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,
42 from .commonprotocols import RtmpIE
43 from .brightcove import (
51 from .nbc import NBCSportsVPlayerIE
52 from .ooyala import OoyalaIE
53 from .rutv import RUTVIE
54 from .tvc import TVCIE
55 from .sportbox import SportBoxIE
56 from .myvi import MyviIE
57 from .condenast import CondeNastIE
58 from .udn import UDNEmbedIE
59 from .senateisvp import SenateISVPIE
60 from .svt import SVTIE
61 from .pornhub import PornHubIE
62 from .xhamster import XHamsterEmbedIE
63 from .tnaflix import TNAFlixNetworkEmbedIE
64 from .drtuber import DrTuberIE
65 from .redtube import RedTubeIE
66 from .tube8 import Tube8IE
67 from .mofosex import MofosexEmbedIE
68 from .spankwire import SpankwireIE
69 from .youporn import YouPornIE
74 from .dailymotion import DailymotionIE
75 from .dailymail import DailyMailIE
76 from .onionstudios import OnionStudiosIE
77 from .viewlift import ViewLiftEmbedIE
78 from .mtv import MTVServicesEmbeddedIE
79 from .pladform import PladformIE
80 from .videomore import VideomoreIE
81 from .webcaster import WebcasterFeedIE
82 from .googledrive import GoogleDriveIE
83 from .jwplatform import JWPlatformIE
84 from .digiteka import DigitekaIE
85 from .arkena import ArkenaIE
86 from .instagram import InstagramIE
87 from .liveleak import LiveLeakIE
88 from .threeqsdn import ThreeQSDNIE
89 from .theplatform import ThePlatformIE
90 from .kaltura import KalturaIE
91 from .eagleplatform import EaglePlatformIE
92 from .facebook import FacebookIE
93 from .soundcloud import SoundcloudEmbedIE
94 from .tunein import TuneInBaseIE
95 from .vbox7 import Vbox7IE
96 from .dbtv import DBTVIE
97 from .piksel import PikselIE
98 from .videa import VideaIE
99 from .twentymin import TwentyMinutenIE
100 from .ustream import UstreamIE
101 from .arte import ArteTVEmbedIE
102 from .videopress import VideoPressIE
103 from .rutube import RutubeIE
104 from .limelight import LimelightBaseIE
105 from .anvato import AnvatoIE
106 from .washingtonpost import WashingtonPostIE
107 from .wistia import WistiaIE
108 from .mediaset import MediasetIE
109 from .joj import JojIE
110 from .megaphone import MegaphoneIE
111 from .vzaar import VzaarIE
112 from .channel9 import Channel9IE
113 from .vshare import VShareIE
114 from .mediasite import MediasiteIE
115 from .springboardplatform import SpringboardPlatformIE
116 from .yapfiles import YapFilesIE
117 from .vice import ViceIE
118 from .xfileshare import XFileShareIE
119 from .cloudflarestream import CloudflareStreamIE
120 from .peertube import PeerTubeIE
121 from .teachable import TeachableIE
122 from .indavideo import IndavideoEmbedIE
123 from .apa import APAIE
124 from .foxnews import FoxNewsIE
125 from .viqeo import ViqeoIE
126 from .expressen import ExpressenIE
127 from .zype import ZypeIE
128 from .odnoklassniki import OdnoklassnikiIE
130 from .kinja import KinjaEmbedIE
131 from .arcpublishing import ArcPublishingIE
132 from .medialaan import MedialaanIE
133 from .simplecast import SimplecastIE
136 class GenericIE(InfoExtractor):
137 IE_DESC = 'Generic downloader that works on some sites'
141 # Direct link to a video
143 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
144 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
149 'upload_date': '20100513',
152 # Direct link to media delivered compressed (until Accept-Encoding is *)
154 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
155 'md5': '128c42e68b13950268b648275386fc74',
157 'id': 'FictionJunction-Parallel_Hearts',
159 'title': 'FictionJunction-Parallel_Hearts',
160 'upload_date': '20140522',
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
165 'skip': 'URL invalid',
167 # Direct download with broken HEAD
169 'url': 'http://ai-radio.org:8000/radio.opus',
176 'skip_download': True, # infinite live stream
178 'expected_warnings': [
179 r'501.*Not Implemented',
183 # Direct link with incorrect MIME type
185 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
186 'md5': '4ccbebe5f36706d85221f204d7eb5913',
188 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
189 'id': '5_Lennart_Poettering_-_Systemd',
191 'title': '5_Lennart_Poettering_-_Systemd',
192 'upload_date': '20141120',
194 'expected_warnings': [
195 'URL could be a direct video link, returning it as such.'
200 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
202 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
203 'title': 'Zero Punctuation',
204 'description': 're:.*groundbreaking video review series.*'
206 'playlist_mincount': 11,
208 # RSS feed with enclosure
210 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
212 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
213 'title': 'MSNBC Rachel Maddow (video)',
214 'description': 're:.*her unique approach to storytelling.*',
219 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
220 'title': 're:MSNBC Rachel Maddow',
221 'description': 're:.*her unique approach to storytelling.*',
223 'upload_date': compat_str,
228 # RSS feed with item with description and thumbnails
230 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
232 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'title': 're:.*100% Hydrogen.*',
234 'description': 're:.*In this episode.*',
239 'id': 'c1c879525ce2cb640b344507e682c36d',
240 'title': 're:Hydrogen!',
241 'description': 're:.*In this episode we are going.*',
242 'timestamp': 1567977776,
243 'upload_date': '20190908',
245 'thumbnail': r're:^https?://.*\.jpg$',
252 'skip_download': True,
255 # RSS feed with enclosures and unsupported link URLs
257 'url': 'http://www.hellointernet.fm/podcast?format=rss',
259 'id': 'http://www.hellointernet.fm/podcast?format=rss',
260 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
261 'title': 'Hello Internet',
263 'playlist_mincount': 100,
265 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
267 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
271 'title': 'Automatics, robotics and biocybernetics',
272 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
273 'upload_date': '20130627',
274 'formats': 'mincount:16',
275 'subtitles': 'mincount:1',
278 'force_generic_extractor': True,
279 'skip_download': True,
282 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
284 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
289 'formats': 'mincount:1',
292 'skip_download': True,
295 # SMIL from https://www.restudy.dk/video/play/id/1637
297 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
301 'title': 'video_1637',
302 'formats': 'mincount:3',
305 'skip_download': True,
308 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
310 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
312 'id': 'smil-service',
314 'title': 'smil-service',
315 'formats': 'mincount:1',
318 'skip_download': True,
321 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
323 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
327 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
328 'formats': 'mincount:3',
331 'skip_download': True,
334 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
336 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
338 'id': 'mZlp2ctYIUEB',
340 'title': 'Tikibad ontruimd wegens brand',
341 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
342 'thumbnail': r're:^https?://.*\.jpg$',
346 'skip_download': True,
349 # MPD from http://dash-mse-test.appspot.com/media.html
351 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
352 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
354 'id': 'car-20120827-manifest',
356 'title': 'car-20120827-manifest',
357 'formats': 'mincount:9',
358 'upload_date': '20130904',
361 'format': 'bestvideo',
364 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
366 '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',
371 'formats': 'mincount:8',
375 'skip_download': True,
377 'skip': 'video gone',
379 # m3u8 served with Content-Type: text/plain
381 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
386 'upload_date': '20140720',
387 'formats': 'mincount:11',
391 'skip_download': True,
393 'skip': 'video gone',
397 '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',
401 'upload_date': '20130224',
402 'uploader_id': 'TheVerge',
403 'description': r're:^Chris Ziegler takes a look at the\.*',
404 'uploader': 'The Verge',
405 'title': 'First Firefox OS phones side-by-side',
408 'skip_download': False,
412 # redirect in Refresh HTTP header
413 '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',
417 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
418 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
419 'upload_date': '20150917',
420 'uploader_id': 'brtvofficial',
421 'uploader': 'Boiler Room',
424 'skip_download': False,
428 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
429 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
431 'id': '13601338388002',
433 'uploader': 'www.hodiho.fr',
434 'title': 'R\u00e9gis plante sa Jeep',
437 # bandcamp page with custom domain
439 'add_ie': ['Bandcamp'],
440 'url': 'http://bronyrock.com/track/the-pony-mash',
444 'title': 'The Pony Mash',
445 'uploader': 'M_Pallante',
447 'skip': 'There is a limit of 200 free downloads / month for the test song',
450 # embedded brightcove video
451 # it also tests brightcove videos that need to set the 'Referer'
452 # in the http requests
453 'add_ie': ['BrightcoveLegacy'],
454 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
456 'id': '2765128793001',
458 'title': 'Le cours de bourse : l’analyse technique',
459 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
460 'uploader': 'BFM BUSINESS',
463 'skip_download': True,
467 # embedded with itemprop embedURL and video id spelled as `idVideo`
468 'add_id': ['BrightcoveLegacy'],
469 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
471 'id': '5255628253001',
473 'title': 'md5:37c519b1128915607601e75a87995fc0',
474 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
475 'uploader': 'BFM BUSINESS',
476 'uploader_id': '876450612001',
477 'timestamp': 1482255315,
478 'upload_date': '20161220',
481 'skip_download': True,
485 # https://github.com/ytdl-org/youtube-dl/issues/2253
486 'url': 'http://bcove.me/i6nfkrc3',
487 'md5': '0ba9446db037002366bab3b3eb30c88c',
489 'id': '3101154703001',
491 'title': 'Still no power',
492 'uploader': 'thestar.com',
493 '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.',
495 'add_ie': ['BrightcoveLegacy'],
496 'skip': 'video gone',
499 'url': 'http://www.championat.com/video/football/v/87/87499.html',
500 'md5': 'fb973ecf6e4a78a67453647444222983',
502 'id': '3414141473001',
