]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Prepare new version
[youtubedl] / youtube_dl / 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 is_html,
24 js_to_json,
25 KNOWN_EXTENSIONS,
26 merge_dicts,
27 mimetype2ext,
28 orderedSet,
29 sanitized_Request,
30 smuggle_url,
31 unescapeHTML,
32 unified_strdate,
33 unsmuggle_url,
34 UnsupportedError,
35 xpath_text,
36 )
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
39 BrightcoveLegacyIE,
40 BrightcoveNewIE,
41 )
42 from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45 )
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import (
93 OpenloadIE,
94 VerystreamIE,
95 )
96 from .videopress import VideoPressIE
97 from .rutube import RutubeIE
98 from .limelight import LimelightBaseIE
99 from .anvato import AnvatoIE
100 from .washingtonpost import WashingtonPostIE
101 from .wistia import WistiaIE
102 from .mediaset import MediasetIE
103 from .joj import JojIE
104 from .megaphone import MegaphoneIE
105 from .vzaar import VzaarIE
106 from .channel9 import Channel9IE
107 from .vshare import VShareIE
108 from .mediasite import MediasiteIE
109 from .springboardplatform import SpringboardPlatformIE
110 from .yapfiles import YapFilesIE
111 from .vice import ViceIE
112 from .xfileshare import XFileShareIE
113 from .cloudflarestream import CloudflareStreamIE
114 from .peertube import PeerTubeIE
115 from .teachable import TeachableIE
116 from .indavideo import IndavideoEmbedIE
117 from .apa import APAIE
118 from .foxnews import FoxNewsIE
119 from .viqeo import ViqeoIE
120 from .expressen import ExpressenIE
121 from .zype import ZypeIE
122
123
124 class GenericIE(InfoExtractor):
125 IE_DESC = 'Generic downloader that works on some sites'
126 _VALID_URL = r'.*'
127 IE_NAME = 'generic'
128 _TESTS = [
129 # Direct link to a video
130 {
131 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
132 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
133 'info_dict': {
134 'id': 'trailer',
135 'ext': 'mp4',
136 'title': 'trailer',
137 'upload_date': '20100513',
138 }
139 },
140 # Direct link to media delivered compressed (until Accept-Encoding is *)
141 {
142 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
143 'md5': '128c42e68b13950268b648275386fc74',
144 'info_dict': {
145 'id': 'FictionJunction-Parallel_Hearts',
146 'ext': 'flac',
147 'title': 'FictionJunction-Parallel_Hearts',
148 'upload_date': '20140522',
149 },
150 'expected_warnings': [
151 'URL could be a direct video link, returning it as such.'
152 ],
153 'skip': 'URL invalid',
154 },
155 # Direct download with broken HEAD
156 {
157 'url': 'http://ai-radio.org:8000/radio.opus',
158 'info_dict': {
159 'id': 'radio',
160 'ext': 'opus',
161 'title': 'radio',
162 },
163 'params': {
164 'skip_download': True, # infinite live stream
165 },
166 'expected_warnings': [
167 r'501.*Not Implemented',
168 r'400.*Bad Request',
169 ],
170 },
171 # Direct link with incorrect MIME type
172 {
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'md5': '4ccbebe5f36706d85221f204d7eb5913',
175 'info_dict': {
176 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
177 'id': '5_Lennart_Poettering_-_Systemd',
178 'ext': 'webm',
179 'title': '5_Lennart_Poettering_-_Systemd',
180 'upload_date': '20141120',
181 },
182 'expected_warnings': [
183 'URL could be a direct video link, returning it as such.'
