]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/generic.py
0d279016b2bfbbb9e4e1a918a77245f3f606cfd7
[yt-dlp.git] / yt_dlp / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 int_or_none,
24 is_html,
25 js_to_json,
26 KNOWN_EXTENSIONS,
27 merge_dicts,
28 mimetype2ext,
29 orderedSet,
30 parse_duration,
31 sanitized_Request,
32 smuggle_url,
33 unescapeHTML,
34 unified_timestamp,
35 unsmuggle_url,
36 UnsupportedError,
37 url_or_none,
38 xpath_attr,
39 xpath_text,
40 xpath_with_ns,
41 )
42 from .commonprotocols import RtmpIE
43 from .brightcove import (
44 BrightcoveLegacyIE,
45 BrightcoveNewIE,
46 )
47 from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50 )
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
70 from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73 )
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 .threeqsdn import ThreeQSDNIE
88 from .theplatform import ThePlatformIE
89 from .kaltura import KalturaIE
90 from .eagleplatform import EaglePlatformIE
91 from .facebook import FacebookIE
92 from .soundcloud import SoundcloudEmbedIE
93 from .tunein import TuneInBaseIE
94 from .vbox7 import Vbox7IE
95 from .dbtv import DBTVIE
96 from .piksel import PikselIE
97 from .videa import VideaIE
98 from .twentymin import TwentyMinutenIE
99 from .ustream import UstreamIE
100 from .arte import ArteTVEmbedIE
101 from .videopress import VideoPressIE
102 from .rutube import RutubeIE
103 from .limelight import LimelightBaseIE
104 from .anvato import AnvatoIE
105 from .washingtonpost import WashingtonPostIE
106 from .wistia import WistiaIE
107 from .mediaset import MediasetIE
108 from .joj import JojIE
109 from .megaphone import MegaphoneIE
110 from .vzaar import VzaarIE
111 from .channel9 import Channel9IE
112 from .vshare import VShareIE
113 from .mediasite import MediasiteIE
114 from .springboardplatform import SpringboardPlatformIE
115 from .yapfiles import YapFilesIE
116 from .vice import ViceIE
117 from .xfileshare import XFileShareIE
118 from .cloudflarestream import CloudflareStreamIE
119 from .peertube import PeerTubeIE
120 from .teachable import TeachableIE
121 from .indavideo import IndavideoEmbedIE
122 from .apa import APAIE
123 from .foxnews import FoxNewsIE
124 from .viqeo import ViqeoIE
125 from .expressen import ExpressenIE
126 from .zype import ZypeIE
127 from .odnoklassniki import OdnoklassnikiIE
128 from .vk import VKIE
129 from .kinja import KinjaEmbedIE
130 from .gedidigital import GediDigitalIE
131 from .rcs import RCSEmbedsIE
132 from .bitchute import BitChuteIE
133 from .rumble import RumbleEmbedIE
134 from .arcpublishing import ArcPublishingIE
135 from .medialaan import MedialaanIE
136 from .simplecast import SimplecastIE
137 from .wimtv import WimTVIE
138
139
140 class GenericIE(InfoExtractor):
141 IE_DESC = 'Generic downloader that works on some sites'
142 _VALID_URL = r'.*'
143 IE_NAME = 'generic'
144 _TESTS = [
145 # Direct link to a video
146 {
147 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
148 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
149 'info_dict': {
150 'id': 'trailer',
151 'ext': 'mp4',
152 'title': 'trailer',
153 'upload_date': '20100513',
154 }
155 },
156 # Direct link to media delivered compressed (until Accept-Encoding is *)
157 {
158 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
159 'md5': '128c42e68b13950268b648275386fc74',
160 'info_dict': {
161 'id': 'FictionJunction-Parallel_Hearts',
162 'ext': 'flac',
163 'title': 'FictionJunction-Parallel_Hearts',
164 'upload_date': '20140522',
165 },
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
168 ],
169 'skip': 'URL invalid',
170 },
171 # Direct download with broken HEAD
172 {
173 'url': 'http://ai-radio.org:8000/radio.opus',
174 'info_dict': {
175 'id': 'radio',
176 'ext': 'opus',
177 'title': 'radio',
178 },
179 'params': {
180 'skip_download': True, # infinite live stream
181 },
182 'expected_warnings': [
183 r'501.*Not Implemented',
184 r'400.*Bad Request',
185 ],
186 },
187 # Direct link with incorrect MIME type
188 {
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'md5': '4ccbebe5f36706d85221f204d7eb5913',
191 'info_dict': {
192 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
193 'id': '5_Lennart_Poettering_-_Systemd',
194 'ext': 'webm',
195 'title': '5_Lennart_Poettering_-_Systemd',
196 'upload_date': '20141120',
197 },
198 'expected_warnings': [
199 'URL could be a direct video link, returning it as such.'
200 ]
201 },
202 # RSS feed
203 {
204 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
205 'info_dict': {
206 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'title': 'Zero Punctuation',
208 'description': 're:.*groundbreaking video review series.*'
209 },
210 'playlist_mincount': 11,
211 },
212 # RSS feed with enclosure
213 {
214 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
215 'info_dict': {
216 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
217 'title': 'MSNBC Rachel Maddow (video)',
218 'description': 're:.*her unique approach to storytelling.*',
219 },
220 'playlist': [{
221 'info_dict': {
222 'ext': 'mov',
223 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
224 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
225 'description': 're:.*her unique approach to storytelling.*',
226 'upload_date': '20201204',
227 },
228 }],
229 },
230 # RSS feed with item with description and thumbnails
231 {
232 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'info_dict': {
234 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'title': 're:.*100% Hydrogen.*',
236 'description': 're:.*In this episode.*',
237 },
238 'playlist': [{
239 'info_dict': {
240 'ext': 'm4a',
241 'id': 'c1c879525ce2cb640b344507e682c36d',
242 'title': 're:Hydrogen!',
243 'description': 're:.*In this episode we are going.*',
244 'timestamp': 1567977776,
245 'upload_date': '20190908',
246 'duration': 459,
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'episode_number': 1,
249 'season_number': 1,
250 'age_limit': 0,
251 },
252 }],
253 'params': {
254 'skip_download': True,
255 },
256 },
257 # RSS feed with enclosures and unsupported link URLs
258 {
259 'url': 'http://www.hellointernet.fm/podcast?format=rss',
260 'info_dict': {
261 'id': 'http://www.hellointernet.fm/podcast?format=rss',
262 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
263 'title': 'Hello Internet',
264 },
265 'playlist_mincount': 100,
266 },
267 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
268 {
269 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
270 'info_dict': {
271 'id': 'smil',
272 'ext': 'mp4',
273 'title': 'Automatics, robotics and biocybernetics',
274 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
275 'upload_date': '20130627',
276 'formats': 'mincount:16',
277 'subtitles': 'mincount:1',
278 },
279 'params': {
280 'force_generic_extractor': True,
281 'skip_download': True,
282 },
283 },
284 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
285 {
286 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
287 'info_dict': {
288 'id': 'hds',
289 'ext': 'flv',
290 'title': 'hds',
291 'formats': 'mincount:1',
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # SMIL from https://www.restudy.dk/video/play/id/1637
298 {
299 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
300 'info_dict': {
301 'id': 'video_1637',
302 'ext': 'flv',
303 'title': 'video_1637',
304 'formats': 'mincount:3',
305 },
306 'params': {
307 'skip_download': True,
308 },
309 },
310 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
311 {
312 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
313 'info_dict': {
314 'id': 'smil-service',
315 'ext': 'flv',
316 'title': 'smil-service',
317 'formats': 'mincount:1',
318 },
319 'params': {
320 'skip_download': True,
321 },
322 },
323 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
324 {
325 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
326 'info_dict': {
327 'id': '4719370',
328 'ext': 'mp4',
329 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
330 'formats': 'mincount:3',
331 },
332 'params': {
333 'skip_download': True,
334 },
335 },
336 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
337 {
338 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
339 'info_dict': {
340 'id': 'mZlp2ctYIUEB',
341 'ext': 'mp4',
342 'title': 'Tikibad ontruimd wegens brand',
343 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
344 'thumbnail': r're:^https?://.*\.jpg$',
345 'duration': 33,
346 },
347 'params': {
348 'skip_download': True,
349 },
350 },
351 # MPD from http://dash-mse-test.appspot.com/media.html
352 {
353 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
354 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
355 'info_dict': {
356 'id': 'car-20120827-manifest',
357 'ext': 'mp4',
358 'title': 'car-20120827-manifest',
359 'formats': 'mincount:9',
360 'upload_date': '20130904',
361 },
362 'params': {
363 'format': 'bestvideo',
364 },
365 },
366 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
367 {
368 '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',
369 'info_dict': {
370 'id': 'content',
371 'ext': 'mp4',
372 'title': 'content',
373 'formats': 'mincount:8',
374 },
375 'params': {
376 # m3u8 downloads
377 'skip_download': True,
378 },
379 'skip': 'video gone',
380 },
381 # m3u8 served with Content-Type: text/plain
382 {
383 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
384 'info_dict': {
385 'id': 'index',
386 'ext': 'mp4',
387 'title': 'index',
388 'upload_date': '20140720',
389 'formats': 'mincount:11',
390 },
391 'params': {
392 # m3u8 downloads
393 'skip_download': True,
394 },
395 'skip': 'video gone',
396 },
397 # google redirect
398 {
399 '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',
400 'info_dict': {
401 'id': 'cmQHVoWB5FY',
402 'ext': 'mp4',
403 'upload_date': '20130224',
404 'uploader_id': 'TheVerge',
405 'description': r're:^Chris Ziegler takes a look at the\.*',
406 'uploader': 'The Verge',
407 'title': 'First Firefox OS phones side-by-side',
408 },
409 'params': {
410 'skip_download': False,
411 }
412 },
413 {
414 # redirect in Refresh HTTP header
415 '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',
416 'info_dict': {
417 'id': 'pO8h3EaFRdo',
418 'ext': 'mp4',
419 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
420 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
421 'upload_date': '20150917',
422 'uploader_id': 'brtvofficial',
423 'uploader': 'Boiler Room',
424 },
425 'params': {
426 'skip_download': False,
427 },
428 },
429 {
430 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
431 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
432 'info_dict': {
433 'id': '13601338388002',
434 'ext': 'mp4',
435 'uploader': 'www.hodiho.fr',
436 'title': 'R\u00e9gis plante sa Jeep',
437 }
438 },
439 # bandcamp page with custom domain
440 {
441 'add_ie': ['Bandcamp'],
442 'url': 'http://bronyrock.com/track/the-pony-mash',
443 'info_dict': {
444 'id': '3235767654',
445 'ext': 'mp3',
446 'title': 'The Pony Mash',
447 'uploader': 'M_Pallante',
448 },
449 'skip': 'There is a limit of 200 free downloads / month for the test song',
450 },
451 {
452 # embedded brightcove video
453 # it also tests brightcove videos that need to set the 'Referer'
454 # in the http requests
455 'add_ie': ['BrightcoveLegacy'],
456 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
457 'info_dict': {
458 'id': '2765128793001',
459 'ext': 'mp4',
460 'title': 'Le cours de bourse : l’analyse technique',
461 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
462 'uploader': 'BFM BUSINESS',
463 },
464 'params': {
465 'skip_download': True,
466 },
467 },
468 {
469 # embedded with itemprop embedURL and video id spelled as `idVideo`
470 'add_id': ['BrightcoveLegacy'],
471 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
472 'info_dict': {
473 'id': '5255628253001',
474 'ext': 'mp4',
475 'title': 'md5:37c519b1128915607601e75a87995fc0',
476 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
477 'uploader': 'BFM BUSINESS',
478 'uploader_id': '876450612001',
479 'timestamp': 1482255315,
480 'upload_date': '20161220',
481 },
482 'params': {
483 'skip_download': True,
484 },
485 },
486 {
487 # https://github.com/ytdl-org/youtube-dl/issues/2253
488 'url': 'http://bcove.me/i6nfkrc3',
489 'md5': '0ba9446db037002366bab3b3eb30c88c',
490 'info_dict': {
491 'id': '3101154703001',
492 'ext': 'mp4',
493 'title': 'Still no power',
494 'uploader': 'thestar.com',
495 '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.',
496 },
497 'add_ie': ['BrightcoveLegacy'],
498 'skip': 'video gone',
499 },
500 {
501 'url': 'http://www.championat.com/video/football/v/87/87499.html',
502 'md5': 'fb973ecf6e4a78a67453647444222983',
503 'info_dict': {
504 'id': '3414141473001',
505 'ext': 'mp4',
506 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
507 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
508 'uploader': 'Championat',
509 },
510 },
511 {
512 # https://github.com/ytdl-org/youtube-dl/issues/3541
513 'add_ie': ['BrightcoveLegacy'],
514 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
515 'info_dict': {
516 'id': '3866516442001',
517 'ext': 'mp4',
518 'title': 'Leer mij vrouwen kennen: Aflevering 1',
519 'description': 'Leer mij vrouwen kennen: Aflevering 1',
520 'uploader': 'SBS Broadcasting',
521 },
522 'skip': 'Restricted to Netherlands',
523 'params': {
524 'skip_download': True, # m3u8 download
525 },
526 },
527 {
528 # Brightcove video in <iframe>
529 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
530 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
531 'info_dict': {
532 'id': '5360463607001',
533 'ext': 'mp4',
534 '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',
535 '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。',
536 'uploader': 'United Nations',
537 'uploader_id': '1362235914001',
538 'timestamp': 1489593889,
539 'upload_date': '20170315',
540 },
541 'add_ie': ['BrightcoveLegacy'],
542 },
543 {
544 # Brightcove with alternative playerID key
545 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
546 'info_dict': {
547 'id': 'nmeth.2062_SV1',
548 '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',
549 },
550 'playlist': [{
551 'info_dict': {
552 'id': '2228375078001',
553 'ext': 'mp4',
554 'title': 'nmeth.2062-sv1',
555 'description': 'nmeth.2062-sv1',
556 'timestamp': 1363357591,
557 'upload_date': '20130315',
558 'uploader': 'Nature Publishing Group',
559 'uploader_id': '1964492299001',
560 },
561 }],
562 },
563 {
564 # Brightcove with UUID in videoPlayer
565 'url': 'http://www8.hp.com/cn/zh/home.html',
566 'info_dict': {
567 'id': '5255815316001',
568 'ext': 'mp4',
569 'title': 'Sprocket Video - China',
570 'description': 'Sprocket Video - China',
571 'uploader': 'HP-Video Gallery',
572 'timestamp': 1482263210,
573 'upload_date': '20161220',
574 'uploader_id': '1107601872001',
575 },
576 'params': {
577 'skip_download': True, # m3u8 download
578 },
579 'skip': 'video rotates...weekly?',
580 },
581 {
582 # Brightcove:new type [2].
