]> jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/generic.py
Update to ytdl-commit-cf2dbec
[yt-dlp.git] / youtube_dlc / 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 .gedi import GediEmbedsIE
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
138
139 class GenericIE(InfoExtractor):
140 IE_DESC = 'Generic downloader that works on some sites'
141 _VALID_URL = r'.*'
142 IE_NAME = 'generic'
143 _TESTS = [
144 # Direct link to a video
145 {
146 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
147 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
148 'info_dict': {
149 'id': 'trailer',
150 'ext': 'mp4',
151 'title': 'trailer',
152 'upload_date': '20100513',
153 }
154 },
155 # Direct link to media delivered compressed (until Accept-Encoding is *)
156 {
157 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
158 'md5': '128c42e68b13950268b648275386fc74',
159 'info_dict': {
160 'id': 'FictionJunction-Parallel_Hearts',
161 'ext': 'flac',
162 'title': 'FictionJunction-Parallel_Hearts',
163 'upload_date': '20140522',
164 },
165 'expected_warnings': [
166 'URL could be a direct video link, returning it as such.'
167 ],
168 'skip': 'URL invalid',
169 },
170 # Direct download with broken HEAD
171 {
172 'url': 'http://ai-radio.org:8000/radio.opus',
173 'info_dict': {
174 'id': 'radio',
175 'ext': 'opus',
176 'title': 'radio',
177 },
178 'params': {
179 'skip_download': True, # infinite live stream
180 },
181 'expected_warnings': [
182 r'501.*Not Implemented',
183 r'400.*Bad Request',
184 ],
185 },
186 # Direct link with incorrect MIME type
187 {
188 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
189 'md5': '4ccbebe5f36706d85221f204d7eb5913',
190 'info_dict': {
191 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
192 'id': '5_Lennart_Poettering_-_Systemd',
193 'ext': 'webm',
194 'title': '5_Lennart_Poettering_-_Systemd',
195 'upload_date': '20141120',
196 },
197 'expected_warnings': [
198 'URL could be a direct video link, returning it as such.'
199 ]
200 },
201 # RSS feed
202 {
203 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
204 'info_dict': {
205 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
206 'title': 'Zero Punctuation',
207 'description': 're:.*groundbreaking video review series.*'
208 },
209 'playlist_mincount': 11,
210 },
211 # RSS feed with enclosure
212 {
213 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
214 'info_dict': {
215 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
216 'title': 'MSNBC Rachel Maddow (video)',
217 'description': 're:.*her unique approach to storytelling.*',
218 },
219 'playlist': [{
220 'info_dict': {
221 'ext': 'mov',
222 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
223 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
224 'description': 're:.*her unique approach to storytelling.*',
225 'upload_date': '20201204',
226 },
227 }],
228 },
229 # RSS feed with item with description and thumbnails
230 {
231 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
232 'info_dict': {
233 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
234 'title': 're:.*100% Hydrogen.*',
235 'description': 're:.*In this episode.*',
236 },
237 'playlist': [{
238 'info_dict': {
239 'ext': 'm4a',
240 'id': 'c1c879525ce2cb640b344507e682c36d',
241 'title': 're:Hydrogen!',
242 'description': 're:.*In this episode we are going.*',
243 'timestamp': 1567977776,
244 'upload_date': '20190908',
245 'duration': 459,
246 'thumbnail': r're:^https?://.*\.jpg$',
247 'episode_number': 1,
248 'season_number': 1,
249 'age_limit': 0,
250 },
251 }],
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # RSS feed with enclosures and unsupported link URLs
257 {
258 'url': 'http://www.hellointernet.fm/podcast?format=rss',
259 'info_dict': {
260 'id': 'http://www.hellointernet.fm/podcast?format=rss',
261 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
262 'title': 'Hello Internet',
263 },
264 'playlist_mincount': 100,
265 },
266 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
267 {
268 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
269 'info_dict': {
270 'id': 'smil',
271 'ext': 'mp4',
272 'title': 'Automatics, robotics and biocybernetics',
273 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
274 'upload_date': '20130627',
275 'formats': 'mincount:16',
276 'subtitles': 'mincount:1',
277 },
278 'params': {
279 'force_generic_extractor': True,
280 'skip_download': True,
281 },
282 },
283 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
284 {
285 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
286 'info_dict': {
287 'id': 'hds',
288 'ext': 'flv',
289 'title': 'hds',
290 'formats': 'mincount:1',
291 },
292 'params': {
293 'skip_download': True,
294 },
295 },
296 # SMIL from https://www.restudy.dk/video/play/id/1637
297 {
298 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
299 'info_dict': {
300 'id': 'video_1637',
301 'ext': 'flv',
302 'title': 'video_1637',
303 'formats': 'mincount:3',
304 },
305 'params': {
306 'skip_download': True,
307 },
308 },
309 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
310 {
311 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
312 'info_dict': {
313 'id': 'smil-service',
314 'ext': 'flv',
315 'title': 'smil-service',
316 'formats': 'mincount:1',
317 },
318 'params': {
319 'skip_download': True,
320 },
321 },
322 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
323 {
324 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
325 'info_dict': {
326 'id': '4719370',
327 'ext': 'mp4',
328 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
329 'formats': 'mincount:3',
330 },
331 'params': {
332 'skip_download': True,
333 },
334 },
335 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
336 {
337 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
338 'info_dict': {
339 'id': 'mZlp2ctYIUEB',
340 'ext': 'mp4',
341 'title': 'Tikibad ontruimd wegens brand',
342 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
343 'thumbnail': r're:^https?://.*\.jpg$',
344 'duration': 33,
345 },
346 'params': {
347 'skip_download': True,
348 },
349 },
350 # MPD from http://dash-mse-test.appspot.com/media.html
351 {
352 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
353 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
354 'info_dict': {
355 'id': 'car-20120827-manifest',
356 'ext': 'mp4',
357 'title': 'car-20120827-manifest',
358 'formats': 'mincount:9',
359 'upload_date': '20130904',
360 },
361 'params': {
362 'format': 'bestvideo',
363 },
364 },
365 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
366 {
367 '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',
368 'info_dict': {
369 'id': 'content',
370 'ext': 'mp4',
371 'title': 'content',
372 'formats': 'mincount:8',
373 },
374 'params': {
375 # m3u8 downloads
376 'skip_download': True,
377 },
378 'skip': 'video gone',
379 },
380 # m3u8 served with Content-Type: text/plain
381 {
382 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
383 'info_dict': {
384 'id': 'index',
385 'ext': 'mp4',
386 'title': 'index',
387 'upload_date': '20140720',
388 'formats': 'mincount:11',
389 },
390 'params': {
391 # m3u8 downloads
392 'skip_download': True,
393 },
394 'skip': 'video gone',
395 },
396 # google redirect
397 {
398 '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',
399 'info_dict': {
400 'id': 'cmQHVoWB5FY',
401 'ext': 'mp4',
402 'upload_date': '20130224',
403 'uploader_id': 'TheVerge',
404 'description': r're:^Chris Ziegler takes a look at the\.*',
405 'uploader': 'The Verge',
406 'title': 'First Firefox OS phones side-by-side',
407 },
408 'params': {
409 'skip_download': False,
410 }
411 },
412 {
413 # redirect in Refresh HTTP header
414 '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',
415 'info_dict': {
416 'id': 'pO8h3EaFRdo',
417 'ext': 'mp4',
418 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
419 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
420 'upload_date': '20150917',
421 'uploader_id': 'brtvofficial',
422 'uploader': 'Boiler Room',
423 },
424 'params': {
425 'skip_download': False,
426 },
427 },
428 {
429 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
430 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
431 'info_dict': {
432 'id': '13601338388002',
433 'ext': 'mp4',
434 'uploader': 'www.hodiho.fr',
435 'title': 'R\u00e9gis plante sa Jeep',
436 }
437 },
438 # bandcamp page with custom domain
439 {
440 'add_ie': ['Bandcamp'],
441 'url': 'http://bronyrock.com/track/the-pony-mash',
442 'info_dict': {
443 'id': '3235767654',
444 'ext': 'mp3',
445 'title': 'The Pony Mash',
446 'uploader': 'M_Pallante',
447 },
448 'skip': 'There is a limit of 200 free downloads / month for the test song',
449 },
450 {
451 # embedded brightcove video
452 # it also tests brightcove videos that need to set the 'Referer'
453 # in the http requests
454 'add_ie': ['BrightcoveLegacy'],
455 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
456 'info_dict': {
457 'id': '2765128793001',
458 'ext': 'mp4',
459 'title': 'Le cours de bourse : l’analyse technique',
460 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
461 'uploader': 'BFM BUSINESS',
462 },
463 'params': {
464 'skip_download': True,
465 },
466 },
467 {
468 # embedded with itemprop embedURL and video id spelled as `idVideo`
469 'add_id': ['BrightcoveLegacy'],
470 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
471 'info_dict': {
472 'id': '5255628253001',
473 'ext': 'mp4',
474 'title': 'md5:37c519b1128915607601e75a87995fc0',
475 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
476 'uploader': 'BFM BUSINESS',
477 'uploader_id': '876450612001',
478 'timestamp': 1482255315,
479 'upload_date': '20161220',
480 },
481 'params': {
482 'skip_download': True,
483 },
484 },
485 {
486 # https://github.com/ytdl-org/youtube-dl/issues/2253
487 'url': 'http://bcove.me/i6nfkrc3',
488 'md5': '0ba9446db037002366bab3b3eb30c88c',
489 'info_dict': {
490 'id': '3101154703001',
491 'ext': 'mp4',
492 'title': 'Still no power',
493 'uploader': 'thestar.com',
494 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
495 },
496 'add_ie': ['BrightcoveLegacy'],
497 'skip': 'video gone',
498 },
499 {
500 'url': 'http://www.championat.com/video/football/v/87/87499.html',
501 'md5': 'fb973ecf6e4a78a67453647444222983',
502 'info_dict': {
503 'id': '3414141473001',
504 'ext': 'mp4',
505 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
506 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
507 'uploader': 'Championat',
508 },
509 },
510 {
511 # https://github.com/ytdl-org/youtube-dl/issues/3541
512 'add_ie': ['BrightcoveLegacy'],
513 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
514 'info_dict': {
515 'id': '3866516442001',
516 'ext': 'mp4',
517 'title': 'Leer mij vrouwen kennen: Aflevering 1',
518 'description': 'Leer mij vrouwen kennen: Aflevering 1',
519 'uploader': 'SBS Broadcasting',
520 },
521 'skip': 'Restricted to Netherlands',
522 'params': {
523 'skip_download': True, # m3u8 download
524 },
525 },
526 {
527 # Brightcove video in <iframe>
528 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
529 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
530 'info_dict': {
531 'id': '5360463607001',
532 'ext': 'mp4',
533 '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',
534 '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。',
535 'uploader': 'United Nations',
536 'uploader_id': '1362235914001',
537 'timestamp': 1489593889,
538 'upload_date': '20170315',
539 },
540 'add_ie': ['BrightcoveLegacy'],
541 },
542 {
543 # Brightcove with alternative playerID key
544 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
545 'info_dict': {
546 'id': 'nmeth.2062_SV1',
547 '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',
548 },
549 'playlist': [{
550 'info_dict': {
551 'id': '2228375078001',
552 'ext': 'mp4',
553 'title': 'nmeth.2062-sv1',
554 'description': 'nmeth.2062-sv1',
555 'timestamp': 1363357591,
556 'upload_date': '20130315',
557 'uploader': 'Nature Publishing Group',
558 'uploader_id': '1964492299001',
559 },
560 }],
561 },
562 {
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'info_dict': {
566 'id': '5255815316001',
567 'ext': 'mp4',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
574 },
575 'params': {
576 'skip_download': True, # m3u8 download
577 },
578 'skip': 'video rotates...weekly?',
579 },
580 {
581 # Brightcove:new type [2].