504 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
505 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
506 'uploader': 'Championat',
510 # https://github.com/ytdl-org/youtube-dl/issues/3541
511 'add_ie': ['BrightcoveLegacy'],
512 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
514 'id': '3866516442001',
516 'title': 'Leer mij vrouwen kennen: Aflevering 1',
517 'description': 'Leer mij vrouwen kennen: Aflevering 1',
518 'uploader': 'SBS Broadcasting',
520 'skip': 'Restricted to Netherlands',
522 'skip_download': True, # m3u8 download
526 # Brightcove video in <iframe>
527 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
528 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
530 'id': '5360463607001',
532 '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',
533 '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。',
534 'uploader': 'United Nations',
535 'uploader_id': '1362235914001',
536 'timestamp': 1489593889,
537 'upload_date': '20170315',
539 'add_ie': ['BrightcoveLegacy'],
542 # Brightcove with alternative playerID key
543 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
545 'id': 'nmeth.2062_SV1',
546 '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',
550 'id': '2228375078001',
552 'title': 'nmeth.2062-sv1',
553 'description': 'nmeth.2062-sv1',
554 'timestamp': 1363357591,
555 'upload_date': '20130315',
556 'uploader': 'Nature Publishing Group',
557 'uploader_id': '1964492299001',
562 # Brightcove with UUID in videoPlayer
563 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'id': '5255815316001',
567 'title': 'Sprocket Video - China',
568 'description': 'Sprocket Video - China',
569 'uploader': 'HP-Video Gallery',
570 'timestamp': 1482263210,
571 'upload_date': '20161220',
572 'uploader_id': '1107601872001',
575 'skip_download': True, # m3u8 download
577 'skip': 'video rotates...weekly?',
580 # Brightcove:new type [2].
581 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
582 'md5': '2b35148fcf48da41c9fb4591650784f3',
584 'id': '5348741021001',
586 'upload_date': '20170306',
587 'uploader_id': '4191638492001',
588 'timestamp': 1488769918,
589 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
594 # Alternative brightcove <video> attributes
595 '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/',
597 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
598 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
601 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
603 'id': '5311302538001',
605 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
606 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
607 'timestamp': 1486321708,
608 'upload_date': '20170205',
609 'uploader_id': '800000640001',
611 'only_matching': True,
615 # Brightcove with UUID in videoPlayer
616 'url': 'http://www8.hp.com/cn/zh/home.html',
618 'id': '5255815316001',
620 'title': 'Sprocket Video - China',
621 'description': 'Sprocket Video - China',
622 'uploader': 'HP-Video Gallery',
623 'timestamp': 1482263210,
624 'upload_date': '20161220',
625 'uploader_id': '1107601872001',
628 'skip_download': True, # m3u8 download
633 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
634 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
636 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
638 'title': '2cc213299525360.mov', # that's what we get
641 'add_ie': ['Ooyala'],
644 # ooyala video embedded with http://player.ooyala.com/iframe.js
645 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
647 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
649 'title': '"Steve Jobs: Man in the Machine" trailer',
650 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
654 'skip_download': True,
656 'skip': 'movie expired',
658 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
660 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
662 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
664 'title': 'Steampunk Fest Comes to Honesdale',
668 'skip_download': True,
673 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
677 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
678 'upload_date': '20140225',
679 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
680 'uploader': 'Tested',
681 'uploader_id': 'testedcom',
683 # No need to test YoutubeIE here
685 'skip_download': True,
690 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
694 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
695 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
697 # HEAD requests lead to endless 301, while GET is OK
698 'expected_warnings': ['301'],
702 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
706 'title': 'Охотское море стало целиком российским',
707 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
711 'skip_download': True,
716 '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/',
720 'title': 'Дошкольное воспитание',
725 'url': 'http://www.vestifinance.ru/articles/25753',
728 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
733 'title': 'Госзаказ. День 3',
739 'title': 'Госзаказ. День 2',
745 'title': 'Госзаказ. День 1',
751 'skip_download': True,
756 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
758 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
760 'title': 'Ужастики, русский трейлер (2015)',
761 'thumbnail': r're:^https?://.*\.jpg$',
767 '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',
770 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
772 'playlist_mincount': 7,
773 # This forum does not allow <iframe> syntaxes anymore
774 # Now HTML tags are displayed as-is
775 'skip': 'No videos on this page',
779 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
780 'md5': '65fdff94098e4a607385a60c5177c638',
784 'title': 'Hidden miracles of the natural world',
785 'uploader': 'Louie Schwartzberg',
786 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
789 # nowvideo embed hidden behind percent encoding
791 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
792 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
794 'id': '06e53103ca9aa',
796 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
797 'description': 'No description',
802 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
803 'md5': '7653032cbb25bf6c80d80f217055fa43',
805 'id': '048195-004_PLUS7-F',
808 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
809 'upload_date': '20140320',
812 'skip_download': 'Requires rtmpdump'
814 'skip': 'video gone',
818 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
822 'title': 'Alcaline, le concert avec Calogero',
823 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
824 'upload_date': '20150226',
825 'timestamp': 1424989860,
830 'skip_download': True,
832 'expected_warnings': [
838 'url': 'http://www.wired.com/2014/04/honda-asimo/',
839 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
841 'id': '53501be369702d3275860000',
843 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
848 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
849 'md5': '441aeeb82eb72c422c7f14ec533999cd',
851 'id': 'k2mm4bCdJ6CQ2i7c8o2',
853 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
854 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
856 'uploader_id': 'xgditw',
857 'upload_date': '20140425',
858 'timestamp': 1398441542,
860 'add_ie': ['Dailymotion'],
864 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
868 'title': 'Care worker punches elderly dementia patient in head 11 times',
869 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
871 'add_ie': ['DailyMail'],
873 'skip_download': True,
878 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
882 'title': 'The NBL Auction 2014',
883 'uploader': 'BADMINTON England',
884 'uploader_id': 'BADMINTONEvents',
885 'upload_date': '20140603',
886 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
888 'add_ie': ['Youtube'],
890 'skip_download': True,
895 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
896 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
898 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
900 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
901 'description': 'Two valets share their love for movie star Liam Neesons.',
902 'timestamp': 1349922600,
903 'upload_date': '20121011',
906 # YouTube embed via <data-embed-url="">
908 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
912 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
913 'uploader': 'Gameloft',
914 'uploader_id': 'gameloft',
915 'upload_date': '20140828',
916 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
919 'skip_download': True,
922 # YouTube <object> embed
924 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
925 'md5': '516718101ec834f74318df76259fb3cc',
929 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
930 'upload_date': '20080526',
931 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
932 'uploader': 'Christopher Sykes',
933 'uploader_id': 'ChristopherJSykes',
935 'add_ie': ['Youtube'],
939 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
941 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
943 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
944 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
949 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
951 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
952 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
958 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
963 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
964 'md5': '9d65602bf31c6e20014319c7d07fba27',
966 'id': '5123ea6d5e5a7',
969 'uploader': 'www.handjobhub.com',
970 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
973 # Multiple brightcove videos
974 # https://github.com/ytdl-org/youtube-dl/issues/2283
976 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
978 'id': 'always-never',
979 'title': 'Always / Never - The New Yorker',
983 'extract_flat': False,
984 'skip_download': True,
989 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
990 'md5': '96f09a37e44da40dd083e12d9a683327',
994 'title': 'Ump changes call to ball',
995 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
997 'timestamp': 1401537900,
998 'upload_date': '20140531',
999 'thumbnail': r're:^https?://.*\.jpg$',
1004 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1005 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1009 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1010 'description': 'a Paywall Videos video from Remilon',
1011 'duration': 644.072,
1012 'uploader': 'study.com',
1013 'timestamp': 1459678540,
1014 'upload_date': '20160403',
1015 'filesize': 24687186,