583 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
584 'md5': '2b35148fcf48da41c9fb4591650784f3',
585 'info_dict': {
586 'id': '5348741021001',
587 'ext': 'mp4',
588 'upload_date': '20170306',
589 'uploader_id': '4191638492001',
590 'timestamp': 1488769918,
591 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
592
593 },
594 },
595 {
596 # Alternative brightcove <video> attributes
597 '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/',
598 'info_dict': {
599 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
600 '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 },
602 'playlist': [{
603 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
604 'info_dict': {
605 'id': '5311302538001',
606 'ext': 'mp4',
607 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
608 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
609 'timestamp': 1486321708,
610 'upload_date': '20170205',
611 'uploader_id': '800000640001',
612 },
613 'only_matching': True,
614 }],
615 },
616 {
617 # Brightcove with UUID in videoPlayer
618 'url': 'http://www8.hp.com/cn/zh/home.html',
619 'info_dict': {
620 'id': '5255815316001',
621 'ext': 'mp4',
622 'title': 'Sprocket Video - China',
623 'description': 'Sprocket Video - China',
624 'uploader': 'HP-Video Gallery',
625 'timestamp': 1482263210,
626 'upload_date': '20161220',
627 'uploader_id': '1107601872001',
628 },
629 'params': {
630 'skip_download': True, # m3u8 download
631 },
632 },
633 # ooyala video
634 {
635 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
636 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
637 'info_dict': {
638 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
639 'ext': 'mp4',
640 'title': '2cc213299525360.mov', # that's what we get
641 'duration': 238.231,
642 },
643 'add_ie': ['Ooyala'],
644 },
645 {
646 # ooyala video embedded with http://player.ooyala.com/iframe.js
647 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
648 'info_dict': {
649 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
650 'ext': 'mp4',
651 'title': '"Steve Jobs: Man in the Machine" trailer',
652 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
653 'duration': 135.427,
654 },
655 'params': {
656 'skip_download': True,
657 },
658 'skip': 'movie expired',
659 },
660 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
661 {
662 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
663 'info_dict': {
664 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
665 'ext': 'mp4',
666 'title': 'Steampunk Fest Comes to Honesdale',
667 'duration': 43.276,
668 },
669 'params': {
670 'skip_download': True,
671 }
672 },
673 # embed.ly video
674 {
675 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
676 'info_dict': {
677 'id': '9ODmcdjQcHQ',
678 'ext': 'mp4',
679 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
680 'upload_date': '20140225',
681 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
682 'uploader': 'Tested',
683 'uploader_id': 'testedcom',
684 },
685 # No need to test YoutubeIE here
686 'params': {
687 'skip_download': True,
688 },
689 },
690 # funnyordie embed
691 {
692 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
693 'info_dict': {
694 'id': '18e820ec3f',
695 'ext': 'mp4',
696 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
697 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
698 },
699 # HEAD requests lead to endless 301, while GET is OK
700 'expected_warnings': ['301'],
701 },
702 # RUTV embed
703 {
704 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
705 'info_dict': {
706 'id': '776940',
707 'ext': 'mp4',
708 'title': 'Охотское море стало целиком российским',
709 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
710 },
711 'params': {
712 # m3u8 download
713 'skip_download': True,
714 },
715 },
716 # TVC embed
717 {
718 '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/',
719 'info_dict': {
720 'id': '55304',
721 'ext': 'mp4',
722 'title': 'Дошкольное воспитание',
723 },
724 },
725 # SportBox embed
726 {
727 'url': 'http://www.vestifinance.ru/articles/25753',
728 'info_dict': {
729 'id': '25753',
730 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
731 },
732 'playlist': [{
733 'info_dict': {
734 'id': '370908',
735 'title': 'Госзаказ. День 3',
736 'ext': 'mp4',
737 }
738 }, {
739 'info_dict': {
740 'id': '370905',
741 'title': 'Госзаказ. День 2',
742 'ext': 'mp4',
743 }
744 }, {
745 'info_dict': {
746 'id': '370902',
747 'title': 'Госзаказ. День 1',
748 'ext': 'mp4',
749 }
750 }],
751 'params': {
752 # m3u8 download
753 'skip_download': True,
754 },
755 },
756 # Myvi.ru embed
757 {
758 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
759 'info_dict': {
760 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
761 'ext': 'mp4',
762 'title': 'Ужастики, русский трейлер (2015)',
763 'thumbnail': r're:^https?://.*\.jpg$',
764 'duration': 153,
765 }
766 },
767 # XHamster embed
768 {
769 '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 'info_dict': {
771 'id': 'showthread',
772 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
773 },
774 'playlist_mincount': 7,
775 # This forum does not allow <iframe> syntaxes anymore
776 # Now HTML tags are displayed as-is
777 'skip': 'No videos on this page',
778 },
779 # Embedded TED video
780 {
781 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
782 'md5': '65fdff94098e4a607385a60c5177c638',
783 'info_dict': {
784 'id': '1969',
785 'ext': 'mp4',
786 'title': 'Hidden miracles of the natural world',
787 'uploader': 'Louie Schwartzberg',
788 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
789 }
790 },
791 # nowvideo embed hidden behind percent encoding
792 {
793 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
794 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
795 'info_dict': {
796 'id': '06e53103ca9aa',
797 'ext': 'flv',
798 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
799 'description': 'No description',
800 },
801 },
802 # arte embed
803 {
804 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
805 'md5': '7653032cbb25bf6c80d80f217055fa43',
806 'info_dict': {
807 'id': '048195-004_PLUS7-F',
808 'ext': 'flv',
809 'title': 'X:enius',
810 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
811 'upload_date': '20140320',
812 },
813 'params': {
814 'skip_download': 'Requires rtmpdump'
815 },
816 'skip': 'video gone',
817 },
818 # francetv embed
819 {
820 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
821 'info_dict': {
822 'id': 'EV_30231',
823 'ext': 'mp4',
824 'title': 'Alcaline, le concert avec Calogero',
825 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
826 'upload_date': '20150226',
827 'timestamp': 1424989860,
828 'duration': 5400,
829 },
830 'params': {
831 # m3u8 downloads
832 'skip_download': True,
833 },
834 'expected_warnings': [
835 'Forbidden'
836 ]
837 },
838 # Condé Nast embed
839 {
840 'url': 'http://www.wired.com/2014/04/honda-asimo/',
841 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
842 'info_dict': {
843 'id': '53501be369702d3275860000',
844 'ext': 'mp4',
845 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
846 }
847 },
848 # Dailymotion embed
849 {
850 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
851 'md5': '441aeeb82eb72c422c7f14ec533999cd',
852 'info_dict': {
853 'id': 'k2mm4bCdJ6CQ2i7c8o2',
854 'ext': 'mp4',
855 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
856 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
857 'uploader': 'Spi0n',
858 'uploader_id': 'xgditw',
859 'upload_date': '20140425',
860 'timestamp': 1398441542,
861 },
862 'add_ie': ['Dailymotion'],
863 },
864 # DailyMail embed
865 {
866 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
867 'info_dict': {
868 'id': '1495629',
869 'ext': 'mp4',
870 'title': 'Care worker punches elderly dementia patient in head 11 times',
871 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
872 },
873 'add_ie': ['DailyMail'],
874 'params': {
875 'skip_download': True,
876 },
877 },
878 # YouTube embed
879 {
880 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
881 'info_dict': {
882 'id': 'FXRb4ykk4S0',
883 'ext': 'mp4',
884 'title': 'The NBL Auction 2014',
885 'uploader': 'BADMINTON England',
886 'uploader_id': 'BADMINTONEvents',
887 'upload_date': '20140603',
888 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
889 },
890 'add_ie': ['Youtube'],
891 'params': {
892 'skip_download': True,
893 }
894 },
895 # MTVServices embed
896 {
897 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
898 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
899 'info_dict': {
900 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
901 'ext': 'mp4',
902 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
903 'description': 'Two valets share their love for movie star Liam Neesons.',
904 'timestamp': 1349922600,
905 'upload_date': '20121011',
906 },
907 },
908 # YouTube embed via <data-embed-url="">
909 {
910 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
911 'info_dict': {
912 'id': '4vAffPZIT44',
913 'ext': 'mp4',
914 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
915 'uploader': 'Gameloft',
916 'uploader_id': 'gameloft',
917 'upload_date': '20140828',
918 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
919 },
920 'params': {
921 'skip_download': True,
922 }
923 },
924 # YouTube <object> embed
925 {
926 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
927 'md5': '516718101ec834f74318df76259fb3cc',
928 'info_dict': {
929 'id': 'msN87y-iEx0',
930 'ext': 'webm',
931 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
932 'upload_date': '20080526',
933 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
934 'uploader': 'Christopher Sykes',
935 'uploader_id': 'ChristopherJSykes',
936 },
937 'add_ie': ['Youtube'],
938 },
939 # Camtasia studio
940 {
941 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
942 'playlist': [{
943 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
944 'info_dict': {
945 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
946 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
947 'ext': 'flv',
948 'duration': 2235.90,
949 }
950 }, {
951 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
952 'info_dict': {
953 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
954 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
955 'ext': 'flv',
956 'duration': 2235.93,
957 }
958 }],
959 'info_dict': {
960 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
961 }
962 },
963 # Flowplayer
964 {
965 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
966 'md5': '9d65602bf31c6e20014319c7d07fba27',
967 'info_dict': {
968 'id': '5123ea6d5e5a7',
969 'ext': 'mp4',
970 'age_limit': 18,
971 'uploader': 'www.handjobhub.com',
972 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
973 }
974 },
975 # Multiple brightcove videos
976 # https://github.com/ytdl-org/youtube-dl/issues/2283
977 {
978 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
979 'info_dict': {
980 'id': 'always-never',
981 'title': 'Always / Never - The New Yorker',
982 },
983 'playlist_count': 3,
984 'params': {
985 'extract_flat': False,
986 'skip_download': True,
987 }
988 },
989 # MLB embed
990 {
991 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
992 'md5': '96f09a37e44da40dd083e12d9a683327',
993 'info_dict': {
994 'id': '33322633',
995 'ext': 'mp4',
996 'title': 'Ump changes call to ball',
997 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
998 'duration': 48,
999 'timestamp': 1401537900,
1000 'upload_date': '20140531',
1001 'thumbnail': r're:^https?://.*\.jpg$',
1002 },
1003 },
1004 # Wistia embed
1005 {
1006 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1007 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1008 'info_dict': {
1009 'id': '6e2wtrbdaf',
1010 'ext': 'mov',
1011 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1012 'description': 'a Paywall Videos video from Remilon',
1013 'duration': 644.072,
1014 'uploader': 'study.com',
1015 'timestamp': 1459678540,
1016 'upload_date': '20160403',
1017 'filesize': 24687186,
1018 },
1019 },
1020 {
1021 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1022 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1023 'info_dict': {
1024 'id': 'uxjb0lwrcz',
1025 'ext': 'mp4',
1026 'title': 'Conversation about Hexagonal Rails Part 1',
1027 'description': 'a Martin Fowler video from ThoughtWorks',
1028 'duration': 1715.0,
1029 'uploader': 'thoughtworks.wistia.com',
1030 'timestamp': 1401832161,
1031 'upload_date': '20140603',
1032 },
1033 },
1034 # Wistia standard embed (async)
1035 {
1036 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1037 'info_dict': {
1038 'id': '807fafadvk',
1039 'ext': 'mp4',
1040 'title': 'Drip Brennan Dunn Workshop',
1041 'description': 'a JV Webinars video from getdrip-1',
1042 'duration': 4986.95,
1043 'timestamp': 1463607249,
1044 'upload_date': '20160518',
1045 },
1046 'params': {
1047 'skip_download': True,
1048 }
1049 },
1050 # Soundcloud embed
1051 {
1052 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1053 'info_dict': {
1054 'id': '174391317',
1055 'ext': 'mp3',
1056 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1057 'uploader': 'Sophos Security',