582 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
583 'md5': '2b35148fcf48da41c9fb4591650784f3',
584 'info_dict': {
585 'id': '5348741021001',
586 'ext': 'mp4',
587 'upload_date': '20170306',
588 'uploader_id': '4191638492001',
589 'timestamp': 1488769918,
590 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
591
592 },
593 },
594 {
595 # Alternative brightcove <video> attributes
596 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
597 'info_dict': {
598 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
599 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
600 },
601 'playlist': [{
602 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
603 'info_dict': {
604 'id': '5311302538001',
605 'ext': 'mp4',
606 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
607 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
608 'timestamp': 1486321708,
609 'upload_date': '20170205',
610 'uploader_id': '800000640001',
611 },
612 'only_matching': True,
613 }],
614 },
615 {
616 # Brightcove with UUID in videoPlayer
617 'url': 'http://www8.hp.com/cn/zh/home.html',
618 'info_dict': {
619 'id': '5255815316001',
620 'ext': 'mp4',
621 'title': 'Sprocket Video - China',
622 'description': 'Sprocket Video - China',
623 'uploader': 'HP-Video Gallery',
624 'timestamp': 1482263210,
625 'upload_date': '20161220',
626 'uploader_id': '1107601872001',
627 },
628 'params': {
629 'skip_download': True, # m3u8 download
630 },
631 },
632 # ooyala video
633 {
634 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
635 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
636 'info_dict': {
637 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
638 'ext': 'mp4',
639 'title': '2cc213299525360.mov', # that's what we get
640 'duration': 238.231,
641 },
642 'add_ie': ['Ooyala'],
643 },
644 {
645 # ooyala video embedded with http://player.ooyala.com/iframe.js
646 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
647 'info_dict': {
648 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
649 'ext': 'mp4',
650 'title': '"Steve Jobs: Man in the Machine" trailer',
651 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
652 'duration': 135.427,
653 },
654 'params': {
655 'skip_download': True,
656 },
657 'skip': 'movie expired',
658 },
659 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
660 {
661 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
662 'info_dict': {
663 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
664 'ext': 'mp4',
665 'title': 'Steampunk Fest Comes to Honesdale',
666 'duration': 43.276,
667 },
668 'params': {
669 'skip_download': True,
670 }
671 },
672 # embed.ly video
673 {
674 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
675 'info_dict': {
676 'id': '9ODmcdjQcHQ',
677 'ext': 'mp4',
678 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
679 'upload_date': '20140225',
680 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
681 'uploader': 'Tested',
682 'uploader_id': 'testedcom',
683 },
684 # No need to test YoutubeIE here
685 'params': {
686 'skip_download': True,
687 },
688 },
689 # funnyordie embed
690 {
691 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
692 'info_dict': {
693 'id': '18e820ec3f',
694 'ext': 'mp4',
695 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
696 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
697 },
698 # HEAD requests lead to endless 301, while GET is OK
699 'expected_warnings': ['301'],
700 },
701 # RUTV embed
702 {
703 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
704 'info_dict': {
705 'id': '776940',
706 'ext': 'mp4',
707 'title': 'Охотское море стало целиком российским',
708 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
709 },
710 'params': {
711 # m3u8 download
712 'skip_download': True,
713 },
714 },
715 # TVC embed
716 {
717 '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/',
718 'info_dict': {
719 'id': '55304',
720 'ext': 'mp4',
721 'title': 'Дошкольное воспитание',
722 },
723 },
724 # SportBox embed
725 {
726 'url': 'http://www.vestifinance.ru/articles/25753',
727 'info_dict': {
728 'id': '25753',
729 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
730 },
731 'playlist': [{
732 'info_dict': {
733 'id': '370908',
734 'title': 'Госзаказ. День 3',
735 'ext': 'mp4',
736 }
737 }, {
738 'info_dict': {
739 'id': '370905',
740 'title': 'Госзаказ. День 2',
741 'ext': 'mp4',
742 }
743 }, {
744 'info_dict': {
745 'id': '370902',
746 'title': 'Госзаказ. День 1',
747 'ext': 'mp4',
748 }
749 }],
750 'params': {
751 # m3u8 download
752 'skip_download': True,
753 },
754 },
755 # Myvi.ru embed
756 {
757 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
758 'info_dict': {
759 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
760 'ext': 'mp4',
761 'title': 'Ужастики, русский трейлер (2015)',
762 'thumbnail': r're:^https?://.*\.jpg$',
763 'duration': 153,
764 }
765 },
766 # XHamster embed
767 {
768 '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',
769 'info_dict': {
770 'id': 'showthread',
771 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
772 },
773 'playlist_mincount': 7,
774 # This forum does not allow <iframe> syntaxes anymore
775 # Now HTML tags are displayed as-is
776 'skip': 'No videos on this page',
777 },
778 # Embedded TED video
779 {
780 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
781 'md5': '65fdff94098e4a607385a60c5177c638',
782 'info_dict': {
783 'id': '1969',
784 'ext': 'mp4',
785 'title': 'Hidden miracles of the natural world',
786 'uploader': 'Louie Schwartzberg',
787 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
788 }
789 },
790 # nowvideo embed hidden behind percent encoding
791 {
792 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
793 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
794 'info_dict': {
795 'id': '06e53103ca9aa',
796 'ext': 'flv',
797 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
798 'description': 'No description',
799 },
800 },
801 # arte embed
802 {
803 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
804 'md5': '7653032cbb25bf6c80d80f217055fa43',
805 'info_dict': {
806 'id': '048195-004_PLUS7-F',
807 'ext': 'flv',
808 'title': 'X:enius',
809 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
810 'upload_date': '20140320',
811 },
812 'params': {
813 'skip_download': 'Requires rtmpdump'
814 },
815 'skip': 'video gone',
816 },
817 # francetv embed
818 {
819 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
820 'info_dict': {
821 'id': 'EV_30231',
822 'ext': 'mp4',
823 'title': 'Alcaline, le concert avec Calogero',
824 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
825 'upload_date': '20150226',
826 'timestamp': 1424989860,
827 'duration': 5400,
828 },
829 'params': {
830 # m3u8 downloads
831 'skip_download': True,
832 },
833 'expected_warnings': [
834 'Forbidden'
835 ]
836 },
837 # Condé Nast embed
838 {
839 'url': 'http://www.wired.com/2014/04/honda-asimo/',
840 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
841 'info_dict': {
842 'id': '53501be369702d3275860000',
843 'ext': 'mp4',
844 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
845 }
846 },
847 # Dailymotion embed
848 {
849 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
850 'md5': '441aeeb82eb72c422c7f14ec533999cd',
851 'info_dict': {
852 'id': 'k2mm4bCdJ6CQ2i7c8o2',
853 'ext': 'mp4',
854 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
855 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
856 'uploader': 'Spi0n',
857 'uploader_id': 'xgditw',
858 'upload_date': '20140425',
859 'timestamp': 1398441542,
860 },
861 'add_ie': ['Dailymotion'],
862 },
863 # DailyMail embed
864 {
865 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
866 'info_dict': {
867 'id': '1495629',
868 'ext': 'mp4',
869 'title': 'Care worker punches elderly dementia patient in head 11 times',
870 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
871 },
872 'add_ie': ['DailyMail'],
873 'params': {
874 'skip_download': True,
875 },
876 },
877 # YouTube embed
878 {
879 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
880 'info_dict': {
881 'id': 'FXRb4ykk4S0',
882 'ext': 'mp4',
883 'title': 'The NBL Auction 2014',
884 'uploader': 'BADMINTON England',
885 'uploader_id': 'BADMINTONEvents',
886 'upload_date': '20140603',
887 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
888 },
889 'add_ie': ['Youtube'],
890 'params': {
891 'skip_download': True,
892 }
893 },
894 # MTVServices embed
895 {
896 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
897 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
898 'info_dict': {
899 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
900 'ext': 'mp4',
901 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
902 'description': 'Two valets share their love for movie star Liam Neesons.',
903 'timestamp': 1349922600,
904 'upload_date': '20121011',
905 },
906 },
907 # YouTube embed via <data-embed-url="">
908 {
909 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
910 'info_dict': {
911 'id': '4vAffPZIT44',
912 'ext': 'mp4',
913 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
914 'uploader': 'Gameloft',
915 'uploader_id': 'gameloft',
916 'upload_date': '20140828',
917 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
918 },
919 'params': {
920 'skip_download': True,
921 }
922 },
923 # YouTube <object> embed
924 {
925 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
926 'md5': '516718101ec834f74318df76259fb3cc',
927 'info_dict': {
928 'id': 'msN87y-iEx0',
929 'ext': 'webm',
930 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
931 'upload_date': '20080526',
932 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
933 'uploader': 'Christopher Sykes',
934 'uploader_id': 'ChristopherJSykes',
935 },
936 'add_ie': ['Youtube'],
937 },
938 # Camtasia studio
939 {
940 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
941 'playlist': [{
942 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
943 'info_dict': {
944 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
945 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
946 'ext': 'flv',
947 'duration': 2235.90,
948 }
949 }, {
950 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
951 'info_dict': {
952 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
953 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
954 'ext': 'flv',
955 'duration': 2235.93,
956 }
957 }],
958 'info_dict': {
959 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
960 }
961 },
962 # Flowplayer
963 {
964 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
965 'md5': '9d65602bf31c6e20014319c7d07fba27',
966 'info_dict': {
967 'id': '5123ea6d5e5a7',
968 'ext': 'mp4',
969 'age_limit': 18,
970 'uploader': 'www.handjobhub.com',
971 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
972 }
973 },
974 # Multiple brightcove videos
975 # https://github.com/ytdl-org/youtube-dl/issues/2283
976 {
977 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
978 'info_dict': {
979 'id': 'always-never',
980 'title': 'Always / Never - The New Yorker',
981 },
982 'playlist_count': 3,
983 'params': {
984 'extract_flat': False,
985 'skip_download': True,
986 }
987 },
988 # MLB embed
989 {
990 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
991 'md5': '96f09a37e44da40dd083e12d9a683327',
992 'info_dict': {
993 'id': '33322633',
994 'ext': 'mp4',
995 'title': 'Ump changes call to ball',
996 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
997 'duration': 48,
998 'timestamp': 1401537900,
999 'upload_date': '20140531',
1000 'thumbnail': r're:^https?://.*\.jpg$',
1001 },
1002 },
1003 # Wistia embed
1004 {
1005 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1006 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1007 'info_dict': {
1008 'id': '6e2wtrbdaf',
1009 'ext': 'mov',
1010 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1011 'description': 'a Paywall Videos video from Remilon',
1012 'duration': 644.072,
1013 'uploader': 'study.com',
1014 'timestamp': 1459678540,
1015 'upload_date': '20160403',
1016 'filesize': 24687186,
1017 },
1018 },
1019 {
1020 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1021 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1022 'info_dict': {
1023 'id': 'uxjb0lwrcz',
1024 'ext': 'mp4',
1025 'title': 'Conversation about Hexagonal Rails Part 1',
1026 'description': 'a Martin Fowler video from ThoughtWorks',
1027 'duration': 1715.0,
1028 'uploader': 'thoughtworks.wistia.com',
1029 'timestamp': 1401832161,
1030 'upload_date': '20140603',
1031 },
1032 },
1033 # Wistia standard embed (async)
1034 {
1035 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1036 'info_dict': {
1037 'id': '807fafadvk',
1038 'ext': 'mp4',
1039 'title': 'Drip Brennan Dunn Workshop',
1040 'description': 'a JV Webinars video from getdrip-1',
1041 'duration': 4986.95,
1042 'timestamp': 1463607249,
1043 'upload_date': '20160518',
1044 },
1045 'params': {
1046 'skip_download': True,
1047 }
1048 },
1049 # Soundcloud embed
1050 {
1051 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1052 'info_dict': {
1053 'id': '174391317',
1054 'ext': 'mp3',
1055 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1056 'uploader': 'Sophos Security',
1057 'title': 'Chet Chat 171 - Oct 29, 2014',
1058 'upload_date': '20141029',
1059 }
1060 },
1061 # Soundcloud multiple embeds
1062 {
1063 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1064 'info_dict': {
1065 'id': '52809',
1066 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1067 },