1019 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1020 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1024 'title': 'Conversation about Hexagonal Rails Part 1',
1025 'description': 'a Martin Fowler video from ThoughtWorks',
1027 'uploader': 'thoughtworks.wistia.com',
1028 'timestamp': 1401832161,
1029 'upload_date': '20140603',
1032 # Wistia standard embed (async)
1034 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1038 'title': 'Drip Brennan Dunn Workshop',
1039 'description': 'a JV Webinars video from getdrip-1',
1040 'duration': 4986.95,
1041 'timestamp': 1463607249,
1042 'upload_date': '20160518',
1045 'skip_download': True,
1050 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1054 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1055 'uploader': 'Sophos Security',
1056 'title': 'Chet Chat 171 - Oct 29, 2014',
1057 'upload_date': '20141029',
1060 # Soundcloud multiple embeds
1062 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1065 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1067 'playlist_mincount': 7,
1069 # TuneIn station embed
1071 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1076 'location': 'Paris, France',
1081 'skip_download': True,
1086 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1090 'upload_date': '20141112',
1091 'title': 'Rosetta #CometLanding webcast HL 10',
1094 # Another Livestream embed, without 'new.' in URL
1096 'url': 'https://www.freespeech.org/',
1100 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1104 'skip_download': True,
1109 'url': 'https://skiplagged.com/',
1112 'title': 'Skiplagged: The smart way to find cheap flights',
1114 'playlist_mincount': 1,
1115 'add_ie': ['Youtube'],
1119 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1123 'upload_date': '20141126',
1124 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1129 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1131 'id': '730m_DandD_1901_512k',
1133 'uploader': 'www.abc.net.au',
1134 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1137 # embedded viddler video
1139 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1143 'uploader': 'deadspin',
1144 'title': 'WALL-TO-GORTAT',
1145 'timestamp': 1422285291,
1146 'upload_date': '20150126',
1148 'add_ie': ['Viddler'],
1152 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1156 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1157 'description': 'md5:601cb790edd05908957dae8aaa866465',
1158 'upload_date': '20150220',
1160 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1164 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1166 'id': 'Mrj4DVp2zeA',
1168 'upload_date': '20150212',
1169 'uploader': 'The National Archives UK',
1170 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1171 'uploader_id': 'NationalArchives08',
1172 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1177 'url': 'http://www.suffolk.edu/sjc/live.php',
1181 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1182 'uploader': 'www.suffolk.edu',
1185 'skip_download': True,
1187 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1191 'url': 'http://www.indiedb.com/games/king-machine/videos',
1195 'title': 'king machine trailer 1',
1196 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1197 'thumbnail': r're:^https?://.*\.jpg$',
1201 # JWPlayer config passed as variable
1202 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1206 'title': 'ARIELE | Tube Cup',
1207 'uploader': 'www.txxx.com',
1211 'skip_download': True,
1216 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1217 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1221 'upload_date': '20171122',
1222 'timestamp': 1511366290,
1223 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1225 'add_ie': [JWPlatformIE.ie_key()],
1228 # Video.js embed, multiple formats
1229 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1231 'id': 'yygqldloqIk',
1233 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1234 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1235 'upload_date': '20130314',
1236 'uploader': 'PROстое3D',
1237 'uploader_id': 'PROstoe3D',
1240 'skip_download': True,
1244 # Video.js embed, single format
1245 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1249 'title': 'Step 1 - Good Foundation',
1250 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1253 'skip_download': True,
1258 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1259 'playlist_mincount': 5,
1261 'id': 'aanslagen-kopenhagen',
1262 'title': 'Aanslagen Kopenhagen',
1267 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1271 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1274 # Kaltura embed (different embed code)
1276 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1280 'upload_date': '20150127',
1281 'uploader_id': 'PremierMedia',
1283 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1286 # Kaltura embed with single quotes
1288 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1293 'timestamp': 1355743100,
1294 'upload_date': '20121217',
1295 'uploader_id': 'cplapp@learn360.com',
1297 'add_ie': ['Kaltura'],
1300 # Kaltura embedded via quoted entry_id
1301 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1305 'title': '06_matthew_brender_raj_dutt',
1306 'timestamp': 1466638791,
1307 'upload_date': '20160622',
1309 'add_ie': ['Kaltura'],
1310 'expected_warnings': [
1311 'Could not send HEAD request'
1314 'skip_download': True,
1318 # Kaltura embedded, some fileExt broken (#11480)
1319 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1323 'title': 'Our "Standard Models" of particle physics and cosmology',
1324 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1325 'timestamp': 1321158993,
1326 'upload_date': '20111113',
1327 'uploader_id': 'kps1',
1329 'add_ie': ['Kaltura'],
1332 # Kaltura iframe embed
1333 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1334 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1338 'title': 'I. M. Pei: A Centennial Celebration',
1339 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1340 'upload_date': '20170403',
1341 'uploader_id': 'batchUser',
1342 'timestamp': 1491232186,
1344 'add_ie': ['Kaltura'],
1347 # Kaltura iframe embed, more sophisticated
1348 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1352 'title': 'lecture-05sep2017',
1353 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1354 'upload_date': '20170913',
1355 'uploader_id': 'eps2',
1356 'timestamp': 1505340777,
1359 'skip_download': True,
1361 'add_ie': ['Kaltura'],
1364 # meta twitter:player
1365 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1369 'title': 'Main Twerk (Video)',
1370 'upload_date': '20171208',
1371 'uploader_id': 'sebastian.salinas@thechive.com',
1372 'timestamp': 1512713057,
1375 'skip_download': True,
1377 'add_ie': ['Kaltura'],
1379 # referrer protected EaglePlatform embed
1381 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1385 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1386 'thumbnail': r're:^https?://.*\.jpg$',
1391 'skip_download': True,
1394 # ClipYou (EaglePlatform) embed (custom URL)
1396 'url': 'http://muz-tv.ru/play/7129/',
1397 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1401 'title': "'O Sole Mio",
1402 'thumbnail': r're:^https?://.*\.jpg$',
1407 'skip_download': True,
1409 'skip': 'This video is unavailable.',
1413 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1417 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1418 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1419 'thumbnail': r're:^https?://.*\.jpg$',
1423 'skip': 'HTTP Error 404: Not Found',
1427 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1431 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1432 'thumbnail': r're:^https?://.*\.png$',
1438 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1439 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1443 'title': 'Facebook Creates "On This Day" | Crunch Report',
1444 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1445 'timestamp': 1427237531,
1446 'uploader': 'Crunch Report',
1447 'upload_date': '20150324',
1451 'skip_download': True,
1454 # Crooks and Liars embed
1456 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1460 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1461 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1462 'timestamp': 1428207000,
1463 'upload_date': '20150405',
1464 'uploader': 'Heather',
1467 # Crooks and Liars external embed
1469 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1471 'id': 'MTE3MjUtMzQ2MzA',
1473 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1474 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1475 'timestamp': 1265032391,
1476 'upload_date': '20100201',
1477 'uploader': 'Heather',
1480 # NBC Sports vplayer embed
1482 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1484 'id': 'ln7x1qSThw4k',
1486 'title': "PFT Live: New leader in the 'new-look' defense",
1487 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1488 'uploader': 'NBCU-SPORTS',
1489 'upload_date': '20140107',
1490 'timestamp': 1389118457,
1492 'skip': 'Invalid Page URL',
1496 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1497 'md5': '1aa589c675898ae6d37a17913cf68d66',
1499 'id': 'x_dtl_oa_LettermanliftPR_160608',
1501 'title': 'David Letterman: A Preview',
1502 '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.',
1503 'upload_date': '20160609',
1504 'timestamp': 1465431544,
1505 'uploader': 'NBCU-NEWS',
1510 'url': 'https://video.udn.com/news/300346',
1511 'md5': 'fd2060e988c326991037b9aff9df21a6',
1515 'title': '中一中男師變性 全校師生力挺',
1516 'thumbnail': r're:^https?://.*\.jpg$',
1520 'skip_download': True,
1522 'expected_warnings': ['Failed to parse JSON Expecting value'],
1524 # Brightcove URL in single quotes
1526 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1527 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1529 'id': '4255764656001',
1531 'title': 'SN Presents: Russell Martin, World Citizen',
1532 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1533 'uploader': 'Rogers Sportsnet',
1534 'uploader_id': '1704050871',
1535 'upload_date': '20150525',
1536 'timestamp': 1432570283,
1541 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1545 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1546 'description': 'Migrated from OnionStudios',
1547 'thumbnail': r're:^https?://.*\.jpe?g$',
1548 'uploader': 'clickhole',
1549 'upload_date': '20150527',
1550 'timestamp': 1432744860,
1555 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1557 'id': '74849a00-85a9-11e1-9660-123139220831',
1559 'title': '#whilewewatch',
1562 # AdobeTVVideo embed
