]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/generic.py
[generic] Extract subtitles from direct DASH manifest links
[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 .liveleak import LiveLeakIE
88 from .threeqsdn import ThreeQSDNIE
89 from .theplatform import ThePlatformIE
90 from .kaltura import KalturaIE
91 from .eagleplatform import EaglePlatformIE
92 from .facebook import FacebookIE
93 from .soundcloud import SoundcloudEmbedIE
94 from .tunein import TuneInBaseIE
95 from .vbox7 import Vbox7IE
96 from .dbtv import DBTVIE
97 from .piksel import PikselIE
98 from .videa import VideaIE
99 from .twentymin import TwentyMinutenIE
100 from .ustream import UstreamIE
101 from .arte import ArteTVEmbedIE
102 from .videopress import VideoPressIE
103 from .rutube import RutubeIE
104 from .limelight import LimelightBaseIE
105 from .anvato import AnvatoIE
106 from .washingtonpost import WashingtonPostIE
107 from .wistia import WistiaIE
108 from .mediaset import MediasetIE
109 from .joj import JojIE
110 from .megaphone import MegaphoneIE
111 from .vzaar import VzaarIE
112 from .channel9 import Channel9IE
113 from .vshare import VShareIE
114 from .mediasite import MediasiteIE
115 from .springboardplatform import SpringboardPlatformIE
116 from .yapfiles import YapFilesIE
117 from .vice import ViceIE
118 from .xfileshare import XFileShareIE
119 from .cloudflarestream import CloudflareStreamIE
120 from .peertube import PeerTubeIE
121 from .teachable import TeachableIE
122 from .indavideo import IndavideoEmbedIE
123 from .apa import APAIE
124 from .foxnews import FoxNewsIE
125 from .viqeo import ViqeoIE
126 from .expressen import ExpressenIE
127 from .zype import ZypeIE
128 from .odnoklassniki import OdnoklassnikiIE
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 # Complex jwplayer
1192 {
1193 'url': 'http://www.indiedb.com/games/king-machine/videos',
1194 'info_dict': {
1195 'id': 'videos',
1196 'ext': 'mp4',
1197 'title': 'king machine trailer 1',
1198 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1199 'thumbnail': r're:^https?://.*\.jpg$',
1200 },
1201 },
1202 {
1203 # JWPlayer config passed as variable
1204 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1205 'info_dict': {
1206 'id': '3326530_hq',
1207 'ext': 'mp4',
1208 'title': 'ARIELE | Tube Cup',
1209 'uploader': 'www.txxx.com',
1210 'age_limit': 18,
1211 },
1212 'params': {
1213 'skip_download': True,
1214 }
1215 },
1216 {
1217 # JWPlatform iframe
1218 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1219 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1220 'info_dict': {
1221 'id': 'O0c5JcKT',
1222 'ext': 'mp4',
1223 'upload_date': '20171122',
1224 'timestamp': 1511366290,
1225 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1226 },
1227 'add_ie': [JWPlatformIE.ie_key()],
1228 },
1229 {
1230 # Video.js embed, multiple formats
1231 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1232 'info_dict': {
1233 'id': 'yygqldloqIk',
1234 'ext': 'mp4',
1235 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1236 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1237 'upload_date': '20130314',
1238 'uploader': 'PROстое3D',
1239 'uploader_id': 'PROstoe3D',
1240 },
1241 'params': {
1242 'skip_download': True,
1243 },
1244 },
1245 {
1246 # Video.js embed, single format
1247 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1248 'info_dict': {
1249 'id': 'watch',
1250 'ext': 'mp4',
1251 'title': 'Step 1 - Good Foundation',
1252 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1253 },
1254 'params': {
1255 'skip_download': True,
1256 },
1257 },
1258 # rtl.nl embed
1259 {
1260 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1261 'playlist_mincount': 5,
1262 'info_dict': {
1263 'id': 'aanslagen-kopenhagen',
1264 'title': 'Aanslagen Kopenhagen',
1265 }
1266 },
1267 # Zapiks embed
1268 {
1269 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1270 'info_dict': {
1271 'id': '118046',
1272 'ext': 'mp4',
1273 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1274 }
1275 },
1276 # Kaltura embed (different embed code)
1277 {
1278 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1279 'info_dict': {
1280 'id': '1_a52wc67y',
1281 'ext': 'flv',
1282 'upload_date': '20150127',
1283 'uploader_id': 'PremierMedia',
1284 'timestamp': int,
1285 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1286 },
1287 },
1288 # Kaltura embed with single quotes
1289 {
1290 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1291 'info_dict': {
1292 'id': '0_izeg5utt',
1293 'ext': 'mp4',
1294 'title': '35871',
1295 'timestamp': 1355743100,
1296 'upload_date': '20121217',
1297 'uploader_id': 'cplapp@learn360.com',
1298 },
1299 'add_ie': ['Kaltura'],
1300 },
1301 {
1302 # Kaltura embedded via quoted entry_id
1303 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1304 'info_dict': {
1305 'id': '0_utuok90b',
1306 'ext': 'mp4',
1307 'title': '06_matthew_brender_raj_dutt',
1308 'timestamp': 1466638791,
1309 'upload_date': '20160622',
1310 },
1311 'add_ie': ['Kaltura'],
1312 'expected_warnings': [
1313 'Could not send HEAD request'
1314 ],
1315 'params': {
1316 'skip_download': True,
1317 }
1318 },
1319 {
1320 # Kaltura embedded, some fileExt broken (#11480)
1321 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1322 'info_dict': {
1323 'id': '1_sgtvehim',
1324 'ext': 'mp4',
1325 'title': 'Our "Standard Models" of particle physics and cosmology',
1326 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1327 'timestamp': 1321158993,
1328 'upload_date': '20111113',
1329 'uploader_id': 'kps1',
1330 },
1331 'add_ie': ['Kaltura'],
1332 },
1333 {
1334 # Kaltura iframe embed
1335 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1336 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1337 'info_dict': {
1338 'id': '0_f2cfbpwy',
1339 'ext': 'mp4',
1340 'title': 'I. M. Pei: A Centennial Celebration',
1341 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1342 'upload_date': '20170403',
1343 'uploader_id': 'batchUser',
1344 'timestamp': 1491232186,
1345 },
1346 'add_ie': ['Kaltura'],
1347 },
1348 {
1349 # Kaltura iframe embed, more sophisticated
1350 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1351 'info_dict': {
1352 'id': '1_9gzouybz',
1353 'ext': 'mp4',
1354 'title': 'lecture-05sep2017',
1355 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1356 'upload_date': '20170913',
1357 'uploader_id': 'eps2',
1358 'timestamp': 1505340777,
1359 },
1360 'params': {
1361 'skip_download': True,
1362 },
1363 'add_ie': ['Kaltura'],
1364 },
1365 {
1366 # meta twitter:player
1367 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1368 'info_dict': {
1369 'id': '0_01b42zps',
1370 'ext': 'mp4',
1371 'title': 'Main Twerk (Video)',
1372 'upload_date': '20171208',
1373 'uploader_id': 'sebastian.salinas@thechive.com',
1374 'timestamp': 1512713057,
1375 },
1376 'params': {
1377 'skip_download': True,
1378 },
1379 'add_ie': ['Kaltura'],
1380 },
1381 # referrer protected EaglePlatform embed
1382 {
1383 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1384 'info_dict': {
1385 'id': '582306',
1386 'ext': 'mp4',
1387 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1388 'thumbnail': r're:^https?://.*\.jpg$',
1389 'duration': 3382,
1390 'view_count': int,
1391 },
1392 'params': {
1393 'skip_download': True,
1394 },
1395 },
1396 # ClipYou (EaglePlatform) embed (custom URL)
1397 {
1398 'url': 'http://muz-tv.ru/play/7129/',
1399 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1400 'info_dict': {
1401 'id': '12820',
1402 'ext': 'mp4',
1403 'title': "'O Sole Mio",
1404 'thumbnail': r're:^https?://.*\.jpg$',
1405 'duration': 216,
1406 'view_count': int,
1407 },
1408 'params': {
1409 'skip_download': True,
1410 },
1411 'skip': 'This video is unavailable.',
1412 },
1413 # Pladform embed
1414 {
1415 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1416 'info_dict': {
1417 'id': '100183293',
1418 'ext': 'mp4',
1419 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1420 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1421 'thumbnail': r're:^https?://.*\.jpg$',
1422 'duration': 694,
1423 'age_limit': 0,
1424 },
1425 'skip': 'HTTP Error 404: Not Found',
1426 },
1427 # Playwire embed
1428 {
1429 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1430 'info_dict': {
1431 'id': '3519514',
1432 'ext': 'mp4',
1433 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1434 'thumbnail': r're:^https?://.*\.png$',
1435 'duration': 45.115,
1436 },
1437 },
1438 # 5min embed
1439 {
1440 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1441 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1442 'info_dict': {
1443 'id': '518726732',
1444 'ext': 'mp4',
1445 'title': 'Facebook Creates "On This Day" | Crunch Report',
1446 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1447 'timestamp': 1427237531,
1448 'uploader': 'Crunch Report',
1449 'upload_date': '20150324',
1450 },
1451 'params': {
1452 # m3u8 download
1453 'skip_download': True,
1454 },
1455 },
1456 # Crooks and Liars embed
1457 {
1458 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1459 'info_dict': {
1460 'id': '8RUoRhRi',
1461 'ext': 'mp4',
1462 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1463 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1464 'timestamp': 1428207000,
1465 'upload_date': '20150405',
1466 'uploader': 'Heather',
1467 },
1468 },
1469 # Crooks and Liars external embed
1470 {
1471 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1472 'info_dict': {
1473 'id': 'MTE3MjUtMzQ2MzA',
1474 'ext': 'mp4',
1475 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1476 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1477 'timestamp': 1265032391,
1478 'upload_date': '20100201',
1479 'uploader': 'Heather',
1480 },
1481 },
1482 # NBC Sports vplayer embed
1483 {