1058 'title': 'Chet Chat 171 - Oct 29, 2014',
1059 'upload_date': '20141029',
1060 }
1061 },
1062 # Soundcloud multiple embeds
1063 {
1064 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1065 'info_dict': {
1066 'id': '52809',
1067 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1068 },
1069 'playlist_mincount': 7,
1070 },
1071 # TuneIn station embed
1072 {
1073 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1074 'info_dict': {
1075 'id': '204146',
1076 'ext': 'mp3',
1077 'title': 'CNRV',
1078 'location': 'Paris, France',
1079 'is_live': True,
1080 },
1081 'params': {
1082 # Live stream
1083 'skip_download': True,
1084 },
1085 },
1086 # Livestream embed
1087 {
1088 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1089 'info_dict': {
1090 'id': '67864563',
1091 'ext': 'flv',
1092 'upload_date': '20141112',
1093 'title': 'Rosetta #CometLanding webcast HL 10',
1094 }
1095 },
1096 # Another Livestream embed, without 'new.' in URL
1097 {
1098 'url': 'https://www.freespeech.org/',
1099 'info_dict': {
1100 'id': '123537347',
1101 'ext': 'mp4',
1102 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1103 },
1104 'params': {
1105 # Live stream
1106 'skip_download': True,
1107 },
1108 },
1109 # LazyYT
1110 {
1111 'url': 'https://skiplagged.com/',
1112 'info_dict': {
1113 'id': 'skiplagged',
1114 'title': 'Skiplagged: The smart way to find cheap flights',
1115 },
1116 'playlist_mincount': 1,
1117 'add_ie': ['Youtube'],
1118 },
1119 # Cinchcast embed
1120 {
1121 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1122 'info_dict': {
1123 'id': '7141703',
1124 'ext': 'mp3',
1125 'upload_date': '20141126',
1126 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1127 }
1128 },
1129 # Cinerama player
1130 {
1131 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1132 'info_dict': {
1133 'id': '730m_DandD_1901_512k',
1134 'ext': 'mp4',
1135 'uploader': 'www.abc.net.au',
1136 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1137 }
1138 },
1139 # embedded viddler video
1140 {
1141 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1142 'info_dict': {
1143 'id': '4d03aad9',
1144 'ext': 'mp4',
1145 'uploader': 'deadspin',
1146 'title': 'WALL-TO-GORTAT',
1147 'timestamp': 1422285291,
1148 'upload_date': '20150126',
1149 },
1150 'add_ie': ['Viddler'],
1151 },
1152 # Libsyn embed
1153 {
1154 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1155 'info_dict': {
1156 'id': '3377616',
1157 'ext': 'mp3',
1158 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1159 'description': 'md5:601cb790edd05908957dae8aaa866465',
1160 'upload_date': '20150220',
1161 },
1162 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1163 },
1164 # jwplayer YouTube
1165 {
1166 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1167 'info_dict': {
1168 'id': 'Mrj4DVp2zeA',
1169 'ext': 'mp4',
1170 'upload_date': '20150212',
1171 'uploader': 'The National Archives UK',
1172 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1173 'uploader_id': 'NationalArchives08',
1174 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1175 },
1176 },
1177 # jwplayer rtmp
1178 {
1179 'url': 'http://www.suffolk.edu/sjc/live.php',
1180 'info_dict': {
1181 'id': 'live',
1182 'ext': 'flv',
1183 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1184 'uploader': 'www.suffolk.edu',
1185 },
1186 'params': {
1187 'skip_download': True,
1188 },
1189 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1190 },
1191 # jwplayer with only the json URL
1192 {
1193 'url': 'https://www.hollywoodreporter.com/news/general-news/dunkirk-team-reveals-what-christopher-nolan-said-oscar-win-meet-your-oscar-winner-1092454',
1194 'info_dict': {
1195 'id': 'TljWkvWH',
1196 'ext': 'mp4',
1197 'upload_date': '20180306',
1198 'title': 'md5:91eb1862f6526415214f62c00b453936',
1199 'description': 'md5:73048ae50ae953da10549d1d2fe9b3aa',
1200 'timestamp': 1520367225,
1201 },
1202 'params': {
1203 'skip_download': True,
1204 },
1205 },
1206 # Complex jwplayer
1207 {
1208 'url': 'http://www.indiedb.com/games/king-machine/videos',
1209 'info_dict': {
1210 'id': 'videos',
1211 'ext': 'mp4',
1212 'title': 'king machine trailer 1',
1213 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1214 'thumbnail': r're:^https?://.*\.jpg$',
1215 },
1216 },
1217 {
1218 # JWPlayer config passed as variable
1219 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1220 'info_dict': {
1221 'id': '3326530_hq',
1222 'ext': 'mp4',
1223 'title': 'ARIELE | Tube Cup',
1224 'uploader': 'www.txxx.com',
1225 'age_limit': 18,
1226 },
1227 'params': {
1228 'skip_download': True,
1229 }
1230 },
1231 {
1232 # JWPlatform iframe
1233 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
1234 'info_dict': {
1235 'id': 'AG26UQXM',
1236 'ext': 'mp4',
1237 'upload_date': '20160719',
1238 'timestamp': 468923808,
1239 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
1240 },
1241 'add_ie': [JWPlatformIE.ie_key()],
1242 },
1243 {
1244 # Video.js embed, multiple formats
1245 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1246 'info_dict': {
1247 'id': 'yygqldloqIk',
1248 'ext': 'mp4',
1249 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1250 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1251 'upload_date': '20130314',
1252 'uploader': 'PROстое3D',
1253 'uploader_id': 'PROstoe3D',
1254 },
1255 'params': {
1256 'skip_download': True,
1257 },
1258 },
1259 {
1260 # Video.js embed, single format
1261 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1262 'info_dict': {
1263 'id': 'watch',
1264 'ext': 'mp4',
1265 'title': 'Step 1 - Good Foundation',
1266 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1267 },
1268 'params': {
1269 'skip_download': True,
1270 },
1271 },
1272 # rtl.nl embed
1273 {
1274 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1275 'playlist_mincount': 5,
1276 'info_dict': {
1277 'id': 'aanslagen-kopenhagen',
1278 'title': 'Aanslagen Kopenhagen',
1279 }
1280 },
1281 # Zapiks embed
1282 {
1283 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1284 'info_dict': {
1285 'id': '118046',
1286 'ext': 'mp4',
1287 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1288 }
1289 },
1290 # Kaltura embed (different embed code)
1291 {
1292 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1293 'info_dict': {
1294 'id': '1_a52wc67y',
1295 'ext': 'flv',
1296 'upload_date': '20150127',
1297 'uploader_id': 'PremierMedia',
1298 'timestamp': int,
1299 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1300 },
1301 },
1302 # Kaltura embed with single quotes
1303 {
1304 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1305 'info_dict': {
1306 'id': '0_izeg5utt',
1307 'ext': 'mp4',
1308 'title': '35871',
1309 'timestamp': 1355743100,
1310 'upload_date': '20121217',
1311 'uploader_id': 'cplapp@learn360.com',
1312 },
1313 'add_ie': ['Kaltura'],
1314 },
1315 {
1316 # Kaltura embedded via quoted entry_id
1317 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1318 'info_dict': {
1319 'id': '0_utuok90b',
1320 'ext': 'mp4',
1321 'title': '06_matthew_brender_raj_dutt',
1322 'timestamp': 1466638791,
1323 'upload_date': '20160622',
1324 },
1325 'add_ie': ['Kaltura'],
1326 'expected_warnings': [
1327 'Could not send HEAD request'
1328 ],
1329 'params': {
1330 'skip_download': True,
1331 }
1332 },
1333 {
1334 # Kaltura embedded, some fileExt broken (#11480)
1335 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1336 'info_dict': {
1337 'id': '1_sgtvehim',
1338 'ext': 'mp4',
1339 'title': 'Our "Standard Models" of particle physics and cosmology',
1340 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1341 'timestamp': 1321158993,
1342 'upload_date': '20111113',
1343 'uploader_id': 'kps1',
1344 },
1345 'add_ie': ['Kaltura'],
1346 },
1347 {
1348 # Kaltura iframe embed
1349 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1350 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1351 'info_dict': {
1352 'id': '0_f2cfbpwy',
1353 'ext': 'mp4',
1354 'title': 'I. M. Pei: A Centennial Celebration',
1355 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1356 'upload_date': '20170403',
1357 'uploader_id': 'batchUser',
1358 'timestamp': 1491232186,
1359 },
1360 'add_ie': ['Kaltura'],
1361 },
1362 {
1363 # Kaltura iframe embed, more sophisticated
1364 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1365 'info_dict': {
1366 'id': '1_9gzouybz',
1367 'ext': 'mp4',
1368 'title': 'lecture-05sep2017',
1369 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1370 'upload_date': '20170913',
1371 'uploader_id': 'eps2',
1372 'timestamp': 1505340777,
1373 },
1374 'params': {
1375 'skip_download': True,
1376 },
1377 'add_ie': ['Kaltura'],
1378 },
1379 {
1380 # meta twitter:player
1381 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1382 'info_dict': {
1383 'id': '0_01b42zps',
1384 'ext': 'mp4',
1385 'title': 'Main Twerk (Video)',
1386 'upload_date': '20171208',
1387 'uploader_id': 'sebastian.salinas@thechive.com',
1388 'timestamp': 1512713057,
1389 },
1390 'params': {
1391 'skip_download': True,
1392 },
1393 'add_ie': ['Kaltura'],
1394 },
1395 # referrer protected EaglePlatform embed
1396 {
1397 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1398 'info_dict': {
1399 'id': '582306',
1400 'ext': 'mp4',
1401 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1402 'thumbnail': r're:^https?://.*\.jpg$',
1403 'duration': 3382,
1404 'view_count': int,
1405 },
1406 'params': {
1407 'skip_download': True,
1408 },
1409 },
1410 # ClipYou (EaglePlatform) embed (custom URL)
1411 {
1412 'url': 'http://muz-tv.ru/play/7129/',
1413 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1414 'info_dict': {
1415 'id': '12820',
1416 'ext': 'mp4',
1417 'title': "'O Sole Mio",
1418 'thumbnail': r're:^https?://.*\.jpg$',
1419 'duration': 216,
1420 'view_count': int,
1421 },
1422 'params': {
1423 'skip_download': True,
1424 },
1425 'skip': 'This video is unavailable.',
1426 },
1427 # Pladform embed
1428 {
1429 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1430 'info_dict': {
1431 'id': '100183293',
1432 'ext': 'mp4',
1433 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1434 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1435 'thumbnail': r're:^https?://.*\.jpg$',
1436 'duration': 694,
1437 'age_limit': 0,
1438 },
1439 'skip': 'HTTP Error 404: Not Found',
1440 },
1441 # Playwire embed
1442 {
1443 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1444 'info_dict': {
1445 'id': '3519514',
1446 'ext': 'mp4',
1447 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1448 'thumbnail': r're:^https?://.*\.png$',
1449 'duration': 45.115,
1450 },
1451 },
1452 # 5min embed
1453 {
1454 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1455 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1456 'info_dict': {
1457 'id': '518726732',
1458 'ext': 'mp4',
1459 'title': 'Facebook Creates "On This Day" | Crunch Report',
1460 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1461 'timestamp': 1427237531,
1462 'uploader': 'Crunch Report',
1463 'upload_date': '20150324',
1464 },
1465 'params': {
1466 # m3u8 download
1467 'skip_download': True,
1468 },
1469 },
1470 # Crooks and Liars embed
1471 {
1472 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1473 'info_dict': {
1474 'id': '8RUoRhRi',
1475 'ext': 'mp4',
1476 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1477 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1478 'timestamp': 1428207000,
1479 'upload_date': '20150405',
1480 'uploader': 'Heather',
1481 },
1482 },
1483 # Crooks and Liars external embed
1484 {
1485 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1486 'info_dict': {
1487 'id': 'MTE3MjUtMzQ2MzA',
1488 'ext': 'mp4',
1489 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1490 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1491 'timestamp': 1265032391,
1492 'upload_date': '20100201',
1493 'uploader': 'Heather',
1494 },
1495 },
1496 # NBC Sports vplayer embed
1497 {
1498 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1499 'info_dict': {
1500 'id': 'ln7x1qSThw4k',
1501 'ext': 'flv',
1502 'title': "PFT Live: New leader in the 'new-look' defense",
1503 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1504 'uploader': 'NBCU-SPORTS',
1505 'upload_date': '20140107',
1506 'timestamp': 1389118457,
1507 },
1508 'skip': 'Invalid Page URL',
1509 },
1510 # NBC News embed
1511 {
1512 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1513 'md5': '1aa589c675898ae6d37a17913cf68d66',
1514 'info_dict': {
1515 'id': 'x_dtl_oa_LettermanliftPR_160608',
1516 'ext': 'mp4',
1517 'title': 'David Letterman: A Preview',
1518 '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.',
1519 'upload_date': '20160609',
1520 'timestamp': 1465431544,
1521 'uploader': 'NBCU-NEWS',
1522 },
1523 },
1524 # UDN embed
1525 {
1526 'url': 'https://video.udn.com/news/300346',
1527 'md5': 'fd2060e988c326991037b9aff9df21a6',
1528 'info_dict': {
1529 'id': '300346',
1530 'ext': 'mp4',
1531 'title': '中一中男師變性 全校師生力挺',
1532 'thumbnail': r're:^https?://.*\.jpg$',
1533 },
1534 'params': {
1535 # m3u8 download
1536 'skip_download': True,
1537 },
1538 'expected_warnings': ['Failed to parse JSON Expecting value'],