1564 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1565 'md5': '43662b577c018ad707a63766462b1e87',
1569 'title': 'New experience with Acrobat DC',
1570 'description': 'New experience with Acrobat DC',
1571 'duration': 248.667,
1574 # BrightcoveInPageEmbed embed
1576 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1578 'id': '4238694884001',
1580 'title': 'Tabletop: Dread, Last Thoughts',
1581 'description': 'Tabletop: Dread, Last Thoughts',
1585 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1586 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1588 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1590 'id': '4785848093001',
1592 'title': 'The Cardinal Pell Interview',
1593 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1594 'uploader': 'GlobeCast Australia - GlobeStream',
1595 'uploader_id': '2733773828001',
1596 'upload_date': '20160304',
1597 'timestamp': 1457083087,
1601 'skip_download': True,
1605 # Brightcove embed with whitespace around attribute names
1606 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1608 'id': '3167554373001',
1610 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1611 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1612 'uploader_id': '1079349493',
1613 'upload_date': '20140207',
1614 'timestamp': 1391810548,
1617 'skip_download': True,
1620 # Another form of arte.tv embed
1622 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1623 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1625 'id': '030273-562_PLUS7-F',
1627 'title': 'ARTE Reportage - Nulle part, en France',
1628 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1629 'upload_date': '20160409',
1634 'url': 'http://www.wykop.pl/link/3088787/',
1635 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1637 'id': '874_1459135191',
1639 'title': 'Man shows poor quality of new apartment building',
1640 'description': 'The wall is like a sand pile.',
1641 'uploader': 'Lake8737',
1643 'add_ie': [LiveLeakIE.ie_key()],
1645 # Another LiveLeak embed pattern (#13336)
1647 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1649 'id': '2eb_1496309988',
1651 'title': 'Thief robs place where everyone was armed',
1652 'description': 'md5:694d73ee79e535953cf2488562288eee',
1653 'uploader': 'brazilwtf',
1655 'add_ie': [LiveLeakIE.ie_key()],
1657 # Duplicated embedded video URLs
1659 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1661 'id': '149298443_480_16c25b74_2',
1663 'title': 'vs. Blue Orange Spring Game',
1664 'uploader': 'www.hudl.com',
1667 # twitter:player:stream embed
1669 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1673 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1674 'uploader': 'www.rtl.be',
1678 'skip_download': True,
1681 # twitter:player embed
1683 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1684 'md5': 'a3e0df96369831de324f0778e126653c',
1686 'id': '4909620399001',
1688 'title': 'What Do Black Holes Sound Like?',
1689 'description': 'what do black holes sound like',
1690 'upload_date': '20160524',
1691 'uploader_id': '29913724001',
1692 'timestamp': 1464107587,
1693 'uploader': 'TheAtlantic',
1695 'add_ie': ['BrightcoveLegacy'],
1697 # Facebook <iframe> embed
1699 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1700 'md5': 'fbcde74f534176ecb015849146dd3aee',
1702 'id': '599637780109885',
1704 'title': 'Facebook video #599637780109885',
1707 # Facebook <iframe> embed, plugin video
1709 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1711 'id': '1754168231264132',
1713 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1714 'uploader': 'Tariq Ramadan (official)',
1715 'timestamp': 1496758379,
1716 'upload_date': '20170606',
1719 'skip_download': True,
1722 # Facebook API embed
1724 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1725 'md5': 'a47372ee61b39a7b90287094d447d94e',
1727 'id': '10153467542406923',
1729 'title': 'Facebook video #10153467542406923',
1732 # Wordpress "YouTube Video Importer" plugin
1734 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1735 'md5': 'd16797741b560b485194eddda8121b48',
1737 'id': 'HNTXWDXV9Is',
1739 'title': 'Blue Devils Drumline Stanford lot 2016',
1740 'upload_date': '20160627',
1741 'uploader_id': 'GENOCIDE8GENERAL10',
1742 'uploader': 'cylus cyrus',
1746 # video stored on custom kaltura server
1747 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1748 'md5': '537617d06e64dfed891fa1593c4b30cc',
1752 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1753 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1754 'uploader_id': 'videos.expansion@el-mundo.net',
1755 'upload_date': '20150429',
1756 'timestamp': 1430303472,
1758 'add_ie': ['Kaltura'],
1761 # multiple kaltura embeds, nsfw
1762 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1764 'id': 'kamila-avec-video-jaime-sadomie',
1765 'title': "Kamila avec vídeo “J'aime sadomie”",
1767 'playlist_count': 8,
1770 # Non-standard Vimeo embed
1771 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1772 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1776 'title': 'Understanding the web - Teaser',
1777 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1778 'upload_date': '20151214',
1779 'uploader': 'OpenClassrooms',
1780 'uploader_id': 'openclassrooms',
1782 'add_ie': ['Vimeo'],
1785 # generic vimeo embed that requires original URL passed as Referer
1786 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1787 'only_matching': True,
1790 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1791 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1793 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1795 'title': 'Big Buck Bunny',
1796 'description': 'Royalty free test video',
1797 'timestamp': 1432816365,
1798 'upload_date': '20150528',
1802 'skip_download': True,
1804 'add_ie': [ArkenaIE.ie_key()],
1807 '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/',
1811 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1814 'skip_download': True,
1816 'add_ie': [Vbox7IE.ie_key()],
1820 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1823 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1825 'playlist_mincount': 3,
1829 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1831 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1832 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1834 'playlist_mincount': 2,
1838 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1842 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1843 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1846 'skip_download': True,
1848 'add_ie': [TwentyMinutenIE.ie_key()],
1852 'url': 'https://en.support.wordpress.com/videopress/',
1856 'title': 'IMG_5786',
1857 'timestamp': 1435711927,
1858 'upload_date': '20150701',
1861 'skip_download': True,
1863 'add_ie': [VideoPressIE.ie_key()],
1867 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1869 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1871 'title': 'Магаззино: Казань 2',
1872 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1873 'uploader': 'Магаззино',
1874 'upload_date': '20170228',
1875 'uploader_id': '996642',
1878 'skip_download': True,
1880 'add_ie': [RutubeIE.ie_key()],
1883 # ThePlatform embedded with whitespaces in URLs
1884 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1885 'only_matching': True,
1888 # Senate ISVP iframe https
1889 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1890 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1892 'id': 'govtaff020316',
1894 'title': 'Integrated Senate Video Player',
1896 'add_ie': [SenateISVPIE.ie_key()],
1899 # Limelight embeds (1 channel embed + 4 media embeds)
1900 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1902 'id': 'FacilitatorTraining2017',
1903 'title': 'Facilitator Training 2017',
1905 'playlist_mincount': 5,
1908 # Limelight embed (LimelightPlayerUtil.embed)
1909 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1911 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1913 'title': '07448641',
1914 'timestamp': 1499890639,
1915 'upload_date': '20170712',
1918 'skip_download': True,
1920 'add_ie': ['LimelightMedia'],
1923 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1925 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1926 'title': 'Standoff with Walnut Creek murder suspect ends',
1927 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1929 'playlist_mincount': 4,
1932 # WashingtonPost embed
1933 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1935 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1937 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1938 '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.',
1939 'timestamp': 1455216756,
1940 'uploader': 'The Washington Post',
1941 'upload_date': '20160211',
1943 'add_ie': [WashingtonPostIE.ie_key()],
1947 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1951 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1954 'skip_download': True,
1956 'add_ie': [MediasetIE.ie_key()],
1960 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1962 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1963 'title': 'Slovenskom sa prehnala vlna silných búrok',
1965 'playlist_mincount': 5,
1966 'add_ie': [JojIE.ie_key()],
1969 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1970 'url': 'https://tvrain.ru/amp/418921/',
1971 'md5': 'cc00413936695987e8de148b67d14f1d',
1975 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1980 'url': 'http://help.vzaar.com/article/165-embedding-video',
1981 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1985 'title': 'Building A Business Online: Principal Chairs Q & A',
1989 # multiple HTML5 videos on one page
1990 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1992 'id': 'keyscenarios',
1993 'title': 'Rescue Kit 14 Free Edition - Getting started',
1995 'playlist_count': 4,
1999 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
2000 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
2003 'title': 'vl14062007715967',
2008 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2009 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2011 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2013 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2014 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2015 'timestamp': 1474354800,
2016 'upload_date': '20160920',
2020 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2024 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2025 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2026 'timestamp': 1516100691,
2027 'upload_date': '20180116',
2030 'skip_download': True,