1484 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1485 'info_dict': {
1486 'id': 'ln7x1qSThw4k',
1487 'ext': 'flv',
1488 'title': "PFT Live: New leader in the 'new-look' defense",
1489 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1490 'uploader': 'NBCU-SPORTS',
1491 'upload_date': '20140107',
1492 'timestamp': 1389118457,
1493 },
1494 'skip': 'Invalid Page URL',
1495 },
1496 # NBC News embed
1497 {
1498 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1499 'md5': '1aa589c675898ae6d37a17913cf68d66',
1500 'info_dict': {
1501 'id': 'x_dtl_oa_LettermanliftPR_160608',
1502 'ext': 'mp4',
1503 'title': 'David Letterman: A Preview',
1504 '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.',
1505 'upload_date': '20160609',
1506 'timestamp': 1465431544,
1507 'uploader': 'NBCU-NEWS',
1508 },
1509 },
1510 # UDN embed
1511 {
1512 'url': 'https://video.udn.com/news/300346',
1513 'md5': 'fd2060e988c326991037b9aff9df21a6',
1514 'info_dict': {
1515 'id': '300346',
1516 'ext': 'mp4',
1517 'title': '中一中男師變性 全校師生力挺',
1518 'thumbnail': r're:^https?://.*\.jpg$',
1519 },
1520 'params': {
1521 # m3u8 download
1522 'skip_download': True,
1523 },
1524 'expected_warnings': ['Failed to parse JSON Expecting value'],
1525 },
1526 # Brightcove URL in single quotes
1527 {
1528 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1529 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1530 'info_dict': {
1531 'id': '4255764656001',
1532 'ext': 'mp4',
1533 'title': 'SN Presents: Russell Martin, World Citizen',
1534 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1535 'uploader': 'Rogers Sportsnet',
1536 'uploader_id': '1704050871',
1537 'upload_date': '20150525',
1538 'timestamp': 1432570283,
1539 },
1540 },
1541 # Kinja embed
1542 {
1543 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1544 'info_dict': {
1545 'id': '106351',
1546 'ext': 'mp4',
1547 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1548 'description': 'Migrated from OnionStudios',
1549 'thumbnail': r're:^https?://.*\.jpe?g$',
1550 'uploader': 'clickhole',
1551 'upload_date': '20150527',
1552 'timestamp': 1432744860,
1553 }
1554 },
1555 # SnagFilms embed
1556 {
1557 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1558 'info_dict': {
1559 'id': '74849a00-85a9-11e1-9660-123139220831',
1560 'ext': 'mp4',
1561 'title': '#whilewewatch',
1562 }
1563 },
1564 # AdobeTVVideo embed
1565 {
1566 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1567 'md5': '43662b577c018ad707a63766462b1e87',
1568 'info_dict': {
1569 'id': '2456',
1570 'ext': 'mp4',
1571 'title': 'New experience with Acrobat DC',
1572 'description': 'New experience with Acrobat DC',
1573 'duration': 248.667,
1574 },
1575 },
1576 # BrightcoveInPageEmbed embed
1577 {
1578 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1579 'info_dict': {
1580 'id': '4238694884001',
1581 'ext': 'flv',
1582 'title': 'Tabletop: Dread, Last Thoughts',
1583 'description': 'Tabletop: Dread, Last Thoughts',
1584 'duration': 51690,
1585 },
1586 },
1587 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1588 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1589 {
1590 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1591 'info_dict': {
1592 'id': '4785848093001',
1593 'ext': 'mp4',
1594 'title': 'The Cardinal Pell Interview',
1595 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1596 'uploader': 'GlobeCast Australia - GlobeStream',
1597 'uploader_id': '2733773828001',
1598 'upload_date': '20160304',
1599 'timestamp': 1457083087,
1600 },
1601 'params': {
1602 # m3u8 downloads
1603 'skip_download': True,
1604 },
1605 },
1606 {
1607 # Brightcove embed with whitespace around attribute names
1608 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1609 'info_dict': {
1610 'id': '3167554373001',
1611 'ext': 'mp4',
1612 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1613 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1614 'uploader_id': '1079349493',
1615 'upload_date': '20140207',
1616 'timestamp': 1391810548,
1617 },
1618 'params': {
1619 'skip_download': True,
1620 },
1621 },
1622 # Another form of arte.tv embed
1623 {
1624 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1625 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1626 'info_dict': {
1627 'id': '030273-562_PLUS7-F',
1628 'ext': 'mp4',
1629 'title': 'ARTE Reportage - Nulle part, en France',
1630 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1631 'upload_date': '20160409',
1632 },
1633 },
1634 # LiveLeak embed
1635 {
1636 'url': 'http://www.wykop.pl/link/3088787/',
1637 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1638 'info_dict': {
1639 'id': '874_1459135191',
1640 'ext': 'mp4',
1641 'title': 'Man shows poor quality of new apartment building',
1642 'description': 'The wall is like a sand pile.',
1643 'uploader': 'Lake8737',
1644 },
1645 'add_ie': [LiveLeakIE.ie_key()],
1646 },
1647 # Another LiveLeak embed pattern (#13336)
1648 {
1649 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1650 'info_dict': {
1651 'id': '2eb_1496309988',
1652 'ext': 'mp4',
1653 'title': 'Thief robs place where everyone was armed',
1654 'description': 'md5:694d73ee79e535953cf2488562288eee',
1655 'uploader': 'brazilwtf',
1656 },
1657 'add_ie': [LiveLeakIE.ie_key()],
1658 },
1659 # Duplicated embedded video URLs
1660 {
1661 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1662 'info_dict': {
1663 'id': '149298443_480_16c25b74_2',
1664 'ext': 'mp4',
1665 'title': 'vs. Blue Orange Spring Game',
1666 'uploader': 'www.hudl.com',
1667 },
1668 },
1669 # twitter:player:stream embed
1670 {
1671 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1672 'info_dict': {
1673 'id': 'master',
1674 'ext': 'mp4',
1675 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1676 'uploader': 'www.rtl.be',
1677 },
1678 'params': {
1679 # m3u8 downloads
1680 'skip_download': True,
1681 },
1682 },
1683 # twitter:player embed
1684 {
1685 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1686 'md5': 'a3e0df96369831de324f0778e126653c',
1687 'info_dict': {
1688 'id': '4909620399001',
1689 'ext': 'mp4',
1690 'title': 'What Do Black Holes Sound Like?',
1691 'description': 'what do black holes sound like',
1692 'upload_date': '20160524',
1693 'uploader_id': '29913724001',
1694 'timestamp': 1464107587,
1695 'uploader': 'TheAtlantic',
1696 },
1697 'add_ie': ['BrightcoveLegacy'],
1698 },
1699 # Facebook <iframe> embed
1700 {
1701 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1702 'md5': 'fbcde74f534176ecb015849146dd3aee',
1703 'info_dict': {
1704 'id': '599637780109885',
1705 'ext': 'mp4',
1706 'title': 'Facebook video #599637780109885',
1707 },
1708 },
1709 # Facebook <iframe> embed, plugin video
1710 {
1711 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1712 'info_dict': {
1713 'id': '1754168231264132',
1714 'ext': 'mp4',
1715 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1716 'uploader': 'Tariq Ramadan (official)',
1717 'timestamp': 1496758379,
1718 'upload_date': '20170606',
1719 },
1720 'params': {
1721 'skip_download': True,
1722 },
1723 },
1724 # Facebook API embed
1725 {
1726 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1727 'md5': 'a47372ee61b39a7b90287094d447d94e',
1728 'info_dict': {
1729 'id': '10153467542406923',
1730 'ext': 'mp4',
1731 'title': 'Facebook video #10153467542406923',
1732 },
1733 },
1734 # Wordpress "YouTube Video Importer" plugin
1735 {
1736 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1737 'md5': 'd16797741b560b485194eddda8121b48',
1738 'info_dict': {
1739 'id': 'HNTXWDXV9Is',
1740 'ext': 'mp4',
1741 'title': 'Blue Devils Drumline Stanford lot 2016',
1742 'upload_date': '20160627',
1743 'uploader_id': 'GENOCIDE8GENERAL10',
1744 'uploader': 'cylus cyrus',
1745 },
1746 },
1747 {
1748 # video stored on custom kaltura server
1749 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1750 'md5': '537617d06e64dfed891fa1593c4b30cc',
1751 'info_dict': {
1752 'id': '0_1iotm5bh',
1753 'ext': 'mp4',
1754 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1755 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1756 'uploader_id': 'videos.expansion@el-mundo.net',
1757 'upload_date': '20150429',
1758 'timestamp': 1430303472,
1759 },
1760 'add_ie': ['Kaltura'],
1761 },
1762 {
1763 # multiple kaltura embeds, nsfw
1764 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1765 'info_dict': {
1766 'id': 'kamila-avec-video-jaime-sadomie',
1767 'title': "Kamila avec vídeo “J'aime sadomie”",
1768 },
1769 'playlist_count': 8,
1770 },
1771 {
1772 # Non-standard Vimeo embed
1773 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1774 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1775 'info_dict': {
1776 'id': '148867247',
1777 'ext': 'mp4',
1778 'title': 'Understanding the web - Teaser',
1779 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1780 'upload_date': '20151214',
1781 'uploader': 'OpenClassrooms',
1782 'uploader_id': 'openclassrooms',
1783 },
1784 'add_ie': ['Vimeo'],
1785 },
1786 {
1787 # generic vimeo embed that requires original URL passed as Referer
1788 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1789 'only_matching': True,
1790 },
1791 {
1792 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1793 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1794 'info_dict': {
1795 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1796 'ext': 'mp4',
1797 'title': 'Big Buck Bunny',
1798 'description': 'Royalty free test video',
1799 'timestamp': 1432816365,
1800 'upload_date': '20150528',
1801 'is_live': False,
1802 },
1803 'params': {
1804 'skip_download': True,
1805 },
1806 'add_ie': [ArkenaIE.ie_key()],
1807 },
1808 {
1809 '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/',
1810 'info_dict': {
1811 'id': '1c7141f46c',
1812 'ext': 'mp4',
1813 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1814 },