1539 },
1540 # Brightcove URL in single quotes
1541 {
1542 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1543 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1544 'info_dict': {
1545 'id': '4255764656001',
1546 'ext': 'mp4',
1547 'title': 'SN Presents: Russell Martin, World Citizen',
1548 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1549 'uploader': 'Rogers Sportsnet',
1550 'uploader_id': '1704050871',
1551 'upload_date': '20150525',
1552 'timestamp': 1432570283,
1553 },
1554 },
1555 # Kinja embed
1556 {
1557 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1558 'info_dict': {
1559 'id': '106351',
1560 'ext': 'mp4',
1561 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1562 'description': 'Migrated from OnionStudios',
1563 'thumbnail': r're:^https?://.*\.jpe?g$',
1564 'uploader': 'clickhole',
1565 'upload_date': '20150527',
1566 'timestamp': 1432744860,
1567 }
1568 },
1569 # SnagFilms embed
1570 {
1571 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1572 'info_dict': {
1573 'id': '74849a00-85a9-11e1-9660-123139220831',
1574 'ext': 'mp4',
1575 'title': '#whilewewatch',
1576 }
1577 },
1578 # AdobeTVVideo embed
1579 {
1580 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1581 'md5': '43662b577c018ad707a63766462b1e87',
1582 'info_dict': {
1583 'id': '2456',
1584 'ext': 'mp4',
1585 'title': 'New experience with Acrobat DC',
1586 'description': 'New experience with Acrobat DC',
1587 'duration': 248.667,
1588 },
1589 },
1590 # BrightcoveInPageEmbed embed
1591 {
1592 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1593 'info_dict': {
1594 'id': '4238694884001',
1595 'ext': 'flv',
1596 'title': 'Tabletop: Dread, Last Thoughts',
1597 'description': 'Tabletop: Dread, Last Thoughts',
1598 'duration': 51690,
1599 },
1600 },
1601 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1602 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1603 {
1604 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1605 'info_dict': {
1606 'id': '4785848093001',
1607 'ext': 'mp4',
1608 'title': 'The Cardinal Pell Interview',
1609 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1610 'uploader': 'GlobeCast Australia - GlobeStream',
1611 'uploader_id': '2733773828001',
1612 'upload_date': '20160304',
1613 'timestamp': 1457083087,
1614 },
1615 'params': {
1616 # m3u8 downloads
1617 'skip_download': True,
1618 },
1619 },
1620 {
1621 # Brightcove embed with whitespace around attribute names
1622 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1623 'info_dict': {
1624 'id': '3167554373001',
1625 'ext': 'mp4',
1626 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1627 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1628 'uploader_id': '1079349493',
1629 'upload_date': '20140207',
1630 'timestamp': 1391810548,
1631 },
1632 'params': {
1633 'skip_download': True,
1634 },
1635 },
1636 # Another form of arte.tv embed
1637 {
1638 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1639 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1640 'info_dict': {
1641 'id': '030273-562_PLUS7-F',
1642 'ext': 'mp4',
1643 'title': 'ARTE Reportage - Nulle part, en France',
1644 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1645 'upload_date': '20160409',
1646 },
1647 },
1648 # Duplicated embedded video URLs
1649 {
1650 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1651 'info_dict': {
1652 'id': '149298443_480_16c25b74_2',
1653 'ext': 'mp4',
1654 'title': 'vs. Blue Orange Spring Game',
1655 'uploader': 'www.hudl.com',
1656 },
1657 },
1658 # twitter:player:stream embed
1659 {
1660 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1661 'info_dict': {
1662 'id': 'master',
1663 'ext': 'mp4',
1664 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1665 'uploader': 'www.rtl.be',
1666 },
1667 'params': {
1668 # m3u8 downloads
1669 'skip_download': True,
1670 },
1671 },
1672 # twitter:player embed
1673 {
1674 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1675 'md5': 'a3e0df96369831de324f0778e126653c',
1676 'info_dict': {
1677 'id': '4909620399001',
1678 'ext': 'mp4',
1679 'title': 'What Do Black Holes Sound Like?',
1680 'description': 'what do black holes sound like',
1681 'upload_date': '20160524',
1682 'uploader_id': '29913724001',
1683 'timestamp': 1464107587,
1684 'uploader': 'TheAtlantic',
1685 },
1686 'add_ie': ['BrightcoveLegacy'],
1687 },
1688 # Facebook <iframe> embed
1689 {
1690 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1691 'md5': 'fbcde74f534176ecb015849146dd3aee',
1692 'info_dict': {
1693 'id': '599637780109885',
1694 'ext': 'mp4',
1695 'title': 'Facebook video #599637780109885',
1696 },
1697 },
1698 # Facebook <iframe> embed, plugin video
1699 {
1700 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1701 'info_dict': {
1702 'id': '1754168231264132',
1703 'ext': 'mp4',
1704 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1705 'uploader': 'Tariq Ramadan (official)',
1706 'timestamp': 1496758379,
1707 'upload_date': '20170606',
1708 },
1709 'params': {
1710 'skip_download': True,
1711 },
1712 },
1713 # Facebook API embed
1714 {
1715 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1716 'md5': 'a47372ee61b39a7b90287094d447d94e',
1717 'info_dict': {
1718 'id': '10153467542406923',
1719 'ext': 'mp4',
1720 'title': 'Facebook video #10153467542406923',
1721 },
1722 },
1723 # Wordpress "YouTube Video Importer" plugin
1724 {
1725 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1726 'md5': 'd16797741b560b485194eddda8121b48',
1727 'info_dict': {
1728 'id': 'HNTXWDXV9Is',
1729 'ext': 'mp4',
1730 'title': 'Blue Devils Drumline Stanford lot 2016',
1731 'upload_date': '20160627',
1732 'uploader_id': 'GENOCIDE8GENERAL10',
1733 'uploader': 'cylus cyrus',
1734 },
1735 },
1736 {
1737 # video stored on custom kaltura server
1738 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1739 'md5': '537617d06e64dfed891fa1593c4b30cc',
1740 'info_dict': {
1741 'id': '0_1iotm5bh',
1742 'ext': 'mp4',
1743 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1744 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1745 'uploader_id': 'videos.expansion@el-mundo.net',
1746 'upload_date': '20150429',
1747 'timestamp': 1430303472,
1748 },
1749 'add_ie': ['Kaltura'],
1750 },
1751 {
1752 # multiple kaltura embeds, nsfw
1753 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1754 'info_dict': {
1755 'id': 'kamila-avec-video-jaime-sadomie',
1756 'title': "Kamila avec vídeo “J'aime sadomie”",
1757 },
1758 'playlist_count': 8,
1759 },
1760 {
1761 # Non-standard Vimeo embed
1762 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1763 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1764 'info_dict': {
1765 'id': '148867247',
1766 'ext': 'mp4',
1767 'title': 'Understanding the web - Teaser',
1768 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1769 'upload_date': '20151214',
1770 'uploader': 'OpenClassrooms',
1771 'uploader_id': 'openclassrooms',
1772 },
1773 'add_ie': ['Vimeo'],
1774 },
1775 {
1776 # generic vimeo embed that requires original URL passed as Referer
1777 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1778 'only_matching': True,
1779 },
1780 {
1781 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1782 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1783 'info_dict': {
1784 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1785 'ext': 'mp4',
1786 'title': 'Big Buck Bunny',
1787 'description': 'Royalty free test video',
1788 'timestamp': 1432816365,
1789 'upload_date': '20150528',
1790 'is_live': False,
1791 },
1792 'params': {
1793 'skip_download': True,
1794 },
1795 'add_ie': [ArkenaIE.ie_key()],
1796 },
1797 {
1798 '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/',
1799 'info_dict': {
1800 'id': '1c7141f46c',
1801 'ext': 'mp4',
1802 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1803 },
1804 'params': {
1805 'skip_download': True,
1806 },
1807 'add_ie': [Vbox7IE.ie_key()],
1808 },
1809 {
1810 # DBTV embeds
1811 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1812 'info_dict': {
1813 'id': '43254897',
1814 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1815 },
1816 'playlist_mincount': 3,
1817 },
1818 {
1819 # Videa embeds
1820 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1821 'info_dict': {
1822 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1823 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1824 },
1825 'playlist_mincount': 2,
1826 },
1827 {
1828 # 20 minuten embed
1829 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1830 'info_dict': {
1831 'id': '523629',
1832 'ext': 'mp4',
1833 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1834 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1835 },
1836 'params': {
1837 'skip_download': True,
1838 },
1839 'add_ie': [TwentyMinutenIE.ie_key()],
1840 },
1841 {
1842 # VideoPress embed
1843 'url': 'https://en.support.wordpress.com/videopress/',
1844 'info_dict': {
1845 'id': 'OcobLTqC',
1846 'ext': 'm4v',
1847 'title': 'IMG_5786',
1848 'timestamp': 1435711927,
1849 'upload_date': '20150701',
1850 },
1851 'params': {
1852 'skip_download': True,
1853 },
1854 'add_ie': [VideoPressIE.ie_key()],
1855 },
1856 {
1857 # Rutube embed
1858 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1859 'info_dict': {
1860 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1861 'ext': 'flv',
1862 'title': 'Магаззино: Казань 2',
1863 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1864 'uploader': 'Магаззино',
1865 'upload_date': '20170228',
1866 'uploader_id': '996642',
1867 },
1868 'params': {
1869 'skip_download': True,
1870 },
1871 'add_ie': [RutubeIE.ie_key()],
1872 },
1873 {
1874 # ThePlatform embedded with whitespaces in URLs
1875 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1876 'only_matching': True,
1877 },
1878 {
1879 # Senate ISVP iframe https
1880 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1881 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1882 'info_dict': {
1883 'id': 'govtaff020316',
1884 'ext': 'mp4',
1885 'title': 'Integrated Senate Video Player',
1886 },
1887 'add_ie': [SenateISVPIE.ie_key()],
1888 },
1889 {
1890 # Limelight embeds (1 channel embed + 4 media embeds)
1891 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1892 'info_dict': {
1893 'id': 'FacilitatorTraining2017',
1894 'title': 'Facilitator Training 2017',
1895 },
1896 'playlist_mincount': 5,
1897 },
1898 {
1899 # Limelight embed (LimelightPlayerUtil.embed)
1900 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1901 'info_dict': {
1902 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1903 'ext': 'mp4',
1904 'title': '07448641',
1905 'timestamp': 1499890639,
1906 'upload_date': '20170712',
1907 },
1908 'params': {
1909 'skip_download': True,
1910 },
1911 'add_ie': ['LimelightMedia'],
1912 },
1913 {
1914 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1915 'info_dict': {
1916 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1917 'title': 'Standoff with Walnut Creek murder suspect ends',
1918 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1919 },
1920 'playlist_mincount': 4,
1921 },
1922 {
1923 # WashingtonPost embed
1924 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1925 'info_dict': {
1926 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1927 'ext': 'mp4',
1928 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1929 '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.',
1930 'timestamp': 1455216756,
1931 'uploader': 'The Washington Post',
1932 'upload_date': '20160211',
1933 },
1934 'add_ie': [WashingtonPostIE.ie_key()],
1935 },
1936 {
1937 # Mediaset embed
1938 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1939 'info_dict': {
1940 'id': '720642',
1941 'ext': 'mp4',
1942 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1943 },
1944 'params': {
1945 'skip_download': True,
1946 },
1947 'add_ie': [MediasetIE.ie_key()],
1948 },
1949 {
1950 # JOJ.sk embeds
1951 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1952 'info_dict': {
1953 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1954 'title': 'Slovenskom sa prehnala vlna silných búrok',
1955 },
1956 'playlist_mincount': 5,
1957 'add_ie': [JojIE.ie_key()],
1958 },
1959 {
1960 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1961 'url': 'https://tvrain.ru/amp/418921/',
1962 'md5': 'cc00413936695987e8de148b67d14f1d',
1963 'info_dict': {
1964 'id': '418921',
1965 'ext': 'mp4',
1966 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1967 },
1968 },
1969 {
1970 # vzaar embed
1971 'url': 'http://help.vzaar.com/article/165-embedding-video',
1972 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1973 'info_dict': {
1974 'id': '8707641',
1975 'ext': 'mp4',
1976 'title': 'Building A Business Online: Principal Chairs Q & A',
1977 },
1978 },
1979 {
1980 # multiple HTML5 videos on one page
1981 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1982 'info_dict': {
1983 'id': 'keyscenarios',
1984 'title': 'Rescue Kit 14 Free Edition - Getting started',
1985 },
1986 'playlist_count': 4,
1987 },
1988 {
1989 # vshare embed
1990 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1991 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1992 'info_dict': {