184 ]
185 },
186 # RSS feed
187 {
188 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
189 'info_dict': {
190 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
191 'title': 'Zero Punctuation',
192 'description': 're:.*groundbreaking video review series.*'
193 },
194 'playlist_mincount': 11,
195 },
196 # RSS feed with enclosure
197 {
198 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
199 'info_dict': {
200 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 'ext': 'm4v',
202 'upload_date': '20150228',
203 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
204 }
205 },
206 # RSS feed with enclosures and unsupported link URLs
207 {
208 'url': 'http://www.hellointernet.fm/podcast?format=rss',
209 'info_dict': {
210 'id': 'http://www.hellointernet.fm/podcast?format=rss',
211 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
212 'title': 'Hello Internet',
213 },
214 'playlist_mincount': 100,
215 },
216 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
217 {
218 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
219 'info_dict': {
220 'id': 'smil',
221 'ext': 'mp4',
222 'title': 'Automatics, robotics and biocybernetics',
223 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
224 'upload_date': '20130627',
225 'formats': 'mincount:16',
226 'subtitles': 'mincount:1',
227 },
228 'params': {
229 'force_generic_extractor': True,
230 'skip_download': True,
231 },
232 },
233 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
234 {
235 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
236 'info_dict': {
237 'id': 'hds',
238 'ext': 'flv',
239 'title': 'hds',
240 'formats': 'mincount:1',
241 },
242 'params': {
243 'skip_download': True,
244 },
245 },
246 # SMIL from https://www.restudy.dk/video/play/id/1637
247 {
248 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
249 'info_dict': {
250 'id': 'video_1637',
251 'ext': 'flv',
252 'title': 'video_1637',
253 'formats': 'mincount:3',
254 },
255 'params': {
256 'skip_download': True,
257 },
258 },
259 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
260 {
261 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
262 'info_dict': {
263 'id': 'smil-service',
264 'ext': 'flv',
265 'title': 'smil-service',
266 'formats': 'mincount:1',
267 },
268 'params': {
269 'skip_download': True,
270 },
271 },
272 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
273 {
274 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
275 'info_dict': {
276 'id': '4719370',
277 'ext': 'mp4',
278 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
279 'formats': 'mincount:3',
280 },
281 'params': {
282 'skip_download': True,
283 },
284 },
285 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
286 {
287 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
288 'info_dict': {
289 'id': 'mZlp2ctYIUEB',
290 'ext': 'mp4',
291 'title': 'Tikibad ontruimd wegens brand',
292 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
293 'thumbnail': r're:^https?://.*\.jpg$',
294 'duration': 33,
295 },
296 'params': {
297 'skip_download': True,
298 },
299 },
300 # MPD from http://dash-mse-test.appspot.com/media.html
301 {
302 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
303 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
304 'info_dict': {
305 'id': 'car-20120827-manifest',
306 'ext': 'mp4',
307 'title': 'car-20120827-manifest',
308 'formats': 'mincount:9',
309 'upload_date': '20130904',
310 },
311 'params': {
312 'format': 'bestvideo',
313 },
314 },
315 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
316 {
317 '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',
318 'info_dict': {
319 'id': 'content',
320 'ext': 'mp4',
321 'title': 'content',
322 'formats': 'mincount:8',
323 },
324 'params': {
325 # m3u8 downloads
326 'skip_download': True,
327 },
328 'skip': 'video gone',
329 },
330 # m3u8 served with Content-Type: text/plain
331 {
332 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
333 'info_dict': {
334 'id': 'index',
335 'ext': 'mp4',
336 'title': 'index',
337 'upload_date': '20140720',
338 'formats': 'mincount:11',
339 },
340 'params': {
341 # m3u8 downloads
342 'skip_download': True,
343 },
344 'skip': 'video gone',
345 },
346 # google redirect
347 {
348 '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',
349 'info_dict': {
350 'id': 'cmQHVoWB5FY',
351 'ext': 'mp4',
352 'upload_date': '20130224',
353 'uploader_id': 'TheVerge',
354 'description': r're:^Chris Ziegler takes a look at the\.*',
355 'uploader': 'The Verge',
356 'title': 'First Firefox OS phones side-by-side',
357 },
358 'params': {
359 'skip_download': False,
360 }
361 },
362 {
363 # redirect in Refresh HTTP header
364 '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',
365 'info_dict': {
366 'id': 'pO8h3EaFRdo',
367 'ext': 'mp4',
368 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
369 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
370 'upload_date': '20150917',