1815 'params': {
1816 'skip_download': True,
1817 },
1818 'add_ie': [Vbox7IE.ie_key()],
1819 },
1820 {
1821 # DBTV embeds
1822 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1823 'info_dict': {
1824 'id': '43254897',
1825 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1826 },
1827 'playlist_mincount': 3,
1828 },
1829 {
1830 # Videa embeds
1831 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1832 'info_dict': {
1833 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1834 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1835 },
1836 'playlist_mincount': 2,
1837 },
1838 {
1839 # 20 minuten embed
1840 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1841 'info_dict': {
1842 'id': '523629',
1843 'ext': 'mp4',
1844 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1845 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1846 },
1847 'params': {
1848 'skip_download': True,
1849 },
1850 'add_ie': [TwentyMinutenIE.ie_key()],
1851 },
1852 {
1853 # VideoPress embed
1854 'url': 'https://en.support.wordpress.com/videopress/',
1855 'info_dict': {
1856 'id': 'OcobLTqC',
1857 'ext': 'm4v',
1858 'title': 'IMG_5786',
1859 'timestamp': 1435711927,
1860 'upload_date': '20150701',
1861 },
1862 'params': {
1863 'skip_download': True,
1864 },
1865 'add_ie': [VideoPressIE.ie_key()],
1866 },
1867 {
1868 # Rutube embed
1869 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1870 'info_dict': {
1871 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1872 'ext': 'flv',
1873 'title': 'Магаззино: Казань 2',
1874 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1875 'uploader': 'Магаззино',
1876 'upload_date': '20170228',
1877 'uploader_id': '996642',
1878 },
1879 'params': {
1880 'skip_download': True,
1881 },
1882 'add_ie': [RutubeIE.ie_key()],
1883 },
1884 {
1885 # ThePlatform embedded with whitespaces in URLs
1886 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1887 'only_matching': True,
1888 },
1889 {
1890 # Senate ISVP iframe https
1891 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1892 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1893 'info_dict': {
1894 'id': 'govtaff020316',
1895 'ext': 'mp4',
1896 'title': 'Integrated Senate Video Player',
1897 },
1898 'add_ie': [SenateISVPIE.ie_key()],
1899 },
1900 {
1901 # Limelight embeds (1 channel embed + 4 media embeds)
1902 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1903 'info_dict': {
1904 'id': 'FacilitatorTraining2017',
1905 'title': 'Facilitator Training 2017',
1906 },
1907 'playlist_mincount': 5,
1908 },
1909 {
1910 # Limelight embed (LimelightPlayerUtil.embed)
1911 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1912 'info_dict': {
1913 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1914 'ext': 'mp4',
1915 'title': '07448641',
1916 'timestamp': 1499890639,
1917 'upload_date': '20170712',
1918 },
1919 'params': {
1920 'skip_download': True,
1921 },
1922 'add_ie': ['LimelightMedia'],
1923 },
1924 {
1925 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1926 'info_dict': {
1927 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1928 'title': 'Standoff with Walnut Creek murder suspect ends',
1929 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1930 },
1931 'playlist_mincount': 4,
1932 },
1933 {
1934 # WashingtonPost embed
1935 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1936 'info_dict': {
1937 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1938 'ext': 'mp4',
1939 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1940 '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.',
1941 'timestamp': 1455216756,
1942 'uploader': 'The Washington Post',
1943 'upload_date': '20160211',
1944 },
1945 'add_ie': [WashingtonPostIE.ie_key()],
1946 },
1947 {
1948 # Mediaset embed
1949 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1950 'info_dict': {
1951 'id': '720642',
1952 'ext': 'mp4',
1953 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1954 },
1955 'params': {
1956 'skip_download': True,
1957 },
1958 'add_ie': [MediasetIE.ie_key()],
1959 },
1960 {
1961 # JOJ.sk embeds
1962 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1963 'info_dict': {
1964 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1965 'title': 'Slovenskom sa prehnala vlna silných búrok',
1966 },
1967 'playlist_mincount': 5,
1968 'add_ie': [JojIE.ie_key()],
1969 },
1970 {
1971 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1972 'url': 'https://tvrain.ru/amp/418921/',
1973 'md5': 'cc00413936695987e8de148b67d14f1d',
1974 'info_dict': {
1975 'id': '418921',
1976 'ext': 'mp4',
1977 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1978 },
1979 },
1980 {
1981 # vzaar embed
1982 'url': 'http://help.vzaar.com/article/165-embedding-video',
1983 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1984 'info_dict': {
1985 'id': '8707641',
1986 'ext': 'mp4',
1987 'title': 'Building A Business Online: Principal Chairs Q & A',
1988 },
1989 },
1990 {
1991 # multiple HTML5 videos on one page
1992 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1993 'info_dict': {
1994 'id': 'keyscenarios',
1995 'title': 'Rescue Kit 14 Free Edition - Getting started',
1996 },
1997 'playlist_count': 4,
1998 },
1999 {
2000 # vshare embed
2001 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
2002 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
2003 'info_dict': {
2004 'id': '0f64ce6',
2005 'title': 'vl14062007715967',
2006 'ext': 'mp4',
2007 }
2008 },
2009 {
2010 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2011 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2012 'info_dict': {
2013 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2014 'ext': 'mp4',
2015 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2016 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2017 'timestamp': 1474354800,
2018 'upload_date': '20160920',
2019 }
2020 },
2021 {
2022 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2023 'info_dict': {
2024 'id': '1731611',
2025 'ext': 'mp4',
2026 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2027 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2028 'timestamp': 1516100691,
2029 'upload_date': '20180116',
2030 },
2031 'params': {
2032 'skip_download': True,
2033 },
2034 'add_ie': [SpringboardPlatformIE.ie_key()],
2035 },
2036 {
2037 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2038 'info_dict': {
2039 'id': 'vMDE4NzI1Mjgt690b',
2040 'ext': 'mp4',
2041 'title': 'Котята',
2042 },
2043 'add_ie': [YapFilesIE.ie_key()],
2044 'params': {
2045 'skip_download': True,
2046 },
2047 },
2048 {
2049 # CloudflareStream embed
2050 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2051 'info_dict': {
2052 'id': '31c9291ab41fac05471db4e73aa11717',
2053 'ext': 'mp4',
2054 'title': '31c9291ab41fac05471db4e73aa11717',
2055 },
2056 'add_ie': [CloudflareStreamIE.ie_key()],
2057 'params': {
2058 'skip_download': True,
2059 },
2060 },
2061 {
2062 # PeerTube embed
2063 'url': 'https://joinpeertube.org/fr/home/',
2064 'info_dict': {
2065 'id': 'home',
2066 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2067 },
2068 'playlist_count': 2,
2069 },
2070 {
2071 # Indavideo embed
2072 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2073 'info_dict': {
2074 'id': '1693903',
2075 'ext': 'mp4',
2076 'title': 'Így kell otthon hamburgert sütni',
2077 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2078 'timestamp': 1426330212,
2079 'upload_date': '20150314',
2080 'uploader': 'StreetKitchen',
2081 'uploader_id': '546363',
2082 },
2083 'add_ie': [IndavideoEmbedIE.ie_key()],
2084 'params': {
2085 'skip_download': True,
2086 },
2087 },
2088 {
2089 # APA embed via JWPlatform embed
2090 'url': 'http://www.vol.at/blue-man-group/5593454',
2091 'info_dict': {
2092 'id': 'jjv85FdZ',
2093 'ext': 'mp4',
2094 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2095 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2096 'thumbnail': r're:^https?://.*\.jpg$',
2097 'duration': 254,
2098 'timestamp': 1519211149,
2099 'upload_date': '20180221',
2100 },
2101 'params': {
2102 'skip_download': True,
2103 },
2104 },
2105 {
2106 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2107 'md5': 'b68d276de422ab07ee1d49388103f457',
2108 'info_dict': {
2109 'id': '83645793',
2110 'title': 'Lock up and get excited',
2111 'ext': 'mp4'
2112 },
2113 'skip': 'TODO: fix nested playlists processing in tests',
2114 },
2115 {
2116 # Viqeo embeds
2117 'url': 'https://viqeo.tv/',
2118 'info_dict': {
2119 'id': 'viqeo',
2120 'title': 'All-new video platform',
2121 },
2122 'playlist_count': 6,
2123 },
2124 {
2125 # Squarespace video embed, 2019-08-28
2126 'url': 'http://ootboxford.com',
2127 'info_dict': {
2128 'id': 'Tc7b_JGdZfw',
2129 'title': 'Out of the Blue, at Childish Things 10',
2130 'ext': 'mp4',
2131 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2132 'uploader_id': 'helendouglashouse',
2133 'uploader': 'Helen & Douglas House',
2134 'upload_date': '20140328',
2135 },
2136 'params': {
2137 'skip_download': True,
2138 },
2139 },
2140 # {
2141 # # Zype embed
2142 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2143 # 'info_dict': {
2144 # 'id': '5b400b834b32992a310622b9',
2145 # 'ext': 'mp4',
2146 # 'title': 'Smoky Barbecue Favorites',
2147 # 'thumbnail': r're:^https?://.*\.jpe?g',
2148 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2149 # 'upload_date': '20170909',
2150 # 'timestamp': 1504915200,
2151 # },
2152 # 'add_ie': [ZypeIE.ie_key()],
2153 # 'params': {
2154 # 'skip_download': True,
2155 # },
2156 # },
2157 {
2158 # videojs embed
2159 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2160 'info_dict': {
2161 'id': 'shell',
2162 'ext': 'mp4',
2163 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2164 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2165 'thumbnail': r're:^https?://.*\.jpg$',
