is
725 'skip': 'No videos on this page',
729 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
730 'md5': '65fdff94098e4a607385a60c5177c638',
734 'title': 'Hidden miracles of the natural world',
735 'uploader': 'Louie Schwartzberg',
736 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
739 # nowvideo embed hidden behind percent encoding
741 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
742 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
744 'id': '06e53103ca9aa',
746 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
747 'description': 'No description',
752 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
753 'md5': '7653032cbb25bf6c80d80f217055fa43',
755 'id': '048195-004_PLUS7-F',
758 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
759 'upload_date': '20140320',
762 'skip_download': 'Requires rtmpdump'
764 'skip': 'video gone',
768 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
772 'title': 'Alcaline, le concert avec Calogero',
773 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
774 'upload_date': '20150226',
775 'timestamp': 1424989860,
780 'skip_download': True,
782 'expected_warnings': [
788 'url': 'http://www.wired.com/2014/04/honda-asimo/',
789 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
791 'id': '53501be369702d3275860000',
793 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
798 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
799 'md5': '441aeeb82eb72c422c7f14ec533999cd',
801 'id': 'k2mm4bCdJ6CQ2i7c8o2',
803 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
804 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
806 'uploader_id': 'xgditw',
807 'upload_date': '20140425',
808 'timestamp': 1398441542,
810 'add_ie': ['Dailymotion'],
814 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
818 'title': 'Care worker punches elderly dementia patient in head 11 times',
819 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
821 'add_ie': ['DailyMail'],
823 'skip_download': True,
828 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
832 'title': 'The NBL Auction 2014',
833 'uploader': 'BADMINTON England',
834 'uploader_id': 'BADMINTONEvents',
835 'upload_date': '20140603',
836 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
838 'add_ie': ['Youtube'],
840 'skip_download': True,
845 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
846 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
848 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
850 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
851 'description': 'Two valets share their love for movie star Liam Neesons.',
852 'timestamp': 1349922600,
853 'upload_date': '20121011',
856 # YouTube embed via <data-embed-url="">
858 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
862 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
863 'uploader': 'Gameloft',
864 'uploader_id': 'gameloft',
865 'upload_date': '20140828',
866 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
869 'skip_download': True,
872 # YouTube <object> embed
874 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
875 'md5': '516718101ec834f74318df76259fb3cc',
879 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
880 'upload_date': '20080526',
881 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
882 'uploader': 'Christopher Sykes',
883 'uploader_id': 'ChristopherJSykes',
885 'add_ie': ['Youtube'],
889 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
891 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
893 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
894 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
899 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
901 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
902 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
908 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
913 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
914 'md5': '9d65602bf31c6e20014319c7d07fba27',
916 'id': '5123ea6d5e5a7',
919 'uploader': 'www.handjobhub.com',
920 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
923 # Multiple brightcove videos
924 # https://github.com/ytdl-org/youtube-dl/issues/2283
926 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
928 'id': 'always-never',
929 'title': 'Always / Never - The New Yorker',
933 'extract_flat': False,
934 'skip_download': True,
939 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
940 'md5': '96f09a37e44da40dd083e12d9a683327',
944 'title': 'Ump changes call to ball',
945 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
947 'timestamp': 1401537900,
948 'upload_date': '20140531',
949 'thumbnail': r're:^https?://.*\.jpg$',
954 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
955 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
959 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
960 'description': 'a Paywall Videos video from Remilon',
962 'uploader': 'study.com',
963 'timestamp': 1459678540,
964 'upload_date': '20160403',
965 'filesize': 24687186,
969 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
970 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
974 'title': 'Conversation about Hexagonal Rails Part 1',
975 'description': 'a Martin Fowler video from ThoughtWorks',
977 'uploader': 'thoughtworks.wistia.com',
978 'timestamp': 1401832161,
979 'upload_date': '20140603',
982 # Wistia standard embed (async)
984 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
988 'title': 'Drip Brennan Dunn Workshop',
989 'description': 'a JV Webinars video from getdrip-1',
991 'timestamp': 1463607249,
992 'upload_date': '20160518',
995 'skip_download': True,
1000 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1004 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1005 'uploader': 'Sophos Security',
1006 'title': 'Chet Chat 171 - Oct 29, 2014',
1007 'upload_date': '20141029',
1010 # Soundcloud multiple embeds
1012 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1015 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1017 'playlist_mincount': 7,
1019 # TuneIn station embed
1021 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1026 'location': 'Paris, France',
1031 'skip_download': True,
1036 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1040 'upload_date': '20141112',
1041 'title': 'Rosetta #CometLanding webcast HL 10',
1044 # Another Livestream embed, without 'new.' in URL
1046 'url': 'https://www.freespeech.org/',
1050 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1054 'skip_download': True,
1059 'url': 'https://skiplagged.com/',
1062 'title': 'Skiplagged: The smart way to find cheap flights',
1064 'playlist_mincount': 1,
1065 'add_ie': ['Youtube'],
1069 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1073 'upload_date': '20141126',
1074 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1079 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1081 'id': '730m_DandD_1901_512k',
1083 'uploader': 'www.abc.net.au',
1084 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1087 # embedded viddler video
1089 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1093 'uploader': 'deadspin',
1094 'title': 'WALL-TO-GORTAT',
1095 'timestamp': 1422285291,
1096 'upload_date': '20150126',
1098 'add_ie': ['Viddler'],
1102 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1106 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1107 'description': 'md5:601cb790edd05908957dae8aaa866465',
1108 'upload_date': '20150220',
1110 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1114 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1116 'id': 'Mrj4DVp2zeA',
1118 'upload_date': '20150212',
1119 'uploader': 'The National Archives UK',
1120 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1121 'uploader_id': 'NationalArchives08',
1122 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1127 'url': 'http://www.suffolk.edu/sjc/live.php',
1131 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1132 'uploader': 'www.suffolk.edu',
1135 'skip_download': True,
1137 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1141 'url': 'http://www.indiedb.com/games/king-machine/videos',
1145 'title': 'king machine trailer 1',
1146 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1147 'thumbnail': r're:^https?://.*\.jpg$',
1151 # JWPlayer config passed as variable
1152 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1156 'title': 'ARIELE | Tube Cup',
1157 'uploader': 'www.txxx.com',
1161 'skip_download': True,
1166 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1167 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1171 'upload_date': '20171122',
1172 'timestamp': 1511366290,
1173 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1175 'add_ie': [JWPlatformIE.ie_key()],