371 'uploader_id': 'brtvofficial',
372 'uploader': 'Boiler Room',
373 },
374 'params': {
375 'skip_download': False,
376 },
377 },
378 {
379 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
380 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
381 'info_dict': {
382 'id': '13601338388002',
383 'ext': 'mp4',
384 'uploader': 'www.hodiho.fr',
385 'title': 'R\u00e9gis plante sa Jeep',
386 }
387 },
388 # bandcamp page with custom domain
389 {
390 'add_ie': ['Bandcamp'],
391 'url': 'http://bronyrock.com/track/the-pony-mash',
392 'info_dict': {
393 'id': '3235767654',
394 'ext': 'mp3',
395 'title': 'The Pony Mash',
396 'uploader': 'M_Pallante',
397 },
398 'skip': 'There is a limit of 200 free downloads / month for the test song',
399 },
400 {
401 # embedded brightcove video
402 # it also tests brightcove videos that need to set the 'Referer'
403 # in the http requests
404 'add_ie': ['BrightcoveLegacy'],
405 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
406 'info_dict': {
407 'id': '2765128793001',
408 'ext': 'mp4',
409 'title': 'Le cours de bourse : lā€™analyse technique',
410 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
411 'uploader': 'BFM BUSINESS',
412 },
413 'params': {
414 'skip_download': True,
415 },
416 },
417 {
418 # embedded with itemprop embedURL and video id spelled as `idVideo`
419 'add_id': ['BrightcoveLegacy'],
420 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
421 'info_dict': {
422 'id': '5255628253001',
423 'ext': 'mp4',
424 'title': 'md5:37c519b1128915607601e75a87995fc0',
425 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
426 'uploader': 'BFM BUSINESS',
427 'uploader_id': '876450612001',
428 'timestamp': 1482255315,
429 'upload_date': '20161220',
430 },
431 'params': {
432 'skip_download': True,
433 },
434 },
435 {
436 # https://github.com/ytdl-org/youtube-dl/issues/2253
437 'url': 'http://bcove.me/i6nfkrc3',
438 'md5': '0ba9446db037002366bab3b3eb30c88c',
439 'info_dict': {
440 'id': '3101154703001',
441 'ext': 'mp4',
442 'title': 'Still no power',
443 'uploader': 'thestar.com',
444 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
445 },
446 'add_ie': ['BrightcoveLegacy'],
447 'skip': 'video gone',
448 },
449 {
450 'url': 'http://www.championat.com/video/football/v/87/87499.html',
451 'md5': 'fb973ecf6e4a78a67453647444222983',
452 'info_dict': {
453 'id': '3414141473001',
454 'ext': 'mp4',
455 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
456 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
457 'uploader': 'Championat',
458 },
459 },
460 {
461 # https://github.com/ytdl-org/youtube-dl/issues/3541
462 'add_ie': ['BrightcoveLegacy'],
463 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
464 'info_dict': {
465 'id': '3866516442001',
466 'ext': 'mp4',
467 'title': 'Leer mij vrouwen kennen: Aflevering 1',
468 'description': 'Leer mij vrouwen kennen: Aflevering 1',
469 'uploader': 'SBS Broadcasting',
470 },
471 'skip': 'Restricted to Netherlands',
472 'params': {
473 'skip_download': True, # m3u8 download
474 },
475 },
476 {
477 # Brightcove video in <iframe>
478 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
479 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
480 'info_dict': {
481 'id': '5360463607001',
482 'ext': 'mp4',
483 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
484 'description': 'č”åˆå›½å„æē«„åŸŗ金会äø­äøœå’ŒåŒ—非åŒŗ域大ä½æć€ä½œę›²å®¶ę‰Žå¾·Ā·čæŖę‹‰å°¼ļ¼ˆZade Diraniļ¼‰åœØ3꜈15ę—„å™åˆ©äŗšå†²ēŖēˆ†å‘7å‘Ø幓ēŗŖåæµę—„之际发åøƒäŗ†äøŗ叙利äŗšč°±å†™ēš„ę­Œę›²ć€Šåæƒč·³ć€‹ļ¼ˆHEARTBEATļ¼‰ļ¼Œäøŗ受到六幓冲ēŖå½±å“ēš„叙利äŗšå„æē«„发å‡ŗå¼ŗēƒˆå‘å–Šļ¼Œå‘¼åäø–ē•Œåšå‡ŗ共同åŠŖ力ļ¼Œä½æ叙利äŗšå„æē«„é‡ę–°čŽ·å¾—äŗ«ęœ‰ę­£åøøē«„幓ē”Ÿę“»ēš„ęƒåˆ©ć€‚',
485 'uploader': 'United Nations',
486 'uploader_id': '1362235914001',
487 'timestamp': 1489593889,
488 'upload_date': '20170315',
489 },
490 'add_ie': ['BrightcoveLegacy'],
491 },
492 {
493 # Brightcove with alternative playerID key
494 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
495 'info_dict': {
496 'id': 'nmeth.2062_SV1',
497 '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',
498 },
499 'playlist': [{
500 'info_dict': {
501 'id': '2228375078001',
502 'ext': 'mp4',
503 'title': 'nmeth.2062-sv1',
504 'description': 'nmeth.2062-sv1',
505 'timestamp': 1363357591,
506 'upload_date': '20130315',
507 'uploader': 'Nature Publishing Group',
508 'uploader_id': '1964492299001',
509 },
510 }],
511 },
512 {
513 # Brightcove with UUID in videoPlayer
514 'url': 'http://www8.hp.com/cn/zh/home.html',
515 'info_dict': {
516 'id': '5255815316001',
517 'ext': 'mp4',
518 'title': 'Sprocket Video - China',
519 'description': 'Sprocket Video - China',
520 'uploader': 'HP-Video Gallery',
521 'timestamp': 1482263210,
522 'upload_date': '20161220',
523 'uploader_id': '1107601872001',
524 },
525 'params': {
526 'skip_download': True, # m3u8 download
527 },
528 'skip': 'video rotates...weekly?',
529 },
530 {
531 # Brightcove:new type [2].