2166 },
2167 'params': {
2168 'skip_download': True,
2169 },
2170 'expected_warnings': ['Failed to download MPD manifest'],
2171 },
2172 {
2173 # DailyMotion embed with DM.player
2174 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2175 'info_dict': {
2176 'id': 'k6aKkGHd9FJs4mtJN39',
2177 'ext': 'mp4',
2178 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2179 'description': 'This video is private.',
2180 'uploader_id': 'x1jf30l',
2181 'uploader': 'beIN SPORTS USA',
2182 'upload_date': '20190528',
2183 'timestamp': 1559062971,
2184 },
2185 'params': {
2186 'skip_download': True,
2187 },
2188 },
2189 # {
2190 # # TODO: find another test
2191 # # http://schema.org/VideoObject
2192 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2193 # 'md5': '888dcf08b7ea671381f00fab74692755',
2194 # 'info_dict': {
2195 # 'id': 'nyvTSJMKId',
2196 # 'ext': 'mp4',
2197 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2198 # 'description': '#love for cats.',
2199 # 'timestamp': 1461244995,
2200 # 'upload_date': '20160421',
2201 # },
2202 # 'params': {
2203 # 'force_generic_extractor': True,
2204 # },
2205 # },
2206 {
2207 # VHX Embed
2208 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2209 'info_dict': {
2210 'id': '858208',
2211 'ext': 'mp4',
2212 'title': 'Untitled',
2213 'uploader_id': 'user80538407',
2214 'uploader': 'OTT Videos',
2215 },
2216 },
2217 {
2218 # ArcPublishing PoWa video player
2219 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2220 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2221 'info_dict': {
2222 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2223 'ext': 'mp4',
2224 'title': 'Senate candidates wave to voters on Anchorage streets',
2225 'description': 'md5:91f51a6511f090617353dc720318b20e',
2226 'timestamp': 1604378735,
2227 'upload_date': '20201103',
2228 'duration': 1581,
2229 },
2230 },
2231 {
2232 # MyChannels SDK embed
2233 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2234 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2235 'md5': '90c0699c37006ef18e198c032d81739c',
2236 'info_dict': {
2237 'id': '194165',
2238 'ext': 'mp4',
2239 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2240 'timestamp': 1611740340,
2241 'upload_date': '20210127',
2242 'duration': 159,
2243 },
2244 },
2245 {
2246 # Simplecast player embed
2247 'url': 'https://www.bio.org/podcast',
2248 'info_dict': {
2249 'id': 'podcast',
2250 'title': 'I AM BIO Podcast | BIO',
2251 },
2252 'playlist_mincount': 52,
2253 },
2254 {
2255 # WimTv embed player
2256 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2257 'info_dict': {
2258 'id': 'wearefmi-pt-2-2021',
2259 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2260 },
2261 'playlist_count': 1,
2262 },
2263 ]
2264
2265 def report_following_redirect(self, new_url):
2266 """Report information extraction."""
2267 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2268
2269 def _extract_rss(self, url, video_id, doc):
2270 playlist_title = doc.find('./channel/title').text
2271 playlist_desc_el = doc.find('./channel/description')
2272 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2273
2274 NS_MAP = {
2275 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2276 }
2277
2278 entries = []
2279 for it in doc.findall('./channel/item'):
2280 next_url = None
2281 enclosure_nodes = it.findall('./enclosure')
2282 for e in enclosure_nodes:
2283 next_url = e.attrib.get('url')
2284 if next_url:
2285 break
2286
2287 if not next_url:
2288 next_url = xpath_text(it, 'link', fatal=False)
2289
2290 if not next_url:
2291 continue
2292
2293 def itunes(key):
2294 return xpath_text(
2295 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2296 default=None)
2297
2298 duration = itunes('duration')
2299 explicit = (itunes('explicit') or '').lower()
2300 if explicit in ('true', 'yes'):
2301 age_limit = 18
2302 elif explicit in ('false', 'no'):
2303 age_limit = 0
2304 else:
2305 age_limit = None
2306
2307 entries.append({
2308 '_type': 'url_transparent',
2309 'url': next_url,
2310 'title': it.find('title').text,
2311 'description': xpath_text(it, 'description', default=None),
2312 'timestamp': unified_timestamp(
2313 xpath_text(it, 'pubDate', default=None)),
2314 'duration': int_or_none(duration) or parse_duration(duration),
2315 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2316 'episode': itunes('title'),
2317 'episode_number': int_or_none(itunes('episode')),
2318 'season_number': int_or_none(itunes('season')),
2319 'age_limit': age_limit,
2320 })
2321
2322 return {
2323 '_type': 'playlist',
2324 'id': url,
2325 'title': playlist_title,
2326 'description': playlist_desc,
2327 'entries': entries,
2328 }
2329
2330 def _extract_camtasia(self, url, video_id, webpage):
2331 """ Returns None if no camtasia video can be found. """
2332
2333 camtasia_cfg = self._search_regex(
2334 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2335 webpage, 'camtasia configuration file', default=None)
2336 if camtasia_cfg is None:
2337 return None
2338
2339 title = self._html_search_meta('DC.title', webpage, fatal=True)
2340
2341 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2342 camtasia_cfg = self._download_xml(
2343 camtasia_url, video_id,
2344 note='Downloading camtasia configuration',
2345 errnote='Failed to download camtasia configuration')
2346 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2347
2348 entries = []
2349 for n in fileset_node.getchildren():
2350 url_n = n.find('./uri')
2351 if url_n is None:
2352 continue
2353
2354 entries.append({
2355 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2356 'title': '%s - %s' % (title, n.tag),
2357 'url': compat_urlparse.urljoin(url, url_n.text),
2358 'duration': float_or_none(n.find('./duration').text),
2359 })
2360
2361 return {
2362 '_type': 'playlist',
2363 'entries': entries,
2364 'title': title,
2365 }
2366
2367 def _real_extract(self, url):
2368 if url.startswith('//'):
2369 return self.url_result(self.http_scheme() + url)
2370
2371 parsed_url = compat_urlparse.urlparse(url)
2372 if not parsed_url.scheme:
2373 default_search = self._downloader.params.get('default_search')
2374 if default_search is None:
2375 default_search = 'fixup_error'
2376
2377 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2378 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2379 self.report_warning('The url doesn\'t specify the protocol, trying with http')
2380 return self.url_result('http://' + url)
2381 elif default_search != 'fixup_error':
2382 if default_search == 'auto_warning':
2383 if re.match(r'^(?:url|URL)$', url):
2384 raise ExtractorError(
2385 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2386 expected=True)
2387 else:
2388 self.report_warning(
2389 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2390 return self.url_result('ytsearch:' + url)
2391
2392 if default_search in ('error', 'fixup_error'):
2393 raise ExtractorError(
2394 '%r is not a valid URL. '
2395 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
2396 % (url, url), expected=True)
2397 else:
2398 if ':' not in default_search:
2399 default_search += ':'
2400 return self.url_result(default_search + url)
2401
2402 url, smuggled_data = unsmuggle_url(url)
2403 force_videoid = None
2404 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2405 if smuggled_data and 'force_videoid' in smuggled_data:
2406 force_videoid = smuggled_data['force_videoid']
2407 video_id = force_videoid
2408 else:
2409 video_id = self._generic_id(url)
2410
2411 self.to_screen('%s: Requesting header' % video_id)
2412
2413 head_req = HEADRequest(url)
2414 head_response = self._request_webpage(
2415 head_req, video_id,
2416 note=False, errnote='Could not send HEAD request to %s' % url,
2417 fatal=False)
2418
2419 if head_response is not False:
2420 # Check for redirect
2421 new_url = head_response.geturl()
2422 if url != new_url:
2423 self.report_following_redirect(new_url)
2424 if force_videoid:
2425 new_url = smuggle_url(
2426 new_url, {'force_videoid': force_videoid})
2427 return self.url_result(new_url)
2428
2429 full_response = None
2430 if head_response is False:
2431 request = sanitized_Request(url)
2432 request.add_header('Accept-Encoding', '*')
2433 full_response = self._request_webpage(request, video_id)
2434 head_response = full_response
2435
2436 info_dict = {
2437 'id': video_id,
2438 'title': self._generic_title(url),
2439 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2440 }
2441
2442 # Check for direct link to a video
2443 content_type = head_response.headers.get('Content-Type', '').lower()
2444 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2445 if m:
2446 format_id = compat_str(m.group('format_id'))
2447 subtitles = {}
2448 if format_id.endswith('mpegurl'):
2449 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2450 elif format_id == 'f4m':
2451 formats = self._extract_f4m_formats(url, video_id)
2452 else:
2453 formats = [{
2454 'format_id': format_id,
2455 'url': url,
2456 'vcodec': 'none' if m.group('type') == 'audio' else None
2457 }]
2458 info_dict['direct'] = True
2459 self._sort_formats(formats)
2460 info_dict['formats'] = formats
2461 info_dict['subtitles'] = subtitles
2462 return info_dict
2463
2464 if not self._downloader.params.get('test', False) and not is_intentional:
2465 force = self._downloader.params.get('force_generic_extractor', False)
2466 self.report_warning(
2467 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2468
2469 if not full_response:
2470 request = sanitized_Request(url)
2471 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2472 # making it impossible to download only chunk of the file (yet we need only 512kB to
2473 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
2474 # that will always result in downloading the whole file that is not desirable.