1178 # Video.js embed, multiple formats
1179 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1181 'id': 'yygqldloqIk',
1183 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1184 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1185 'upload_date': '20130314',
1186 'uploader': 'PROстое3D',
1187 'uploader_id': 'PROstoe3D',
1190 'skip_download': True,
1194 # Video.js embed, single format
1195 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1199 'title': 'Step 1 - Good Foundation',
1200 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1203 'skip_download': True,
1208 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1209 'playlist_mincount': 5,
1211 'id': 'aanslagen-kopenhagen',
1212 'title': 'Aanslagen Kopenhagen',
1217 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1221 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1224 # Kaltura embed (different embed code)
1226 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1230 'upload_date': '20150127',
1231 'uploader_id': 'PremierMedia',
1233 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1236 # Kaltura embed with single quotes
1238 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1243 'timestamp': 1355743100,
1244 'upload_date': '20121217',
1245 'uploader_id': 'cplapp@learn360.com',
1247 'add_ie': ['Kaltura'],
1250 # Kaltura embedded via quoted entry_id
1251 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1255 'title': '06_matthew_brender_raj_dutt',
1256 'timestamp': 1466638791,
1257 'upload_date': '20160622',
1259 'add_ie': ['Kaltura'],
1260 'expected_warnings': [
1261 'Could not send HEAD request'
1264 'skip_download': True,
1268 # Kaltura embedded, some fileExt broken (#11480)
1269 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1273 'title': 'Our "Standard Models" of particle physics and cosmology',
1274 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1275 'timestamp': 1321158993,
1276 'upload_date': '20111113',
1277 'uploader_id': 'kps1',
1279 'add_ie': ['Kaltura'],
1282 # Kaltura iframe embed
1283 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1284 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1288 'title': 'I. M. Pei: A Centennial Celebration',
1289 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1290 'upload_date': '20170403',
1291 'uploader_id': 'batchUser',
1292 'timestamp': 1491232186,
1294 'add_ie': ['Kaltura'],
1297 # Kaltura iframe embed, more sophisticated
1298 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1302 'title': 'lecture-05sep2017',
1303 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1304 'upload_date': '20170913',
1305 'uploader_id': 'eps2',
1306 'timestamp': 1505340777,
1309 'skip_download': True,
1311 'add_ie': ['Kaltura'],
1314 # meta twitter:player
1315 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1319 'title': 'Main Twerk (Video)',
1320 'upload_date': '20171208',
1321 'uploader_id': 'sebastian.salinas@thechive.com',
1322 'timestamp': 1512713057,
1325 'skip_download': True,
1327 'add_ie': ['Kaltura'],
1329 # referrer protected EaglePlatform embed
1331 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1335 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1336 'thumbnail': r're:^https?://.*\.jpg$',
1341 'skip_download': True,
1344 # ClipYou (EaglePlatform) embed (custom URL)
1346 'url': 'http://muz-tv.ru/play/7129/',
1347 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1351 'title': "'O Sole Mio",
1352 'thumbnail': r're:^https?://.*\.jpg$',
1357 'skip_download': True,
1359 'skip': 'This video is unavailable.',
1363 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1367 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1368 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1369 'thumbnail': r're:^https?://.*\.jpg$',
1373 'skip': 'HTTP Error 404: Not Found',
1377 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1381 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1382 'thumbnail': r're:^https?://.*\.png$',
1388 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1389 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1393 'title': 'Facebook Creates "On This Day" | Crunch Report',
1394 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1395 'timestamp': 1427237531,
1396 'uploader': 'Crunch Report',
1397 'upload_date': '20150324',
1401 'skip_download': True,
1404 # Crooks and Liars embed
1406 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1410 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1411 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1412 'timestamp': 1428207000,
1413 'upload_date': '20150405',
1414 'uploader': 'Heather',
1417 # Crooks and Liars external embed
1419 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1421 'id': 'MTE3MjUtMzQ2MzA',
1423 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1424 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1425 'timestamp': 1265032391,
1426 'upload_date': '20100201',
1427 'uploader': 'Heather',
1430 # NBC Sports vplayer embed
1432 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1434 'id': 'ln7x1qSThw4k',
1436 'title': "PFT Live: New leader in the 'new-look' defense",
1437 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1438 'uploader': 'NBCU-SPORTS',
1439 'upload_date': '20140107',
1440 'timestamp': 1389118457,
1442 'skip': 'Invalid Page URL',
1446 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1447 'md5': '1aa589c675898ae6d37a17913cf68d66',
1449 'id': 'x_dtl_oa_LettermanliftPR_160608',
1451 'title': 'David Letterman: A Preview',
1452 '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.',
1453 'upload_date': '20160609',
1454 'timestamp': 1465431544,
1455 'uploader': 'NBCU-NEWS',
1460 'url': 'https://video.udn.com/news/300346',
1461 'md5': 'fd2060e988c326991037b9aff9df21a6',
1465 'title': '中一中男師變性 全校師生力挺',
1466 'thumbnail': r're:^https?://.*\.jpg$',
1470 'skip_download': True,
1472 'expected_warnings': ['Failed to parse JSON Expecting value'],
1474 # Brightcove URL in single quotes
1476 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1477 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1479 'id': '4255764656001',
1481 'title': 'SN Presents: Russell Martin, World Citizen',
1482 '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.',
1483 'uploader': 'Rogers Sportsnet',
1484 'uploader_id': '1704050871',
1485 'upload_date': '20150525',
1486 'timestamp': 1432570283,
1491 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1495 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1496 'description': 'Migrated from OnionStudios',
1497 'thumbnail': r're:^https?://.*\.jpe?g$',
1498 'uploader': 'clickhole',
1499 'upload_date': '20150527',
1500 'timestamp': 1432744860,
1505 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1507 'id': '74849a00-85a9-11e1-9660-123139220831',
1509 'title': '#whilewewatch',
1512 # AdobeTVVideo embed
1514 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1515 'md5': '43662b577c018ad707a63766462b1e87',
1519 'title': 'New experience with Acrobat DC',
1520 'description': 'New experience with Acrobat DC',
1521 'duration': 248.667,
1524 # BrightcoveInPageEmbed embed
1526 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1528 'id': '4238694884001',
1530 'title': 'Tabletop: Dread, Last Thoughts',
1531 'description': 'Tabletop: Dread, Last Thoughts',
1535 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1536 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1538 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1540 'id': '4785848093001',
1542 'title': 'The Cardinal Pell Interview',
1543 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1544 'uploader': 'GlobeCast Australia - GlobeStream',
1545 'uploader_id': '2733773828001',
1546 'upload_date': '20160304',
1547 'timestamp': 1457083087,
1551 'skip_download': True,
1555 # Brightcove embed with whitespace around attribute names
1556 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1558 'id': '3167554373001',
1560 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1561 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1562 'uploader_id': '1079349493',
1563 'upload_date': '20140207',
1564 'timestamp': 1391810548,
1567 'skip_download': True,
1570 # Another form of arte.tv embed
1572 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1573 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1575 'id': '030273-562_PLUS7-F',
1577 'title': 'ARTE Reportage - Nulle part, en France',
1578 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1579 'upload_date': '20160409',
1584 'url': 'http://www.wykop.pl/link/3088787/',
1585 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1587 'id': '874_1459135191',
1589 'title': 'Man shows poor quality of new apartment building',
1590 'description': 'The wall is like a sand pile.',