1068 'playlist_mincount': 7,
1069 },
1070 # TuneIn station embed
1071 {
1072 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1073 'info_dict': {
1074 'id': '204146',
1075 'ext': 'mp3',
1076 'title': 'CNRV',
1077 'location': 'Paris, France',
1078 'is_live': True,
1079 },
1080 'params': {
1081 # Live stream
1082 'skip_download': True,
1083 },
1084 },
1085 # Livestream embed
1086 {
1087 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1088 'info_dict': {
1089 'id': '67864563',
1090 'ext': 'flv',
1091 'upload_date': '20141112',
1092 'title': 'Rosetta #CometLanding webcast HL 10',
1093 }
1094 },
1095 # Another Livestream embed, without 'new.' in URL
1096 {
1097 'url': 'https://www.freespeech.org/',
1098 'info_dict': {
1099 'id': '123537347',
1100 'ext': 'mp4',
1101 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1102 },
1103 'params': {
1104 # Live stream
1105 'skip_download': True,
1106 },
1107 },
1108 # LazyYT
1109 {
1110 'url': 'https://skiplagged.com/',
1111 'info_dict': {
1112 'id': 'skiplagged',
1113 'title': 'Skiplagged: The smart way to find cheap flights',
1114 },
1115 'playlist_mincount': 1,
1116 'add_ie': ['Youtube'],
1117 },
1118 # Cinchcast embed
1119 {
1120 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1121 'info_dict': {
1122 'id': '7141703',
1123 'ext': 'mp3',
1124 'upload_date': '20141126',
1125 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1126 }
1127 },
1128 # Cinerama player
1129 {
1130 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1131 'info_dict': {
1132 'id': '730m_DandD_1901_512k',
1133 'ext': 'mp4',
1134 'uploader': 'www.abc.net.au',
1135 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1136 }
1137 },
1138 # embedded viddler video
1139 {
1140 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1141 'info_dict': {
1142 'id': '4d03aad9',
1143 'ext': 'mp4',
1144 'uploader': 'deadspin',
1145 'title': 'WALL-TO-GORTAT',
1146 'timestamp': 1422285291,
1147 'upload_date': '20150126',
1148 },
1149 'add_ie': ['Viddler'],
1150 },
1151 # Libsyn embed
1152 {
1153 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1154 'info_dict': {
1155 'id': '3377616',
1156 'ext': 'mp3',
1157 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1158 'description': 'md5:601cb790edd05908957dae8aaa866465',
1159 'upload_date': '20150220',
1160 },
1161 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1162 },
1163 # jwplayer YouTube
1164 {
1165 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1166 'info_dict': {
1167 'id': 'Mrj4DVp2zeA',
1168 'ext': 'mp4',
1169 'upload_date': '20150212',
1170 'uploader': 'The National Archives UK',
1171 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1172 'uploader_id': 'NationalArchives08',
1173 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1174 },
1175 },
1176 # jwplayer rtmp
1177 {
1178 'url': 'http://www.suffolk.edu/sjc/live.php',
1179 'info_dict': {
1180 'id': 'live',
1181 'ext': 'flv',
1182 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1183 'uploader': 'www.suffolk.edu',
1184 },
1185 'params': {
1186 'skip_download': True,
1187 },
1188 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1189 },
1190 # Complex jwplayer
1191 {
1192 'url': 'http://www.indiedb.com/games/king-machine/videos',
1193 'info_dict': {
1194 'id': 'videos',
1195 'ext': 'mp4',
1196 'title': 'king machine trailer 1',
1197 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1198 'thumbnail': r're:^https?://.*\.jpg$',
1199 },
1200 },
1201 {
1202 # JWPlayer config passed as variable
1203 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1204 'info_dict': {
1205 'id': '3326530_hq',
1206 'ext': 'mp4',
1207 'title': 'ARIELE | Tube Cup',
1208 'uploader': 'www.txxx.com',
1209 'age_limit': 18,
1210 },
1211 'params': {
1212 'skip_download': True,
1213 }
1214 },
1215 {
1216 # JWPlatform iframe
1217 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1218 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1219 'info_dict': {
1220 'id': 'O0c5JcKT',
1221 'ext': 'mp4',
1222 'upload_date': '20171122',
1223 'timestamp': 1511366290,
1224 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1225 },
1226 'add_ie': [JWPlatformIE.ie_key()],
1227 },
1228 {
1229 # Video.js embed, multiple formats
1230 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1231 'info_dict': {
1232 'id': 'yygqldloqIk',
1233 'ext': 'mp4',
1234 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1235 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1236 'upload_date': '20130314',
1237 'uploader': 'PROстое3D',
1238 'uploader_id': 'PROstoe3D',
1239 },
1240 'params': {
1241 'skip_download': True,
1242 },
1243 },
1244 {
1245 # Video.js embed, single format
1246 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1247 'info_dict': {
1248 'id': 'watch',
1249 'ext': 'mp4',
1250 'title': 'Step 1 - Good Foundation',
1251 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1252 },
1253 'params': {
1254 'skip_download': True,
1255 },
1256 },
1257 # rtl.nl embed
1258 {
1259 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1260 'playlist_mincount': 5,
1261 'info_dict': {
1262 'id': 'aanslagen-kopenhagen',
1263 'title': 'Aanslagen Kopenhagen',
1264 }
1265 },
1266 # Zapiks embed
1267 {
1268 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1269 'info_dict': {
1270 'id': '118046',
1271 'ext': 'mp4',
1272 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1273 }
1274 },
1275 # Kaltura embed (different embed code)
1276 {
1277 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1278 'info_dict': {
1279 'id': '1_a52wc67y',
1280 'ext': 'flv',
1281 'upload_date': '20150127',
1282 'uploader_id': 'PremierMedia',
1283 'timestamp': int,
1284 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1285 },
1286 },
1287 # Kaltura embed with single quotes
1288 {
1289 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1290 'info_dict': {
1291 'id': '0_izeg5utt',
1292 'ext': 'mp4',
1293 'title': '35871',
1294 'timestamp': 1355743100,
1295 'upload_date': '20121217',
1296 'uploader_id': 'cplapp@learn360.com',
1297 },
1298 'add_ie': ['Kaltura'],
1299 },
1300 {
1301 # Kaltura embedded via quoted entry_id
1302 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1303 'info_dict': {
1304 'id': '0_utuok90b',
1305 'ext': 'mp4',
1306 'title': '06_matthew_brender_raj_dutt',
1307 'timestamp': 1466638791,
1308 'upload_date': '20160622',
1309 },
1310 'add_ie': ['Kaltura'],
1311 'expected_warnings': [
1312 'Could not send HEAD request'
1313 ],
1314 'params': {
1315 'skip_download': True,
1316 }
1317 },
1318 {
1319 # Kaltura embedded, some fileExt broken (#11480)
1320 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1321 'info_dict': {
1322 'id': '1_sgtvehim',
1323 'ext': 'mp4',
1324 'title': 'Our "Standard Models" of particle physics and cosmology',
1325 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1326 'timestamp': 1321158993,
1327 'upload_date': '20111113',
1328 'uploader_id': 'kps1',
1329 },
1330 'add_ie': ['Kaltura'],
1331 },
1332 {
1333 # Kaltura iframe embed
1334 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1335 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1336 'info_dict': {
1337 'id': '0_f2cfbpwy',
1338 'ext': 'mp4',
1339 'title': 'I. M. Pei: A Centennial Celebration',
1340 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1341 'upload_date': '20170403',
1342 'uploader_id': 'batchUser',
1343 'timestamp': 1491232186,
1344 },
1345 'add_ie': ['Kaltura'],
1346 },
1347 {
1348 # Kaltura iframe embed, more sophisticated
1349 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1350 'info_dict': {
1351 'id': '1_9gzouybz',
1352 'ext': 'mp4',
1353 'title': 'lecture-05sep2017',
1354 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1355 'upload_date': '20170913',
1356 'uploader_id': 'eps2',
1357 'timestamp': 1505340777,
1358 },
1359 'params': {
1360 'skip_download': True,
1361 },
1362 'add_ie': ['Kaltura'],
1363 },
1364 {
1365 # meta twitter:player
1366 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1367 'info_dict': {
1368 'id': '0_01b42zps',
1369 'ext': 'mp4',
1370 'title': 'Main Twerk (Video)',
1371 'upload_date': '20171208',
1372 'uploader_id': 'sebastian.salinas@thechive.com',
1373 'timestamp': 1512713057,
1374 },
1375 'params': {
1376 'skip_download': True,
1377 },
1378 'add_ie': ['Kaltura'],
1379 },
1380 # referrer protected EaglePlatform embed
1381 {
1382 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1383 'info_dict': {
1384 'id': '582306',
1385 'ext': 'mp4',
1386 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1387 'thumbnail': r're:^https?://.*\.jpg$',
1388 'duration': 3382,
1389 'view_count': int,
1390 },
1391 'params': {
1392 'skip_download': True,
1393 },
1394 },
1395 # ClipYou (EaglePlatform) embed (custom URL)
1396 {
1397 'url': 'http://muz-tv.ru/play/7129/',
1398 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1399 'info_dict': {
1400 'id': '12820',
1401 'ext': 'mp4',
1402 'title': "'O Sole Mio",
1403 'thumbnail': r're:^https?://.*\.jpg$',
1404 'duration': 216,
1405 'view_count': int,
1406 },
1407 'params': {
1408 'skip_download': True,
1409 },
1410 'skip': 'This video is unavailable.',
1411 },
1412 # Pladform embed
1413 {
1414 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1415 'info_dict': {
1416 'id': '100183293',
1417 'ext': 'mp4',
1418 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1419 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1420 'thumbnail': r're:^https?://.*\.jpg$',
1421 'duration': 694,
1422 'age_limit': 0,
1423 },
1424 'skip': 'HTTP Error 404: Not Found',
1425 },
1426 # Playwire embed
1427 {
1428 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1429 'info_dict': {
1430 'id': '3519514',
1431 'ext': 'mp4',
1432 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1433 'thumbnail': r're:^https?://.*\.png$',
1434 'duration': 45.115,
1435 },
1436 },
1437 # 5min embed
1438 {
1439 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1440 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1441 'info_dict': {
1442 'id': '518726732',
1443 'ext': 'mp4',
1444 'title': 'Facebook Creates "On This Day" | Crunch Report',
1445 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1446 'timestamp': 1427237531,
1447 'uploader': 'Crunch Report',
1448 'upload_date': '20150324',
1449 },
1450 'params': {
1451 # m3u8 download
1452 'skip_download': True,
1453 },
1454 },
1455 # Crooks and Liars embed
1456 {
1457 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1458 'info_dict': {
1459 'id': '8RUoRhRi',
1460 'ext': 'mp4',
1461 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1462 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1463 'timestamp': 1428207000,
1464 'upload_date': '20150405',
1465 'uploader': 'Heather',
1466 },
1467 },
1468 # Crooks and Liars external embed
1469 {
1470 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1471 'info_dict': {
1472 'id': 'MTE3MjUtMzQ2MzA',
1473 'ext': 'mp4',
1474 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1475 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1476 'timestamp': 1265032391,
1477 'upload_date': '20100201',
1478 'uploader': 'Heather',
1479 },
1480 },
1481 # NBC Sports vplayer embed
1482 {
1483 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1484 'info_dict': {
1485 'id': 'ln7x1qSThw4k',
1486 'ext': 'flv',
1487 'title': "PFT Live: New leader in the 'new-look' defense",
1488 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1489 'uploader': 'NBCU-SPORTS',
1490 'upload_date': '20140107',
1491 'timestamp': 1389118457,
1492 },
1493 'skip': 'Invalid Page URL',
1494 },
1495 # NBC News embed
1496 {
1497 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1498 'md5': '1aa589c675898ae6d37a17913cf68d66',
1499 'info_dict': {
1500 'id': 'x_dtl_oa_LettermanliftPR_160608',
1501 'ext': 'mp4',
1502 'title': 'David Letterman: A Preview',
1503 '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.',
1504 'upload_date': '20160609',
1505 'timestamp': 1465431544,
1506 'uploader': 'NBCU-NEWS',
1507 },
1508 },
1509 # UDN embed
1510 {
1511 'url': 'https://video.udn.com/news/300346',
1512 'md5': 'fd2060e988c326991037b9aff9df21a6',
1513 'info_dict': {
1514 'id': '300346',
1515 'ext': 'mp4',
1516 'title': '中一中男師變性 全校師生力挺',
1517 'thumbnail': r're:^https?://.*\.jpg$',
1518 },
1519 'params': {
1520 # m3u8 download
1521 'skip_download': True,
1522 },
1523 'expected_warnings': ['Failed to parse JSON Expecting value'],
1524 },
1525 # Brightcove URL in single quotes
1526 {
1527 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1528 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1529 'info_dict': {
1530 'id': '4255764656001',
1531 'ext': 'mp4',
1532 'title': 'SN Presents: Russell Martin, World Citizen',
1533 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1534 'uploader': 'Rogers Sportsnet',
1535 'uploader_id': '1704050871',
1536 'upload_date': '20150525',
1537 'timestamp': 1432570283,
1538 },
1539 },
1540 # Kinja embed
1541 {
1542 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1543 'info_dict': {
1544 'id': '106351',
1545 'ext': 'mp4',
1546 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1547 'description': 'Migrated from OnionStudios',
1548 'thumbnail': r're:^https?://.*\.jpe?g$',
1549 'uploader': 'clickhole',
1550 'upload_date': '20150527',
1551 'timestamp': 1432744860,
1552 }
1553 },
1554 # SnagFilms embed
1555 {
1556 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1557 'info_dict': {
1558 'id': '74849a00-85a9-11e1-9660-123139220831',
1559 'ext': 'mp4',