2475 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2476 # to accept raw bytes and being able to download only a chunk.
2477 # It may probably better to solve this by checking Content-Type for application/octet-stream
2478 # after HEAD request finishes, but not sure if we can rely on this.
2479 request.add_header('Accept-Encoding', '*')
2480 full_response = self._request_webpage(request, video_id)
2481
2482 first_bytes = full_response.read(512)
2483
2484 # Is it an M3U playlist?
2485 if first_bytes.startswith(b'#EXTM3U'):
2486 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2487 self._sort_formats(info_dict['formats'])
2488 return info_dict
2489
2490 # Maybe it's a direct link to a video?
2491 # Be careful not to download the whole thing!
2492 if not is_html(first_bytes):
2493 self.report_warning(
2494 'URL could be a direct video link, returning it as such.')
2495 info_dict.update({
2496 'direct': True,
2497 'url': url,
2498 })
2499 return info_dict
2500
2501 webpage = self._webpage_read_content(
2502 full_response, url, video_id, prefix=first_bytes)
2503
2504 if '<title>DPG Media Privacy Gate</title>' in webpage:
2505 webpage = self._download_webpage(url, video_id)
2506
2507 self.report_extraction(video_id)
2508
2509 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2510 try:
2511 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2512 if doc.tag == 'rss':
2513 return self._extract_rss(url, video_id, doc)
2514 elif doc.tag == 'SmoothStreamingMedia':
2515 info_dict['formats'] = self._parse_ism_formats(doc, url)
2516 self._sort_formats(info_dict['formats'])
2517 return info_dict
2518 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2519 smil = self._parse_smil(doc, url, video_id)
2520 self._sort_formats(smil['formats'])
2521 return smil
2522 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2523 return self.playlist_result(
2524 self._parse_xspf(
2525 doc, video_id, xspf_url=url,
2526 xspf_base_url=full_response.geturl()),
2527 video_id)
2528 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2529 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
2530 doc,
2531 mpd_base_url=full_response.geturl().rpartition('/')[0],
2532 mpd_url=url)
2533 self._sort_formats(info_dict['formats'])
2534 return info_dict
2535 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2536 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2537 self._sort_formats(info_dict['formats'])
2538 return info_dict
2539 except compat_xml_parse_error:
2540 pass
2541
2542 # Is it a Camtasia project?
2543 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2544 if camtasia_res is not None:
2545 return camtasia_res
2546
2547 # Sometimes embedded video player is hidden behind percent encoding
2548 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2549 # Unescaping the whole page allows to handle those cases in a generic way
2550 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2551 # There probably should be a second run of generic extractor on unescaped webpage.
2552 # webpage = compat_urllib_parse_unquote(webpage)
2553
2554 # Unescape squarespace embeds to be detected by generic extractor,
2555 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2556 webpage = re.sub(
2557 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2558 lambda x: unescapeHTML(x.group(0)), webpage)
2559
2560 # it's tempting to parse this further, but you would
2561 # have to take into account all the variations like
2562 # Video Title - Site Name
2563 # Site Name | Video Title
2564 # Video Title - Tagline | Site Name
2565 # and so on and so forth; it's just not practical
2566 video_title = self._og_search_title(
2567 webpage, default=None) or self._html_search_regex(
2568 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2569 default='video')
2570
2571 # Try to detect age limit automatically
2572 age_limit = self._rta_search(webpage)
2573 # And then there are the jokers who advertise that they use RTA,
2574 # but actually don't.
2575 AGE_LIMIT_MARKERS = [
2576 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2577 ]
2578 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2579 age_limit = 18
2580
2581 # video uploader is domain name
2582 video_uploader = self._search_regex(
2583 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2584
2585 video_description = self._og_search_description(webpage, default=None)
2586 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2587
2588 info_dict.update({
2589 'title': video_title,
2590 'description': video_description,
2591 'thumbnail': video_thumbnail,
2592 'age_limit': age_limit,
2593 })
2594
2595 # Look for Brightcove Legacy Studio embeds
2596 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2597 if bc_urls:
2598 entries = [{
2599 '_type': 'url',
2600 'url': smuggle_url(bc_url, {'Referer': url}),
2601 'ie_key': 'BrightcoveLegacy'
2602 } for bc_url in bc_urls]
2603
2604 return {
2605 '_type': 'playlist',
2606 'title': video_title,
2607 'id': video_id,
2608 'entries': entries,
2609 }
2610
2611 # Look for Brightcove New Studio embeds
2612 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2613 if bc_urls:
2614 return self.playlist_from_matches(
2615 bc_urls, video_id, video_title,
2616 getter=lambda x: smuggle_url(x, {'referrer': url}),
2617 ie='BrightcoveNew')
2618
2619 # Look for Nexx embeds
2620 nexx_urls = NexxIE._extract_urls(webpage)
2621 if nexx_urls:
2622 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2623
2624 # Look for Nexx iFrame embeds
2625 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2626 if nexx_embed_urls:
2627 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2628
2629 # Look for ThePlatform embeds
2630 tp_urls = ThePlatformIE._extract_urls(webpage)
2631 if tp_urls:
2632 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2633
2634 arc_urls = ArcPublishingIE._extract_urls(webpage)
2635 if arc_urls:
2636 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2637
2638 mychannels_urls = MedialaanIE._extract_urls(webpage)
2639 if mychannels_urls:
2640 return self.playlist_from_matches(
2641 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2642
2643 # Look for embedded rtl.nl player
2644 matches = re.findall(
2645 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2646 webpage)
2647 if matches:
2648 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2649
2650 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2651 if vimeo_urls:
2652 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2653
2654 vhx_url = VHXEmbedIE._extract_url(webpage)
2655 if vhx_url:
2656 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2657
2658 vid_me_embed_url = self._search_regex(
2659 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2660 webpage, 'vid.me embed', default=None)
2661 if vid_me_embed_url is not None:
2662 return self.url_result(vid_me_embed_url, 'Vidme')
2663
2664 # Invidious Instances
2665 # https://github.com/yt-dlp/yt-dlp/issues/195
2666 # https://github.com/iv-org/invidious/pull/1730
2667 youtube_url = self._search_regex(
2668 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2669 webpage, 'youtube link', default=None)
2670 if youtube_url:
2671 return self.url_result(youtube_url, YoutubeIE.ie_key())
2672
2673 # Look for YouTube embeds
2674 youtube_urls = YoutubeIE._extract_urls(webpage)
2675 if youtube_urls:
2676 return self.playlist_from_matches(
2677 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2678
2679 matches = DailymotionIE._extract_urls(webpage)
2680 if matches:
2681 return self.playlist_from_matches(matches, video_id, video_title)
2682
2683 # Look for embedded Dailymotion playlist player (#3822)
2684 m = re.search(
2685 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2686 if m:
2687 playlists = re.findall(
2688 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2689 if playlists:
2690 return self.playlist_from_matches(
2691 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2692
2693 # Look for DailyMail embeds
2694 dailymail_urls = DailyMailIE._extract_urls(webpage)
2695 if dailymail_urls:
2696 return self.playlist_from_matches(
2697 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2698
2699 # Look for Teachable embeds, must be before Wistia
2700 teachable_url = TeachableIE._extract_url(webpage, url)
2701 if teachable_url:
2702 return self.url_result(teachable_url)
2703
2704 # Look for embedded Wistia player
2705 wistia_urls = WistiaIE._extract_urls(webpage)
2706 if wistia_urls:
2707 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2708 for entry in playlist['entries']:
2709 entry.update({
2710 '_type': 'url_transparent',
2711 'uploader': video_uploader,
2712 })
2713 return playlist
2714
2715 # Look for SVT player
2716 svt_url = SVTIE._extract_url(webpage)
2717 if svt_url:
2718 return self.url_result(svt_url, 'SVT')
2719
2720 # Look for Bandcamp pages with custom domain
2721 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2722 if mobj is not None:
2723 burl = unescapeHTML(mobj.group(1))
2724 # Don't set the extractor because it can be a track url or an album
2725 return self.url_result(burl)
2726
2727 # Look for embedded Vevo player
2728 mobj = re.search(
2729 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2730 if mobj is not None:
2731 return self.url_result(mobj.group('url'))
2732
2733 # Look for embedded Viddler player
2734 mobj = re.search(
2735 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2736 webpage)
2737 if mobj is not None:
2738 return self.url_result(mobj.group('url'))
2739
2740 # Look for NYTimes player
2741 mobj = re.search(
2742 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2743 webpage)
2744 if mobj is not None:
2745 return self.url_result(mobj.group('url'))
2746
2747 # Look for Libsyn player
2748 mobj = re.search(
2749 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2750 if mobj is not None:
2751 return self.url_result(mobj.group('url'))
2752
2753 # Look for Ooyala videos