1591 'uploader': 'Lake8737',
1593 'add_ie': [LiveLeakIE.ie_key()],
1595 # Another LiveLeak embed pattern (#13336)
1597 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1599 'id': '2eb_1496309988',
1601 'title': 'Thief robs place where everyone was armed',
1602 'description': 'md5:694d73ee79e535953cf2488562288eee',
1603 'uploader': 'brazilwtf',
1605 'add_ie': [LiveLeakIE.ie_key()],
1607 # Duplicated embedded video URLs
1609 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1611 'id': '149298443_480_16c25b74_2',
1613 'title': 'vs. Blue Orange Spring Game',
1614 'uploader': 'www.hudl.com',
1617 # twitter:player:stream embed
1619 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1623 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1624 'uploader': 'www.rtl.be',
1628 'skip_download': True,
1631 # twitter:player embed
1633 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1634 'md5': 'a3e0df96369831de324f0778e126653c',
1636 'id': '4909620399001',
1638 'title': 'What Do Black Holes Sound Like?',
1639 'description': 'what do black holes sound like',
1640 'upload_date': '20160524',
1641 'uploader_id': '29913724001',
1642 'timestamp': 1464107587,
1643 'uploader': 'TheAtlantic',
1645 'add_ie': ['BrightcoveLegacy'],
1647 # Facebook <iframe> embed
1649 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1650 'md5': 'fbcde74f534176ecb015849146dd3aee',
1652 'id': '599637780109885',
1654 'title': 'Facebook video #599637780109885',
1657 # Facebook <iframe> embed, plugin video
1659 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1661 'id': '1754168231264132',
1663 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1664 'uploader': 'Tariq Ramadan (official)',
1665 'timestamp': 1496758379,
1666 'upload_date': '20170606',
1669 'skip_download': True,
1672 # Facebook API embed
1674 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1675 'md5': 'a47372ee61b39a7b90287094d447d94e',
1677 'id': '10153467542406923',
1679 'title': 'Facebook video #10153467542406923',
1682 # Wordpress "YouTube Video Importer" plugin
1684 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1685 'md5': 'd16797741b560b485194eddda8121b48',
1687 'id': 'HNTXWDXV9Is',
1689 'title': 'Blue Devils Drumline Stanford lot 2016',
1690 'upload_date': '20160627',
1691 'uploader_id': 'GENOCIDE8GENERAL10',
1692 'uploader': 'cylus cyrus',
1696 # video stored on custom kaltura server
1697 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1698 'md5': '537617d06e64dfed891fa1593c4b30cc',
1702 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1703 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1704 'uploader_id': 'videos.expansion@el-mundo.net',
1705 'upload_date': '20150429',
1706 'timestamp': 1430303472,
1708 'add_ie': ['Kaltura'],
1711 # Non-standard Vimeo embed
1712 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1713 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1717 'title': 'Understanding the web - Teaser',
1718 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1719 'upload_date': '20151214',
1720 'uploader': 'OpenClassrooms',
1721 'uploader_id': 'openclassrooms',
1723 'add_ie': ['Vimeo'],
1726 # generic vimeo embed that requires original URL passed as Referer
1727 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1728 'only_matching': True,
1731 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1732 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1734 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1736 'title': 'Big Buck Bunny',
1737 'description': 'Royalty free test video',
1738 'timestamp': 1432816365,
1739 'upload_date': '20150528',
1743 'skip_download': True,
1745 'add_ie': [ArkenaIE.ie_key()],
1748 '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/',
1752 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1755 'skip_download': True,
1757 'add_ie': [Vbox7IE.ie_key()],
1761 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1764 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1766 'playlist_mincount': 3,
1770 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1772 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1773 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1775 'playlist_mincount': 2,
1779 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1783 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1784 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1787 'skip_download': True,
1789 'add_ie': [TwentyMinutenIE.ie_key()],
1793 'url': 'https://en.support.wordpress.com/videopress/',
1797 'title': 'IMG_5786',
1798 'timestamp': 1435711927,
1799 'upload_date': '20150701',
1802 'skip_download': True,
1804 'add_ie': [VideoPressIE.ie_key()],
1808 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1810 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1812 'title': 'Магаззино: Казань 2',
1813 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1814 'uploader': 'Магаззино',
1815 'upload_date': '20170228',
1816 'uploader_id': '996642',
1819 'skip_download': True,
1821 'add_ie': [RutubeIE.ie_key()],
1824 # ThePlatform embedded with whitespaces in URLs
1825 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1826 'only_matching': True,
1829 # Senate ISVP iframe https
1830 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1831 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1833 'id': 'govtaff020316',
1835 'title': 'Integrated Senate Video Player',
1837 'add_ie': [SenateISVPIE.ie_key()],
1840 # Limelight embeds (1 channel embed + 4 media embeds)
1841 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1843 'id': 'FacilitatorTraining2017',
1844 'title': 'Facilitator Training 2017',
1846 'playlist_mincount': 5,
1849 # Limelight embed (LimelightPlayerUtil.embed)
1850 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1852 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1854 'title': '07448641',
1855 'timestamp': 1499890639,
1856 'upload_date': '20170712',
1859 'skip_download': True,
1861 'add_ie': ['LimelightMedia'],
1864 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1866 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1867 'title': 'Standoff with Walnut Creek murder suspect ends',
1868 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1870 'playlist_mincount': 4,
1873 # WashingtonPost embed
1874 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1876 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1878 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1879 '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.',
1880 'timestamp': 1455216756,
1881 'uploader': 'The Washington Post',
1882 'upload_date': '20160211',
1884 'add_ie': [WashingtonPostIE.ie_key()],
1888 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1892 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1895 'skip_download': True,
1897 'add_ie': [MediasetIE.ie_key()],
1901 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1904 'title': 'Slovenskom sa prehnala vlna silných búrok',
1906 'playlist_mincount': 5,
1907 'add_ie': [JojIE.ie_key()],
1910 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1911 'url': 'https://tvrain.ru/amp/418921/',
1912 'md5': 'cc00413936695987e8de148b67d14f1d',
1916 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1921 'url': 'http://help.vzaar.com/article/165-embedding-video',
1922 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1926 'title': 'Building A Business Online: Principal Chairs Q & A',
1930 # multiple HTML5 videos on one page
1931 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1933 'id': 'keyscenarios',
1934 'title': 'Rescue Kit 14 Free Edition - Getting started',
1936 'playlist_count': 4,
1940 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1941 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1944 'title': 'vl14062007715967',
1949 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1950 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1952 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1954 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1955 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1956 'timestamp': 1474354800,
1957 'upload_date': '20160920',
1961 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1965 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1966 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1967 'timestamp': 1516100691,
1968 'upload_date': '20180116',
1971 'skip_download': True,
1973 'add_ie': [SpringboardPlatformIE.ie_key()],
1976 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1978 'id': 'uPDB5I9wfp8',
1980 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1981 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1982 'upload_date': '20160219',
1983 'uploader': 'Pocoyo - Português (BR)',