532 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
533 'md5': '2b35148fcf48da41c9fb4591650784f3',
534 'info_dict': {
535 'id': '5348741021001',
536 'ext': 'mp4',
537 'upload_date': '20170306',
538 'uploader_id': '4191638492001',
539 'timestamp': 1488769918,
540 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
541
542 },
543 },
544 {
545 # Alternative brightcove <video> attributes
546 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
547 'info_dict': {
548 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
549 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
550 },
551 'playlist': [{
552 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
553 'info_dict': {
554 'id': '5311302538001',
555 'ext': 'mp4',
556 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
557 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
558 'timestamp': 1486321708,
559 'upload_date': '20170205',
560 'uploader_id': '800000640001',
561 },
562 'only_matching': True,
563 }],
564 },
565 {
566 # Brightcove with UUID in videoPlayer
567 'url': 'http://www8.hp.com/cn/zh/home.html',
568 'info_dict': {
569 'id': '5255815316001',
570 'ext': 'mp4',
571 'title': 'Sprocket Video - China',
572 'description': 'Sprocket Video - China',
573 'uploader': 'HP-Video Gallery',
574 'timestamp': 1482263210,
575 'upload_date': '20161220',
576 'uploader_id': '1107601872001',
577 },
578 'params': {
579 'skip_download': True, # m3u8 download
580 },
581 },
582 # ooyala video
583 {
584 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
585 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
586 'info_dict': {
587 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
588 'ext': 'mp4',
589 'title': '2cc213299525360.mov', # that's what we get
590 'duration': 238.231,
591 },
592 'add_ie': ['Ooyala'],
593 },
594 {
595 # ooyala video embedded with http://player.ooyala.com/iframe.js
596 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
597 'info_dict': {
598 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
599 'ext': 'mp4',
600 'title': '"Steve Jobs: Man in the Machine" trailer',
601 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
602 'duration': 135.427,
603 },
604 'params': {
605 'skip_download': True,
606 },
607 'skip': 'movie expired',
608 },
609 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
610 {
611 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
612 'info_dict': {
613 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
614 'ext': 'mp4',
615 'title': 'Steampunk Fest Comes to Honesdale',
616 'duration': 43.276,
617 },
618 'params': {
619 'skip_download': True,
620 }
621 },
622 # embed.ly video
623 {
624 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
625 'info_dict': {
626 'id': '9ODmcdjQcHQ',
627 'ext': 'mp4',
628 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
629 'upload_date': '20140225',
630 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
631 'uploader': 'Tested',
632 'uploader_id': 'testedcom',
633 },
634 # No need to test YoutubeIE here
635 'params': {
636 'skip_download': True,
637 },
638 },
639 # funnyordie embed
640 {
641 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
642 'info_dict': {
643 'id': '18e820ec3f',
644 'ext': 'mp4',
645 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
646 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
647 },
648 # HEAD requests lead to endless 301, while GET is OK
649 'expected_warnings': ['301'],
650 },
651 # RUTV embed
652 {
653 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
654 'info_dict': {
655 'id': '776940',
656 'ext': 'mp4',
657 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
658 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
659 },
660 'params': {
661 # m3u8 download
662 'skip_download': True,
663 },
664 },
665 # TVC embed
666 {
667 '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/',
668 'info_dict': {
669 'id': '55304',
670 'ext': 'mp4',
671 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
672 },
673 },
674 # SportBox embed
675 {
676 'url': 'http://www.vestifinance.ru/articles/25753',
677 'info_dict': {
678 'id': '25753',
679 'title': 'ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
680 },
681 'playlist': [{
682 'info_dict': {
683 'id': '370908',
684 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
685 'ext': 'mp4',
686 }
687 }, {
688 'info_dict': {
689 'id': '370905',
690 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
691 'ext': 'mp4',
692 }
693 }, {
694 'info_dict': {
695 'id': '370902',
696 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
697 'ext': 'mp4',
698 }
699 }],
700 'params': {