2032 'add_ie': [SpringboardPlatformIE.ie_key()],
2035 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2037 'id': 'vMDE4NzI1Mjgt690b',
2041 'add_ie': [YapFilesIE.ie_key()],
2043 'skip_download': True,
2047 # CloudflareStream embed
2048 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2050 'id': '31c9291ab41fac05471db4e73aa11717',
2052 'title': '31c9291ab41fac05471db4e73aa11717',
2054 'add_ie': [CloudflareStreamIE.ie_key()],
2056 'skip_download': True,
2061 'url': 'https://joinpeertube.org/fr/home/',
2064 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2066 'playlist_count': 2,
2070 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2074 'title': 'Így kell otthon hamburgert sütni',
2075 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2076 'timestamp': 1426330212,
2077 'upload_date': '20150314',
2078 'uploader': 'StreetKitchen',
2079 'uploader_id': '546363',
2081 'add_ie': [IndavideoEmbedIE.ie_key()],
2083 'skip_download': True,
2087 # APA embed via JWPlatform embed
2088 'url': 'http://www.vol.at/blue-man-group/5593454',
2092 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2093 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2094 'thumbnail': r're:^https?://.*\.jpg$',
2096 'timestamp': 1519211149,
2097 'upload_date': '20180221',
2100 'skip_download': True,
2104 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2105 'md5': 'b68d276de422ab07ee1d49388103f457',
2108 'title': 'Lock up and get excited',
2111 'skip': 'TODO: fix nested playlists processing in tests',
2115 'url': 'https://viqeo.tv/',
2118 'title': 'All-new video platform',
2120 'playlist_count': 6,
2123 # Squarespace video embed, 2019-08-28
2124 'url': 'http://ootboxford.com',
2126 'id': 'Tc7b_JGdZfw',
2127 'title': 'Out of the Blue, at Childish Things 10',
2129 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2130 'uploader_id': 'helendouglashouse',
2131 'uploader': 'Helen & Douglas House',
2132 'upload_date': '20140328',
2135 'skip_download': True,
2140 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2142 # 'id': '5b400b834b32992a310622b9',
2144 # 'title': 'Smoky Barbecue Favorites',
2145 # 'thumbnail': r're:^https?://.*\.jpe?g',
2146 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2147 # 'upload_date': '20170909',
2148 # 'timestamp': 1504915200,
2150 # 'add_ie': [ZypeIE.ie_key()],
2152 # 'skip_download': True,
2157 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2161 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2162 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2163 'thumbnail': r're:^https?://.*\.jpg$',
2166 'skip_download': True,
2168 'expected_warnings': ['Failed to download MPD manifest'],
2171 # DailyMotion embed with DM.player
2172 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2174 'id': 'k6aKkGHd9FJs4mtJN39',
2176 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2177 'description': 'This video is private.',
2178 'uploader_id': 'x1jf30l',
2179 'uploader': 'beIN SPORTS USA',
2180 'upload_date': '20190528',
2181 'timestamp': 1559062971,
2184 'skip_download': True,
2188 # # TODO: find another test
2189 # # http://schema.org/VideoObject
2190 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2191 # 'md5': '888dcf08b7ea671381f00fab74692755',
2193 # 'id': 'nyvTSJMKId',
2195 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2196 # 'description': '#love for cats.',
2197 # 'timestamp': 1461244995,
2198 # 'upload_date': '20160421',
2201 # 'force_generic_extractor': True,
2206 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2210 'title': 'Untitled',
2211 'uploader_id': 'user80538407',
2212 'uploader': 'OTT Videos',
2216 # ArcPublishing PoWa video player
2217 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2218 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2220 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2222 'title': 'Senate candidates wave to voters on Anchorage streets',
2223 'description': 'md5:91f51a6511f090617353dc720318b20e',
2224 'timestamp': 1604378735,
2225 'upload_date': '20201103',
2230 # MyChannels SDK embed
2231 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2232 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2233 'md5': '90c0699c37006ef18e198c032d81739c',
2237 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2238 'timestamp': 1611740340,
2239 'upload_date': '20210127',
2244 # Simplecast player embed
2245 'url': 'https://www.bio.org/podcast',
2248 'title': 'I AM BIO Podcast | BIO',
2250 'playlist_mincount': 52,
2253 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2254 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2255 'only_matching': True,
2259 def report_following_redirect(self, new_url):
2260 """Report information extraction."""
2261 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2263 def _extract_rss(self, url, video_id, doc):
2264 playlist_title = doc.find('./channel/title').text
2265 playlist_desc_el = doc.find('./channel/description')
2266 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2269 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2273 for it in doc.findall('./channel/item'):
2275 enclosure_nodes = it.findall('./enclosure')
2276 for e in enclosure_nodes:
2277 next_url = e.attrib.get('url')
2282 next_url = xpath_text(it, 'link', fatal=False)
2289 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2292 duration = itunes('duration')
2293 explicit = (itunes('explicit') or '').lower()
2294 if explicit in ('true', 'yes'):
2296 elif explicit in ('false', 'no'):
2302 '_type': 'url_transparent',
2304 'title': it.find('title').text,
2305 'description': xpath_text(it, 'description', default=None),
2306 'timestamp': unified_timestamp(
2307 xpath_text(it, 'pubDate', default=None)),
2308 'duration': int_or_none(duration) or parse_duration(duration),
2309 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2310 'episode': itunes('title'),
2311 'episode_number': int_or_none(itunes('episode')),
2312 'season_number': int_or_none(itunes('season')),
2313 'age_limit': age_limit,
2317 '_type': 'playlist',
2319 'title': playlist_title,
2320 'description': playlist_desc,
2324 def _extract_camtasia(self, url, video_id, webpage):
2325 """ Returns None if no camtasia video can be found. """
2327 camtasia_cfg = self._search_regex(
2328 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2329 webpage, 'camtasia configuration file', default=None)
2330 if camtasia_cfg is None:
2333 title = self._html_search_meta('DC.title', webpage, fatal=True)
2335 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2336 camtasia_cfg = self._download_xml(
2337 camtasia_url, video_id,
2338 note='Downloading camtasia configuration',
2339 errnote='Failed to download camtasia configuration')
2340 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2343 for n in fileset_node.getchildren():
2344 url_n = n.find('./uri')
2349 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2350 'title': '%s - %s' % (title, n.tag),
2351 'url': compat_urlparse.urljoin(url, url_n.text),
2352 'duration': float_or_none(n.find('./duration').text),
2356 '_type': 'playlist',
2361 def _real_extract(self, url):
2362 if url.startswith('//'):
2363 return self.url_result(self.http_scheme() + url)
2365 parsed_url = compat_urlparse.urlparse(url)
2366 if not parsed_url.scheme:
2367 default_search = self._downloader.params.get('default_search')
2368 if default_search is None:
2369 default_search = 'fixup_error'
2371 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2372 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2373 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2374 return self.url_result('http://' + url)
2375 elif default_search != 'fixup_error':
2376 if default_search == 'auto_warning':
2377 if re.match(r'^(?:url|URL)$', url):
2378 raise ExtractorError(
2379 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2382 self._downloader.report_warning(
2383 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2384 return self.url_result('ytsearch:' + url)
2386 if default_search in ('error', 'fixup_error'):
2387 raise ExtractorError(
2388 '%r is not a valid URL. '
2389 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2390 % (url, url), expected=True)
2392 if ':' not in default_search:
2393 default_search += ':'
2394 return self.url_result(default_search + url)
2396 url, smuggled_data = unsmuggle_url(url)
2397 force_videoid = None
2398 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2399 if smuggled_data and 'force_videoid' in smuggled_data:
2400 force_videoid = smuggled_data['force_videoid']
2401 video_id = force_videoid
2403 video_id = self._generic_id(url)
2405 self.to_screen('%s: Requesting header' % video_id)
2407 head_req = HEADRequest(url)
2408 head_response = self._request_webpage(
2410 note=False, errnote='Could not send HEAD request to %s' % url,
2413 if head_response is not False:
2414 # Check for redirect
2415 new_url = head_response.geturl()
2417 self.report_following_redirect(new_url)
2419 new_url = smuggle_url(
2420 new_url, {'force_videoid': force_videoid})
2421 return self.url_result(new_url)
2423 full_response = None
2424 if head_response is False:
2425 request = sanitized_Request(url)
2426 request.add_header('Accept-Encoding', '*')
2427 full_response = self._request_webpage(request, video_id)
2428 head_response = full_response
2432 'title': self._generic_title(url),
2433 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2436 # Check for direct link to a video
2437 content_type = head_response.headers.get('Content-Type', '').lower()
2438 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2440 format_id = compat_str(m.group('format_id'))
2441 if format_id.endswith('mpegurl'):
2442 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2443 elif format_id == 'f4m':
2444 formats = self._extract_f4m_formats(url, video_id)
2447 'format_id': format_id,
2449 'vcodec': 'none' if m.group('type') == 'audio' else None
2451 info_dict['direct'] = True
2452 self._sort_formats(formats)
2453 info_dict['formats'] = formats
2456 if not self._downloader.params.get('test', False) and not is_intentional:
2457 force = self._downloader.params.get('force_generic_extractor', False)
2458 self._downloader.report_warning(
2459 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2461 if not full_response:
2462 request = sanitized_Request(url)
2463 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2464 # making it impossible to download only chunk of the file (yet we need only 512kB to
2465 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2466 # that will always result in downloading the whole file that is not desirable.