1560 'title': '#whilewewatch',
1561 }
1562 },
1563 # AdobeTVVideo embed
1564 {
1565 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1566 'md5': '43662b577c018ad707a63766462b1e87',
1567 'info_dict': {
1568 'id': '2456',
1569 'ext': 'mp4',
1570 'title': 'New experience with Acrobat DC',
1571 'description': 'New experience with Acrobat DC',
1572 'duration': 248.667,
1573 },
1574 },
1575 # BrightcoveInPageEmbed embed
1576 {
1577 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1578 'info_dict': {
1579 'id': '4238694884001',
1580 'ext': 'flv',
1581 'title': 'Tabletop: Dread, Last Thoughts',
1582 'description': 'Tabletop: Dread, Last Thoughts',
1583 'duration': 51690,
1584 },
1585 },
1586 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1587 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1588 {
1589 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1590 'info_dict': {
1591 'id': '4785848093001',
1592 'ext': 'mp4',
1593 'title': 'The Cardinal Pell Interview',
1594 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1595 'uploader': 'GlobeCast Australia - GlobeStream',
1596 'uploader_id': '2733773828001',
1597 'upload_date': '20160304',
1598 'timestamp': 1457083087,
1599 },
1600 'params': {
1601 # m3u8 downloads
1602 'skip_download': True,
1603 },
1604 },
1605 {
1606 # Brightcove embed with whitespace around attribute names
1607 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1608 'info_dict': {
1609 'id': '3167554373001',
1610 'ext': 'mp4',
1611 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1612 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1613 'uploader_id': '1079349493',
1614 'upload_date': '20140207',
1615 'timestamp': 1391810548,
1616 },
1617 'params': {
1618 'skip_download': True,
1619 },
1620 },
1621 # Another form of arte.tv embed
1622 {
1623 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1624 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1625 'info_dict': {
1626 'id': '030273-562_PLUS7-F',
1627 'ext': 'mp4',
1628 'title': 'ARTE Reportage - Nulle part, en France',
1629 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1630 'upload_date': '20160409',
1631 },
1632 },
1633 # LiveLeak embed
1634 {
1635 'url': 'http://www.wykop.pl/link/3088787/',
1636 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1637 'info_dict': {
1638 'id': '874_1459135191',
1639 'ext': 'mp4',
1640 'title': 'Man shows poor quality of new apartment building',
1641 'description': 'The wall is like a sand pile.',
1642 'uploader': 'Lake8737',
1643 },
1644 'add_ie': [LiveLeakIE.ie_key()],
1645 },
1646 # Another LiveLeak embed pattern (#13336)
1647 {
1648 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1649 'info_dict': {
1650 'id': '2eb_1496309988',
1651 'ext': 'mp4',
1652 'title': 'Thief robs place where everyone was armed',
1653 'description': 'md5:694d73ee79e535953cf2488562288eee',
1654 'uploader': 'brazilwtf',
1655 },
1656 'add_ie': [LiveLeakIE.ie_key()],
1657 },
1658 # Duplicated embedded video URLs
1659 {
1660 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1661 'info_dict': {
1662 'id': '149298443_480_16c25b74_2',
1663 'ext': 'mp4',
1664 'title': 'vs. Blue Orange Spring Game',
1665 'uploader': 'www.hudl.com',
1666 },
1667 },
1668 # twitter:player:stream embed
1669 {
1670 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1671 'info_dict': {
1672 'id': 'master',
1673 'ext': 'mp4',
1674 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1675 'uploader': 'www.rtl.be',
1676 },
1677 'params': {
1678 # m3u8 downloads
1679 'skip_download': True,
1680 },
1681 },
1682 # twitter:player embed
1683 {
1684 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1685 'md5': 'a3e0df96369831de324f0778e126653c',
1686 'info_dict': {
1687 'id': '4909620399001',
1688 'ext': 'mp4',
1689 'title': 'What Do Black Holes Sound Like?',
1690 'description': 'what do black holes sound like',
1691 'upload_date': '20160524',
1692 'uploader_id': '29913724001',
1693 'timestamp': 1464107587,
1694 'uploader': 'TheAtlantic',
1695 },
1696 'add_ie': ['BrightcoveLegacy'],
1697 },
1698 # Facebook <iframe> embed
1699 {
1700 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1701 'md5': 'fbcde74f534176ecb015849146dd3aee',
1702 'info_dict': {
1703 'id': '599637780109885',
1704 'ext': 'mp4',
1705 'title': 'Facebook video #599637780109885',
1706 },
1707 },
1708 # Facebook <iframe> embed, plugin video
1709 {
1710 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1711 'info_dict': {
1712 'id': '1754168231264132',
1713 'ext': 'mp4',
1714 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1715 'uploader': 'Tariq Ramadan (official)',
1716 'timestamp': 1496758379,
1717 'upload_date': '20170606',
1718 },
1719 'params': {
1720 'skip_download': True,
1721 },
1722 },
1723 # Facebook API embed
1724 {
1725 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1726 'md5': 'a47372ee61b39a7b90287094d447d94e',
1727 'info_dict': {
1728 'id': '10153467542406923',
1729 'ext': 'mp4',
1730 'title': 'Facebook video #10153467542406923',
1731 },
1732 },
1733 # Wordpress "YouTube Video Importer" plugin
1734 {
1735 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1736 'md5': 'd16797741b560b485194eddda8121b48',
1737 'info_dict': {
1738 'id': 'HNTXWDXV9Is',
1739 'ext': 'mp4',
1740 'title': 'Blue Devils Drumline Stanford lot 2016',
1741 'upload_date': '20160627',
1742 'uploader_id': 'GENOCIDE8GENERAL10',
1743 'uploader': 'cylus cyrus',
1744 },
1745 },
1746 {
1747 # video stored on custom kaltura server
1748 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1749 'md5': '537617d06e64dfed891fa1593c4b30cc',
1750 'info_dict': {
1751 'id': '0_1iotm5bh',
1752 'ext': 'mp4',
1753 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1754 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1755 'uploader_id': 'videos.expansion@el-mundo.net',
1756 'upload_date': '20150429',
1757 'timestamp': 1430303472,
1758 },
1759 'add_ie': ['Kaltura'],
1760 },
1761 {
1762 # multiple kaltura embeds, nsfw
1763 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1764 'info_dict': {
1765 'id': 'kamila-avec-video-jaime-sadomie',
1766 'title': "Kamila avec vídeo “J'aime sadomie”",
1767 },
1768 'playlist_count': 8,
1769 },
1770 {
1771 # Non-standard Vimeo embed
1772 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1773 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1774 'info_dict': {
1775 'id': '148867247',
1776 'ext': 'mp4',
1777 'title': 'Understanding the web - Teaser',
1778 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1779 'upload_date': '20151214',
1780 'uploader': 'OpenClassrooms',
1781 'uploader_id': 'openclassrooms',
1782 },
1783 'add_ie': ['Vimeo'],
1784 },
1785 {
1786 # generic vimeo embed that requires original URL passed as Referer
1787 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1788 'only_matching': True,
1789 },
1790 {
1791 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1792 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1793 'info_dict': {
1794 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1795 'ext': 'mp4',
1796 'title': 'Big Buck Bunny',
1797 'description': 'Royalty free test video',
1798 'timestamp': 1432816365,
1799 'upload_date': '20150528',
1800 'is_live': False,
1801 },
1802 'params': {
1803 'skip_download': True,
1804 },
1805 'add_ie': [ArkenaIE.ie_key()],
1806 },
1807 {
1808 '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/',
1809 'info_dict': {
1810 'id': '1c7141f46c',
1811 'ext': 'mp4',
1812 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1813 },
1814 'params': {
1815 'skip_download': True,
1816 },
1817 'add_ie': [Vbox7IE.ie_key()],
1818 },
1819 {
1820 # DBTV embeds
1821 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1822 'info_dict': {
1823 'id': '43254897',
1824 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1825 },
1826 'playlist_mincount': 3,
1827 },
1828 {
1829 # Videa embeds
1830 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1831 'info_dict': {
1832 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1833 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1834 },
1835 'playlist_mincount': 2,
1836 },
1837 {
1838 # 20 minuten embed
1839 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1840 'info_dict': {
1841 'id': '523629',
1842 'ext': 'mp4',
1843 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1844 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1845 },
1846 'params': {
1847 'skip_download': True,
1848 },
1849 'add_ie': [TwentyMinutenIE.ie_key()],
1850 },
1851 {
1852 # VideoPress embed
1853 'url': 'https://en.support.wordpress.com/videopress/',
1854 'info_dict': {
1855 'id': 'OcobLTqC',
1856 'ext': 'm4v',
1857 'title': 'IMG_5786',
1858 'timestamp': 1435711927,
1859 'upload_date': '20150701',
1860 },
1861 'params': {
1862 'skip_download': True,
1863 },
1864 'add_ie': [VideoPressIE.ie_key()],
1865 },
1866 {
1867 # Rutube embed
1868 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1869 'info_dict': {
1870 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1871 'ext': 'flv',
1872 'title': 'Магаззино: Казань 2',
1873 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1874 'uploader': 'Магаззино',
1875 'upload_date': '20170228',
1876 'uploader_id': '996642',
1877 },
1878 'params': {
1879 'skip_download': True,
1880 },
1881 'add_ie': [RutubeIE.ie_key()],
1882 },
1883 {
1884 # ThePlatform embedded with whitespaces in URLs
1885 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1886 'only_matching': True,
1887 },
1888 {
1889 # Senate ISVP iframe https
1890 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1891 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1892 'info_dict': {
1893 'id': 'govtaff020316',
1894 'ext': 'mp4',
1895 'title': 'Integrated Senate Video Player',
1896 },
1897 'add_ie': [SenateISVPIE.ie_key()],
1898 },
1899 {
1900 # Limelight embeds (1 channel embed + 4 media embeds)
1901 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1902 'info_dict': {
1903 'id': 'FacilitatorTraining2017',
1904 'title': 'Facilitator Training 2017',
1905 },
1906 'playlist_mincount': 5,
1907 },
1908 {
1909 # Limelight embed (LimelightPlayerUtil.embed)
1910 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1911 'info_dict': {
1912 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1913 'ext': 'mp4',
1914 'title': '07448641',
1915 'timestamp': 1499890639,
1916 'upload_date': '20170712',
1917 },
1918 'params': {
1919 'skip_download': True,
1920 },
1921 'add_ie': ['LimelightMedia'],
1922 },
1923 {
1924 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1925 'info_dict': {
1926 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1927 'title': 'Standoff with Walnut Creek murder suspect ends',
1928 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1929 },
1930 'playlist_mincount': 4,
1931 },
1932 {
1933 # WashingtonPost embed
1934 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1935 'info_dict': {
1936 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1937 'ext': 'mp4',
1938 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1939 '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.',
1940 'timestamp': 1455216756,
1941 'uploader': 'The Washington Post',
1942 'upload_date': '20160211',
1943 },
1944 'add_ie': [WashingtonPostIE.ie_key()],
1945 },
1946 {
1947 # Mediaset embed
1948 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1949 'info_dict': {
1950 'id': '720642',
1951 'ext': 'mp4',
1952 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1953 },
1954 'params': {
1955 'skip_download': True,
1956 },
1957 'add_ie': [MediasetIE.ie_key()],
1958 },
1959 {
1960 # JOJ.sk embeds
1961 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1962 'info_dict': {
1963 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1964 'title': 'Slovenskom sa prehnala vlna silných búrok',
1965 },
1966 'playlist_mincount': 5,
1967 'add_ie': [JojIE.ie_key()],
1968 },
1969 {
1970 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1971 'url': 'https://tvrain.ru/amp/418921/',
1972 'md5': 'cc00413936695987e8de148b67d14f1d',
1973 'info_dict': {
1974 'id': '418921',
1975 'ext': 'mp4',
1976 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1977 },
1978 },
1979 {
1980 # vzaar embed
1981 'url': 'http://help.vzaar.com/article/165-embedding-video',
1982 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1983 'info_dict': {
1984 'id': '8707641',
1985 'ext': 'mp4',
1986 'title': 'Building A Business Online: Principal Chairs Q & A',
1987 },
1988 },
1989 {
1990 # multiple HTML5 videos on one page
1991 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1992 'info_dict': {
1993 'id': 'keyscenarios',
1994 'title': 'Rescue Kit 14 Free Edition - Getting started',
1995 },
1996 'playlist_count': 4,
1997 },
1998 {
1999 # vshare embed
2000 'url': 'https://youtube-dlc-demo.neocities.org/vshare.html',
2001 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
2002 'info_dict': {
2003 'id': '0f64ce6',
2004 'title': 'vl14062007715967',
2005 'ext': 'mp4',
2006 }
2007 },
2008 {
2009 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2010 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2011 'info_dict': {
2012 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2013 'ext': 'mp4',
2014 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2015 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2016 'timestamp': 1474354800,
2017 'upload_date': '20160920',
2018 }
2019 },
2020 {
2021 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2022 'info_dict': {