701 # m3u8 download
702 'skip_download': True,
703 },
704 },
705 # Myvi.ru embed
706 {
707 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
708 'info_dict': {
709 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
710 'ext': 'mp4',
711 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
712 'thumbnail': r're:^https?://.*\.jpg$',
713 'duration': 153,
714 }
715 },
716 # XHamster embed
717 {
718 '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',
719 'info_dict': {
720 'id': 'showthread',
721 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
722 },
723 'playlist_mincount': 7,
724 # This forum does not allow <iframe> syntaxes anymore
725 # Now HTML tags are displayed as-is
726 'skip': 'No videos on this page',
727 },
728 # Embedded TED video
729 {
730 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
731 'md5': '65fdff94098e4a607385a60c5177c638',
732 'info_dict': {
733 'id': '1969',
734 'ext': 'mp4',
735 'title': 'Hidden miracles of the natural world',
736 'uploader': 'Louie Schwartzberg',
737 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
738 }
739 },
740 # nowvideo embed hidden behind percent encoding
741 {
742 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
743 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
744 'info_dict': {
745 'id': '06e53103ca9aa',
746 'ext': 'flv',
747 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
748 'description': 'No description',
749 },
750 },
751 # arte embed
752 {
753 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
754 'md5': '7653032cbb25bf6c80d80f217055fa43',
755 'info_dict': {
756 'id': '048195-004_PLUS7-F',
757 'ext': 'flv',
758 'title': 'X:enius',
759 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
760 'upload_date': '20140320',
761 },
762 'params': {
763 'skip_download': 'Requires rtmpdump'
764 },
765 'skip': 'video gone',
766 },
767 # francetv embed
768 {
769 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
770 'info_dict': {
771 'id': 'EV_30231',
772 'ext': 'mp4',
773 'title': 'Alcaline, le concert avec Calogero',
774 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
775 'upload_date': '20150226',
776 'timestamp': 1424989860,
777 'duration': 5400,
778 },
779 'params': {
780 # m3u8 downloads
781 'skip_download': True,
782 },
783 'expected_warnings': [
784 'Forbidden'
785 ]
786 },
787 # CondƩ Nast embed
788 {
789 'url': 'http://www.wired.com/2014/04/honda-asimo/',
790 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
791 'info_dict': {
792 'id': '53501be369702d3275860000',
793 'ext': 'mp4',
794 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
795 }
796 },
797 # Dailymotion embed
798 {
799 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
800 'md5': '441aeeb82eb72c422c7f14ec533999cd',
801 'info_dict': {
802 'id': 'k2mm4bCdJ6CQ2i7c8o2',
803 'ext': 'mp4',
804 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
805 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
806 'uploader': 'Spi0n',
807 'uploader_id': 'xgditw',
808 'upload_date': '20140425',
809 'timestamp': 1398441542,
810 },
811 'add_ie': ['Dailymotion'],
812 },
813 # DailyMail embed
814 {
815 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
816 'info_dict': {
817 'id': '1495629',
818 'ext': 'mp4',
819 'title': 'Care worker punches elderly dementia patient in head 11 times',
820 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
821 },
822 'add_ie': ['DailyMail'],
823 'params': {
824 'skip_download': True,
825 },
826 },
827 # YouTube embed
828 {
829 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
830 'info_dict': {
831 'id': 'FXRb4ykk4S0',
832 'ext': 'mp4',
833 'title': 'The NBL Auction 2014',
834 'uploader': 'BADMINTON England',
835 'uploader_id': 'BADMINTONEvents',
836 'upload_date': '20140603',
837 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
838 },
839 'add_ie': ['Youtube'],
840 'params': {
841 'skip_download': True,
842 }
843 },
844 # MTVSercices embed
845 {
846 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
847 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
848 'info_dict': {
849 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
850 'ext': 'mp4',
851 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
852 'description': 'Two valets share their love for movie star Liam Neesons.',
853 'timestamp': 1349922600,
854 'upload_date': '20121011',
855 },
856 },
857 # YouTube embed via <data-embed-url="">
858 {
859 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
860 'info_dict': {
861 'id': '4vAffPZIT44',
862 'ext': 'mp4',
863 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
864 'uploader': 'Gameloft',