1993 'id': '0f64ce6',
1994 'title': 'vl14062007715967',
1995 'ext': 'mp4',
1996 }
1997 },
1998 {
1999 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2000 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2001 'info_dict': {
2002 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2003 'ext': 'mp4',
2004 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2005 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2006 'timestamp': 1474354800,
2007 'upload_date': '20160920',
2008 }
2009 },
2010 {
2011 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2012 'info_dict': {
2013 'id': '1731611',
2014 'ext': 'mp4',
2015 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2016 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2017 'timestamp': 1516100691,
2018 'upload_date': '20180116',
2019 },
2020 'params': {
2021 'skip_download': True,
2022 },
2023 'add_ie': [SpringboardPlatformIE.ie_key()],
2024 },
2025 {
2026 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2027 'info_dict': {
2028 'id': 'vMDE4NzI1Mjgt690b',
2029 'ext': 'mp4',
2030 'title': 'Котята',
2031 },
2032 'add_ie': [YapFilesIE.ie_key()],
2033 'params': {
2034 'skip_download': True,
2035 },
2036 },
2037 {
2038 # CloudflareStream embed
2039 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2040 'info_dict': {
2041 'id': '31c9291ab41fac05471db4e73aa11717',
2042 'ext': 'mp4',
2043 'title': '31c9291ab41fac05471db4e73aa11717',
2044 },
2045 'add_ie': [CloudflareStreamIE.ie_key()],
2046 'params': {
2047 'skip_download': True,
2048 },
2049 },
2050 {
2051 # PeerTube embed
2052 'url': 'https://joinpeertube.org/fr/home/',
2053 'info_dict': {
2054 'id': 'home',
2055 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2056 },
2057 'playlist_count': 2,
2058 },
2059 {
2060 # Indavideo embed
2061 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2062 'info_dict': {
2063 'id': '1693903',
2064 'ext': 'mp4',
2065 'title': 'Így kell otthon hamburgert sütni',
2066 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2067 'timestamp': 1426330212,
2068 'upload_date': '20150314',
2069 'uploader': 'StreetKitchen',
2070 'uploader_id': '546363',
2071 },
2072 'add_ie': [IndavideoEmbedIE.ie_key()],
2073 'params': {
2074 'skip_download': True,
2075 },
2076 },
2077 {
2078 # APA embed via JWPlatform embed
2079 'url': 'http://www.vol.at/blue-man-group/5593454',
2080 'info_dict': {
2081 'id': 'jjv85FdZ',
2082 'ext': 'mp4',
2083 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2084 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2085 'thumbnail': r're:^https?://.*\.jpg$',
2086 'duration': 254,
2087 'timestamp': 1519211149,
2088 'upload_date': '20180221',
2089 },
2090 'params': {
2091 'skip_download': True,
2092 },
2093 },
2094 {
2095 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2096 'md5': 'b68d276de422ab07ee1d49388103f457',
2097 'info_dict': {
2098 'id': '83645793',
2099 'title': 'Lock up and get excited',
2100 'ext': 'mp4'
2101 },
2102 'skip': 'TODO: fix nested playlists processing in tests',
2103 },
2104 {
2105 # Viqeo embeds
2106 'url': 'https://viqeo.tv/',
2107 'info_dict': {
2108 'id': 'viqeo',
2109 'title': 'All-new video platform',
2110 },
2111 'playlist_count': 6,
2112 },
2113 {
2114 # Squarespace video embed, 2019-08-28
2115 'url': 'http://ootboxford.com',
2116 'info_dict': {
2117 'id': 'Tc7b_JGdZfw',
2118 'title': 'Out of the Blue, at Childish Things 10',
2119 'ext': 'mp4',
2120 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2121 'uploader_id': 'helendouglashouse',
2122 'uploader': 'Helen & Douglas House',
2123 'upload_date': '20140328',
2124 },
2125 'params': {
2126 'skip_download': True,
2127 },
2128 },
2129 # {
2130 # # Zype embed
2131 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2132 # 'info_dict': {
2133 # 'id': '5b400b834b32992a310622b9',
2134 # 'ext': 'mp4',
2135 # 'title': 'Smoky Barbecue Favorites',
2136 # 'thumbnail': r're:^https?://.*\.jpe?g',
2137 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2138 # 'upload_date': '20170909',
2139 # 'timestamp': 1504915200,
2140 # },
2141 # 'add_ie': [ZypeIE.ie_key()],
2142 # 'params': {
2143 # 'skip_download': True,
2144 # },
2145 # },
2146 {
2147 # videojs embed
2148 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2149 'info_dict': {
2150 'id': 'shell',
2151 'ext': 'mp4',
2152 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2153 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2154 'thumbnail': r're:^https?://.*\.jpg$',
2155 },
2156 'params': {
2157 'skip_download': True,
2158 },
2159 'expected_warnings': ['Failed to download MPD manifest'],
2160 },
2161 {
2162 # DailyMotion embed with DM.player
2163 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2164 'info_dict': {
2165 'id': 'k6aKkGHd9FJs4mtJN39',
2166 'ext': 'mp4',
2167 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2168 'description': 'This video is private.',
2169 'uploader_id': 'x1jf30l',
2170 'uploader': 'beIN SPORTS USA',
2171 'upload_date': '20190528',
2172 'timestamp': 1559062971,
2173 },
2174 'params': {
2175 'skip_download': True,
2176 },
2177 },
2178 # {
2179 # # TODO: find another test
2180 # # http://schema.org/VideoObject
2181 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2182 # 'md5': '888dcf08b7ea671381f00fab74692755',
2183 # 'info_dict': {
2184 # 'id': 'nyvTSJMKId',
2185 # 'ext': 'mp4',
2186 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2187 # 'description': '#love for cats.',
2188 # 'timestamp': 1461244995,
2189 # 'upload_date': '20160421',
2190 # },
2191 # 'params': {
2192 # 'force_generic_extractor': True,
2193 # },
2194 # },
2195 {
2196 # VHX Embed
2197 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2198 'info_dict': {
2199 'id': '858208',
2200 'ext': 'mp4',
2201 'title': 'Untitled',
2202 'uploader_id': 'user80538407',
2203 'uploader': 'OTT Videos',
2204 },
2205 },
2206 {
2207 # ArcPublishing PoWa video player
2208 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2209 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2210 'info_dict': {
2211 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2212 'ext': 'mp4',
2213 'title': 'Senate candidates wave to voters on Anchorage streets',
2214 'description': 'md5:91f51a6511f090617353dc720318b20e',
2215 'timestamp': 1604378735,
2216 'upload_date': '20201103',
2217 'duration': 1581,
2218 },
2219 },
2220 {
2221 # MyChannels SDK embed
2222 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2223 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2224 'md5': '90c0699c37006ef18e198c032d81739c',
2225 'info_dict': {
2226 'id': '194165',
2227 'ext': 'mp4',
2228 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2229 'timestamp': 1611740340,
2230 'upload_date': '20210127',
2231 'duration': 159,
2232 },
2233 },
2234 {
2235 # Simplecast player embed
2236 'url': 'https://www.bio.org/podcast',
2237 'info_dict': {
2238 'id': 'podcast',
2239 'title': 'I AM BIO Podcast | BIO',
2240 },
2241 'playlist_mincount': 52,
2242 },
2243 {
2244 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2245 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2246 'only_matching': True,
2247 }, {
2248 # WimTv embed player
2249 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2250 'info_dict': {
2251 'id': 'wearefmi-pt-2-2021',
2252 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2253 },
2254 'playlist_count': 1,
2255 }, {
2256 # KVS Player
2257 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2258 'info_dict': {
2259 'id': '105',
2260 'display_id': 'kelis-4th-of-july',
2261 'ext': 'mp4',
2262 'title': 'Kelis - 4th Of July',
2263 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2264 },
2265 'params': {
2266 'skip_download': True,
2267 },
2268 }, {
2269 # KVS Player
2270 'url': 'https://www.kvs-demo.com/embed/105/',
2271 'info_dict': {
2272 'id': '105',
2273 'display_id': 'kelis-4th-of-july',
2274 'ext': 'mp4',
2275 'title': 'Kelis - 4th Of July / Embed Player',
2276 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2277 },
2278 'params': {
2279 'skip_download': True,
2280 },
2281 }, {
2282 # KVS Player
2283 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2284 'md5': '3397979512c682f6b85b3b04989df224',
2285 'info_dict': {
2286 'id': '2400174',
2287 'display_id': 'french-boy-pantsed',
2288 'ext': 'mp4',
2289 'title': 'French Boy Pantsed - ThisVid.com',
2290 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2291 }
2292 }, {
2293 # KVS Player
2294 'url': 'https://thisvid.com/embed/2400174/',
2295 'md5': '3397979512c682f6b85b3b04989df224',
2296 'info_dict': {
2297 'id': '2400174',
2298 'display_id': 'french-boy-pantsed',
2299 'ext': 'mp4',
2300 'title': 'French Boy Pantsed - ThisVid.com',
2301 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2302 }
2303 }, {
2304 # KVS Player
2305 'url': 'https://youix.com/video/leningrad-zoj/',
2306 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2307 'info_dict': {
2308 'id': '18485',
2309 'display_id': 'leningrad-zoj',
2310 'ext': 'mp4',
2311 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2312 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2313 }
2314 }, {
2315 # KVS Player
2316 'url': 'https://youix.com/embed/18485',
2317 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2318 'info_dict': {
2319 'id': '18485',
2320 'display_id': 'leningrad-zoj',
2321 'ext': 'mp4',
2322 'title': 'Ленинград - ЗОЖ',
2323 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2324 }
2325 }, {
2326 # KVS Player
2327 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2328 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2329 'info_dict': {
2330 'id': '21217',
2331 'display_id': '40-nochey-40-nights-2016',
2332 'ext': 'mp4',
2333 'title': '40 ночей (2016) - BogMedia.org',
2334 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2335 }
2336 },
2337 ]
2338
2339 def report_following_redirect(self, new_url):
2340 """Report information extraction."""
2341 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2342
2343 def _extract_rss(self, url, video_id, doc):
2344 playlist_title = doc.find('./channel/title').text
2345 playlist_desc_el = doc.find('./channel/description')
2346 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2347
2348 NS_MAP = {
2349 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2350 }
2351
2352 entries = []
2353 for it in doc.findall('./channel/item'):
2354 next_url = None
2355 enclosure_nodes = it.findall('./enclosure')
2356 for e in enclosure_nodes:
2357 next_url = e.attrib.get('url')
2358 if next_url:
2359 break
2360
2361 if not next_url:
2362 next_url = xpath_text(it, 'link', fatal=False)
2363
2364 if not next_url:
2365 continue
2366
2367 def itunes(key):
2368 return xpath_text(
2369 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2370 default=None)
2371
2372 duration = itunes('duration')
2373 explicit = (itunes('explicit') or '').lower()
2374 if explicit in ('true', 'yes'):
2375 age_limit = 18
2376 elif explicit in ('false', 'no'):
2377 age_limit = 0
2378 else:
2379 age_limit = None
2380
2381 entries.append({
2382 '_type': 'url_transparent',
2383 'url': next_url,
2384 'title': it.find('title').text,
2385 'description': xpath_text(it, 'description', default=None),
2386 'timestamp': unified_timestamp(
2387 xpath_text(it, 'pubDate', default=None)),
2388 'duration': int_or_none(duration) or parse_duration(duration),
2389 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2390 'episode': itunes('title'),
2391 'episode_number': int_or_none(itunes('episode')),
2392 'season_number': int_or_none(itunes('season')),
2393 'age_limit': age_limit,
2394 })
2395
2396 return {
2397 '_type': 'playlist',
2398 'id': url,
2399 'title': playlist_title,
2400 'description': playlist_desc,
2401 'entries': entries,
2402 }
2403
2404 def _extract_camtasia(self, url, video_id, webpage):
2405 """ Returns None if no camtasia video can be found. """
2406
2407 camtasia_cfg = self._search_regex(
2408 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2409 webpage, 'camtasia configuration file', default=None)
2410 if camtasia_cfg is None:
2411 return None
2412
2413 title = self._html_search_meta('DC.title', webpage, fatal=True)
2414
2415 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2416 camtasia_cfg = self._download_xml(
2417 camtasia_url, video_id,
2418 note='Downloading camtasia configuration',
2419 errnote='Failed to download camtasia configuration')
2420 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2421
2422 entries = []
2423 for n in fileset_node.getchildren():
2424 url_n = n.find('./uri')
2425 if url_n is None:
2426 continue
2427
2428 entries.append({
2429 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2430 'title': '%s - %s' % (title, n.tag),
2431 'url': compat_urlparse.urljoin(url, url_n.text),
2432 'duration': float_or_none(n.find('./duration').text),
2433 })
2434
2435 return {
2436 '_type': 'playlist',
2437 'entries': entries,
2438 'title': title,
2439 }
2440
2441 def _kvs_getrealurl(self, video_url, license_code):
2442 if not video_url.startswith('function/0/'):
2443 return video_url # not obfuscated
2444
2445 url_path, _, url_query = video_url.partition('?')