1984 'uploader_id': 'PocoyoBrazil',
1986 'add_ie': [YoutubeIE.ie_key()],
1988 'skip_download': True,
1992 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1994 'id': 'vMDE4NzI1Mjgt690b',
1998 'add_ie': [YapFilesIE.ie_key()],
2000 'skip_download': True,
2004 # CloudflareStream embed
2005 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2007 'id': '31c9291ab41fac05471db4e73aa11717',
2009 'title': '31c9291ab41fac05471db4e73aa11717',
2011 'add_ie': [CloudflareStreamIE.ie_key()],
2013 'skip_download': True,
2018 'url': 'https://joinpeertube.org/fr/home/',
2021 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2023 'playlist_count': 2,
2027 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2031 'title': 'Így kell otthon hamburgert sütni',
2032 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2033 'timestamp': 1426330212,
2034 'upload_date': '20150314',
2035 'uploader': 'StreetKitchen',
2036 'uploader_id': '546363',
2038 'add_ie': [IndavideoEmbedIE.ie_key()],
2040 'skip_download': True,
2044 # APA embed via JWPlatform embed
2045 'url': 'http://www.vol.at/blue-man-group/5593454',
2049 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2050 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2051 'thumbnail': r're:^https?://.*\.jpg$',
2053 'timestamp': 1519211149,
2054 'upload_date': '20180221',
2057 'skip_download': True,
2061 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2062 'md5': 'b68d276de422ab07ee1d49388103f457',
2065 'title': 'Lock up and get excited',
2068 'skip': 'TODO: fix nested playlists processing in tests',
2072 'url': 'https://viqeo.tv/',
2075 'title': 'All-new video platform',
2077 'playlist_count': 6,
2080 # Squarespace video embed, 2019-08-28
2081 'url': 'http://ootboxford.com',
2083 'id': 'Tc7b_JGdZfw',
2084 'title': 'Out of the Blue, at Childish Things 10',
2086 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2087 'uploader_id': 'helendouglashouse',
2088 'uploader': 'Helen & Douglas House',
2089 'upload_date': '20140328',
2092 'skip_download': True,
2097 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2099 'id': '5b400b834b32992a310622b9',
2101 'title': 'Smoky Barbecue Favorites',
2102 'thumbnail': r're:^https?://.*\.jpe?g',
2103 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2104 'upload_date': '20170909',
2105 'timestamp': 1504915200,
2107 'add_ie': [ZypeIE.ie_key()],
2109 'skip_download': True,
2114 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2118 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2119 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2120 'thumbnail': r're:^https?://.*\.jpg$',
2123 'skip_download': True,
2125 'expected_warnings': ['Failed to download MPD manifest'],
2128 # DailyMotion embed with DM.player
2129 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2131 'id': 'k6aKkGHd9FJs4mtJN39',
2133 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2134 'description': 'This video is private.',
2135 'uploader_id': 'x1jf30l',
2136 'uploader': 'beIN SPORTS USA',
2137 'upload_date': '20190528',
2138 'timestamp': 1559062971,
2141 'skip_download': True,
2145 # # TODO: find another test
2146 # # http://schema.org/VideoObject
2147 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2148 # 'md5': '888dcf08b7ea671381f00fab74692755',
2150 # 'id': 'nyvTSJMKId',
2152 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2153 # 'description': '#love for cats.',
2154 # 'timestamp': 1461244995,
2155 # 'upload_date': '20160421',
2158 # 'force_generic_extractor': True,
2163 def report_following_redirect(self, new_url):
2164 """Report information extraction."""
2165 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2167 def _extract_rss(self, url, video_id, doc):
2168 playlist_title = doc.find('./channel/title').text
2169 playlist_desc_el = doc.find('./channel/description')
2170 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2173 for it in doc.findall('./channel/item'):
2175 enclosure_nodes = it.findall('./enclosure')
2176 for e in enclosure_nodes:
2177 next_url = e.attrib.get('url')
2182 next_url = xpath_text(it, 'link', fatal=False)
2188 '_type': 'url_transparent',
2190 'title': it.find('title').text,
2194 '_type': 'playlist',
2196 'title': playlist_title,
2197 'description': playlist_desc,
2201 def _extract_camtasia(self, url, video_id, webpage):
2202 """ Returns None if no camtasia video can be found. """
2204 camtasia_cfg = self._search_regex(
2205 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2206 webpage, 'camtasia configuration file', default=None)
2207 if camtasia_cfg is None:
2210 title = self._html_search_meta('DC.title', webpage, fatal=True)
2212 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2213 camtasia_cfg = self._download_xml(
2214 camtasia_url, video_id,
2215 note='Downloading camtasia configuration',
2216 errnote='Failed to download camtasia configuration')
2217 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2220 for n in fileset_node.getchildren():
2221 url_n = n.find('./uri')
2226 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2227 'title': '%s - %s' % (title, n.tag),
2228 'url': compat_urlparse.urljoin(url, url_n.text),
2229 'duration': float_or_none(n.find('./duration').text),
2233 '_type': 'playlist',
2238 def _real_extract(self, url):
2239 if url.startswith('//'):
2240 return self.url_result(self.http_scheme() + url)
2242 parsed_url = compat_urlparse.urlparse(url)
2243 if not parsed_url.scheme:
2244 default_search = self._downloader.params.get('default_search')
2245 if default_search is None:
2246 default_search = 'fixup_error'
2248 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2249 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2250 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2251 return self.url_result('http://' + url)
2252 elif default_search != 'fixup_error':
2253 if default_search == 'auto_warning':
2254 if re.match(r'^(?:url|URL)$', url):
2255 raise ExtractorError(
2256 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2259 self._downloader.report_warning(
2260 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2261 return self.url_result('ytsearch:' + url)
2263 if default_search in ('error', 'fixup_error'):
2264 raise ExtractorError(
2265 '%r is not a valid URL. '
2266 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2267 % (url, url), expected=True)
2269 if ':' not in default_search:
2270 default_search += ':'
2271 return self.url_result(default_search + url)
2273 url, smuggled_data = unsmuggle_url(url)
2274 force_videoid = None
2275 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2276 if smuggled_data and 'force_videoid' in smuggled_data:
2277 force_videoid = smuggled_data['force_videoid']
2278 video_id = force_videoid
2280 video_id = self._generic_id(url)
2282 self.to_screen('%s: Requesting header' % video_id)
2284 head_req = HEADRequest(url)
2285 head_response = self._request_webpage(
2287 note=False, errnote='Could not send HEAD request to %s' % url,
2290 if head_response is not False:
2291 # Check for redirect
2292 new_url = head_response.geturl()
2294 self.report_following_redirect(new_url)
2296 new_url = smuggle_url(
2297 new_url, {'force_videoid': force_videoid})
2298 return self.url_result(new_url)
2300 full_response = None
2301 if head_response is False:
2302 request = sanitized_Request(url)
2303 request.add_header('Accept-Encoding', '*')
2304 full_response = self._request_webpage(request, video_id)
2305 head_response = full_response
2309 'title': self._generic_title(url),
2310 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2313 # Check for direct link to a video
2314 content_type = head_response.headers.get('Content-Type', '').lower()
2315 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2317 format_id = compat_str(m.group('format_id'))
2318 if format_id.endswith('mpegurl'):
2319 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2320 elif format_id == 'f4m':
2321 formats = self._extract_f4m_formats(url, video_id)
2324 'format_id': format_id,
2326 'vcodec': 'none' if m.group('type') == 'audio' else None
2328 info_dict['direct'] = True
2329 self._sort_formats(formats)
2330 info_dict['formats'] = formats
2333 if not self._downloader.params.get('test', False) and not is_intentional:
2334 force = self._downloader.params.get('force_generic_extractor', False)
2335 self._downloader.report_warning(
2336 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2338 if not full_response:
2339 request = sanitized_Request(url)
2340 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2341 # making it impossible to download only chunk of the file (yet we need only 512kB to
2342 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2343 # that will always result in downloading the whole file that is not desirable.