2467 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2468 # to accept raw bytes and being able to download only a chunk.
2469 # It may probably better to solve this by checking Content-Type for application/octet-stream
2470 # after HEAD request finishes, but not sure if we can rely on this.
2471 request.add_header('Accept-Encoding', '*')
2472 full_response = self._request_webpage(request, video_id)
2474 first_bytes = full_response.read(512)
2476 # Is it an M3U playlist?
2477 if first_bytes.startswith(b'#EXTM3U'):
2478 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2479 self._sort_formats(info_dict['formats'])
2482 # Maybe it's a direct link to a video?
2483 # Be careful not to download the whole thing!
2484 if not is_html(first_bytes):
2485 self._downloader.report_warning(
2486 'URL could be a direct video link, returning it as such.')
2493 webpage = self._webpage_read_content(
2494 full_response, url, video_id, prefix=first_bytes)
2496 if '<title>DPG Media Privacy Gate</title>' in webpage:
2497 webpage = self._download_webpage(url, video_id)
2499 self.report_extraction(video_id)
2501 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2503 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2504 if doc.tag == 'rss':
2505 return self._extract_rss(url, video_id, doc)
2506 elif doc.tag == 'SmoothStreamingMedia':
2507 info_dict['formats'] = self._parse_ism_formats(doc, url)
2508 self._sort_formats(info_dict['formats'])
2510 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2511 smil = self._parse_smil(doc, url, video_id)
2512 self._sort_formats(smil['formats'])
2514 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2515 return self.playlist_result(
2517 doc, video_id, xspf_url=url,
2518 xspf_base_url=full_response.geturl()),
2520 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2521 info_dict['formats'] = self._parse_mpd_formats(
2523 mpd_base_url=full_response.geturl().rpartition('/')[0],
2525 self._sort_formats(info_dict['formats'])
2527 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2528 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2529 self._sort_formats(info_dict['formats'])
2531 except compat_xml_parse_error:
2534 # Is it a Camtasia project?
2535 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2536 if camtasia_res is not None:
2539 # Sometimes embedded video player is hidden behind percent encoding
2540 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2541 # Unescaping the whole page allows to handle those cases in a generic way
2542 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2543 # There probably should be a second run of generic extractor on unescaped webpage.
2544 # webpage = compat_urllib_parse_unquote(webpage)
2546 # Unescape squarespace embeds to be detected by generic extractor,
2547 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2549 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2550 lambda x: unescapeHTML(x.group(0)), webpage)
2552 # it's tempting to parse this further, but you would
2553 # have to take into account all the variations like
2554 # Video Title - Site Name
2555 # Site Name | Video Title
2556 # Video Title - Tagline | Site Name
2557 # and so on and so forth; it's just not practical
2558 video_title = self._og_search_title(
2559 webpage, default=None) or self._html_search_regex(
2560 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2563 # Try to detect age limit automatically
2564 age_limit = self._rta_search(webpage)
2565 # And then there are the jokers who advertise that they use RTA,
2566 # but actually don't.
2567 AGE_LIMIT_MARKERS = [
2568 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2570 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2573 # video uploader is domain name
2574 video_uploader = self._search_regex(
2575 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2577 video_description = self._og_search_description(webpage, default=None)
2578 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2581 'title': video_title,
2582 'description': video_description,
2583 'thumbnail': video_thumbnail,
2584 'age_limit': age_limit,
2587 # Look for Brightcove Legacy Studio embeds
2588 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2592 'url': smuggle_url(bc_url, {'Referer': url}),
2593 'ie_key': 'BrightcoveLegacy'
2594 } for bc_url in bc_urls]
2597 '_type': 'playlist',
2598 'title': video_title,
2603 # Look for Brightcove New Studio embeds
2604 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2606 return self.playlist_from_matches(
2607 bc_urls, video_id, video_title,
2608 getter=lambda x: smuggle_url(x, {'referrer': url}),
2611 # Look for Nexx embeds
2612 nexx_urls = NexxIE._extract_urls(webpage)
2614 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2616 # Look for Nexx iFrame embeds
2617 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2619 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2621 # Look for ThePlatform embeds
2622 tp_urls = ThePlatformIE._extract_urls(webpage)
2624 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2626 arc_urls = ArcPublishingIE._extract_urls(webpage)
2628 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2630 mychannels_urls = MedialaanIE._extract_urls(webpage)
2632 return self.playlist_from_matches(
2633 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2635 # Look for embedded rtl.nl player
2636 matches = re.findall(
2637 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2640 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2642 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2644 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2646 vhx_url = VHXEmbedIE._extract_url(webpage)
2648 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2650 vid_me_embed_url = self._search_regex(
2651 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2652 webpage, 'vid.me embed', default=None)
2653 if vid_me_embed_url is not None:
2654 return self.url_result(vid_me_embed_url, 'Vidme')
2656 # Look for YouTube embeds
2657 youtube_urls = YoutubeIE._extract_urls(webpage)
2659 return self.playlist_from_matches(
2660 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2662 matches = DailymotionIE._extract_urls(webpage)
2664 return self.playlist_from_matches(matches, video_id, video_title)
2666 # Look for embedded Dailymotion playlist player (#3822)
2668 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2670 playlists = re.findall(
2671 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2673 return self.playlist_from_matches(
2674 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2676 # Look for DailyMail embeds
2677 dailymail_urls = DailyMailIE._extract_urls(webpage)
2679 return self.playlist_from_matches(
2680 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2682 # Look for Teachable embeds, must be before Wistia
2683 teachable_url = TeachableIE._extract_url(webpage, url)
2685 return self.url_result(teachable_url)
2687 # Look for embedded Wistia player
2688 wistia_urls = WistiaIE._extract_urls(webpage)
2690 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2691 for entry in playlist['entries']:
2693 '_type': 'url_transparent',
2694 'uploader': video_uploader,
2698 # Look for SVT player
2699 svt_url = SVTIE._extract_url(webpage)
2701 return self.url_result(svt_url, 'SVT')
2703 # Look for Bandcamp pages with custom domain
2704 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2705 if mobj is not None:
2706 burl = unescapeHTML(mobj.group(1))
2707 # Don't set the extractor because it can be a track url or an album
2708 return self.url_result(burl)
2710 # Look for embedded Vevo player
2712 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2713 if mobj is not None:
2714 return self.url_result(mobj.group('url'))
2716 # Look for embedded Viddler player
2718 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2720 if mobj is not None:
2721 return self.url_result(mobj.group('url'))
2723 # Look for NYTimes player
2725 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2727 if mobj is not None:
2728 return self.url_result(mobj.group('url'))
2730 # Look for Libsyn player
2732 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2733 if mobj is not None:
2734 return self.url_result(mobj.group('url'))
2736 # Look for Ooyala videos
2737 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2738 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2739 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2740 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2741 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2742 if mobj is not None:
2743 embed_token = self._search_regex(
2744 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2745 webpage, 'ooyala embed token', default=None)
2746 return OoyalaIE._build_url_result(smuggle_url(
2749 'embed_token': embed_token,
2752 # Look for multiple Ooyala embeds on SBN network websites
2753 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2754 if mobj is not None:
2755 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2757 return self.playlist_from_matches(
2758 embeds, video_id, video_title,
2759 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2761 # Look for Aparat videos
2762 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2763 if mobj is not None:
2764 return self.url_result(mobj.group(1), 'Aparat')
2766 # Look for MPORA videos
2767 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2768 if mobj is not None:
2769 return self.url_result(mobj.group(1), 'Mpora')
2771 # Look for embedded Facebook player
2772 facebook_urls = FacebookIE._extract_urls(webpage)
2774 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2776 # Look for embedded VK player
2777 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2778 if mobj is not None:
2779 return self.url_result(mobj.group('url'), 'VK')
2781 # Look for embedded Odnoklassniki player
2782 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2783 if odnoklassniki_url:
2784 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2786 # Look for sibnet embedded player
2787 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2789 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2791 # Look for embedded ivi player
2792 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2793 if mobj is not None:
2794 return self.url_result(mobj.group('url'), 'Ivi')
2796 # Look for embedded Huffington Post player
2798 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2799 if mobj is not None:
2800 return self.url_result(mobj.group('url'), 'HuffPost')
2803 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2804 if mobj is not None:
2805 return self.url_result(mobj.group('url'))
2806 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2807 if mobj is not None:
2808 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2810 # Look for funnyordie embed
2811 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2813 return self.playlist_from_matches(
2814 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2816 # Look for Simplecast embeds
2817 simplecast_urls = SimplecastIE._extract_urls(webpage)
2819 return self.playlist_from_matches(
2820 simplecast_urls, video_id, video_title)