865 'uploader_id': 'gameloft',
866 'upload_date': '20140828',
867 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
868 },
869 'params': {
870 'skip_download': True,
871 }
872 },
873 # YouTube <object> embed
874 {
875 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
876 'md5': '516718101ec834f74318df76259fb3cc',
877 'info_dict': {
878 'id': 'msN87y-iEx0',
879 'ext': 'webm',
880 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
881 'upload_date': '20080526',
882 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
883 'uploader': 'Christopher Sykes',
884 'uploader_id': 'ChristopherJSykes',
885 },
886 'add_ie': ['Youtube'],
887 },
888 # Camtasia studio
889 {
890 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
891 'playlist': [{
892 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
893 'info_dict': {
894 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
895 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
896 'ext': 'flv',
897 'duration': 2235.90,
898 }
899 }, {
900 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
901 'info_dict': {
902 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
903 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
904 'ext': 'flv',
905 'duration': 2235.93,
906 }
907 }],
908 'info_dict': {
909 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
910 }
911 },
912 # Flowplayer
913 {
914 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
915 'md5': '9d65602bf31c6e20014319c7d07fba27',
916 'info_dict': {
917 'id': '5123ea6d5e5a7',
918 'ext': 'mp4',
919 'age_limit': 18,
920 'uploader': 'www.handjobhub.com',
921 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
922 }
923 },
924 # Multiple brightcove videos
925 # https://github.com/ytdl-org/youtube-dl/issues/2283
926 {
927 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
928 'info_dict': {
929 'id': 'always-never',
930 'title': 'Always / Never - The New Yorker',
931 },
932 'playlist_count': 3,
933 'params': {
934 'extract_flat': False,
935 'skip_download': True,
936 }
937 },
938 # MLB embed
939 {
940 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
941 'md5': '96f09a37e44da40dd083e12d9a683327',
942 'info_dict': {
943 'id': '33322633',
944 'ext': 'mp4',
945 'title': 'Ump changes call to ball',
946 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
947 'duration': 48,
948 'timestamp': 1401537900,
949 'upload_date': '20140531',
950 'thumbnail': r're:^https?://.*\.jpg$',
951 },
952 },
953 # Wistia embed
954 {
955 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
956 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
957 'info_dict': {
958 'id': '6e2wtrbdaf',
959 'ext': 'mov',
960 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
961 'description': 'a Paywall Videos video from Remilon',
962 'duration': 644.072,
963 'uploader': 'study.com',
964 'timestamp': 1459678540,
965 'upload_date': '20160403',
966 'filesize': 24687186,
967 },
968 },
969 {
970 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
971 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
972 'info_dict': {
973 'id': 'uxjb0lwrcz',
974 'ext': 'mp4',
975 'title': 'Conversation about Hexagonal Rails Part 1',
976 'description': 'a Martin Fowler video from ThoughtWorks',
977 'duration': 1715.0,
978 'uploader': 'thoughtworks.wistia.com',
979 'timestamp': 1401832161,
980 'upload_date': '20140603',
981 },
982 },
983 # Wistia standard embed (async)
984 {
985 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
986 'info_dict': {
987 'id': '807fafadvk',
988 'ext': 'mp4',
989 'title': 'Drip Brennan Dunn Workshop',
990 'description': 'a JV Webinars video from getdrip-1',
991 'duration': 4986.95,
992 'timestamp': 1463607249,
993 'upload_date': '20160518',
994 },
995 'params': {
996 'skip_download': True,
997 }
998 },
999 # Soundcloud embed
1000 {
1001 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1002 'info_dict': {
1003 'id': '174391317',
1004 'ext': 'mp3',
1005 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1006 'uploader': 'Sophos Security',
1007 'title': 'Chet Chat 171 - Oct 29, 2014',
1008 'upload_date': '20141029',
1009 }
1010 },
1011 # Soundcloud multiple embeds
1012 {
1013 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1014 'info_dict': {
1015 'id': '52809',
1016 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
1017 },
1018 'playlist_mincount': 7,
1019 },
1020 # TuneIn station embed
1021 {
1022 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1023 'info_dict': {
1024 'id': '204146',
1025 'ext': 'mp3',
1026 'title': 'CNRV',
1027 'location': 'Paris, France',
1028 'is_live': True,
1029 },
1030 'params': {
1031 # Live stream