2754 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2755 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2756 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2757 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2758 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2759 if mobj is not None:
2760 embed_token = self._search_regex(
2761 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2762 webpage, 'ooyala embed token', default=None)
2763 return OoyalaIE._build_url_result(smuggle_url(
2764 mobj.group('ec'), {
2765 'domain': url,
2766 'embed_token': embed_token,
2767 }))
2768
2769 # Look for multiple Ooyala embeds on SBN network websites
2770 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2771 if mobj is not None:
2772 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2773 if embeds:
2774 return self.playlist_from_matches(
2775 embeds, video_id, video_title,
2776 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2777
2778 # Look for Aparat videos
2779 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2780 if mobj is not None:
2781 return self.url_result(mobj.group(1), 'Aparat')
2782
2783 # Look for MPORA videos
2784 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2785 if mobj is not None:
2786 return self.url_result(mobj.group(1), 'Mpora')
2787
2788 # Look for embedded Facebook player
2789 facebook_urls = FacebookIE._extract_urls(webpage)
2790 if facebook_urls:
2791 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2792
2793 # Look for embedded VK player
2794 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2795 if mobj is not None:
2796 return self.url_result(mobj.group('url'), 'VK')
2797
2798 # Look for embedded Odnoklassniki player
2799 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2800 if odnoklassniki_url:
2801 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2802
2803 # Look for embedded ivi player
2804 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2805 if mobj is not None:
2806 return self.url_result(mobj.group('url'), 'Ivi')
2807
2808 # Look for embedded Huffington Post player
2809 mobj = re.search(
2810 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2811 if mobj is not None:
2812 return self.url_result(mobj.group('url'), 'HuffPost')
2813
2814 # Look for embed.ly
2815 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2816 if mobj is not None:
2817 return self.url_result(mobj.group('url'))
2818 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2819 if mobj is not None:
2820 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2821
2822 # Look for funnyordie embed
2823 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2824 if matches:
2825 return self.playlist_from_matches(
2826 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2827
2828 # Look for Simplecast embeds
2829 simplecast_urls = SimplecastIE._extract_urls(webpage)
2830 if simplecast_urls:
2831 return self.playlist_from_matches(
2832 simplecast_urls, video_id, video_title)
2833
2834 # Look for BBC iPlayer embed
2835 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2836 if matches:
2837 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2838
2839 # Look for embedded RUTV player
2840 rutv_url = RUTVIE._extract_url(webpage)
2841 if rutv_url:
2842 return self.url_result(rutv_url, 'RUTV')
2843
2844 # Look for embedded TVC player
2845 tvc_url = TVCIE._extract_url(webpage)
2846 if tvc_url:
2847 return self.url_result(tvc_url, 'TVC')
2848
2849 # Look for embedded SportBox player
2850 sportbox_urls = SportBoxIE._extract_urls(webpage)
2851 if sportbox_urls:
2852 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2853
2854 # Look for embedded XHamster player
2855 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2856 if xhamster_urls:
2857 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2858
2859 # Look for embedded TNAFlixNetwork player
2860 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2861 if tnaflix_urls:
2862 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2863
2864 # Look for embedded PornHub player
2865 pornhub_urls = PornHubIE._extract_urls(webpage)
2866 if pornhub_urls:
2867 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2868
2869 # Look for embedded DrTuber player
2870 drtuber_urls = DrTuberIE._extract_urls(webpage)
2871 if drtuber_urls:
2872 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2873
2874 # Look for embedded RedTube player
2875 redtube_urls = RedTubeIE._extract_urls(webpage)
2876 if redtube_urls:
2877 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2878
2879 # Look for embedded Tube8 player
2880 tube8_urls = Tube8IE._extract_urls(webpage)
2881 if tube8_urls:
2882 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2883
2884 # Look for embedded Mofosex player
2885 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2886 if mofosex_urls:
2887 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2888
2889 # Look for embedded Spankwire player
2890 spankwire_urls = SpankwireIE._extract_urls(webpage)
2891 if spankwire_urls:
2892 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2893
2894 # Look for embedded YouPorn player
2895 youporn_urls = YouPornIE._extract_urls(webpage)
2896 if youporn_urls:
2897 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2898
2899 # Look for embedded Tvigle player
2900 mobj = re.search(
2901 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2902 if mobj is not None:
2903 return self.url_result(mobj.group('url'), 'Tvigle')
2904
2905 # Look for embedded TED player
2906 mobj = re.search(
2907 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2908 if mobj is not None:
2909 return self.url_result(mobj.group('url'), 'TED')
2910
2911 # Look for embedded Ustream videos
2912 ustream_url = UstreamIE._extract_url(webpage)
2913 if ustream_url:
2914 return self.url_result(ustream_url, UstreamIE.ie_key())
2915
2916 # Look for embedded arte.tv player
2917 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2918 if arte_urls:
2919 return self.playlist_from_matches(arte_urls, video_id, video_title)
2920
2921 # Look for embedded francetv player
2922 mobj = re.search(
2923 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2924 webpage)
2925 if mobj is not None:
2926 return self.url_result(mobj.group('url'))
2927
2928 # Look for embedded Myvi.ru player
2929 myvi_url = MyviIE._extract_url(webpage)
2930 if myvi_url:
2931 return self.url_result(myvi_url)
2932
2933 # Look for embedded soundcloud player
2934 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2935 if soundcloud_urls:
2936 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2937
2938 # Look for tunein player
2939 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2940 if tunein_urls:
2941 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2942
2943 # Look for embedded mtvservices player
2944 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2945 if mtvservices_url:
2946 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2947
2948 # Look for embedded yahoo player
2949 mobj = re.search(
2950 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2951 webpage)
2952 if mobj is not None:
2953 return self.url_result(mobj.group('url'), 'Yahoo')
2954
2955 # Look for embedded sbs.com.au player
2956 mobj = re.search(
2957 r'''(?x)
2958 (?:
2959 <meta\s+property="og:video"\s+content=|
2960 <iframe[^>]+?src=
2961 )
2962 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2963 webpage)
2964 if mobj is not None:
2965 return self.url_result(mobj.group('url'), 'SBS')
2966
2967 # Look for embedded Cinchcast player
2968 mobj = re.search(
2969 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2970 webpage)
2971 if mobj is not None:
2972 return self.url_result(mobj.group('url'), 'Cinchcast')
2973
2974 mobj = re.search(
2975 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2976 webpage)
2977 if not mobj:
2978 mobj = re.search(
2979 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
2980 webpage)
2981 if mobj is not None:
2982 return self.url_result(mobj.group('url'), 'MLB')
2983
2984 mobj = re.search(
2985 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2986 webpage)
2987 if mobj is not None:
2988 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2989
2990 mobj = re.search(
2991 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2992 webpage)
2993 if mobj is not None:
2994 return self.url_result(mobj.group('url'), 'Livestream')
2995
2996 # Look for Zapiks embed
2997 mobj = re.search(
2998 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2999 if mobj is not None:
3000 return self.url_result(mobj.group('url'), 'Zapiks')
3001
3002 # Look for Kaltura embeds
3003 kaltura_urls = KalturaIE._extract_urls(webpage)
3004 if kaltura_urls:
3005 return self.playlist_from_matches(
3006 kaltura_urls, video_id, video_title,
3007 getter=lambda x: smuggle_url(x, {'source_url': url}),
3008 ie=KalturaIE.ie_key())
3009
3010 # Look for EaglePlatform embeds
3011 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3012 if eagleplatform_url:
3013 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3014
3015 # Look for ClipYou (uses EaglePlatform) embeds
3016 mobj = re.search(
3017 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3018 if mobj is not None:
3019 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3020
3021 # Look for Pladform embeds
3022 pladform_url = PladformIE._extract_url(webpage)
3023 if pladform_url:
3024 return self.url_result(pladform_url)
3025
3026 # Look for Videomore embeds
3027 videomore_url = VideomoreIE._extract_url(webpage)
3028 if videomore_url:
3029 return self.url_result(videomore_url)
3030
3031 # Look for Webcaster embeds
3032 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3033 if webcaster_url:
3034 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3035
3036 # Look for Playwire embeds
3037 mobj = re.search(
3038 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3039 if mobj is not None:
3040 return self.url_result(mobj.group('url'))
3041
3042 # Look for 5min embeds
3043 mobj = re.search(
3044 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3045 if mobj is not None:
3046 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3047
3048 # Look for Crooks and Liars embeds