2446 urlparts = url_path.split('/')[2:]
2447 license = self._kvs_getlicensetoken(license_code)
2448 newmagic = urlparts[5][:32]
2449
2450 for o in range(len(newmagic) - 1, -1, -1):
2451 new = ''
2452 l = (o + sum([int(n) for n in license[o:]])) % 32
2453
2454 for i in range(0, len(newmagic)):
2455 if i == o:
2456 new += newmagic[l]
2457 elif i == l:
2458 new += newmagic[o]
2459 else:
2460 new += newmagic[i]
2461 newmagic = new
2462
2463 urlparts[5] = newmagic + urlparts[5][32:]
2464 return '/'.join(urlparts) + '?' + url_query
2465
2466 def _kvs_getlicensetoken(self, license):
2467 modlicense = license.replace('$', '').replace('0', '1')
2468 center = int(len(modlicense) / 2)
2469 fronthalf = int(modlicense[:center + 1])
2470 backhalf = int(modlicense[center:])
2471
2472 modlicense = str(4 * abs(fronthalf - backhalf))
2473 retval = ''
2474 for o in range(0, center + 1):
2475 for i in range(1, 5):
2476 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2477 return retval
2478
2479 def _real_extract(self, url):
2480 if url.startswith('//'):
2481 return self.url_result(self.http_scheme() + url)
2482
2483 parsed_url = compat_urlparse.urlparse(url)
2484 if not parsed_url.scheme:
2485 default_search = self.get_param('default_search')
2486 if default_search is None:
2487 default_search = 'fixup_error'
2488
2489 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2490 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2491 self.report_warning('The url doesn\'t specify the protocol, trying with http')
2492 return self.url_result('http://' + url)
2493 elif default_search != 'fixup_error':
2494 if default_search == 'auto_warning':
2495 if re.match(r'^(?:url|URL)$', url):
2496 raise ExtractorError(
2497 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2498 expected=True)
2499 else:
2500 self.report_warning(
2501 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2502 return self.url_result('ytsearch:' + url)
2503
2504 if default_search in ('error', 'fixup_error'):
2505 raise ExtractorError(
2506 '%r is not a valid URL. '
2507 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
2508 % (url, url), expected=True)
2509 else:
2510 if ':' not in default_search:
2511 default_search += ':'
2512 return self.url_result(default_search + url)
2513
2514 url, smuggled_data = unsmuggle_url(url)
2515 force_videoid = None
2516 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2517 if smuggled_data and 'force_videoid' in smuggled_data:
2518 force_videoid = smuggled_data['force_videoid']
2519 video_id = force_videoid
2520 else:
2521 video_id = self._generic_id(url)
2522
2523 self.to_screen('%s: Requesting header' % video_id)
2524
2525 head_req = HEADRequest(url)
2526 head_response = self._request_webpage(
2527 head_req, video_id,
2528 note=False, errnote='Could not send HEAD request to %s' % url,
2529 fatal=False)
2530
2531 if head_response is not False:
2532 # Check for redirect
2533 new_url = head_response.geturl()
2534 if url != new_url:
2535 self.report_following_redirect(new_url)
2536 if force_videoid:
2537 new_url = smuggle_url(
2538 new_url, {'force_videoid': force_videoid})
2539 return self.url_result(new_url)
2540
2541 full_response = None
2542 if head_response is False:
2543 request = sanitized_Request(url)
2544 request.add_header('Accept-Encoding', '*')
2545 full_response = self._request_webpage(request, video_id)
2546 head_response = full_response
2547
2548 info_dict = {
2549 'id': video_id,
2550 'title': self._generic_title(url),
2551 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2552 }
2553
2554 # Check for direct link to a video
2555 content_type = head_response.headers.get('Content-Type', '').lower()
2556 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2557 if m:
2558 format_id = compat_str(m.group('format_id'))
2559 subtitles = {}
2560 if format_id.endswith('mpegurl'):
2561 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2562 elif format_id == 'f4m':
2563 formats = self._extract_f4m_formats(url, video_id)
2564 else:
2565 formats = [{
2566 'format_id': format_id,
2567 'url': url,
2568 'vcodec': 'none' if m.group('type') == 'audio' else None
2569 }]
2570 info_dict['direct'] = True
2571 self._sort_formats(formats)
2572 info_dict['formats'] = formats
2573 info_dict['subtitles'] = subtitles
2574 return info_dict
2575
2576 if not self.get_param('test', False) and not is_intentional:
2577 force = self.get_param('force_generic_extractor', False)
2578 self.report_warning(
2579 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2580
2581 if not full_response:
2582 request = sanitized_Request(url)
2583 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2584 # making it impossible to download only chunk of the file (yet we need only 512kB to
2585 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
2586 # that will always result in downloading the whole file that is not desirable.
2587 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2588 # to accept raw bytes and being able to download only a chunk.
2589 # It may probably better to solve this by checking Content-Type for application/octet-stream
2590 # after HEAD request finishes, but not sure if we can rely on this.
2591 request.add_header('Accept-Encoding', '*')
2592 full_response = self._request_webpage(request, video_id)
2593
2594 first_bytes = full_response.read(512)
2595
2596 # Is it an M3U playlist?
2597 if first_bytes.startswith(b'#EXTM3U'):
2598 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2599 self._sort_formats(info_dict['formats'])
2600 return info_dict
2601
2602 # Maybe it's a direct link to a video?
2603 # Be careful not to download the whole thing!
2604 if not is_html(first_bytes):
2605 self.report_warning(
2606 'URL could be a direct video link, returning it as such.')
2607 info_dict.update({
2608 'direct': True,
2609 'url': url,
2610 })
2611 return info_dict
2612
2613 webpage = self._webpage_read_content(
2614 full_response, url, video_id, prefix=first_bytes)
2615
2616 if '<title>DPG Media Privacy Gate</title>' in webpage:
2617 webpage = self._download_webpage(url, video_id)
2618
2619 self.report_extraction(video_id)
2620
2621 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2622 try:
2623 try:
2624 doc = compat_etree_fromstring(webpage)
2625 except compat_xml_parse_error:
2626 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2627 if doc.tag == 'rss':
2628 return self._extract_rss(url, video_id, doc)
2629 elif doc.tag == 'SmoothStreamingMedia':
2630 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
2631 self._sort_formats(info_dict['formats'])
2632 return info_dict
2633 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2634 smil = self._parse_smil(doc, url, video_id)
2635 self._sort_formats(smil['formats'])
2636 return smil
2637 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2638 return self.playlist_result(
2639 self._parse_xspf(
2640 doc, video_id, xspf_url=url,
2641 xspf_base_url=full_response.geturl()),
2642 video_id)
2643 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2644 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
2645 doc,
2646 mpd_base_url=full_response.geturl().rpartition('/')[0],
2647 mpd_url=url)
2648 self._sort_formats(info_dict['formats'])
2649 return info_dict
2650 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2651 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2652 self._sort_formats(info_dict['formats'])
2653 return info_dict
2654 except compat_xml_parse_error:
2655 pass
2656
2657 # Is it a Camtasia project?
2658 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2659 if camtasia_res is not None:
2660 return camtasia_res
2661
2662 # Sometimes embedded video player is hidden behind percent encoding
2663 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2664 # Unescaping the whole page allows to handle those cases in a generic way
2665 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2666 # There probably should be a second run of generic extractor on unescaped webpage.
2667 # webpage = compat_urllib_parse_unquote(webpage)
2668
2669 # Unescape squarespace embeds to be detected by generic extractor,
2670 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2671 webpage = re.sub(
2672 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2673 lambda x: unescapeHTML(x.group(0)), webpage)
2674
2675 # it's tempting to parse this further, but you would
2676 # have to take into account all the variations like
2677 # Video Title - Site Name
2678 # Site Name | Video Title
2679 # Video Title - Tagline | Site Name
2680 # and so on and so forth; it's just not practical
2681 video_title = self._og_search_title(
2682 webpage, default=None) or self._html_search_regex(
2683 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2684 default='video')
2685
2686 # Try to detect age limit automatically
2687 age_limit = self._rta_search(webpage)
2688 # And then there are the jokers who advertise that they use RTA,
2689 # but actually don't.
2690 AGE_LIMIT_MARKERS = [
2691 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2692 ]
2693 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2694 age_limit = 18
2695
2696 # video uploader is domain name
2697 video_uploader = self._search_regex(
2698 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2699
2700 video_description = self._og_search_description(webpage, default=None)
2701 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2702
2703 info_dict.update({
2704 'title': video_title,
2705 'description': video_description,
2706 'thumbnail': video_thumbnail,
2707 'age_limit': age_limit,
2708 })
2709
2710 # Look for Brightcove Legacy Studio embeds
2711 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2712 if bc_urls:
2713 entries = [{
2714 '_type': 'url',
2715 'url': smuggle_url(bc_url, {'Referer': url}),
2716 'ie_key': 'BrightcoveLegacy'
2717 } for bc_url in bc_urls]
2718
2719 return {
2720 '_type': 'playlist',
2721 'title': video_title,
2722 'id': video_id,
2723 'entries': entries,
2724 }
2725
2726 # Look for Brightcove New Studio embeds
2727 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2728 if bc_urls:
2729 return self.playlist_from_matches(
2730 bc_urls, video_id, video_title,
2731 getter=lambda x: smuggle_url(x, {'referrer': url}),
2732 ie='BrightcoveNew')
2733
2734 # Look for Nexx embeds
2735 nexx_urls = NexxIE._extract_urls(webpage)
2736 if nexx_urls:
2737 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2738
2739 # Look for Nexx iFrame embeds
2740 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2741 if nexx_embed_urls:
2742 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2743
2744 # Look for ThePlatform embeds
2745 tp_urls = ThePlatformIE._extract_urls(webpage)
2746 if tp_urls:
2747 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2748
2749 arc_urls = ArcPublishingIE._extract_urls(webpage)
2750 if arc_urls:
2751 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2752
2753 mychannels_urls = MedialaanIE._extract_urls(webpage)
2754 if mychannels_urls:
2755 return self.playlist_from_matches(
2756 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2757
2758 # Look for embedded rtl.nl player
2759 matches = re.findall(
2760 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2761 webpage)
2762 if matches:
2763 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2764
2765 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2766 if vimeo_urls:
2767 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2768
2769 vhx_url = VHXEmbedIE._extract_url(webpage)
2770 if vhx_url:
2771 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2772
2773 # Invidious Instances
2774 # https://github.com/yt-dlp/yt-dlp/issues/195
2775 # https://github.com/iv-org/invidious/pull/1730
2776 youtube_url = self._search_regex(
2777 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2778 webpage, 'youtube link', default=None)
2779 if youtube_url:
2780 return self.url_result(youtube_url, YoutubeIE.ie_key())
2781
2782 # Look for YouTube embeds
2783 youtube_urls = YoutubeIE._extract_urls(webpage)
2784 if youtube_urls:
2785 return self.playlist_from_matches(
2786 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2787
2788 matches = DailymotionIE._extract_urls(webpage)
2789 if matches:
2790 return self.playlist_from_matches(matches, video_id, video_title)
2791
2792 # Look for embedded Dailymotion playlist player (#3822)
2793 m = re.search(
2794 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2795 if m:
2796 playlists = re.findall(
2797 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2798 if playlists:
2799 return self.playlist_from_matches(
2800 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2801
2802 # Look for DailyMail embeds
2803 dailymail_urls = DailyMailIE._extract_urls(webpage)
2804 if dailymail_urls:
2805 return self.playlist_from_matches(
2806 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2807
2808 # Look for Teachable embeds, must be before Wistia
2809 teachable_url = TeachableIE._extract_url(webpage, url)
2810 if teachable_url:
2811 return self.url_result(teachable_url)
2812
2813 # Look for embedded Wistia player
2814 wistia_urls = WistiaIE._extract_urls(webpage)
2815 if wistia_urls:
2816 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2817 for entry in playlist['entries']:
2818 entry.update({
2819 '_type': 'url_transparent',
2820 'uploader': video_uploader,
2821 })
2822 return playlist
2823
2824 # Look for SVT player
2825 svt_url = SVTIE._extract_url(webpage)
2826 if svt_url:
2827 return self.url_result(svt_url, 'SVT')
2828
2829 # Look for Bandcamp pages with custom domain
2830 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2831 if mobj is not None:
2832 burl = unescapeHTML(mobj.group(1))
2833 # Don't set the extractor because it can be a track url or an album
2834 return self.url_result(burl)
2835
2836 # Look for embedded Vevo player
2837 mobj = re.search(
2838 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2839 if mobj is not None:
2840 return self.url_result(mobj.group('url'))
2841
2842 # Look for embedded Viddler player
2843 mobj = re.search(
2844 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2845 webpage)
2846 if mobj is not None:
2847 return self.url_result(mobj.group('url'))
2848
2849 # Look for NYTimes player
2850 mobj = re.search(
2851 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2852 webpage)
2853 if mobj is not None:
2854 return self.url_result(mobj.group('url'))
2855
2856 # Look for Libsyn player
2857 mobj = re.search(
2858 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2859 if mobj is not None:
2860 return self.url_result(mobj.group('url'))
2861
2862 # Look for Ooyala videos
2863 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2864 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2865 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2866 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2867 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2868 if mobj is not None:
2869 embed_token = self._search_regex(
2870 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2871 webpage, 'ooyala embed token', default=None)
2872 return OoyalaIE._build_url_result(smuggle_url(
2873 mobj.group('ec'), {
2874 'domain': url,
2875 'embed_token': embed_token,
2876 }))
2877
2878 # Look for multiple Ooyala embeds on SBN network websites
2879 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2880 if mobj is not None:
2881 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2882 if embeds:
2883 return self.playlist_from_matches(
2884 embeds, video_id, video_title,
2885 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2886
2887 # Look for Aparat videos