2023 'id': '1731611',
2024 'ext': 'mp4',
2025 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2026 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2027 'timestamp': 1516100691,
2028 'upload_date': '20180116',
2029 },
2030 'params': {
2031 'skip_download': True,
2032 },
2033 'add_ie': [SpringboardPlatformIE.ie_key()],
2034 },
2035 {
2036 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2037 'info_dict': {
2038 'id': 'vMDE4NzI1Mjgt690b',
2039 'ext': 'mp4',
2040 'title': 'Котята',
2041 },
2042 'add_ie': [YapFilesIE.ie_key()],
2043 'params': {
2044 'skip_download': True,
2045 },
2046 },
2047 {
2048 # CloudflareStream embed
2049 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2050 'info_dict': {
2051 'id': '31c9291ab41fac05471db4e73aa11717',
2052 'ext': 'mp4',
2053 'title': '31c9291ab41fac05471db4e73aa11717',
2054 },
2055 'add_ie': [CloudflareStreamIE.ie_key()],
2056 'params': {
2057 'skip_download': True,
2058 },
2059 },
2060 {
2061 # PeerTube embed
2062 'url': 'https://joinpeertube.org/fr/home/',
2063 'info_dict': {
2064 'id': 'home',
2065 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2066 },
2067 'playlist_count': 2,
2068 },
2069 {
2070 # Indavideo embed
2071 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2072 'info_dict': {
2073 'id': '1693903',
2074 'ext': 'mp4',
2075 'title': 'Így kell otthon hamburgert sütni',
2076 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2077 'timestamp': 1426330212,
2078 'upload_date': '20150314',
2079 'uploader': 'StreetKitchen',
2080 'uploader_id': '546363',
2081 },
2082 'add_ie': [IndavideoEmbedIE.ie_key()],
2083 'params': {
2084 'skip_download': True,
2085 },
2086 },
2087 {
2088 # APA embed via JWPlatform embed
2089 'url': 'http://www.vol.at/blue-man-group/5593454',
2090 'info_dict': {
2091 'id': 'jjv85FdZ',
2092 'ext': 'mp4',
2093 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2094 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2095 'thumbnail': r're:^https?://.*\.jpg$',
2096 'duration': 254,
2097 'timestamp': 1519211149,
2098 'upload_date': '20180221',
2099 },
2100 'params': {
2101 'skip_download': True,
2102 },
2103 },
2104 {
2105 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2106 'md5': 'b68d276de422ab07ee1d49388103f457',
2107 'info_dict': {
2108 'id': '83645793',
2109 'title': 'Lock up and get excited',
2110 'ext': 'mp4'
2111 },
2112 'skip': 'TODO: fix nested playlists processing in tests',
2113 },
2114 {
2115 # Viqeo embeds
2116 'url': 'https://viqeo.tv/',
2117 'info_dict': {
2118 'id': 'viqeo',
2119 'title': 'All-new video platform',
2120 },
2121 'playlist_count': 6,
2122 },
2123 {
2124 # Squarespace video embed, 2019-08-28
2125 'url': 'http://ootboxford.com',
2126 'info_dict': {
2127 'id': 'Tc7b_JGdZfw',
2128 'title': 'Out of the Blue, at Childish Things 10',
2129 'ext': 'mp4',
2130 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2131 'uploader_id': 'helendouglashouse',
2132 'uploader': 'Helen & Douglas House',
2133 'upload_date': '20140328',
2134 },
2135 'params': {
2136 'skip_download': True,
2137 },
2138 },
2139 # {
2140 # # Zype embed
2141 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2142 # 'info_dict': {
2143 # 'id': '5b400b834b32992a310622b9',
2144 # 'ext': 'mp4',
2145 # 'title': 'Smoky Barbecue Favorites',
2146 # 'thumbnail': r're:^https?://.*\.jpe?g',
2147 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2148 # 'upload_date': '20170909',
2149 # 'timestamp': 1504915200,
2150 # },
2151 # 'add_ie': [ZypeIE.ie_key()],
2152 # 'params': {
2153 # 'skip_download': True,
2154 # },
2155 # },
2156 {
2157 # videojs embed
2158 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2159 'info_dict': {
2160 'id': 'shell',
2161 'ext': 'mp4',
2162 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2163 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2164 'thumbnail': r're:^https?://.*\.jpg$',
2165 },
2166 'params': {
2167 'skip_download': True,
2168 },
2169 'expected_warnings': ['Failed to download MPD manifest'],
2170 },
2171 {
2172 # DailyMotion embed with DM.player
2173 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2174 'info_dict': {
2175 'id': 'k6aKkGHd9FJs4mtJN39',
2176 'ext': 'mp4',
2177 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2178 'description': 'This video is private.',
2179 'uploader_id': 'x1jf30l',
2180 'uploader': 'beIN SPORTS USA',
2181 'upload_date': '20190528',
2182 'timestamp': 1559062971,
2183 },
2184 'params': {
2185 'skip_download': True,
2186 },
2187 },
2188 # {
2189 # # TODO: find another test
2190 # # http://schema.org/VideoObject
2191 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2192 # 'md5': '888dcf08b7ea671381f00fab74692755',
2193 # 'info_dict': {
2194 # 'id': 'nyvTSJMKId',
2195 # 'ext': 'mp4',
2196 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2197 # 'description': '#love for cats.',
2198 # 'timestamp': 1461244995,
2199 # 'upload_date': '20160421',
2200 # },
2201 # 'params': {
2202 # 'force_generic_extractor': True,
2203 # },
2204 # },
2205 {
2206 # VHX Embed
2207 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2208 'info_dict': {
2209 'id': '858208',
2210 'ext': 'mp4',
2211 'title': 'Untitled',
2212 'uploader_id': 'user80538407',
2213 'uploader': 'OTT Videos',
2214 },
2215 },
2216 {
2217 # ArcPublishing PoWa video player
2218 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2219 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2220 'info_dict': {
2221 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2222 'ext': 'mp4',
2223 'title': 'Senate candidates wave to voters on Anchorage streets',
2224 'description': 'md5:91f51a6511f090617353dc720318b20e',
2225 'timestamp': 1604378735,
2226 'upload_date': '20201103',
2227 'duration': 1581,
2228 },
2229 },
2230 {
2231 # MyChannels SDK embed
2232 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2233 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2234 'md5': '90c0699c37006ef18e198c032d81739c',
2235 'info_dict': {
2236 'id': '194165',
2237 'ext': 'mp4',
2238 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2239 'timestamp': 1611740340,
2240 'upload_date': '20210127',
2241 'duration': 159,
2242 },
2243 },
2244 {
2245 # Simplecast player embed
2246 'url': 'https://www.bio.org/podcast',
2247 'info_dict': {
2248 'id': 'podcast',
2249 'title': 'I AM BIO Podcast | BIO',
2250 },
2251 'playlist_mincount': 52,
2252 },
2253 ]
2254
2255 def report_following_redirect(self, new_url):
2256 """Report information extraction."""
2257 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2258
2259 def _extract_rss(self, url, video_id, doc):
2260 playlist_title = doc.find('./channel/title').text
2261 playlist_desc_el = doc.find('./channel/description')
2262 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2263
2264 NS_MAP = {
2265 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2266 }
2267
2268 entries = []
2269 for it in doc.findall('./channel/item'):
2270 next_url = None
2271 enclosure_nodes = it.findall('./enclosure')
2272 for e in enclosure_nodes:
2273 next_url = e.attrib.get('url')
2274 if next_url:
2275 break
2276
2277 if not next_url:
2278 next_url = xpath_text(it, 'link', fatal=False)
2279
2280 if not next_url:
2281 continue
2282
2283 def itunes(key):
2284 return xpath_text(
2285 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2286 default=None)
2287
2288 duration = itunes('duration')
2289 explicit = (itunes('explicit') or '').lower()
2290 if explicit in ('true', 'yes'):
2291 age_limit = 18
2292 elif explicit in ('false', 'no'):
2293 age_limit = 0
2294 else:
2295 age_limit = None
2296
2297 entries.append({
2298 '_type': 'url_transparent',
2299 'url': next_url,
2300 'title': it.find('title').text,
2301 'description': xpath_text(it, 'description', default=None),
2302 'timestamp': unified_timestamp(
2303 xpath_text(it, 'pubDate', default=None)),
2304 'duration': int_or_none(duration) or parse_duration(duration),
2305 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2306 'episode': itunes('title'),
2307 'episode_number': int_or_none(itunes('episode')),
2308 'season_number': int_or_none(itunes('season')),
2309 'age_limit': age_limit,
2310 })
2311
2312 return {
2313 '_type': 'playlist',
2314 'id': url,
2315 'title': playlist_title,
2316 'description': playlist_desc,
2317 'entries': entries,
2318 }
2319
2320 def _extract_camtasia(self, url, video_id, webpage):
2321 """ Returns None if no camtasia video can be found. """
2322
2323 camtasia_cfg = self._search_regex(
2324 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2325 webpage, 'camtasia configuration file', default=None)
2326 if camtasia_cfg is None:
2327 return None
2328
2329 title = self._html_search_meta('DC.title', webpage, fatal=True)
2330
2331 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2332 camtasia_cfg = self._download_xml(
2333 camtasia_url, video_id,
2334 note='Downloading camtasia configuration',
2335 errnote='Failed to download camtasia configuration')
2336 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2337
2338 entries = []
2339 for n in fileset_node.getchildren():
2340 url_n = n.find('./uri')
2341 if url_n is None:
2342 continue
2343
2344 entries.append({
2345 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2346 'title': '%s - %s' % (title, n.tag),
2347 'url': compat_urlparse.urljoin(url, url_n.text),
2348 'duration': float_or_none(n.find('./duration').text),
2349 })
2350
2351 return {
2352 '_type': 'playlist',
2353 'entries': entries,
2354 'title': title,
2355 }
2356
2357 def _real_extract(self, url):
2358 if url.startswith('//'):
2359 return self.url_result(self.http_scheme() + url)
2360
2361 parsed_url = compat_urlparse.urlparse(url)
2362 if not parsed_url.scheme:
2363 default_search = self._downloader.params.get('default_search')
2364 if default_search is None:
2365 default_search = 'fixup_error'
2366
2367 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2368 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2369 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2370 return self.url_result('http://' + url)
2371 elif default_search != 'fixup_error':
2372 if default_search == 'auto_warning':
2373 if re.match(r'^(?:url|URL)$', url):
2374 raise ExtractorError(
2375 'Invalid URL: %r . Call youtube-dlc like this: youtube-dlc -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2376 expected=True)
2377 else:
2378 self._downloader.report_warning(
2379 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2380 return self.url_result('ytsearch:' + url)
2381
2382 if default_search in ('error', 'fixup_error'):
2383 raise ExtractorError(
2384 '%r is not a valid URL. '
2385 'Set --default-search "ytsearch" (or run youtube-dlc "ytsearch:%s" ) to search YouTube'
2386 % (url, url), expected=True)
2387 else:
2388 if ':' not in default_search:
2389 default_search += ':'
2390 return self.url_result(default_search + url)
2391
2392 url, smuggled_data = unsmuggle_url(url)
2393 force_videoid = None
2394 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2395 if smuggled_data and 'force_videoid' in smuggled_data:
2396 force_videoid = smuggled_data['force_videoid']
2397 video_id = force_videoid
2398 else:
2399 video_id = self._generic_id(url)
2400
2401 self.to_screen('%s: Requesting header' % video_id)
2402
2403 head_req = HEADRequest(url)
2404 head_response = self._request_webpage(
2405 head_req, video_id,
2406 note=False, errnote='Could not send HEAD request to %s' % url,
2407 fatal=False)
2408
2409 if head_response is not False:
2410 # Check for redirect
2411 new_url = head_response.geturl()
2412 if url != new_url:
2413 self.report_following_redirect(new_url)
2414 if force_videoid:
2415 new_url = smuggle_url(
2416 new_url, {'force_videoid': force_videoid})
2417 return self.url_result(new_url)
2418
2419 full_response = None
2420 if head_response is False:
2421 request = sanitized_Request(url)
2422 request.add_header('Accept-Encoding', '*')
2423 full_response = self._request_webpage(request, video_id)
2424 head_response = full_response
2425
2426 info_dict = {
2427 'id': video_id,
2428 'title': self._generic_title(url),
2429 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2430 }
2431
2432 # Check for direct link to a video
2433 content_type = head_response.headers.get('Content-Type', '').lower()
2434 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2435 if m:
2436 format_id = compat_str(m.group('format_id'))
2437 if format_id.endswith('mpegurl'):
2438 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2439 elif format_id == 'f4m':
2440 formats = self._extract_f4m_formats(url, video_id)
2441 else:
2442 formats = [{
2443 'format_id': format_id,
2444 'url': url,
2445 'vcodec': 'none' if m.group('type') == 'audio' else None
2446 }]
2447 info_dict['direct'] = True
2448 self._sort_formats(formats)
2449 info_dict['formats'] = formats
2450 return info_dict
2451
2452 if not self._downloader.params.get('test', False) and not is_intentional:
2453 force = self._downloader.params.get('force_generic_extractor', False)
2454 self._downloader.report_warning(
2455 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2456
2457 if not full_response:
2458 request = sanitized_Request(url)
2459 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2460 # making it impossible to download only chunk of the file (yet we need only 512kB to
2461 # test whether it's HTML or not). According to youtube-dlc default Accept-Encoding
2462 # that will always result in downloading the whole file that is not desirable.