2822 # Look for BBC iPlayer embed
2823 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2825 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2827 # Look for embedded RUTV player
2828 rutv_url = RUTVIE._extract_url(webpage)
2830 return self.url_result(rutv_url, 'RUTV')
2832 # Look for embedded TVC player
2833 tvc_url = TVCIE._extract_url(webpage)
2835 return self.url_result(tvc_url, 'TVC')
2837 # Look for embedded SportBox player
2838 sportbox_urls = SportBoxIE._extract_urls(webpage)
2840 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2842 # Look for embedded XHamster player
2843 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2845 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2847 # Look for embedded TNAFlixNetwork player
2848 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2850 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2852 # Look for embedded PornHub player
2853 pornhub_urls = PornHubIE._extract_urls(webpage)
2855 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2857 # Look for embedded DrTuber player
2858 drtuber_urls = DrTuberIE._extract_urls(webpage)
2860 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2862 # Look for embedded RedTube player
2863 redtube_urls = RedTubeIE._extract_urls(webpage)
2865 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2867 # Look for embedded Tube8 player
2868 tube8_urls = Tube8IE._extract_urls(webpage)
2870 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2872 # Look for embedded Mofosex player
2873 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2875 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2877 # Look for embedded Spankwire player
2878 spankwire_urls = SpankwireIE._extract_urls(webpage)
2880 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2882 # Look for embedded YouPorn player
2883 youporn_urls = YouPornIE._extract_urls(webpage)
2885 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2887 # Look for embedded Tvigle player
2889 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2890 if mobj is not None:
2891 return self.url_result(mobj.group('url'), 'Tvigle')
2893 # Look for embedded TED player
2895 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2896 if mobj is not None:
2897 return self.url_result(mobj.group('url'), 'TED')
2899 # Look for embedded Ustream videos
2900 ustream_url = UstreamIE._extract_url(webpage)
2902 return self.url_result(ustream_url, UstreamIE.ie_key())
2904 # Look for embedded arte.tv player
2905 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2907 return self.playlist_from_matches(arte_urls, video_id, video_title)
2909 # Look for embedded francetv player
2911 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2913 if mobj is not None:
2914 return self.url_result(mobj.group('url'))
2916 # Look for embedded Myvi.ru player
2917 myvi_url = MyviIE._extract_url(webpage)
2919 return self.url_result(myvi_url)
2921 # Look for embedded soundcloud player
2922 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2924 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2926 # Look for tunein player
2927 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2929 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2931 # Look for embedded mtvservices player
2932 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2934 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2936 # Look for embedded yahoo player
2938 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2940 if mobj is not None:
2941 return self.url_result(mobj.group('url'), 'Yahoo')
2943 # Look for embedded sbs.com.au player
2947 <meta\s+property="og:video"\s+content=|
2950 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2952 if mobj is not None:
2953 return self.url_result(mobj.group('url'), 'SBS')
2955 # Look for embedded Cinchcast player
2957 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2959 if mobj is not None:
2960 return self.url_result(mobj.group('url'), 'Cinchcast')
2963 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2967 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
2969 if mobj is not None:
2970 return self.url_result(mobj.group('url'), 'MLB')
2973 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2975 if mobj is not None:
2976 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2979 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2981 if mobj is not None:
2982 return self.url_result(mobj.group('url'), 'Livestream')
2984 # Look for Zapiks embed
2986 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2987 if mobj is not None:
2988 return self.url_result(mobj.group('url'), 'Zapiks')
2990 # Look for Kaltura embeds
2991 kaltura_urls = KalturaIE._extract_urls(webpage)
2993 return self.playlist_from_matches(
2994 kaltura_urls, video_id, video_title,
2995 getter=lambda x: smuggle_url(x, {'source_url': url}),
2996 ie=KalturaIE.ie_key())
2998 # Look for EaglePlatform embeds
2999 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3000 if eagleplatform_url:
3001 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3003 # Look for ClipYou (uses EaglePlatform) embeds
3005 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3006 if mobj is not None:
3007 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3009 # Look for Pladform embeds
3010 pladform_url = PladformIE._extract_url(webpage)
3012 return self.url_result(pladform_url)
3014 # Look for Videomore embeds
3015 videomore_url = VideomoreIE._extract_url(webpage)
3017 return self.url_result(videomore_url)
3019 # Look for Webcaster embeds
3020 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3022 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3024 # Look for Playwire embeds
3026 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3027 if mobj is not None:
3028 return self.url_result(mobj.group('url'))
3030 # Look for 5min embeds
3032 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3033 if mobj is not None:
3034 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3036 # Look for Crooks and Liars embeds
3038 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3039 if mobj is not None:
3040 return self.url_result(mobj.group('url'))
3042 # Look for NBC Sports VPlayer embeds
3043 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3045 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3047 # Look for NBC News embeds
3048 nbc_news_embed_url = re.search(
3049 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3050 if nbc_news_embed_url:
3051 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3053 # Look for Google Drive embeds
3054 google_drive_url = GoogleDriveIE._extract_url(webpage)
3055 if google_drive_url:
3056 return self.url_result(google_drive_url, 'GoogleDrive')
3058 # Look for UDN embeds
3060 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3061 if mobj is not None:
3062 return self.url_result(
3063 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3065 # Look for Senate ISVP iframe
3066 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3068 return self.url_result(senate_isvp_url, 'SenateISVP')
3070 # Look for Kinja embeds
3071 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3072 if kinja_embed_urls:
3073 return self.playlist_from_matches(
3074 kinja_embed_urls, video_id, video_title)
3076 # Look for OnionStudios embeds
3077 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3078 if onionstudios_url:
3079 return self.url_result(onionstudios_url)
3081 # Look for ViewLift embeds
3082 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3084 return self.url_result(viewlift_url)
3086 # Look for JWPlatform embeds
3087 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3089 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3091 # Look for Digiteka embeds
3092 digiteka_url = DigitekaIE._extract_url(webpage)
3094 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3096 # Look for Arkena embeds
3097 arkena_url = ArkenaIE._extract_url(webpage)
3099 return self.url_result(arkena_url, ArkenaIE.ie_key())
3101 # Look for Piksel embeds
3102 piksel_url = PikselIE._extract_url(webpage)
3104 return self.url_result(piksel_url, PikselIE.ie_key())
3106 # Look for Limelight embeds
3107 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3109 return self.playlist_result(
3110 limelight_urls, video_id, video_title, video_description)
3112 # Look for Anvato embeds
3113 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3115 return self.playlist_result(
3116 anvato_urls, video_id, video_title, video_description)
3118 # Look for AdobeTVVideo embeds
3120 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3122 if mobj is not None:
3123 return self.url_result(
3124 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3127 # Look for Vine embeds
3129 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3131 if mobj is not None:
3132 return self.url_result(
3133 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3135 # Look for VODPlatform embeds
3137 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3139 if mobj is not None:
3140 return self.url_result(
3141 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3143 # Look for Mangomolo embeds
3145 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3147 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3148 player\.mangomolo\.com/v1
3151 video\?.*?\bid=(?P<video_id>\d+)|
3152 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3153 ).+?)\1''', webpage)
3154 if mobj is not None:
3156 '_type': 'url_transparent',
3157 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3158 'title': video_title,
3159 'description': video_description,
3160 'thumbnail': video_thumbnail,
3161 'uploader': video_uploader,
3163 video_id = mobj.group('video_id')
3166 'ie_key': 'MangomoloVideo',
3171 'ie_key': 'MangomoloLive',
3172 'id': mobj.group('channel_id'),
3176 # Look for Instagram embeds
3177 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3178 if instagram_embed_url is not None:
3179 return self.url_result(
3180 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3182 # Look for LiveLeak embeds
3183 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3185 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3187 # Look for 3Q SDN embeds
3188 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3191 '_type': 'url_transparent',
3192 'ie_key': ThreeQSDNIE.ie_key(),
3193 'url': self._proto_relative_url(threeqsdn_url),
3194 'title': video_title,
3195 'description': video_description,
3196 'thumbnail': video_thumbnail,
3197 'uploader': video_uploader,
3200 # Look for VBOX7 embeds
3201 vbox7_url = Vbox7IE._extract_url(webpage)
3203 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3205 # Look for DBTV embeds
3206 dbtv_urls = DBTVIE._extract_urls(webpage)
3208 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3210 # Look for Videa embeds
3211 videa_urls = VideaIE._extract_urls(webpage)
3213 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3215 # Look for 20 minuten embeds
3216 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3218 return self.playlist_from_matches(
3219 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3221 # Look for VideoPress embeds