3049 mobj = re.search(
3050 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3051 if mobj is not None:
3052 return self.url_result(mobj.group('url'))
3053
3054 # Look for NBC Sports VPlayer embeds
3055 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3056 if nbc_sports_url:
3057 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3058
3059 # Look for NBC News embeds
3060 nbc_news_embed_url = re.search(
3061 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3062 if nbc_news_embed_url:
3063 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3064
3065 # Look for Google Drive embeds
3066 google_drive_url = GoogleDriveIE._extract_url(webpage)
3067 if google_drive_url:
3068 return self.url_result(google_drive_url, 'GoogleDrive')
3069
3070 # Look for UDN embeds
3071 mobj = re.search(
3072 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3073 if mobj is not None:
3074 return self.url_result(
3075 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3076
3077 # Look for Senate ISVP iframe
3078 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3079 if senate_isvp_url:
3080 return self.url_result(senate_isvp_url, 'SenateISVP')
3081
3082 # Look for Kinja embeds
3083 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3084 if kinja_embed_urls:
3085 return self.playlist_from_matches(
3086 kinja_embed_urls, video_id, video_title)
3087
3088 # Look for OnionStudios embeds
3089 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3090 if onionstudios_url:
3091 return self.url_result(onionstudios_url)
3092
3093 # Look for ViewLift embeds
3094 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3095 if viewlift_url:
3096 return self.url_result(viewlift_url)
3097
3098 # Look for JWPlatform embeds
3099 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3100 if jwplatform_urls:
3101 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3102
3103 # Look for Digiteka embeds
3104 digiteka_url = DigitekaIE._extract_url(webpage)
3105 if digiteka_url:
3106 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3107
3108 # Look for Arkena embeds
3109 arkena_url = ArkenaIE._extract_url(webpage)
3110 if arkena_url:
3111 return self.url_result(arkena_url, ArkenaIE.ie_key())
3112
3113 # Look for Piksel embeds
3114 piksel_url = PikselIE._extract_url(webpage)
3115 if piksel_url:
3116 return self.url_result(piksel_url, PikselIE.ie_key())
3117
3118 # Look for Limelight embeds
3119 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3120 if limelight_urls:
3121 return self.playlist_result(
3122 limelight_urls, video_id, video_title, video_description)
3123
3124 # Look for Anvato embeds
3125 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3126 if anvato_urls:
3127 return self.playlist_result(
3128 anvato_urls, video_id, video_title, video_description)
3129
3130 # Look for AdobeTVVideo embeds
3131 mobj = re.search(
3132 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3133 webpage)
3134 if mobj is not None:
3135 return self.url_result(
3136 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3137 'AdobeTVVideo')
3138
3139 # Look for Vine embeds
3140 mobj = re.search(
3141 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3142 webpage)
3143 if mobj is not None:
3144 return self.url_result(
3145 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3146
3147 # Look for VODPlatform embeds
3148 mobj = re.search(
3149 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3150 webpage)
3151 if mobj is not None:
3152 return self.url_result(
3153 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3154
3155 # Look for Mangomolo embeds
3156 mobj = re.search(
3157 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3158 (?:
3159 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3160 player\.mangomolo\.com/v1
3161 )/
3162 (?:
3163 video\?.*?\bid=(?P<video_id>\d+)|
3164 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3165 ).+?)\1''', webpage)
3166 if mobj is not None:
3167 info = {
3168 '_type': 'url_transparent',
3169 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3170 'title': video_title,
3171 'description': video_description,
3172 'thumbnail': video_thumbnail,
3173 'uploader': video_uploader,
3174 }
3175 video_id = mobj.group('video_id')
3176 if video_id:
3177 info.update({
3178 'ie_key': 'MangomoloVideo',
3179 'id': video_id,
3180 })
3181 else:
3182 info.update({
3183 'ie_key': 'MangomoloLive',
3184 'id': mobj.group('channel_id'),
3185 })
3186 return info
3187
3188 # Look for Instagram embeds
3189 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3190 if instagram_embed_url is not None:
3191 return self.url_result(
3192 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3193
3194 # Look for LiveLeak embeds
3195 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3196 if liveleak_urls:
3197 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3198
3199 # Look for 3Q SDN embeds
3200 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3201 if threeqsdn_url:
3202 return {
3203 '_type': 'url_transparent',
3204 'ie_key': ThreeQSDNIE.ie_key(),
3205 'url': self._proto_relative_url(threeqsdn_url),
3206 'title': video_title,
3207 'description': video_description,
3208 'thumbnail': video_thumbnail,
3209 'uploader': video_uploader,
3210 }
3211
3212 # Look for VBOX7 embeds
3213 vbox7_url = Vbox7IE._extract_url(webpage)
3214 if vbox7_url:
3215 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3216
3217 # Look for DBTV embeds
3218 dbtv_urls = DBTVIE._extract_urls(webpage)
3219 if dbtv_urls:
3220 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3221
3222 # Look for Videa embeds
3223 videa_urls = VideaIE._extract_urls(webpage)
3224 if videa_urls:
3225 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3226
3227 # Look for 20 minuten embeds
3228 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3229 if twentymin_urls:
3230 return self.playlist_from_matches(
3231 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3232
3233 # Look for VideoPress embeds
3234 videopress_urls = VideoPressIE._extract_urls(webpage)
3235 if videopress_urls:
3236 return self.playlist_from_matches(
3237 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3238
3239 # Look for Rutube embeds
3240 rutube_urls = RutubeIE._extract_urls(webpage)
3241 if rutube_urls:
3242 return self.playlist_from_matches(
3243 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3244
3245 # Look for WashingtonPost embeds
3246 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3247 if wapo_urls:
3248 return self.playlist_from_matches(
3249 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3250
3251 # Look for Mediaset embeds
3252 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3253 if mediaset_urls:
3254 return self.playlist_from_matches(
3255 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3256
3257 # Look for JOJ.sk embeds
3258 joj_urls = JojIE._extract_urls(webpage)
3259 if joj_urls:
3260 return self.playlist_from_matches(
3261 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3262
3263 # Look for megaphone.fm embeds
3264 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3265 if mpfn_urls:
3266 return self.playlist_from_matches(
3267 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3268
3269 # Look for vzaar embeds
3270 vzaar_urls = VzaarIE._extract_urls(webpage)
3271 if vzaar_urls:
3272 return self.playlist_from_matches(
3273 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3274
3275 channel9_urls = Channel9IE._extract_urls(webpage)
3276 if channel9_urls:
3277 return self.playlist_from_matches(
3278 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3279
3280 vshare_urls = VShareIE._extract_urls(webpage)
3281 if vshare_urls:
3282 return self.playlist_from_matches(
3283 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3284
3285 # Look for Mediasite embeds
3286 mediasite_urls = MediasiteIE._extract_urls(webpage)
3287 if mediasite_urls:
3288 entries = [
3289 self.url_result(smuggle_url(
3290 compat_urlparse.urljoin(url, mediasite_url),
3291 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3292 for mediasite_url in mediasite_urls]
3293 return self.playlist_result(entries, video_id, video_title)
3294
3295 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3296 if springboardplatform_urls:
3297 return self.playlist_from_matches(
3298 springboardplatform_urls, video_id, video_title,
3299 ie=SpringboardPlatformIE.ie_key())
3300
3301 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3302 if yapfiles_urls:
3303 return self.playlist_from_matches(
3304 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3305
3306 vice_urls = ViceIE._extract_urls(webpage)
3307 if vice_urls:
3308 return self.playlist_from_matches(
3309 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3310
3311 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3312 if xfileshare_urls:
3313 return self.playlist_from_matches(
3314 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3315
3316 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3317 if cloudflarestream_urls:
3318 return self.playlist_from_matches(
3319 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3320
3321 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3322 if peertube_urls:
3323 return self.playlist_from_matches(
3324 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3325
3326 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3327 if indavideo_urls:
3328 return self.playlist_from_matches(
3329 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3330
3331 apa_urls = APAIE._extract_urls(webpage)
3332 if apa_urls:
3333 return self.playlist_from_matches(
3334 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3335
3336 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3337 if foxnews_urls:
3338 return self.playlist_from_matches(
3339 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3340
3341 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3342 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3343 webpage)]
3344 if sharevideos_urls:
3345 return self.playlist_from_matches(
3346 sharevideos_urls, video_id, video_title)