2463 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2464 # to accept raw bytes and being able to download only a chunk.
2465 # It may probably better to solve this by checking Content-Type for application/octet-stream
2466 # after HEAD request finishes, but not sure if we can rely on this.
2467 request.add_header('Accept-Encoding', '*')
2468 full_response = self._request_webpage(request, video_id)
2469
2470 first_bytes = full_response.read(512)
2471
2472 # Is it an M3U playlist?
2473 if first_bytes.startswith(b'#EXTM3U'):
2474 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2475 self._sort_formats(info_dict['formats'])
2476 return info_dict
2477
2478 # Maybe it's a direct link to a video?
2479 # Be careful not to download the whole thing!
2480 if not is_html(first_bytes):
2481 self._downloader.report_warning(
2482 'URL could be a direct video link, returning it as such.')
2483 info_dict.update({
2484 'direct': True,
2485 'url': url,
2486 })
2487 return info_dict
2488
2489 webpage = self._webpage_read_content(
2490 full_response, url, video_id, prefix=first_bytes)
2491
2492 if '<title>DPG Media Privacy Gate</title>' in webpage:
2493 webpage = self._download_webpage(url, video_id)
2494
2495 self.report_extraction(video_id)
2496
2497 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2498 try:
2499 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2500 if doc.tag == 'rss':
2501 return self._extract_rss(url, video_id, doc)
2502 elif doc.tag == 'SmoothStreamingMedia':
2503 info_dict['formats'] = self._parse_ism_formats(doc, url)
2504 self._sort_formats(info_dict['formats'])
2505 return info_dict
2506 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2507 smil = self._parse_smil(doc, url, video_id)
2508 self._sort_formats(smil['formats'])
2509 return smil
2510 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2511 return self.playlist_result(
2512 self._parse_xspf(
2513 doc, video_id, xspf_url=url,
2514 xspf_base_url=full_response.geturl()),
2515 video_id)
2516 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2517 info_dict['formats'] = self._parse_mpd_formats(
2518 doc,
2519 mpd_base_url=full_response.geturl().rpartition('/')[0],
2520 mpd_url=url)
2521 self._sort_formats(info_dict['formats'])
2522 return info_dict
2523 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2524 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2525 self._sort_formats(info_dict['formats'])
2526 return info_dict
2527 except compat_xml_parse_error:
2528 pass
2529
2530 # Is it a Camtasia project?
2531 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2532 if camtasia_res is not None:
2533 return camtasia_res
2534
2535 # Sometimes embedded video player is hidden behind percent encoding
2536 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2537 # Unescaping the whole page allows to handle those cases in a generic way
2538 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2539 # There probably should be a second run of generic extractor on unescaped webpage.
2540 # webpage = compat_urllib_parse_unquote(webpage)
2541
2542 # Unescape squarespace embeds to be detected by generic extractor,
2543 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2544 webpage = re.sub(
2545 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2546 lambda x: unescapeHTML(x.group(0)), webpage)
2547
2548 # it's tempting to parse this further, but you would
2549 # have to take into account all the variations like
2550 # Video Title - Site Name
2551 # Site Name | Video Title
2552 # Video Title - Tagline | Site Name
2553 # and so on and so forth; it's just not practical
2554 video_title = self._og_search_title(
2555 webpage, default=None) or self._html_search_regex(
2556 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2557 default='video')
2558
2559 # Try to detect age limit automatically
2560 age_limit = self._rta_search(webpage)
2561 # And then there are the jokers who advertise that they use RTA,
2562 # but actually don't.
2563 AGE_LIMIT_MARKERS = [
2564 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2565 ]
2566 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2567 age_limit = 18
2568
2569 # video uploader is domain name
2570 video_uploader = self._search_regex(
2571 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2572
2573 video_description = self._og_search_description(webpage, default=None)
2574 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2575
2576 info_dict.update({
2577 'title': video_title,
2578 'description': video_description,
2579 'thumbnail': video_thumbnail,
2580 'age_limit': age_limit,
2581 })
2582
2583 # Look for Brightcove Legacy Studio embeds
2584 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2585 if bc_urls:
2586 entries = [{
2587 '_type': 'url',
2588 'url': smuggle_url(bc_url, {'Referer': url}),
2589 'ie_key': 'BrightcoveLegacy'
2590 } for bc_url in bc_urls]
2591
2592 return {
2593 '_type': 'playlist',
2594 'title': video_title,
2595 'id': video_id,
2596 'entries': entries,
2597 }
2598
2599 # Look for Brightcove New Studio embeds
2600 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2601 if bc_urls:
2602 return self.playlist_from_matches(
2603 bc_urls, video_id, video_title,
2604 getter=lambda x: smuggle_url(x, {'referrer': url}),
2605 ie='BrightcoveNew')
2606
2607 # Look for Nexx embeds
2608 nexx_urls = NexxIE._extract_urls(webpage)
2609 if nexx_urls:
2610 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2611
2612 # Look for Nexx iFrame embeds
2613 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2614 if nexx_embed_urls:
2615 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2616
2617 # Look for ThePlatform embeds
2618 tp_urls = ThePlatformIE._extract_urls(webpage)
2619 if tp_urls:
2620 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2621
2622 arc_urls = ArcPublishingIE._extract_urls(webpage)
2623 if arc_urls:
2624 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2625
2626 mychannels_urls = MedialaanIE._extract_urls(webpage)
2627 if mychannels_urls:
2628 return self.playlist_from_matches(
2629 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2630
2631 # Look for embedded rtl.nl player
2632 matches = re.findall(
2633 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2634 webpage)
2635 if matches:
2636 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2637
2638 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2639 if vimeo_urls:
2640 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2641
2642 vhx_url = VHXEmbedIE._extract_url(webpage)
2643 if vhx_url:
2644 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2645
2646 vid_me_embed_url = self._search_regex(
2647 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2648 webpage, 'vid.me embed', default=None)
2649 if vid_me_embed_url is not None:
2650 return self.url_result(vid_me_embed_url, 'Vidme')
2651
2652 # Look for YouTube embeds
2653 youtube_urls = YoutubeIE._extract_urls(webpage)
2654 if youtube_urls:
2655 return self.playlist_from_matches(
2656 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2657
2658 matches = DailymotionIE._extract_urls(webpage)
2659 if matches:
2660 return self.playlist_from_matches(matches, video_id, video_title)
2661
2662 # Look for embedded Dailymotion playlist player (#3822)
2663 m = re.search(
2664 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2665 if m:
2666 playlists = re.findall(
2667 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2668 if playlists:
2669 return self.playlist_from_matches(
2670 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2671
2672 # Look for DailyMail embeds
2673 dailymail_urls = DailyMailIE._extract_urls(webpage)
2674 if dailymail_urls:
2675 return self.playlist_from_matches(
2676 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2677
2678 # Look for Teachable embeds, must be before Wistia
2679 teachable_url = TeachableIE._extract_url(webpage, url)
2680 if teachable_url:
2681 return self.url_result(teachable_url)
2682
2683 # Look for embedded Wistia player
2684 wistia_urls = WistiaIE._extract_urls(webpage)
2685 if wistia_urls:
2686 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2687 for entry in playlist['entries']:
2688 entry.update({
2689 '_type': 'url_transparent',
2690 'uploader': video_uploader,
2691 })
2692 return playlist
2693
2694 # Look for SVT player
2695 svt_url = SVTIE._extract_url(webpage)
2696 if svt_url:
2697 return self.url_result(svt_url, 'SVT')
2698
2699 # Look for Bandcamp pages with custom domain
2700 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2701 if mobj is not None:
2702 burl = unescapeHTML(mobj.group(1))
2703 # Don't set the extractor because it can be a track url or an album
2704 return self.url_result(burl)
2705
2706 # Look for embedded Vevo player
2707 mobj = re.search(
2708 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2709 if mobj is not None:
2710 return self.url_result(mobj.group('url'))
2711
2712 # Look for embedded Viddler player
2713 mobj = re.search(
2714 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2715 webpage)
2716 if mobj is not None:
2717 return self.url_result(mobj.group('url'))
2718
2719 # Look for NYTimes player
2720 mobj = re.search(
2721 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2722 webpage)
2723 if mobj is not None:
2724 return self.url_result(mobj.group('url'))
2725
2726 # Look for Libsyn player
2727 mobj = re.search(
2728 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2729 if mobj is not None:
2730 return self.url_result(mobj.group('url'))
2731
2732 # Look for Ooyala videos
2733 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2734 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2735 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2736 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2737 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2738 if mobj is not None:
2739 embed_token = self._search_regex(
2740 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2741 webpage, 'ooyala embed token', default=None)
2742 return OoyalaIE._build_url_result(smuggle_url(
2743 mobj.group('ec'), {
2744 'domain': url,
2745 'embed_token': embed_token,
2746 }))
2747
2748 # Look for multiple Ooyala embeds on SBN network websites
2749 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2750 if mobj is not None:
2751 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2752 if embeds:
2753 return self.playlist_from_matches(
2754 embeds, video_id, video_title,
2755 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2756
2757 # Look for Aparat videos
2758 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2759 if mobj is not None:
2760 return self.url_result(mobj.group(1), 'Aparat')
2761
2762 # Look for MPORA videos
2763 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2764 if mobj is not None:
2765 return self.url_result(mobj.group(1), 'Mpora')
2766
2767 # Look for embedded Facebook player
2768 facebook_urls = FacebookIE._extract_urls(webpage)
2769 if facebook_urls:
2770 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2771
2772 # Look for embedded VK player
2773 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2774 if mobj is not None:
2775 return self.url_result(mobj.group('url'), 'VK')
2776
2777 # Look for embedded Odnoklassniki player
2778 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2779 if odnoklassniki_url:
2780 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2781
2782 # Look for embedded ivi player
2783 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2784 if mobj is not None:
2785 return self.url_result(mobj.group('url'), 'Ivi')
2786
2787 # Look for embedded Huffington Post player
2788 mobj = re.search(
2789 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2790 if mobj is not None:
2791 return self.url_result(mobj.group('url'), 'HuffPost')
2792
2793 # Look for embed.ly
2794 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2795 if mobj is not None:
2796 return self.url_result(mobj.group('url'))
2797 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2798 if mobj is not None:
2799 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2800
2801 # Look for funnyordie embed
2802 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2803 if matches:
2804 return self.playlist_from_matches(
2805 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2806
2807 # Look for Simplecast embeds
2808 simplecast_urls = SimplecastIE._extract_urls(webpage)
2809 if simplecast_urls:
2810 return self.playlist_from_matches(
2811 simplecast_urls, video_id, video_title)
2812
2813 # Look for BBC iPlayer embed
2814 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2815 if matches:
2816 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2817
2818 # Look for embedded RUTV player
2819 rutv_url = RUTVIE._extract_url(webpage)
2820 if rutv_url:
2821 return self.url_result(rutv_url, 'RUTV')
2822
2823 # Look for embedded TVC player
2824 tvc_url = TVCIE._extract_url(webpage)
2825 if tvc_url:
2826 return self.url_result(tvc_url, 'TVC')
2827
2828 # Look for embedded SportBox player
2829 sportbox_urls = SportBoxIE._extract_urls(webpage)
2830 if sportbox_urls:
2831 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2832
2833 # Look for embedded XHamster player