2344 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2345 # to accept raw bytes and being able to download only a chunk.
2346 # It may probably better to solve this by checking Content-Type for application/octet-stream
2347 # after HEAD request finishes, but not sure if we can rely on this.
2348 request.add_header('Accept-Encoding', '*')
2349 full_response = self._request_webpage(request, video_id)
2351 first_bytes = full_response.read(512)
2353 # Is it an M3U playlist?
2354 if first_bytes.startswith(b'#EXTM3U'):
2355 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2356 self._sort_formats(info_dict['formats'])
2359 # Maybe it's a direct link to a video?
2360 # Be careful not to download the whole thing!
2361 if not is_html(first_bytes):
2362 self._downloader.report_warning(
2363 'URL could be a direct video link, returning it as such.')
2370 webpage = self._webpage_read_content(
2371 full_response, url, video_id, prefix=first_bytes)
2373 self.report_extraction(video_id)
2375 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2377 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2378 if doc.tag == 'rss':
2379 return self._extract_rss(url, video_id, doc)
2380 elif doc.tag == 'SmoothStreamingMedia':
2381 info_dict['formats'] = self._parse_ism_formats(doc, url)
2382 self._sort_formats(info_dict['formats'])
2384 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2385 smil = self._parse_smil(doc, url, video_id)
2386 self._sort_formats(smil['formats'])
2388 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2389 return self.playlist_result(
2391 doc, video_id, xspf_url=url,
2392 xspf_base_url=full_response.geturl()),
2394 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2395 info_dict['formats'] = self._parse_mpd_formats(
2397 mpd_base_url=full_response.geturl().rpartition('/')[0],
2399 self._sort_formats(info_dict['formats'])
2401 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2402 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2403 self._sort_formats(info_dict['formats'])
2405 except compat_xml_parse_error:
2408 # Is it a Camtasia project?
2409 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2410 if camtasia_res is not None:
2413 # Sometimes embedded video player is hidden behind percent encoding
2414 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2415 # Unescaping the whole page allows to handle those cases in a generic way
2416 webpage = compat_urllib_parse_unquote(webpage)
2418 # Unescape squarespace embeds to be detected by generic extractor,
2419 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2421 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2422 lambda x: unescapeHTML(x.group(0)), webpage)
2424 # it's tempting to parse this further, but you would
2425 # have to take into account all the variations like
2426 # Video Title - Site Name
2427 # Site Name | Video Title
2428 # Video Title - Tagline | Site Name
2429 # and so on and so forth; it's just not practical
2430 video_title = self._og_search_title(
2431 webpage, default=None) or self._html_search_regex(
2432 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2435 # Try to detect age limit automatically
2436 age_limit = self._rta_search(webpage)
2437 # And then there are the jokers who advertise that they use RTA,
2438 # but actually don't.
2439 AGE_LIMIT_MARKERS = [
2440 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2442 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2445 # video uploader is domain name
2446 video_uploader = self._search_regex(
2447 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2449 video_description = self._og_search_description(webpage, default=None)
2450 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2453 'title': video_title,
2454 'description': video_description,
2455 'thumbnail': video_thumbnail,
2456 'age_limit': age_limit,
2459 # Look for Brightcove Legacy Studio embeds
2460 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2464 'url': smuggle_url(bc_url, {'Referer': url}),
2465 'ie_key': 'BrightcoveLegacy'
2466 } for bc_url in bc_urls]
2469 '_type': 'playlist',
2470 'title': video_title,
2475 # Look for Brightcove New Studio embeds
2476 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2478 return self.playlist_from_matches(
2479 bc_urls, video_id, video_title,
2480 getter=lambda x: smuggle_url(x, {'referrer': url}),
2483 # Look for Nexx embeds
2484 nexx_urls = NexxIE._extract_urls(webpage)
2486 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2488 # Look for Nexx iFrame embeds
2489 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2491 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2493 # Look for ThePlatform embeds
2494 tp_urls = ThePlatformIE._extract_urls(webpage)
2496 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2498 # Look for embedded rtl.nl player
2499 matches = re.findall(
2500 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2503 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2505 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2507 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2509 vid_me_embed_url = self._search_regex(
2510 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2511 webpage, 'vid.me embed', default=None)
2512 if vid_me_embed_url is not None:
2513 return self.url_result(vid_me_embed_url, 'Vidme')
2515 # Look for YouTube embeds
2516 youtube_urls = YoutubeIE._extract_urls(webpage)
2518 return self.playlist_from_matches(
2519 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2521 matches = DailymotionIE._extract_urls(webpage)
2523 return self.playlist_from_matches(matches, video_id, video_title)
2525 # Look for embedded Dailymotion playlist player (#3822)
2527 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2529 playlists = re.findall(
2530 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2532 return self.playlist_from_matches(
2533 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2535 # Look for DailyMail embeds
2536 dailymail_urls = DailyMailIE._extract_urls(webpage)
2538 return self.playlist_from_matches(
2539 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2541 # Look for Teachable embeds, must be before Wistia
2542 teachable_url = TeachableIE._extract_url(webpage, url)
2544 return self.url_result(teachable_url)
2546 # Look for embedded Wistia player
2547 wistia_urls = WistiaIE._extract_urls(webpage)
2549 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2550 for entry in playlist['entries']:
2552 '_type': 'url_transparent',
2553 'uploader': video_uploader,
2557 # Look for SVT player
2558 svt_url = SVTIE._extract_url(webpage)
2560 return self.url_result(svt_url, 'SVT')
2562 # Look for Bandcamp pages with custom domain
2563 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2564 if mobj is not None:
2565 burl = unescapeHTML(mobj.group(1))
2566 # Don't set the extractor because it can be a track url or an album
2567 return self.url_result(burl)
2569 # Look for embedded Vevo player
2571 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'))
2575 # Look for embedded Viddler player
2577 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2579 if mobj is not None:
2580 return self.url_result(mobj.group('url'))
2582 # Look for NYTimes player
2584 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2586 if mobj is not None:
2587 return self.url_result(mobj.group('url'))
2589 # Look for Libsyn player
2591 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2592 if mobj is not None:
2593 return self.url_result(mobj.group('url'))
2595 # Look for Ooyala videos
2596 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2597 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2598 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2599 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2600 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2601 if mobj is not None:
2602 embed_token = self._search_regex(
2603 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2604 webpage, 'ooyala embed token', default=None)
2605 return OoyalaIE._build_url_result(smuggle_url(