3222 videopress_urls = VideoPressIE._extract_urls(webpage)
3224 return self.playlist_from_matches(
3225 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3227 # Look for Rutube embeds
3228 rutube_urls = RutubeIE._extract_urls(webpage)
3230 return self.playlist_from_matches(
3231 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3233 # Look for WashingtonPost embeds
3234 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3236 return self.playlist_from_matches(
3237 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3239 # Look for Mediaset embeds
3240 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3242 return self.playlist_from_matches(
3243 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3245 # Look for JOJ.sk embeds
3246 joj_urls = JojIE._extract_urls(webpage)
3248 return self.playlist_from_matches(
3249 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3251 # Look for megaphone.fm embeds
3252 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3254 return self.playlist_from_matches(
3255 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3257 # Look for vzaar embeds
3258 vzaar_urls = VzaarIE._extract_urls(webpage)
3260 return self.playlist_from_matches(
3261 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3263 channel9_urls = Channel9IE._extract_urls(webpage)
3265 return self.playlist_from_matches(
3266 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3268 vshare_urls = VShareIE._extract_urls(webpage)
3270 return self.playlist_from_matches(
3271 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3273 # Look for Mediasite embeds
3274 mediasite_urls = MediasiteIE._extract_urls(webpage)
3277 self.url_result(smuggle_url(
3278 compat_urlparse.urljoin(url, mediasite_url),
3279 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3280 for mediasite_url in mediasite_urls]
3281 return self.playlist_result(entries, video_id, video_title)
3283 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3284 if springboardplatform_urls:
3285 return self.playlist_from_matches(
3286 springboardplatform_urls, video_id, video_title,
3287 ie=SpringboardPlatformIE.ie_key())
3289 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3291 return self.playlist_from_matches(
3292 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3294 vice_urls = ViceIE._extract_urls(webpage)
3296 return self.playlist_from_matches(
3297 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3299 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3301 return self.playlist_from_matches(
3302 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3304 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3305 if cloudflarestream_urls:
3306 return self.playlist_from_matches(
3307 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3309 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3311 return self.playlist_from_matches(
3312 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3314 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3316 return self.playlist_from_matches(
3317 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3319 apa_urls = APAIE._extract_urls(webpage)
3321 return self.playlist_from_matches(
3322 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3324 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3326 return self.playlist_from_matches(
3327 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3329 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3330 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3332 if sharevideos_urls:
3333 return self.playlist_from_matches(
3334 sharevideos_urls, video_id, video_title)
3336 viqeo_urls = ViqeoIE._extract_urls(webpage)
3338 return self.playlist_from_matches(
3339 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3341 expressen_urls = ExpressenIE._extract_urls(webpage)
3343 return self.playlist_from_matches(
3344 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3346 zype_urls = ZypeIE._extract_urls(webpage)
3348 return self.playlist_from_matches(
3349 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3351 # Look for HTML5 media
3352 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3354 if len(entries) == 1:
3357 'title': video_title,
3360 for num, entry in enumerate(entries, start=1):
3362 'id': '%s-%s' % (video_id, num),
3363 'title': '%s (%d)' % (video_title, num),
3365 for entry in entries:
3366 self._sort_formats(entry['formats'])
3367 return self.playlist_result(entries, video_id, video_title)
3369 jwplayer_data = self._find_jwplayer_data(
3370 webpage, video_id, transform_source=js_to_json)
3373 info = self._parse_jwplayer_data(
3374 jwplayer_data, video_id, require_title=False, base_url=url)
3375 return merge_dicts(info, info_dict)
3376 except ExtractorError:
3377 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3382 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3384 if mobj is not None:
3385 sources = self._parse_json(
3386 mobj.group(1), video_id, transform_source=js_to_json,
3388 if not isinstance(sources, list):
3391 for source in sources:
3392 src = source.get('src')
3393 if not src or not isinstance(src, compat_str):
3395 src = compat_urlparse.urljoin(url, src)
3396 src_type = source.get('type')
3397 if isinstance(src_type, compat_str):
3398 src_type = src_type.lower()
3399 ext = determine_ext(src).lower()
3400 if src_type == 'video/youtube':
3401 return self.url_result(src, YoutubeIE.ie_key())
3402 if src_type == 'application/dash+xml' or ext == 'mpd':
3403 formats.extend(self._extract_mpd_formats(
3404 src, video_id, mpd_id='dash', fatal=False))
3405 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3406 formats.extend(self._extract_m3u8_formats(
3407 src, video_id, 'mp4', entry_protocol='m3u8_native',
3408 m3u8_id='hls', fatal=False))
3412 'ext': (mimetype2ext(src_type)
3413 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3415 'Referer': full_response.geturl(),
3419 self._sort_formats(formats)
3420 info_dict['formats'] = formats
3423 # Looking for http://schema.org/VideoObject
3424 json_ld = self._search_json_ld(
3425 webpage, video_id, default={}, expected_type='VideoObject')
3426 if json_ld.get('url'):
3427 return merge_dicts(json_ld, info_dict)
3429 def check_video(vurl):
3430 if YoutubeIE.suitable(vurl):
3432 if RtmpIE.suitable(vurl):
3434 vpath = compat_urlparse.urlparse(vurl).path
3435 vext = determine_ext(vpath)
3436 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3438 def filter_video(urls):
3439 return list(filter(check_video, urls))
3441 # Start with something easy: JW Player in SWFObject
3442 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3444 # Look for gorilla-vid style embedding
3445 found = filter_video(re.findall(r'''(?sx)
3449 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3452 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3454 # Broaden the search a little bit
3455 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3457 # Broaden the findall a little bit: JWPlayer JS loader
3458 found = filter_video(re.findall(
3459 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3462 found = filter_video(re.findall(r'''(?xs)
3463 flowplayer\("[^"]+",\s*
3465 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3466 ["']?url["']?\s*:\s*["']([^"']+)["']
3471 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3473 # Try to find twitter cards info
3474 # twitter:player:stream should be checked before twitter:player since
3475 # it is expected to contain a raw stream (see
3476 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3477 found = filter_video(re.findall(
3478 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3480 # We look for Open Graph info:
3481 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3482 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3483 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3484 if m_video_type is not None:
3485 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3487 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3489 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3490 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3493 # Look also in Refresh HTTP header
3494 refresh_header = head_response.headers.get('Refresh')
3496 # In python 2 response HTTP headers are bytestrings
3497 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3498 refresh_header = refresh_header.decode('iso-8859-1')
3499 found = re.search(REDIRECT_REGEX, refresh_header)
3501 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3503 self.report_following_redirect(new_url)
3512 # twitter:player is a https URL to iframe player that may or may not
3513 # be supported by youtube-dl thus this is checked the very last (see
3514 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3515 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3516 if embed_url and embed_url != url:
3517 return self.url_result(embed_url)
3520 raise UnsupportedError(url)
3523 for video_url in orderedSet(found):
3524 video_url = unescapeHTML(video_url)
3525 video_url = video_url.replace('\\/', '/')
3526 video_url = compat_urlparse.urljoin(url, video_url)
3527 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3529 # Sometimes, jwplayer extraction will result in a YouTube URL
3530 if YoutubeIE.suitable(video_url):
3531 entries.append(self.url_result(video_url, 'Youtube'))
3534 # here's a fun little line of code for you:
3535 video_id = os.path.splitext(video_id)[0]
3539 'uploader': video_uploader,
3540 'title': video_title,
3541 'age_limit': age_limit,
3544 if RtmpIE.suitable(video_url):
3545 entry_info_dict.update({
3546 '_type': 'url_transparent',
3547 'ie_key': RtmpIE.ie_key(),
3550 entries.append(entry_info_dict)
3553 ext = determine_ext(video_url)
3555 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3557 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3559 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3561 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3563 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3564 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3565 # Just matching .ism/manifest is not enough to be reliably sure
3566 # whether it's actually an ISM manifest or some other streaming
3567 # manifest since there are various streaming URL formats
3568 # possible (see [1]) as well as some other shenanigans like
3569 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3571 # Thus the most reasonable way to solve this is to delegate
3572 # to generic extractor in order to look into the contents of
3573 # the manifest itself.
3574 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3575 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3576 entry_info_dict = self.url_result(
3577 smuggle_url(video_url, {'to_generic': True}),
3580 entry_info_dict['url'] = video_url
3582 if entry_info_dict.get('formats'):
3583 self._sort_formats(entry_info_dict['formats'])
3585 entries.append(entry_info_dict)
3587 if len(entries) == 1:
3590 for num, e in enumerate(entries, start=1):
3591 # 'url' results don't have a title
3592 if e.get('title') is not None:
3593 e['title'] = '%s (%d)' % (e['title'], num)
3595 '_type': 'playlist',