2834 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2835 if xhamster_urls:
2836 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2837
2838 # Look for embedded TNAFlixNetwork player
2839 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2840 if tnaflix_urls:
2841 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2842
2843 # Look for embedded PornHub player
2844 pornhub_urls = PornHubIE._extract_urls(webpage)
2845 if pornhub_urls:
2846 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2847
2848 # Look for embedded DrTuber player
2849 drtuber_urls = DrTuberIE._extract_urls(webpage)
2850 if drtuber_urls:
2851 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2852
2853 # Look for embedded RedTube player
2854 redtube_urls = RedTubeIE._extract_urls(webpage)
2855 if redtube_urls:
2856 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2857
2858 # Look for embedded Tube8 player
2859 tube8_urls = Tube8IE._extract_urls(webpage)
2860 if tube8_urls:
2861 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2862
2863 # Look for embedded Mofosex player
2864 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2865 if mofosex_urls:
2866 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2867
2868 # Look for embedded Spankwire player
2869 spankwire_urls = SpankwireIE._extract_urls(webpage)
2870 if spankwire_urls:
2871 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2872
2873 # Look for embedded YouPorn player
2874 youporn_urls = YouPornIE._extract_urls(webpage)
2875 if youporn_urls:
2876 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2877
2878 # Look for embedded Tvigle player
2879 mobj = re.search(
2880 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2881 if mobj is not None:
2882 return self.url_result(mobj.group('url'), 'Tvigle')
2883
2884 # Look for embedded TED player
2885 mobj = re.search(
2886 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2887 if mobj is not None:
2888 return self.url_result(mobj.group('url'), 'TED')
2889
2890 # Look for embedded Ustream videos
2891 ustream_url = UstreamIE._extract_url(webpage)
2892 if ustream_url:
2893 return self.url_result(ustream_url, UstreamIE.ie_key())
2894
2895 # Look for embedded arte.tv player
2896 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2897 if arte_urls:
2898 return self.playlist_from_matches(arte_urls, video_id, video_title)
2899
2900 # Look for embedded francetv player
2901 mobj = re.search(
2902 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2903 webpage)
2904 if mobj is not None:
2905 return self.url_result(mobj.group('url'))
2906
2907 # Look for embedded Myvi.ru player
2908 myvi_url = MyviIE._extract_url(webpage)
2909 if myvi_url:
2910 return self.url_result(myvi_url)
2911
2912 # Look for embedded soundcloud player
2913 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2914 if soundcloud_urls:
2915 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2916
2917 # Look for tunein player
2918 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2919 if tunein_urls:
2920 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2921
2922 # Look for embedded mtvservices player
2923 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2924 if mtvservices_url:
2925 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2926
2927 # Look for embedded yahoo player
2928 mobj = re.search(
2929 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2930 webpage)
2931 if mobj is not None:
2932 return self.url_result(mobj.group('url'), 'Yahoo')
2933
2934 # Look for embedded sbs.com.au player
2935 mobj = re.search(
2936 r'''(?x)
2937 (?:
2938 <meta\s+property="og:video"\s+content=|
2939 <iframe[^>]+?src=
2940 )
2941 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2942 webpage)
2943 if mobj is not None:
2944 return self.url_result(mobj.group('url'), 'SBS')
2945
2946 # Look for embedded Cinchcast player
2947 mobj = re.search(
2948 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2949 webpage)
2950 if mobj is not None:
2951 return self.url_result(mobj.group('url'), 'Cinchcast')
2952
2953 mobj = re.search(
2954 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2955 webpage)
2956 if not mobj:
2957 mobj = re.search(
2958 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2959 webpage)
2960 if mobj is not None:
2961 return self.url_result(mobj.group('url'), 'MLB')
2962
2963 mobj = re.search(
2964 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2965 webpage)
2966 if mobj is not None:
2967 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2968
2969 mobj = re.search(
2970 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2971 webpage)
2972 if mobj is not None:
2973 return self.url_result(mobj.group('url'), 'Livestream')
2974
2975 # Look for Zapiks embed
2976 mobj = re.search(
2977 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2978 if mobj is not None:
2979 return self.url_result(mobj.group('url'), 'Zapiks')
2980
2981 # Look for Kaltura embeds
2982 kaltura_urls = KalturaIE._extract_urls(webpage)
2983 if kaltura_urls:
2984 return self.playlist_from_matches(
2985 kaltura_urls, video_id, video_title,
2986 getter=lambda x: smuggle_url(x, {'source_url': url}),
2987 ie=KalturaIE.ie_key())
2988
2989 # Look for EaglePlatform embeds
2990 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2991 if eagleplatform_url:
2992 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2993
2994 # Look for ClipYou (uses EaglePlatform) embeds
2995 mobj = re.search(
2996 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2997 if mobj is not None:
2998 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2999
3000 # Look for Pladform embeds
3001 pladform_url = PladformIE._extract_url(webpage)
3002 if pladform_url:
3003 return self.url_result(pladform_url)
3004
3005 # Look for Videomore embeds
3006 videomore_url = VideomoreIE._extract_url(webpage)
3007 if videomore_url:
3008 return self.url_result(videomore_url)
3009
3010 # Look for Webcaster embeds
3011 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3012 if webcaster_url:
3013 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3014
3015 # Look for Playwire embeds
3016 mobj = re.search(
3017 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3018 if mobj is not None:
3019 return self.url_result(mobj.group('url'))
3020
3021 # Look for 5min embeds
3022 mobj = re.search(
3023 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3024 if mobj is not None:
3025 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3026
3027 # Look for Crooks and Liars embeds
3028 mobj = re.search(
3029 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3030 if mobj is not None:
3031 return self.url_result(mobj.group('url'))
3032
3033 # Look for NBC Sports VPlayer embeds
3034 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3035 if nbc_sports_url:
3036 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3037
3038 # Look for NBC News embeds
3039 nbc_news_embed_url = re.search(
3040 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3041 if nbc_news_embed_url:
3042 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3043
3044 # Look for Google Drive embeds
3045 google_drive_url = GoogleDriveIE._extract_url(webpage)
3046 if google_drive_url:
3047 return self.url_result(google_drive_url, 'GoogleDrive')
3048
3049 # Look for UDN embeds
3050 mobj = re.search(
3051 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3052 if mobj is not None:
3053 return self.url_result(
3054 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3055
3056 # Look for Senate ISVP iframe
3057 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3058 if senate_isvp_url:
3059 return self.url_result(senate_isvp_url, 'SenateISVP')
3060
3061 # Look for Kinja embeds
3062 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3063 if kinja_embed_urls:
3064 return self.playlist_from_matches(
3065 kinja_embed_urls, video_id, video_title)
3066
3067 # Look for OnionStudios embeds
3068 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3069 if onionstudios_url:
3070 return self.url_result(onionstudios_url)
3071
3072 # Look for ViewLift embeds
3073 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3074 if viewlift_url:
3075 return self.url_result(viewlift_url)
3076
3077 # Look for JWPlatform embeds
3078 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3079 if jwplatform_urls:
3080 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3081
3082 # Look for Digiteka embeds
3083 digiteka_url = DigitekaIE._extract_url(webpage)
3084 if digiteka_url:
3085 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3086
3087 # Look for Arkena embeds
3088 arkena_url = ArkenaIE._extract_url(webpage)
3089 if arkena_url:
3090 return self.url_result(arkena_url, ArkenaIE.ie_key())
3091
3092 # Look for Piksel embeds
3093 piksel_url = PikselIE._extract_url(webpage)
3094 if piksel_url:
3095 return self.url_result(piksel_url, PikselIE.ie_key())
3096
3097 # Look for Limelight embeds
3098 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3099 if limelight_urls:
3100 return self.playlist_result(
3101 limelight_urls, video_id, video_title, video_description)
3102
3103 # Look for Anvato embeds
3104 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3105 if anvato_urls:
3106 return self.playlist_result(
3107 anvato_urls, video_id, video_title, video_description)
3108
3109 # Look for AdobeTVVideo embeds
3110 mobj = re.search(
3111 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3112 webpage)
3113 if mobj is not None:
3114 return self.url_result(
3115 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3116 'AdobeTVVideo')
3117
3118 # Look for Vine embeds
3119 mobj = re.search(
3120 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3121 webpage)
3122 if mobj is not None:
3123 return self.url_result(
3124 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3125
3126 # Look for VODPlatform embeds
3127 mobj = re.search(
3128 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3129 webpage)
3130 if mobj is not None:
3131 return self.url_result(
3132 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3133
3134 # Look for Mangomolo embeds
3135 mobj = re.search(
3136 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3137 (?:
3138 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3139 player\.mangomolo\.com/v1
3140 )/
3141 (?:
3142 video\?.*?\bid=(?P<video_id>\d+)|
3143 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3144 ).+?)\1''', webpage)
3145 if mobj is not None:
3146 info = {
3147 '_type': 'url_transparent',
3148 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3149 'title': video_title,
3150 'description': video_description,
3151 'thumbnail': video_thumbnail,
3152 'uploader': video_uploader,
3153 }
3154 video_id = mobj.group('video_id')
3155 if video_id:
3156 info.update({
3157 'ie_key': 'MangomoloVideo',
3158 'id': video_id,
3159 })
3160 else:
3161 info.update({
3162 'ie_key': 'MangomoloLive',
3163 'id': mobj.group('channel_id'),
3164 })
3165 return info
3166
3167 # Look for Instagram embeds
3168 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3169 if instagram_embed_url is not None:
3170 return self.url_result(
3171 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3172
3173 # Look for LiveLeak embeds
3174 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3175 if liveleak_urls:
3176 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3177
3178 # Look for 3Q SDN embeds
3179 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3180 if threeqsdn_url:
3181 return {
3182 '_type': 'url_transparent',
3183 'ie_key': ThreeQSDNIE.ie_key(),
3184 'url': self._proto_relative_url(threeqsdn_url),
3185 'title': video_title,
3186 'description': video_description,
3187 'thumbnail': video_thumbnail,
3188 'uploader': video_uploader,
3189 }
3190
3191 # Look for VBOX7 embeds
3192 vbox7_url = Vbox7IE._extract_url(webpage)
3193 if vbox7_url:
3194 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3195
3196 # Look for DBTV embeds
3197 dbtv_urls = DBTVIE._extract_urls(webpage)
3198 if dbtv_urls:
3199 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3200
3201 # Look for Videa embeds
3202 videa_urls = VideaIE._extract_urls(webpage)
3203 if videa_urls:
3204 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3205
3206 # Look for 20 minuten embeds
3207 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3208 if twentymin_urls:
3209 return self.playlist_from_matches(
3210 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3211
3212 # Look for VideoPress embeds
3213 videopress_urls = VideoPressIE._extract_urls(webpage)
3214 if videopress_urls:
3215 return self.playlist_from_matches(
3216 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3217
3218 # Look for Rutube embeds
3219 rutube_urls = RutubeIE._extract_urls(webpage)
3220 if rutube_urls:
3221 return self.playlist_from_matches(
3222 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3223
3224 # Look for WashingtonPost embeds
3225 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3226 if wapo_urls:
3227 return self.playlist_from_matches(
3228 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3229
3230 # Look for Mediaset embeds
3231 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3232 if mediaset_urls:
3233 return self.playlist_from_matches(