3347
3348 viqeo_urls = ViqeoIE._extract_urls(webpage)
3349 if viqeo_urls:
3350 return self.playlist_from_matches(
3351 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3352
3353 expressen_urls = ExpressenIE._extract_urls(webpage)
3354 if expressen_urls:
3355 return self.playlist_from_matches(
3356 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3357
3358 zype_urls = ZypeIE._extract_urls(webpage)
3359 if zype_urls:
3360 return self.playlist_from_matches(
3361 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3362
3363 gedi_urls = GediDigitalIE._extract_urls(webpage)
3364 if gedi_urls:
3365 return self.playlist_from_matches(
3366 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
3367
3368 # Look for RCS media group embeds
3369 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3370 if rcs_urls:
3371 return self.playlist_from_matches(
3372 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3373
3374 wimtv_urls = WimTVIE._extract_urls(webpage)
3375 if wimtv_urls:
3376 return self.playlist_from_matches(
3377 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3378
3379 bitchute_urls = BitChuteIE._extract_urls(webpage)
3380 if bitchute_urls:
3381 return self.playlist_from_matches(
3382 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3383
3384 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3385 if len(rumble_urls) == 1:
3386 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3387 if rumble_urls:
3388 return self.playlist_from_matches(
3389 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3390
3391 # Look for HTML5 media
3392 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3393 if entries:
3394 if len(entries) == 1:
3395 entries[0].update({
3396 'id': video_id,
3397 'title': video_title,
3398 })
3399 else:
3400 for num, entry in enumerate(entries, start=1):
3401 entry.update({
3402 'id': '%s-%s' % (video_id, num),
3403 'title': '%s (%d)' % (video_title, num),
3404 })
3405 for entry in entries:
3406 self._sort_formats(entry['formats'])
3407 return self.playlist_result(entries, video_id, video_title)
3408
3409 jwplayer_data = self._find_jwplayer_data(
3410 webpage, video_id, transform_source=js_to_json)
3411 if jwplayer_data:
3412 try:
3413 info = self._parse_jwplayer_data(
3414 jwplayer_data, video_id, require_title=False, base_url=url)
3415 return merge_dicts(info, info_dict)
3416 except ExtractorError:
3417 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3418 pass
3419
3420 # Video.js embed
3421 mobj = re.search(
3422 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3423 webpage)
3424 if mobj is not None:
3425 sources = self._parse_json(
3426 mobj.group(1), video_id, transform_source=js_to_json,
3427 fatal=False) or []
3428 if not isinstance(sources, list):
3429 sources = [sources]
3430 formats = []
3431 for source in sources:
3432 src = source.get('src')
3433 if not src or not isinstance(src, compat_str):
3434 continue
3435 src = compat_urlparse.urljoin(url, src)
3436 src_type = source.get('type')
3437 if isinstance(src_type, compat_str):
3438 src_type = src_type.lower()
3439 ext = determine_ext(src).lower()
3440 if src_type == 'video/youtube':
3441 return self.url_result(src, YoutubeIE.ie_key())
3442 if src_type == 'application/dash+xml' or ext == 'mpd':
3443 formats.extend(self._extract_mpd_formats(
3444 src, video_id, mpd_id='dash', fatal=False))
3445 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3446 formats.extend(self._extract_m3u8_formats(
3447 src, video_id, 'mp4', entry_protocol='m3u8_native',
3448 m3u8_id='hls', fatal=False))
3449 else:
3450 formats.append({
3451 'url': src,
3452 'ext': (mimetype2ext(src_type)
3453 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3454 })
3455 if formats:
3456 self._sort_formats(formats)
3457 info_dict['formats'] = formats
3458 return info_dict
3459
3460 # Looking for http://schema.org/VideoObject
3461 json_ld = self._search_json_ld(
3462 webpage, video_id, default={}, expected_type='VideoObject')
3463 if json_ld.get('url'):
3464 return merge_dicts(json_ld, info_dict)
3465
3466 def check_video(vurl):
3467 if YoutubeIE.suitable(vurl):
3468 return True
3469 if RtmpIE.suitable(vurl):
3470 return True
3471 vpath = compat_urlparse.urlparse(vurl).path
3472 vext = determine_ext(vpath)
3473 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3474
3475 def filter_video(urls):
3476 return list(filter(check_video, urls))
3477
3478 # Start with something easy: JW Player in SWFObject
3479 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3480 if not found:
3481 # Look for gorilla-vid style embedding
3482 found = filter_video(re.findall(r'''(?sx)
3483 (?:
3484 jw_plugins|
3485 JWPlayerOptions|
3486 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3487 )
3488 .*?
3489 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3490 if not found:
3491 # Broaden the search a little bit
3492 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3493 if not found:
3494 # Broaden the findall a little bit: JWPlayer JS loader
3495 found = filter_video(re.findall(
3496 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3497 if not found:
3498 # Flow player
3499 found = filter_video(re.findall(r'''(?xs)
3500 flowplayer\("[^"]+",\s*
3501 \{[^}]+?\}\s*,
3502 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3503 ["']?url["']?\s*:\s*["']([^"']+)["']
3504 ''', webpage))
3505 if not found:
3506 # Cinerama player
3507 found = re.findall(
3508 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3509 if not found:
3510 # Try to find twitter cards info
3511 # twitter:player:stream should be checked before twitter:player since
3512 # it is expected to contain a raw stream (see
3513 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3514 found = filter_video(re.findall(
3515 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3516 if not found:
3517 # We look for Open Graph info:
3518 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3519 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3520 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3521 if m_video_type is not None:
3522 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3523 if not found:
3524 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3525 found = re.search(
3526 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3527 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3528 webpage)
3529 if not found:
3530 # Look also in Refresh HTTP header
3531 refresh_header = head_response.headers.get('Refresh')
3532 if refresh_header:
3533 # In python 2 response HTTP headers are bytestrings
3534 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3535 refresh_header = refresh_header.decode('iso-8859-1')
3536 found = re.search(REDIRECT_REGEX, refresh_header)
3537 if found:
3538 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3539 if new_url != url:
3540 self.report_following_redirect(new_url)
3541 return {
3542 '_type': 'url',
3543 'url': new_url,
3544 }
3545 else:
3546 found = None
3547
3548 if not found:
3549 # twitter:player is a https URL to iframe player that may or may not
3550 # be supported by yt-dlp thus this is checked the very last (see
3551 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3552 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3553 if embed_url and embed_url != url:
3554 return self.url_result(embed_url)
3555
3556 if not found:
3557 raise UnsupportedError(url)
3558
3559 entries = []
3560 for video_url in orderedSet(found):
3561 video_url = unescapeHTML(video_url)
3562 video_url = video_url.replace('\\/', '/')
3563 video_url = compat_urlparse.urljoin(url, video_url)
3564 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3565
3566 # Sometimes, jwplayer extraction will result in a YouTube URL
3567 if YoutubeIE.suitable(video_url):
3568 entries.append(self.url_result(video_url, 'Youtube'))
3569 continue
3570
3571 # here's a fun little line of code for you:
3572 video_id = os.path.splitext(video_id)[0]
3573
3574 entry_info_dict = {
3575 'id': video_id,
3576 'uploader': video_uploader,
3577 'title': video_title,
3578 'age_limit': age_limit,
3579 }
3580
3581 if RtmpIE.suitable(video_url):
3582 entry_info_dict.update({
3583 '_type': 'url_transparent',
3584 'ie_key': RtmpIE.ie_key(),
3585 'url': video_url,
3586 })
3587 entries.append(entry_info_dict)
3588 continue
3589
3590 ext = determine_ext(video_url)
3591 if ext == 'smil':
3592 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3593 elif ext == 'xspf':
3594 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3595 elif ext == 'm3u8':
3596 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3597 elif ext == 'mpd':
3598 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3599 elif ext == 'f4m':
3600 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3601 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3602 # Just matching .ism/manifest is not enough to be reliably sure
3603 # whether it's actually an ISM manifest or some other streaming
3604 # manifest since there are various streaming URL formats
3605 # possible (see [1]) as well as some other shenanigans like
3606 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3607 # so on.
3608 # Thus the most reasonable way to solve this is to delegate
3609 # to generic extractor in order to look into the contents of
3610 # the manifest itself.
3611 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3612 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3613 entry_info_dict = self.url_result(
3614 smuggle_url(video_url, {'to_generic': True}),
3615 GenericIE.ie_key())
3616 else:
3617 entry_info_dict['url'] = video_url
3618
3619 if entry_info_dict.get('formats'):
3620 self._sort_formats(entry_info_dict['formats'])
3621
3622 entries.append(entry_info_dict)
3623
3624 if len(entries) == 1:
3625 return entries[0]
3626 else:
3627 for num, e in enumerate(entries, start=1):
3628 # 'url' results don't have a title
3629 if e.get('title') is not None:
3630 e['title'] = '%s (%d)' % (e['title'], num)
3631 return {
3632 '_type': 'playlist',
3633 'entries': entries,
3634 }