1032 'skip_download': True,
1033 },
1034 },
1035 # Livestream embed
1036 {
1037 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1038 'info_dict': {
1039 'id': '67864563',
1040 'ext': 'flv',
1041 'upload_date': '20141112',
1042 'title': 'Rosetta #CometLanding webcast HL 10',
1043 }
1044 },
1045 # Another Livestream embed, without 'new.' in URL
1046 {
1047 'url': 'https://www.freespeech.org/',
1048 'info_dict': {
1049 'id': '123537347',
1050 'ext': 'mp4',
1051 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1052 },
1053 'params': {
1054 # Live stream
1055 'skip_download': True,
1056 },
1057 },
1058 # LazyYT
1059 {
1060 'url': 'https://skiplagged.com/',
1061 'info_dict': {
1062 'id': 'skiplagged',
1063 'title': 'Skiplagged: The smart way to find cheap flights',
1064 },
1065 'playlist_mincount': 1,
1066 'add_ie': ['Youtube'],
1067 },
1068 # Cinchcast embed
1069 {
1070 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1071 'info_dict': {
1072 'id': '7141703',
1073 'ext': 'mp3',
1074 'upload_date': '20141126',
1075 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1076 }
1077 },
1078 # Cinerama player
1079 {
1080 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1081 'info_dict': {
1082 'id': '730m_DandD_1901_512k',
1083 'ext': 'mp4',
1084 'uploader': 'www.abc.net.au',
1085 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1086 }
1087 },
1088 # embedded viddler video
1089 {
1090 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1091 'info_dict': {
1092 'id': '4d03aad9',
1093 'ext': 'mp4',
1094 'uploader': 'deadspin',
1095 'title': 'WALL-TO-GORTAT',
1096 'timestamp': 1422285291,
1097 'upload_date': '20150126',
1098 },
1099 'add_ie': ['Viddler'],
1100 },
1101 # Libsyn embed
1102 {
1103 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1104 'info_dict': {
1105 'id': '3377616',
1106 'ext': 'mp3',
1107 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1108 'description': 'md5:601cb790edd05908957dae8aaa866465',
1109 'upload_date': '20150220',
1110 },
1111 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1112 },
1113 # jwplayer YouTube
1114 {
1115 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1116 'info_dict': {
1117 'id': 'Mrj4DVp2zeA',
1118 'ext': 'mp4',
1119 'upload_date': '20150212',
1120 'uploader': 'The National Archives UK',
1121 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1122 'uploader_id': 'NationalArchives08',
1123 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1124 },
1125 },
1126 # jwplayer rtmp
1127 {
1128 'url': 'http://www.suffolk.edu/sjc/live.php',
1129 'info_dict': {
1130 'id': 'live',
1131 'ext': 'flv',
1132 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1133 'uploader': 'www.suffolk.edu',
1134 },
1135 'params': {
1136 'skip_download': True,
1137 },
1138 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1139 },
1140 # Complex jwplayer
1141 {
1142 'url': 'http://www.indiedb.com/games/king-machine/videos',
1143 'info_dict': {
1144 'id': 'videos',
1145 'ext': 'mp4',
1146 'title': 'king machine trailer 1',
1147 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1148 'thumbnail': r're:^https?://.*\.jpg$',
1149 },
1150 },
1151 {
1152 # JWPlayer config passed as variable
1153 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1154 'info_dict': {
1155 'id': '3326530_hq',
1156 'ext': 'mp4',
1157 'title': 'ARIELE | Tube Cup',
1158 'uploader': 'www.txxx.com',
1159 'age_limit': 18,
1160 },
1161 'params': {
1162 'skip_download': True,
1163 }
1164 },
1165 {
1166 # JWPlatform iframe
1167 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1168 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1169 'info_dict': {
1170 'id': 'O0c5JcKT',
1171 'ext': 'mp4',
1172 'upload_date': '20171122',
1173 'timestamp': 1511366290,
1174 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1175 },
1176 'add_ie': [JWPlatformIE.ie_key()],
1177 },
1178 {
1179 # Video.js embed, multiple formats
1180 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1181 'info_dict': {
1182 'id': 'yygqldloqIk',
1183 'ext': 'mp4',
1184 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1185 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1186 'upload_date': '20130314',
1187 'uploader': 'PROстŠ¾Šµ3D',
1188 'uploader_id': 'PROstoe3D',
1189 },
1190 'params': {
1191 'skip_download': True,
1192 },
1193 },
1194 {
1195 # Video.js embed, single format
1196 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1197 'info_dict': {
1198 'id': 'watch',
1199 'ext': 'mp4',
1200 'title': 'Step 1 - Good Foundation',
1201 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1202 },
1203 'params': {