2888 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2889 if mobj is not None:
2890 return self.url_result(mobj.group(1), 'Aparat')
2891
2892 # Look for MPORA videos
2893 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2894 if mobj is not None:
2895 return self.url_result(mobj.group(1), 'Mpora')
2896
2897 # Look for embedded Facebook player
2898 facebook_urls = FacebookIE._extract_urls(webpage)
2899 if facebook_urls:
2900 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2901
2902 # Look for embedded VK player
2903 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2904 if mobj is not None:
2905 return self.url_result(mobj.group('url'), 'VK')
2906
2907 # Look for embedded Odnoklassniki player
2908 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2909 if odnoklassniki_url:
2910 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2911
2912 # Look for sibnet embedded player
2913 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2914 if sibnet_urls:
2915 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2916
2917 # Look for embedded ivi player
2918 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2919 if mobj is not None:
2920 return self.url_result(mobj.group('url'), 'Ivi')
2921
2922 # Look for embedded Huffington Post player
2923 mobj = re.search(
2924 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2925 if mobj is not None:
2926 return self.url_result(mobj.group('url'), 'HuffPost')
2927
2928 # Look for embed.ly
2929 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2930 if mobj is not None:
2931 return self.url_result(mobj.group('url'))
2932 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2933 if mobj is not None:
2934 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2935
2936 # Look for funnyordie embed
2937 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2938 if matches:
2939 return self.playlist_from_matches(
2940 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2941
2942 # Look for Simplecast embeds
2943 simplecast_urls = SimplecastIE._extract_urls(webpage)
2944 if simplecast_urls:
2945 return self.playlist_from_matches(
2946 simplecast_urls, video_id, video_title)
2947
2948 # Look for BBC iPlayer embed
2949 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2950 if matches:
2951 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2952
2953 # Look for embedded RUTV player
2954 rutv_url = RUTVIE._extract_url(webpage)
2955 if rutv_url:
2956 return self.url_result(rutv_url, 'RUTV')
2957
2958 # Look for embedded TVC player
2959 tvc_url = TVCIE._extract_url(webpage)
2960 if tvc_url:
2961 return self.url_result(tvc_url, 'TVC')
2962
2963 # Look for embedded SportBox player
2964 sportbox_urls = SportBoxIE._extract_urls(webpage)
2965 if sportbox_urls:
2966 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2967
2968 # Look for embedded XHamster player
2969 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2970 if xhamster_urls:
2971 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2972
2973 # Look for embedded TNAFlixNetwork player
2974 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2975 if tnaflix_urls:
2976 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2977
2978 # Look for embedded PornHub player
2979 pornhub_urls = PornHubIE._extract_urls(webpage)
2980 if pornhub_urls:
2981 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2982
2983 # Look for embedded DrTuber player
2984 drtuber_urls = DrTuberIE._extract_urls(webpage)
2985 if drtuber_urls:
2986 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2987
2988 # Look for embedded RedTube player
2989 redtube_urls = RedTubeIE._extract_urls(webpage)
2990 if redtube_urls:
2991 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2992
2993 # Look for embedded Tube8 player
2994 tube8_urls = Tube8IE._extract_urls(webpage)
2995 if tube8_urls:
2996 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2997
2998 # Look for embedded Mofosex player
2999 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3000 if mofosex_urls:
3001 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3002
3003 # Look for embedded Spankwire player
3004 spankwire_urls = SpankwireIE._extract_urls(webpage)
3005 if spankwire_urls:
3006 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3007
3008 # Look for embedded YouPorn player
3009 youporn_urls = YouPornIE._extract_urls(webpage)
3010 if youporn_urls:
3011 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3012
3013 # Look for embedded Tvigle player
3014 mobj = re.search(
3015 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3016 if mobj is not None:
3017 return self.url_result(mobj.group('url'), 'Tvigle')
3018
3019 # Look for embedded TED player
3020 mobj = re.search(
3021 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
3022 if mobj is not None:
3023 return self.url_result(mobj.group('url'), 'TED')
3024
3025 # Look for embedded Ustream videos
3026 ustream_url = UstreamIE._extract_url(webpage)
3027 if ustream_url:
3028 return self.url_result(ustream_url, UstreamIE.ie_key())
3029
3030 # Look for embedded arte.tv player
3031 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3032 if arte_urls:
3033 return self.playlist_from_matches(arte_urls, video_id, video_title)
3034
3035 # Look for embedded francetv player
3036 mobj = re.search(
3037 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3038 webpage)
3039 if mobj is not None:
3040 return self.url_result(mobj.group('url'))
3041
3042 # Look for embedded Myvi.ru player
3043 myvi_url = MyviIE._extract_url(webpage)
3044 if myvi_url:
3045 return self.url_result(myvi_url)
3046
3047 # Look for embedded soundcloud player
3048 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3049 if soundcloud_urls:
3050 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3051
3052 # Look for tunein player
3053 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3054 if tunein_urls:
3055 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3056
3057 # Look for embedded mtvservices player
3058 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3059 if mtvservices_url:
3060 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3061
3062 # Look for embedded yahoo player
3063 mobj = re.search(
3064 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3065 webpage)
3066 if mobj is not None:
3067 return self.url_result(mobj.group('url'), 'Yahoo')
3068
3069 # Look for embedded sbs.com.au player
3070 mobj = re.search(
3071 r'''(?x)
3072 (?:
3073 <meta\s+property="og:video"\s+content=|
3074 <iframe[^>]+?src=
3075 )
3076 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3077 webpage)
3078 if mobj is not None:
3079 return self.url_result(mobj.group('url'), 'SBS')
3080
3081 # Look for embedded Cinchcast player
3082 mobj = re.search(
3083 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3084 webpage)
3085 if mobj is not None:
3086 return self.url_result(mobj.group('url'), 'Cinchcast')
3087
3088 mobj = re.search(
3089 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
3090 webpage)
3091 if not mobj:
3092 mobj = re.search(
3093 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3094 webpage)
3095 if mobj is not None:
3096 return self.url_result(mobj.group('url'), 'MLB')
3097
3098 mobj = re.search(
3099 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3100 webpage)
3101 if mobj is not None:
3102 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3103
3104 mobj = re.search(
3105 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
3106 webpage)
3107 if mobj is not None:
3108 return self.url_result(mobj.group('url'), 'Livestream')
3109
3110 # Look for Zapiks embed
3111 mobj = re.search(
3112 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3113 if mobj is not None:
3114 return self.url_result(mobj.group('url'), 'Zapiks')
3115
3116 # Look for Kaltura embeds
3117 kaltura_urls = KalturaIE._extract_urls(webpage)
3118 if kaltura_urls:
3119 return self.playlist_from_matches(
3120 kaltura_urls, video_id, video_title,
3121 getter=lambda x: smuggle_url(x, {'source_url': url}),
3122 ie=KalturaIE.ie_key())
3123
3124 # Look for EaglePlatform embeds
3125 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3126 if eagleplatform_url:
3127 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3128
3129 # Look for ClipYou (uses EaglePlatform) embeds
3130 mobj = re.search(
3131 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3132 if mobj is not None:
3133 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3134
3135 # Look for Pladform embeds
3136 pladform_url = PladformIE._extract_url(webpage)
3137 if pladform_url:
3138 return self.url_result(pladform_url)
3139
3140 # Look for Videomore embeds
3141 videomore_url = VideomoreIE._extract_url(webpage)
3142 if videomore_url:
3143 return self.url_result(videomore_url)
3144
3145 # Look for Webcaster embeds
3146 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3147 if webcaster_url:
3148 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3149
3150 # Look for Playwire embeds
3151 mobj = re.search(
3152 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3153 if mobj is not None:
3154 return self.url_result(mobj.group('url'))
3155
3156 # Look for 5min embeds
3157 mobj = re.search(
3158 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3159 if mobj is not None:
3160 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3161
3162 # Look for Crooks and Liars embeds
3163 mobj = re.search(
3164 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3165 if mobj is not None:
3166 return self.url_result(mobj.group('url'))
3167
3168 # Look for NBC Sports VPlayer embeds
3169 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3170 if nbc_sports_url:
3171 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3172
3173 # Look for NBC News embeds
3174 nbc_news_embed_url = re.search(
3175 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3176 if nbc_news_embed_url:
3177 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3178
3179 # Look for Google Drive embeds
3180 google_drive_url = GoogleDriveIE._extract_url(webpage)
3181 if google_drive_url:
3182 return self.url_result(google_drive_url, 'GoogleDrive')
3183
3184 # Look for UDN embeds
3185 mobj = re.search(
3186 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3187 if mobj is not None:
3188 return self.url_result(
3189 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3190
3191 # Look for Senate ISVP iframe
3192 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3193 if senate_isvp_url:
3194 return self.url_result(senate_isvp_url, 'SenateISVP')
3195
3196 # Look for Kinja embeds
3197 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3198 if kinja_embed_urls:
3199 return self.playlist_from_matches(
3200 kinja_embed_urls, video_id, video_title)
3201
3202 # Look for OnionStudios embeds
3203 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3204 if onionstudios_url:
3205 return self.url_result(onionstudios_url)
3206
3207 # Look for ViewLift embeds
3208 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3209 if viewlift_url:
3210 return self.url_result(viewlift_url)
3211
3212 # Look for JWPlatform embeds
3213 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3214 if jwplatform_urls:
3215 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3216
3217 # Look for Digiteka embeds
3218 digiteka_url = DigitekaIE._extract_url(webpage)
3219 if digiteka_url:
3220 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3221
3222 # Look for Arkena embeds
3223 arkena_url = ArkenaIE._extract_url(webpage)
3224 if arkena_url:
3225 return self.url_result(arkena_url, ArkenaIE.ie_key())
3226
3227 # Look for Piksel embeds
3228 piksel_url = PikselIE._extract_url(webpage)
3229 if piksel_url:
3230 return self.url_result(piksel_url, PikselIE.ie_key())
3231
3232 # Look for Limelight embeds
3233 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3234 if limelight_urls:
3235 return self.playlist_result(
3236 limelight_urls, video_id, video_title, video_description)
3237
3238 # Look for Anvato embeds
3239 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3240 if anvato_urls:
3241 return self.playlist_result(
3242 anvato_urls, video_id, video_title, video_description)
3243
3244 # Look for AdobeTVVideo embeds
3245 mobj = re.search(
3246 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3247 webpage)
3248 if mobj is not None:
3249 return self.url_result(
3250 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3251 'AdobeTVVideo')
3252
3253 # Look for Vine embeds
3254 mobj = re.search(
3255 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3256 webpage)
3257 if mobj is not None:
3258 return self.url_result(
3259 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3260
3261 # Look for VODPlatform embeds
3262 mobj = re.search(
3263 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3264 webpage)
3265 if mobj is not None:
3266 return self.url_result(
3267 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3268
3269 # Look for Mangomolo embeds
3270 mobj = re.search(
3271 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3272 (?:
3273 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3274 player\.mangomolo\.com/v1
3275 )/
3276 (?:
3277 video\?.*?\bid=(?P<video_id>\d+)|
3278 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3279 ).+?)\1''', webpage)
3280 if mobj is not None:
3281 info = {
3282 '_type': 'url_transparent',
3283 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3284 'title': video_title,
3285 'description': video_description,
3286 'thumbnail': video_thumbnail,
3287 'uploader': video_uploader,
3288 }
3289 video_id = mobj.group('video_id')
3290 if video_id:
3291 info.update({
3292 'ie_key': 'MangomoloVideo',
3293 'id': video_id,
3294 })
3295 else:
3296 info.update({
3297 'ie_key': 'MangomoloLive',
3298 'id': mobj.group('channel_id'),
3299 })
3300 return info
3301
3302 # Look for Instagram embeds
3303 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3304 if instagram_embed_url is not None:
3305 return self.url_result(
3306 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3307
3308 # Look for 3Q SDN embeds
3309 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3310 if threeqsdn_url:
3311 return {
3312 '_type': 'url_transparent',
3313 'ie_key': ThreeQSDNIE.ie_key(),
3314 'url': self._proto_relative_url(threeqsdn_url),
3315 'title': video_title,
3316 'description': video_description,
3317 'thumbnail': video_thumbnail,
3318 'uploader': video_uploader,
3319 }
3320
3321 # Look for VBOX7 embeds
3322 vbox7_url = Vbox7IE._extract_url(webpage)
3323 if vbox7_url:
3324 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3325
3326 # Look for DBTV embeds
3327 dbtv_urls = DBTVIE._extract_urls(webpage)
3328 if dbtv_urls:
3329 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3330
3331 # Look for Videa embeds
3332 videa_urls = VideaIE._extract_urls(webpage)
3333 if videa_urls:
3334 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3335
3336 # Look for 20 minuten embeds
3337 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3338 if twentymin_urls:
3339 return self.playlist_from_matches(
3340 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3341
3342 # Look for VideoPress embeds
3343 videopress_urls = VideoPressIE._extract_urls(webpage)
3344 if videopress_urls:
3345 return self.playlist_from_matches(
3346 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3347
3348 # Look for Rutube embeds
3349 rutube_urls = RutubeIE._extract_urls(webpage)
3350 if rutube_urls:
3351 return self.playlist_from_matches(
3352 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3353
3354 # Look for WashingtonPost embeds
3355 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3356 if wapo_urls:
3357 return self.playlist_from_matches(
3358 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3359
3360 # Look for Mediaset embeds
3361 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3362 if mediaset_urls:
3363 return self.playlist_from_matches(
3364 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3365
3366 # Look for JOJ.sk embeds
3367 joj_urls = JojIE._extract_urls(webpage)
3368 if joj_urls:
3369 return self.playlist_from_matches(
3370 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3371
3372 # Look for megaphone.fm embeds
3373 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3374 if mpfn_urls:
3375 return self.playlist_from_matches(
3376 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3377
3378 # Look for vzaar embeds
3379 vzaar_urls = VzaarIE._extract_urls(webpage)
3380 if vzaar_urls:
3381 return self.playlist_from_matches(
3382 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3383
3384 channel9_urls = Channel9IE._extract_urls(webpage)
3385 if channel9_urls:
3386 return self.playlist_from_matches(
3387 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3388
3389 vshare_urls = VShareIE._extract_urls(webpage)
3390 if vshare_urls:
3391 return self.playlist_from_matches(
3392 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3393
3394 # Look for Mediasite embeds
3395 mediasite_urls = MediasiteIE._extract_urls(webpage)
3396 if mediasite_urls:
3397 entries = [
3398 self.url_result(smuggle_url(
3399 compat_urlparse.urljoin(url, mediasite_url),
3400 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3401 for mediasite_url in mediasite_urls]
3402 return self.playlist_result(entries, video_id, video_title)
3403
3404 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3405 if springboardplatform_urls:
3406 return self.playlist_from_matches(
3407 springboardplatform_urls, video_id, video_title,
3408 ie=SpringboardPlatformIE.ie_key())
3409
3410 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3411 if yapfiles_urls:
3412 return self.playlist_from_matches(
3413 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3414
3415 vice_urls = ViceIE._extract_urls(webpage)
3416 if vice_urls:
3417 return self.playlist_from_matches(
3418 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3419
3420 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3421 if xfileshare_urls:
3422 return self.playlist_from_matches(
3423 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3424
3425 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3426 if cloudflarestream_urls:
3427 return self.playlist_from_matches(
3428 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3429
3430 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3431 if peertube_urls:
3432 return self.playlist_from_matches(
3433 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3434
3435 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3436 if indavideo_urls:
3437 return self.playlist_from_matches(
3438 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3439
3440 apa_urls = APAIE._extract_urls(webpage)
3441 if apa_urls:
3442 return self.playlist_from_matches(
3443 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3444
3445 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3446 if foxnews_urls:
3447 return self.playlist_from_matches(
3448 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3449
3450 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3451 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3452 webpage)]
3453 if sharevideos_urls:
3454 return self.playlist_from_matches(
3455 sharevideos_urls, video_id, video_title)
3456
3457 viqeo_urls = ViqeoIE._extract_urls(webpage)
3458 if viqeo_urls:
3459 return self.playlist_from_matches(
3460 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3461
3462 expressen_urls = ExpressenIE._extract_urls(webpage)
3463 if expressen_urls:
3464 return self.playlist_from_matches(
3465 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3466
3467 zype_urls = ZypeIE._extract_urls(webpage)
3468 if zype_urls:
3469 return self.playlist_from_matches(
3470 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3471
3472 gedi_urls = GediDigitalIE._extract_urls(webpage)
3473 if gedi_urls:
3474 return self.playlist_from_matches(
3475 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
3476
3477 # Look for RCS media group embeds
3478 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3479 if rcs_urls:
3480 return self.playlist_from_matches(
3481 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3482
3483 wimtv_urls = WimTVIE._extract_urls(webpage)
3484 if wimtv_urls:
3485 return self.playlist_from_matches(
3486 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3487
3488 bitchute_urls = BitChuteIE._extract_urls(webpage)
3489 if bitchute_urls:
3490 return self.playlist_from_matches(
3491 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3492
3493 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3494 if len(rumble_urls) == 1:
3495 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3496 if rumble_urls:
3497 return self.playlist_from_matches(
3498 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3499
3500 # Look for HTML5 media
3501 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3502 if entries:
3503 if len(entries) == 1:
3504 entries[0].update({
3505 'id': video_id,
3506 'title': video_title,
3507 })
3508 else:
3509 for num, entry in enumerate(entries, start=1):
3510 entry.update({
3511 'id': '%s-%s' % (video_id, num),
3512 'title': '%s (%d)' % (video_title, num),
3513 })
3514 for entry in entries:
3515 self._sort_formats(entry['formats'])
3516 return self.playlist_result(entries, video_id, video_title)
3517
3518 jwplayer_data = self._find_jwplayer_data(
3519 webpage, video_id, transform_source=js_to_json)
3520 if jwplayer_data:
3521 if isinstance(jwplayer_data.get('playlist'), str):
3522 return {
3523 **info_dict,
3524 '_type': 'url',
3525 'ie_key': JWPlatformIE.ie_key(),
3526 'url': jwplayer_data['playlist'],
3527 }
3528 try:
3529 info = self._parse_jwplayer_data(
3530 jwplayer_data, video_id, require_title=False, base_url=url)
3531 return merge_dicts(info, info_dict)
3532 except ExtractorError:
3533 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3534 pass
3535
3536 # Video.js embed
3537 mobj = re.search(
3538 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3539 webpage)
3540 if mobj is not None:
3541 sources = self._parse_json(
3542 mobj.group(1), video_id, transform_source=js_to_json,
3543 fatal=False) or []
3544 if not isinstance(sources, list):
3545 sources = [sources]
3546 formats = []
3547 subtitles = {}
3548 for source in sources:
3549 src = source.get('src')
3550 if not src or not isinstance(src, compat_str):
3551 continue
3552 src = compat_urlparse.urljoin(url, src)
3553 src_type = source.get('type')
3554 if isinstance(src_type, compat_str):
3555 src_type = src_type.lower()
3556 ext = determine_ext(src).lower()
3557 if src_type == 'video/youtube':
3558 return self.url_result(src, YoutubeIE.ie_key())
3559 if src_type == 'application/dash+xml' or ext == 'mpd':
3560 fmts, subs = self._extract_mpd_formats_and_subtitles(
3561 src, video_id, mpd_id='dash', fatal=False)
3562 formats.extend(fmts)
3563 self._merge_subtitles(subs, target=subtitles)
3564 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3565 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3566 src, video_id, 'mp4', entry_protocol='m3u8_native',
3567 m3u8_id='hls', fatal=False)
3568 formats.extend(fmts)
3569 self._merge_subtitles(subs, target=subtitles)
3570 else:
3571 formats.append({
3572 'url': src,
3573 'ext': (mimetype2ext(src_type)
3574 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3575 'http_headers': {
3576 'Referer': full_response.geturl(),
3577 },
3578 })
3579 if formats or subtitles:
3580 self._sort_formats(formats)
3581 info_dict['formats'] = formats
3582 info_dict['subtitles'] = subtitles
3583 return info_dict
3584
3585 # Looking for http://schema.org/VideoObject
3586 json_ld = self._search_json_ld(webpage, video_id, default={})
3587 if json_ld.get('url'):
3588 return merge_dicts(json_ld, info_dict)
3589
3590 def check_video(vurl):
3591 if YoutubeIE.suitable(vurl):
3592 return True
3593 if RtmpIE.suitable(vurl):
3594 return True
3595 vpath = compat_urlparse.urlparse(vurl).path
3596 vext = determine_ext(vpath)
3597 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3598
3599 def filter_video(urls):
3600 return list(filter(check_video, urls))
3601
3602 # Start with something easy: JW Player in SWFObject
3603 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3604 if not found:
3605 # Look for gorilla-vid style embedding
3606 found = filter_video(re.findall(r'''(?sx)
3607 (?:
3608 jw_plugins|
3609 JWPlayerOptions|
3610 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3611 )
3612 .*?
3613 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3614 if not found:
3615 # Look for generic KVS player
3616 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3617 if found:
3618 if found.group('maj_ver') not in ['4', '5']:
3619 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3620 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3621 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3622
3623 # extract the part after the last / as the display_id from the
3624 # canonical URL.
3625 display_id = self._search_regex(
3626 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3627 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3628 webpage, 'display_id', fatal=False
3629 )
3630 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3631
3632 thumbnail = flashvars['preview_url']
3633 if thumbnail.startswith('//'):
3634 protocol, _, _ = url.partition('/')
3635 thumbnail = protocol + thumbnail
3636
3637 formats = []
3638 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3639 if key in flashvars and '/get_file/' in flashvars[key]:
3640 next_format = {
3641 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3642 'format_id': flashvars.get(key + '_text', key),
3643 'ext': 'mp4',
3644 }
3645 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3646 if height:
3647 next_format['height'] = int(height.group(1))
3648 else:
3649 next_format['quality'] = 1
3650 formats.append(next_format)
3651 self._sort_formats(formats)
3652
3653 return {
3654 'id': flashvars['video_id'],
3655 'display_id': display_id,
3656 'title': title,
3657 'thumbnail': thumbnail,
3658 'formats': formats,
3659 }
3660 if not found:
3661 # Broaden the search a little bit
3662 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3663 if not found:
3664 # Broaden the findall a little bit: JWPlayer JS loader
3665 found = filter_video(re.findall(
3666 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3667 if not found:
3668 # Flow player
3669 found = filter_video(re.findall(r'''(?xs)
3670 flowplayer\("[^"]+",\s*
3671 \{[^}]+?\}\s*,
3672 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3673 ["']?url["']?\s*:\s*["']([^"']+)["']
3674 ''', webpage))
3675 if not found:
3676 # Cinerama player
3677 found = re.findall(
3678 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3679 if not found:
3680 # Try to find twitter cards info
3681 # twitter:player:stream should be checked before twitter:player since
3682 # it is expected to contain a raw stream (see
3683 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3684 found = filter_video(re.findall(
3685 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3686 if not found:
3687 # We look for Open Graph info:
3688 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3689 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3690 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3691 if m_video_type is not None:
3692 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3693 if not found:
3694 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3695 found = re.search(
3696 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3697 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3698 webpage)
3699 if not found:
3700 # Look also in Refresh HTTP header
3701 refresh_header = head_response.headers.get('Refresh')
3702 if refresh_header:
3703 # In python 2 response HTTP headers are bytestrings
3704 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3705 refresh_header = refresh_header.decode('iso-8859-1')
3706 found = re.search(REDIRECT_REGEX, refresh_header)
3707 if found:
3708 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3709 if new_url != url:
3710 self.report_following_redirect(new_url)
3711 return {
3712 '_type': 'url',
3713 'url': new_url,
3714 }
3715 else:
3716 found = None
3717
3718 if not found:
3719 # twitter:player is a https URL to iframe player that may or may not
3720 # be supported by yt-dlp thus this is checked the very last (see
3721 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3722 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3723 if embed_url and embed_url != url:
3724 return self.url_result(embed_url)
3725
3726 if not found:
3727 raise UnsupportedError(url)
3728
3729 entries = []
3730 for video_url in orderedSet(found):
3731 video_url = unescapeHTML(video_url)
3732 video_url = video_url.replace('\\/', '/')
3733 video_url = compat_urlparse.urljoin(url, video_url)
3734 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3735
3736 # Sometimes, jwplayer extraction will result in a YouTube URL
3737 if YoutubeIE.suitable(video_url):
3738 entries.append(self.url_result(video_url, 'Youtube'))
3739 continue
3740
3741 # here's a fun little line of code for you:
3742 video_id = os.path.splitext(video_id)[0]
3743
3744 entry_info_dict = {
3745 'id': video_id,
3746 'uploader': video_uploader,
3747 'title': video_title,
3748 'age_limit': age_limit,
3749 }
3750
3751 if RtmpIE.suitable(video_url):
3752 entry_info_dict.update({
3753 '_type': 'url_transparent',
3754 'ie_key': RtmpIE.ie_key(),
3755 'url': video_url,
3756 })
3757 entries.append(entry_info_dict)
3758 continue
3759
3760 ext = determine_ext(video_url)
3761 if ext == 'smil':
3762 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
3763 elif ext == 'xspf':
3764 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3765 elif ext == 'm3u8':
3766 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
3767 elif ext == 'mpd':
3768 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3769 elif ext == 'f4m':
3770 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3771 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3772 # Just matching .ism/manifest is not enough to be reliably sure
3773 # whether it's actually an ISM manifest or some other streaming
3774 # manifest since there are various streaming URL formats
3775 # possible (see [1]) as well as some other shenanigans like
3776 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3777 # so on.
3778 # Thus the most reasonable way to solve this is to delegate
3779 # to generic extractor in order to look into the contents of
3780 # the manifest itself.
3781 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3782 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3783 entry_info_dict = self.url_result(
3784 smuggle_url(video_url, {'to_generic': True}),
3785 GenericIE.ie_key())
3786 else:
3787 entry_info_dict['url'] = video_url
3788
3789 if entry_info_dict.get('formats'):
3790 self._sort_formats(entry_info_dict['formats'])
3791
3792 entries.append(entry_info_dict)
3793
3794 if len(entries) == 1:
3795 return entries[0]
3796 else:
3797 for num, e in enumerate(entries, start=1):
3798 # 'url' results don't have a title
3799 if e.get('title') is not None:
3800 e['title'] = '%s (%d)' % (e['title'], num)
3801 return {
3802 '_type': 'playlist',
3803 'entries': entries,
3804 }