2608 'embed_token': embed_token,
2611 # Look for multiple Ooyala embeds on SBN network websites
2612 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2613 if mobj is not None:
2614 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2616 return self.playlist_from_matches(
2617 embeds, video_id, video_title,
2618 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2620 # Look for Aparat videos
2621 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2622 if mobj is not None:
2623 return self.url_result(mobj.group(1), 'Aparat')
2625 # Look for MPORA videos
2626 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2627 if mobj is not None:
2628 return self.url_result(mobj.group(1), 'Mpora')
2630 # Look for embedded Facebook player
2631 facebook_urls = FacebookIE._extract_urls(webpage)
2633 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2635 # Look for embedded VK player
2636 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2637 if mobj is not None:
2638 return self.url_result(mobj.group('url'), 'VK')
2640 # Look for embedded Odnoklassniki player
2641 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2642 if odnoklassniki_url:
2643 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2645 # Look for embedded ivi player
2646 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2647 if mobj is not None:
2648 return self.url_result(mobj.group('url'), 'Ivi')
2650 # Look for embedded Huffington Post player
2652 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2653 if mobj is not None:
2654 return self.url_result(mobj.group('url'), 'HuffPost')
2657 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2658 if mobj is not None:
2659 return self.url_result(mobj.group('url'))
2660 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2661 if mobj is not None:
2662 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2664 # Look for funnyordie embed
2665 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2667 return self.playlist_from_matches(
2668 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2670 # Look for BBC iPlayer embed
2671 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2673 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2675 # Look for embedded RUTV player
2676 rutv_url = RUTVIE._extract_url(webpage)
2678 return self.url_result(rutv_url, 'RUTV')
2680 # Look for embedded TVC player
2681 tvc_url = TVCIE._extract_url(webpage)
2683 return self.url_result(tvc_url, 'TVC')
2685 # Look for embedded SportBox player
2686 sportbox_urls = SportBoxIE._extract_urls(webpage)
2688 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2690 # Look for embedded XHamster player
2691 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2693 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2695 # Look for embedded TNAFlixNetwork player
2696 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2698 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2700 # Look for embedded PornHub player
2701 pornhub_urls = PornHubIE._extract_urls(webpage)
2703 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2705 # Look for embedded DrTuber player
2706 drtuber_urls = DrTuberIE._extract_urls(webpage)
2708 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2710 # Look for embedded RedTube player
2711 redtube_urls = RedTubeIE._extract_urls(webpage)
2713 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2715 # Look for embedded Tube8 player
2716 tube8_urls = Tube8IE._extract_urls(webpage)
2718 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2720 # Look for embedded Spankwire player
2721 spankwire_urls = SpankwireIE._extract_urls(webpage)
2723 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2725 # Look for embedded YouPorn player
2726 youporn_urls = YouPornIE._extract_urls(webpage)
2728 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2730 # Look for embedded Tvigle player
2732 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2733 if mobj is not None:
2734 return self.url_result(mobj.group('url'), 'Tvigle')
2736 # Look for embedded TED player
2738 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2739 if mobj is not None:
2740 return self.url_result(mobj.group('url'), 'TED')
2742 # Look for embedded Ustream videos
2743 ustream_url = UstreamIE._extract_url(webpage)
2745 return self.url_result(ustream_url, UstreamIE.ie_key())
2747 # Look for embedded arte.tv player
2749 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2751 if mobj is not None:
2752 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2754 # Look for embedded francetv player
2756 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2758 if mobj is not None:
2759 return self.url_result(mobj.group('url'))
2761 # Look for embedded smotri.com player
2762 smotri_url = SmotriIE._extract_url(webpage)
2764 return self.url_result(smotri_url, 'Smotri')
2766 # Look for embedded Myvi.ru player
2767 myvi_url = MyviIE._extract_url(webpage)
2769 return self.url_result(myvi_url)
2771 # Look for embedded soundcloud player
2772 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2774 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2776 # Look for tunein player
2777 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2779 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2781 # Look for embedded mtvservices player
2782 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2784 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2786 # Look for embedded yahoo player
2788 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2790 if mobj is not None:
2791 return self.url_result(mobj.group('url'), 'Yahoo')
2793 # Look for embedded sbs.com.au player
2797 <meta\s+property="og:video"\s+content=|
2800 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2802 if mobj is not None:
2803 return self.url_result(mobj.group('url'), 'SBS')
2805 # Look for embedded Cinchcast player
2807 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2809 if mobj is not None:
2810 return self.url_result(mobj.group('url'), 'Cinchcast')
2813 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2817 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2819 if mobj is not None:
2820 return self.url_result(mobj.group('url'), 'MLB')
2823 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2825 if mobj is not None:
2826 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2829 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2831 if mobj is not None:
2832 return self.url_result(mobj.group('url'), 'Livestream')
2834 # Look for Zapiks embed
2836 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2837 if mobj is not None:
2838 return self.url_result(mobj.group('url'), 'Zapiks')
2840 # Look for Kaltura embeds
2841 kaltura_url = KalturaIE._extract_url(webpage)
2843 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2845 # Look for EaglePlatform embeds
2846 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2847 if eagleplatform_url:
2848 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2850 # Look for ClipYou (uses EaglePlatform) embeds
2852 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2853 if mobj is not None:
2854 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2856 # Look for Pladform embeds
2857 pladform_url = PladformIE._extract_url(webpage)
2859 return self.url_result(pladform_url)
2861 # Look for Videomore embeds
2862 videomore_url = VideomoreIE._extract_url(webpage)
2864 return self.url_result(videomore_url)
2866 # Look for Webcaster embeds
2867 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2869 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2871 # Look for Playwire embeds
2873 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2874 if mobj is not None:
2875 return self.url_result(mobj.group('url'))
2877 # Look for 5min embeds
2879 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2880 if mobj is not None:
2881 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2883 # Look for Crooks and Liars embeds
2885 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2886 if mobj is not None:
2887 return self.url_result(mobj.group('url'))
2889 # Look for NBC Sports VPlayer embeds
2890 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2892 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2894 # Look for NBC News embeds
2895 nbc_news_embed_url = re.search(
2896 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2897 if nbc_news_embed_url:
2898 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2900 # Look for Google Drive embeds
2901 google_drive_url = GoogleDriveIE._extract_url(webpage)
2902 if google_drive_url:
2903 return self.url_result(google_drive_url, 'GoogleDrive')
2905 # Look for UDN embeds
2907 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2908 if mobj is not None:
2909 return self.url_result(
2910 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2912 # Look for Senate ISVP iframe
2913 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2915 return self.url_result(senate_isvp_url, 'SenateISVP')
2917 # Look for Kinja embeds
2918 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2919 if kinja_embed_urls:
2920 return self.playlist_from_matches(
2921 kinja_embed_urls, video_id, video_title)
2923 # Look for OnionStudios embeds
2924 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2925 if onionstudios_url:
2926 return self.url_result(onionstudios_url)
2928 # Look for ViewLift embeds
2929 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2931 return self.url_result(viewlift_url)
2933 # Look for JWPlatform embeds
2934 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2936 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2938 # Look for Digiteka embeds
2939 digiteka_url = DigitekaIE._extract_url(webpage)
2941 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2943 # Look for Arkena embeds
2944 arkena_url = ArkenaIE._extract_url(webpage)
2946 return self.url_result(arkena_url, ArkenaIE.ie_key())
2948 # Look for Piksel embeds
2949 piksel_url = PikselIE._extract_url(webpage)
2951 return self.url_result(piksel_url, PikselIE.ie_key())
2953 # Look for Limelight embeds
2954 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2956 return self.playlist_result(
2957 limelight_urls, video_id, video_title, video_description)
2959 # Look for Anvato embeds
2960 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2962 return self.playlist_result(
2963 anvato_urls, video_id, video_title, video_description)
2965 # Look for AdobeTVVideo embeds
2967 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2969 if mobj is not None:
2970 return self.url_result(
2971 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2974 # Look for Vine embeds
2976 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2978 if mobj is not None:
2979 return self.url_result(
2980 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2982 # Look for VODPlatform embeds
2984 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
2986 if mobj is not None:
2987 return self.url_result(
2988 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2990 # Look for Mangomolo embeds
2992 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
2994 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
2995 player\.mangomolo\.com/v1
2998 video\?.*?\bid=(?P<video_id>\d+)|
2999 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3000 ).+?)\1''', webpage)
3001 if mobj is not None:
3003 '_type': 'url_transparent',
3004 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3005 'title': video_title,
3006 'description': video_description,
3007 'thumbnail': video_thumbnail,
3008 'uploader': video_uploader,
3010 video_id = mobj.group('video_id')
3013 'ie_key': 'MangomoloVideo',
3018 'ie_key': 'MangomoloLive',
3019 'id': mobj.group('channel_id'),
3023 # Look for Instagram embeds
3024 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3025 if instagram_embed_url is not None:
3026 return self.url_result(
3027 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3029 # Look for LiveLeak embeds
3030 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3032 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3034 # Look for 3Q SDN embeds
3035 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3038 '_type': 'url_transparent',
3039 'ie_key': ThreeQSDNIE.ie_key(),
3040 'url': self._proto_relative_url(threeqsdn_url),
3041 'title': video_title,
3042 'description': video_description,
3043 'thumbnail': video_thumbnail,
3044 'uploader': video_uploader,
3047 # Look for VBOX7 embeds
3048 vbox7_url = Vbox7IE._extract_url(webpage)
3050 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3052 # Look for DBTV embeds
3053 dbtv_urls = DBTVIE._extract_urls(webpage)
3055 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3057 # Look for Videa embeds
3058 videa_urls = VideaIE._extract_urls(webpage)
3060 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3062 # Look for 20 minuten embeds
3063 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3065 return self.playlist_from_matches(
3066 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3068 # Look for VideoPress embeds
3069 videopress_urls = VideoPressIE._extract_urls(webpage)
3071 return self.playlist_from_matches(
3072 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3074 # Look for Rutube embeds
3075 rutube_urls = RutubeIE._extract_urls(webpage)
3077 return self.playlist_from_matches(
3078 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3080 # Look for WashingtonPost embeds
3081 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3083 return self.playlist_from_matches(
3084 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3086 # Look for Mediaset embeds
3087 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3089 return self.playlist_from_matches(
3090 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3092 # Look for JOJ.sk embeds
3093 joj_urls = JojIE._extract_urls(webpage)
3095 return self.playlist_from_matches(
3096 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3098 # Look for megaphone.fm embeds
3099 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3101 return self.playlist_from_matches(
3102 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3104 # Look for vzaar embeds
3105 vzaar_urls = VzaarIE._extract_urls(webpage)
3107 return self.playlist_from_matches(
3108 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3110 channel9_urls = Channel9IE._extract_urls(webpage)
3112 return self.playlist_from_matches(
3113 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3115 vshare_urls = VShareIE._extract_urls(webpage)
3117 return self.playlist_from_matches(
3118 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3120 # Look for Mediasite embeds
3121 mediasite_urls = MediasiteIE._extract_urls(webpage)
3124 self.url_result(smuggle_url(
3125 compat_urlparse.urljoin(url, mediasite_url),
3126 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3127 for mediasite_url in mediasite_urls]
3128 return self.playlist_result(entries, video_id, video_title)
3130 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3131 if springboardplatform_urls:
3132 return self.playlist_from_matches(
3133 springboardplatform_urls, video_id, video_title,
3134 ie=SpringboardPlatformIE.ie_key())
3136 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3138 return self.playlist_from_matches(
3139 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3141 vice_urls = ViceIE._extract_urls(webpage)
3143 return self.playlist_from_matches(
3144 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3146 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3148 return self.playlist_from_matches(
3149 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3151 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3152 if cloudflarestream_urls:
3153 return self.playlist_from_matches(
3154 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3156 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3158 return self.playlist_from_matches(
3159 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3161 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3163 return self.playlist_from_matches(