3234 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3235
3236 # Look for JOJ.sk embeds
3237 joj_urls = JojIE._extract_urls(webpage)
3238 if joj_urls:
3239 return self.playlist_from_matches(
3240 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3241
3242 # Look for megaphone.fm embeds
3243 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3244 if mpfn_urls:
3245 return self.playlist_from_matches(
3246 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3247
3248 # Look for vzaar embeds
3249 vzaar_urls = VzaarIE._extract_urls(webpage)
3250 if vzaar_urls:
3251 return self.playlist_from_matches(
3252 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3253
3254 channel9_urls = Channel9IE._extract_urls(webpage)
3255 if channel9_urls:
3256 return self.playlist_from_matches(
3257 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3258
3259 vshare_urls = VShareIE._extract_urls(webpage)
3260 if vshare_urls:
3261 return self.playlist_from_matches(
3262 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3263
3264 # Look for Mediasite embeds
3265 mediasite_urls = MediasiteIE._extract_urls(webpage)
3266 if mediasite_urls:
3267 entries = [
3268 self.url_result(smuggle_url(
3269 compat_urlparse.urljoin(url, mediasite_url),
3270 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3271 for mediasite_url in mediasite_urls]
3272 return self.playlist_result(entries, video_id, video_title)
3273
3274 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3275 if springboardplatform_urls:
3276 return self.playlist_from_matches(
3277 springboardplatform_urls, video_id, video_title,
3278 ie=SpringboardPlatformIE.ie_key())
3279
3280 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3281 if yapfiles_urls:
3282 return self.playlist_from_matches(
3283 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3284
3285 vice_urls = ViceIE._extract_urls(webpage)
3286 if vice_urls:
3287 return self.playlist_from_matches(
3288 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3289
3290 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3291 if xfileshare_urls:
3292 return self.playlist_from_matches(
3293 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3294
3295 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3296 if cloudflarestream_urls:
3297 return self.playlist_from_matches(
3298 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3299
3300 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3301 if peertube_urls:
3302 return self.playlist_from_matches(
3303 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3304
3305 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3306 if indavideo_urls:
3307 return self.playlist_from_matches(
3308 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3309
3310 apa_urls = APAIE._extract_urls(webpage)
3311 if apa_urls:
3312 return self.playlist_from_matches(
3313 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3314
3315 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3316 if foxnews_urls:
3317 return self.playlist_from_matches(
3318 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3319
3320 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3321 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3322 webpage)]
3323 if sharevideos_urls:
3324 return self.playlist_from_matches(
3325 sharevideos_urls, video_id, video_title)
3326
3327 viqeo_urls = ViqeoIE._extract_urls(webpage)
3328 if viqeo_urls:
3329 return self.playlist_from_matches(
3330 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3331
3332 expressen_urls = ExpressenIE._extract_urls(webpage)
3333 if expressen_urls:
3334 return self.playlist_from_matches(
3335 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3336
3337 zype_urls = ZypeIE._extract_urls(webpage)
3338 if zype_urls:
3339 return self.playlist_from_matches(
3340 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3341
3342 # Look for RCS media group embeds
3343 gedi_urls = GediEmbedsIE._extract_urls(webpage)
3344 if gedi_urls:
3345 return self.playlist_from_matches(
3346 gedi_urls, video_id, video_title, ie=GediEmbedsIE.ie_key())
3347
3348 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3349 if rcs_urls:
3350 return self.playlist_from_matches(
3351 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3352
3353 bitchute_urls = BitChuteIE._extract_urls(webpage)
3354 if bitchute_urls:
3355 return self.playlist_from_matches(
3356 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3357
3358 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3359 if len(rumble_urls) == 1:
3360 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3361 if rumble_urls:
3362 return self.playlist_from_matches(
3363 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3364
3365 # Look for HTML5 media
3366 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3367 if entries:
3368 if len(entries) == 1:
3369 entries[0].update({
3370 'id': video_id,
3371 'title': video_title,
3372 })
3373 else:
3374 for num, entry in enumerate(entries, start=1):
3375 entry.update({
3376 'id': '%s-%s' % (video_id, num),
3377 'title': '%s (%d)' % (video_title, num),
3378 })
3379 for entry in entries:
3380 self._sort_formats(entry['formats'])
3381 return self.playlist_result(entries, video_id, video_title)
3382
3383 jwplayer_data = self._find_jwplayer_data(
3384 webpage, video_id, transform_source=js_to_json)
3385 if jwplayer_data:
3386 try:
3387 info = self._parse_jwplayer_data(
3388 jwplayer_data, video_id, require_title=False, base_url=url)
3389 return merge_dicts(info, info_dict)
3390 except ExtractorError:
3391 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3392 pass
3393
3394 # Video.js embed
3395 mobj = re.search(
3396 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3397 webpage)
3398 if mobj is not None:
3399 sources = self._parse_json(
3400 mobj.group(1), video_id, transform_source=js_to_json,
3401 fatal=False) or []
3402 if not isinstance(sources, list):
3403 sources = [sources]
3404 formats = []
3405 for source in sources:
3406 src = source.get('src')
3407 if not src or not isinstance(src, compat_str):
3408 continue
3409 src = compat_urlparse.urljoin(url, src)
3410 src_type = source.get('type')
3411 if isinstance(src_type, compat_str):
3412 src_type = src_type.lower()
3413 ext = determine_ext(src).lower()
3414 if src_type == 'video/youtube':
3415 return self.url_result(src, YoutubeIE.ie_key())
3416 if src_type == 'application/dash+xml' or ext == 'mpd':
3417 formats.extend(self._extract_mpd_formats(
3418 src, video_id, mpd_id='dash', fatal=False))
3419 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3420 formats.extend(self._extract_m3u8_formats(
3421 src, video_id, 'mp4', entry_protocol='m3u8_native',
3422 m3u8_id='hls', fatal=False))
3423 else:
3424 formats.append({
3425 'url': src,
3426 'ext': (mimetype2ext(src_type)
3427 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3428 })
3429 if formats:
3430 self._sort_formats(formats)
3431 info_dict['formats'] = formats
3432 return info_dict
3433
3434 # Looking for http://schema.org/VideoObject
3435 json_ld = self._search_json_ld(
3436 webpage, video_id, default={}, expected_type='VideoObject')
3437 if json_ld.get('url'):
3438 return merge_dicts(json_ld, info_dict)
3439
3440 def check_video(vurl):
3441 if YoutubeIE.suitable(vurl):
3442 return True
3443 if RtmpIE.suitable(vurl):
3444 return True
3445 vpath = compat_urlparse.urlparse(vurl).path
3446 vext = determine_ext(vpath)
3447 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3448
3449 def filter_video(urls):
3450 return list(filter(check_video, urls))
3451
3452 # Start with something easy: JW Player in SWFObject
3453 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3454 if not found:
3455 # Look for gorilla-vid style embedding
3456 found = filter_video(re.findall(r'''(?sx)
3457 (?:
3458 jw_plugins|
3459 JWPlayerOptions|
3460 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3461 )
3462 .*?
3463 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3464 if not found:
3465 # Broaden the search a little bit
3466 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3467 if not found:
3468 # Broaden the findall a little bit: JWPlayer JS loader
3469 found = filter_video(re.findall(
3470 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3471 if not found:
3472 # Flow player
3473 found = filter_video(re.findall(r'''(?xs)
3474 flowplayer\("[^"]+",\s*
3475 \{[^}]+?\}\s*,
3476 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3477 ["']?url["']?\s*:\s*["']([^"']+)["']
3478 ''', webpage))
3479 if not found:
3480 # Cinerama player
3481 found = re.findall(
3482 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3483 if not found:
3484 # Try to find twitter cards info
3485 # twitter:player:stream should be checked before twitter:player since
3486 # it is expected to contain a raw stream (see
3487 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3488 found = filter_video(re.findall(
3489 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3490 if not found:
3491 # We look for Open Graph info:
3492 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3493 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3494 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3495 if m_video_type is not None:
3496 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3497 if not found:
3498 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3499 found = re.search(
3500 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3501 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3502 webpage)
3503 if not found:
3504 # Look also in Refresh HTTP header
3505 refresh_header = head_response.headers.get('Refresh')
3506 if refresh_header:
3507 # In python 2 response HTTP headers are bytestrings
3508 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3509 refresh_header = refresh_header.decode('iso-8859-1')
3510 found = re.search(REDIRECT_REGEX, refresh_header)
3511 if found:
3512 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3513 if new_url != url:
3514 self.report_following_redirect(new_url)
3515 return {
3516 '_type': 'url',
3517 'url': new_url,
3518 }
3519 else:
3520 found = None
3521
3522 if not found:
3523 # twitter:player is a https URL to iframe player that may or may not
3524 # be supported by youtube-dlc thus this is checked the very last (see
3525 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3526 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3527 if embed_url and embed_url != url:
3528 return self.url_result(embed_url)
3529
3530 if not found:
3531 raise UnsupportedError(url)
3532
3533 entries = []
3534 for video_url in orderedSet(found):
3535 video_url = unescapeHTML(video_url)
3536 video_url = video_url.replace('\\/', '/')
3537 video_url = compat_urlparse.urljoin(url, video_url)
3538 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3539
3540 # Sometimes, jwplayer extraction will result in a YouTube URL
3541 if YoutubeIE.suitable(video_url):
3542 entries.append(self.url_result(video_url, 'Youtube'))
3543 continue
3544
3545 # here's a fun little line of code for you:
3546 video_id = os.path.splitext(video_id)[0]
3547
3548 entry_info_dict = {
3549 'id': video_id,
3550 'uploader': video_uploader,
3551 'title': video_title,
3552 'age_limit': age_limit,
3553 }
3554
3555 if RtmpIE.suitable(video_url):
3556 entry_info_dict.update({
3557 '_type': 'url_transparent',
3558 'ie_key': RtmpIE.ie_key(),
3559 'url': video_url,
3560 })
3561 entries.append(entry_info_dict)
3562 continue
3563
3564 ext = determine_ext(video_url)
3565 if ext == 'smil':
3566 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3567 elif ext == 'xspf':
3568 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3569 elif ext == 'm3u8':
3570 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3571 elif ext == 'mpd':
3572 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3573 elif ext == 'f4m':
3574 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3575 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3576 # Just matching .ism/manifest is not enough to be reliably sure
3577 # whether it's actually an ISM manifest or some other streaming
3578 # manifest since there are various streaming URL formats
3579 # possible (see [1]) as well as some other shenanigans like
3580 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3581 # so on.
3582 # Thus the most reasonable way to solve this is to delegate
3583 # to generic extractor in order to look into the contents of
3584 # the manifest itself.
3585 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3586 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3587 entry_info_dict = self.url_result(
3588 smuggle_url(video_url, {'to_generic': True}),
3589 GenericIE.ie_key())
3590 else:
3591 entry_info_dict['url'] = video_url
3592
3593 if entry_info_dict.get('formats'):
3594 self._sort_formats(entry_info_dict['formats'])
3595
3596 entries.append(entry_info_dict)
3597
3598 if len(entries) == 1:
3599 return entries[0]
3600 else:
3601 for num, e in enumerate(entries, start=1):
3602 # 'url' results don't have a title
3603 if e.get('title') is not None:
3604 e['title'] = '%s (%d)' % (e['title'], num)
3605 return {
3606 '_type': 'playlist',
3607 'entries': entries,
3608 }