3164 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3166 apa_urls = APAIE._extract_urls(webpage)
3168 return self.playlist_from_matches(
3169 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3171 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3173 return self.playlist_from_matches(
3174 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3176 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3177 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3179 if sharevideos_urls:
3180 return self.playlist_from_matches(
3181 sharevideos_urls, video_id, video_title)
3183 viqeo_urls = ViqeoIE._extract_urls(webpage)
3185 return self.playlist_from_matches(
3186 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3188 expressen_urls = ExpressenIE._extract_urls(webpage)
3190 return self.playlist_from_matches(
3191 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3193 zype_urls = ZypeIE._extract_urls(webpage)
3195 return self.playlist_from_matches(
3196 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3198 # Look for HTML5 media
3199 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3201 if len(entries) == 1:
3204 'title': video_title,
3207 for num, entry in enumerate(entries, start=1):
3209 'id': '%s-%s' % (video_id, num),
3210 'title': '%s (%d)' % (video_title, num),
3212 for entry in entries:
3213 self._sort_formats(entry['formats'])
3214 return self.playlist_result(entries, video_id, video_title)
3216 jwplayer_data = self._find_jwplayer_data(
3217 webpage, video_id, transform_source=js_to_json)
3220 info = self._parse_jwplayer_data(
3221 jwplayer_data, video_id, require_title=False, base_url=url)
3222 return merge_dicts(info, info_dict)
3223 except ExtractorError:
3224 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3229 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3231 if mobj is not None:
3232 sources = self._parse_json(
3233 mobj.group(1), video_id, transform_source=js_to_json,
3235 if not isinstance(sources, list):
3238 for source in sources:
3239 src = source.get('src')
3240 if not src or not isinstance(src, compat_str):
3242 src = compat_urlparse.urljoin(url, src)
3243 src_type = source.get('type')
3244 if isinstance(src_type, compat_str):
3245 src_type = src_type.lower()
3246 ext = determine_ext(src).lower()
3247 if src_type == 'video/youtube':
3248 return self.url_result(src, YoutubeIE.ie_key())
3249 if src_type == 'application/dash+xml' or ext == 'mpd':
3250 formats.extend(self._extract_mpd_formats(
3251 src, video_id, mpd_id='dash', fatal=False))
3252 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3253 formats.extend(self._extract_m3u8_formats(
3254 src, video_id, 'mp4', entry_protocol='m3u8_native',
3255 m3u8_id='hls', fatal=False))
3259 'ext': (mimetype2ext(src_type)
3260 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3263 self._sort_formats(formats)
3264 info_dict['formats'] = formats
3267 # Looking for http://schema.org/VideoObject
3268 json_ld = self._search_json_ld(
3269 webpage, video_id, default={}, expected_type='VideoObject')
3270 if json_ld.get('url'):
3271 return merge_dicts(json_ld, info_dict)
3273 def check_video(vurl):
3274 if YoutubeIE.suitable(vurl):
3276 if RtmpIE.suitable(vurl):
3278 vpath = compat_urlparse.urlparse(vurl).path
3279 vext = determine_ext(vpath)
3280 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3282 def filter_video(urls):
3283 return list(filter(check_video, urls))
3285 # Start with something easy: JW Player in SWFObject
3286 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3288 # Look for gorilla-vid style embedding
3289 found = filter_video(re.findall(r'''(?sx)
3293 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3296 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3298 # Broaden the search a little bit
3299 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3301 # Broaden the findall a little bit: JWPlayer JS loader
3302 found = filter_video(re.findall(
3303 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3306 found = filter_video(re.findall(r'''(?xs)
3307 flowplayer\("[^"]+",\s*
3309 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3310 ["']?url["']?\s*:\s*["']([^"']+)["']
3315 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3317 # Try to find twitter cards info
3318 # twitter:player:stream should be checked before twitter:player since
3319 # it is expected to contain a raw stream (see
3320 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3321 found = filter_video(re.findall(
3322 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3324 # We look for Open Graph info:
3325 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3326 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3327 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3328 if m_video_type is not None:
3329 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3331 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3333 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3334 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3337 # Look also in Refresh HTTP header
3338 refresh_header = head_response.headers.get('Refresh')
3340 # In python 2 response HTTP headers are bytestrings
3341 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3342 refresh_header = refresh_header.decode('iso-8859-1')
3343 found = re.search(REDIRECT_REGEX, refresh_header)
3345 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3347 self.report_following_redirect(new_url)
3356 # twitter:player is a https URL to iframe player that may or may not
3357 # be supported by youtube-dl thus this is checked the very last (see
3358 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3359 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3360 if embed_url and embed_url != url:
3361 return self.url_result(embed_url)
3364 raise UnsupportedError(url)
3367 for video_url in orderedSet(found):
3368 video_url = unescapeHTML(video_url)
3369 video_url = video_url.replace('\\/', '/')
3370 video_url = compat_urlparse.urljoin(url, video_url)
3371 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3373 # Sometimes, jwplayer extraction will result in a YouTube URL
3374 if YoutubeIE.suitable(video_url):
3375 entries.append(self.url_result(video_url, 'Youtube'))
3378 # here's a fun little line of code for you:
3379 video_id = os.path.splitext(video_id)[0]
3383 'uploader': video_uploader,
3384 'title': video_title,
3385 'age_limit': age_limit,
3388 if RtmpIE.suitable(video_url):
3389 entry_info_dict.update({
3390 '_type': 'url_transparent',
3391 'ie_key': RtmpIE.ie_key(),
3394 entries.append(entry_info_dict)
3397 ext = determine_ext(video_url)
3399 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3401 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3403 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3405 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3407 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3408 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3409 # Just matching .ism/manifest is not enough to be reliably sure
3410 # whether it's actually an ISM manifest or some other streaming
3411 # manifest since there are various streaming URL formats
3412 # possible (see [1]) as well as some other shenanigans like
3413 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3415 # Thus the most reasonable way to solve this is to delegate
3416 # to generic extractor in order to look into the contents of
3417 # the manifest itself.
3418 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3419 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3420 entry_info_dict = self.url_result(
3421 smuggle_url(video_url, {'to_generic': True}),
3424 entry_info_dict['url'] = video_url
3426 if entry_info_dict.get('formats'):
3427 self._sort_formats(entry_info_dict['formats'])
3429 entries.append(entry_info_dict)
3431 if len(entries) == 1:
3434 for num, e in enumerate(entries, start=1):
3435 # 'url' results don't have a title
3436 if e.get('title') is not None:
3437 e['title'] = '%s (%d)' % (e['title'], num)
3439 '_type': 'playlist',