1204 'skip_download': True,
1205 },
1206 },
1207 # rtl.nl embed
1208 {
1209 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1210 'playlist_mincount': 5,
1211 'info_dict': {
1212 'id': 'aanslagen-kopenhagen',
1213 'title': 'Aanslagen Kopenhagen',
1214 }
1215 },
1216 # Zapiks embed
1217 {
1218 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1219 'info_dict': {
1220 'id': '118046',
1221 'ext': 'mp4',
1222 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1223 }
1224 },
1225 # Kaltura embed (different embed code)
1226 {
1227 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1228 'info_dict': {
1229 'id': '1_a52wc67y',
1230 'ext': 'flv',
1231 'upload_date': '20150127',
1232 'uploader_id': 'PremierMedia',
1233 'timestamp': int,
1234 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1235 },
1236 },
1237 # Kaltura embed with single quotes
1238 {
1239 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1240 'info_dict': {
1241 'id': '0_izeg5utt',
1242 'ext': 'mp4',
1243 'title': '35871',
1244 'timestamp': 1355743100,
1245 'upload_date': '20121217',
1246 'uploader_id': 'cplapp@learn360.com',
1247 },
1248 'add_ie': ['Kaltura'],
1249 },
1250 {
1251 # Kaltura embedded via quoted entry_id
1252 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1253 'info_dict': {
1254 'id': '0_utuok90b',
1255 'ext': 'mp4',
1256 'title': '06_matthew_brender_raj_dutt',
1257 'timestamp': 1466638791,
1258 'upload_date': '20160622',
1259 },
1260 'add_ie': ['Kaltura'],
1261 'expected_warnings': [
1262 'Could not send HEAD request'
1263 ],
1264 'params': {
1265 'skip_download': True,
1266 }
1267 },
1268 {
1269 # Kaltura embedded, some fileExt broken (#11480)
1270 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1271 'info_dict': {
1272 'id': '1_sgtvehim',
1273 'ext': 'mp4',
1274 'title': 'Our "Standard Models" of particle physics and cosmology',
1275 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1276 'timestamp': 1321158993,
1277 'upload_date': '20111113',
1278 'uploader_id': 'kps1',
1279 },
1280 'add_ie': ['Kaltura'],
1281 },
1282 {
1283 # Kaltura iframe embed
1284 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1285 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1286 'info_dict': {
1287 'id': '0_f2cfbpwy',
1288 'ext': 'mp4',
1289 'title': 'I. M. Pei: A Centennial Celebration',
1290 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1291 'upload_date': '20170403',
1292 'uploader_id': 'batchUser',
1293 'timestamp': 1491232186,
1294 },
1295 'add_ie': ['Kaltura'],
1296 },
1297 {
1298 # Kaltura iframe embed, more sophisticated
1299 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1300 'info_dict': {
1301 'id': '1_9gzouybz',
1302 'ext': 'mp4',
1303 'title': 'lecture-05sep2017',
1304 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1305 'upload_date': '20170913',
1306 'uploader_id': 'eps2',
1307 'timestamp': 1505340777,
1308 },
1309 'params': {
1310 'skip_download': True,
1311 },
1312 'add_ie': ['Kaltura'],
1313 },
1314 {
1315 # meta twitter:player
1316 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1317 'info_dict': {
1318 'id': '0_01b42zps',
1319 'ext': 'mp4',
1320 'title': 'Main Twerk (Video)',
1321 'upload_date': '20171208',
1322 'uploader_id': 'sebastian.salinas@thechive.com',
1323 'timestamp': 1512713057,
1324 },
1325 'params': {
1326 'skip_download': True,
1327 },
1328 'add_ie': ['Kaltura'],
1329 },
1330 # referrer protected EaglePlatform embed
1331 {
1332 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1333 'info_dict': {
1334 'id': '582306',
1335 'ext': 'mp4',
1336 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1337 'thumbnail': r're:^https?://.*\.jpg$',
1338 'duration': 3382,
1339 'view_count': int,
1340 },
1341 'params': {
1342 'skip_download': True,
1343 },
1344 },
1345 # ClipYou (EaglePlatform) embed (custom URL)
1346 {
1347 'url': 'http://muz-tv.ru/play/7129/',
1348 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1349 'info_dict': {
1350 'id': '12820',
1351 'ext': 'mp4',
1352 'title': "'O Sole Mio",
1353 'thumbnail': r're:^https?://.*\.jpg$',
1354 'duration': 216,
1355 'view_count': int,
1356 },
1357 'params': {
1358 'skip_download': True,
1359 },
1360 'skip': 'This video is unavailable.',
1361 },
1362 # Pladform embed
1363 {
1364 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1365 'info_dict': {
1366 'id': '100183293',
1367 'ext': 'mp4',
1368 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1369 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1370 'thumbnail': r're:^https?://.*\.jpg$',
1371 'duration': 694,
1372 'age_limit': 0,
1373 },
1374 'skip': 'HTTP Error 404: Not Found',
1375 },
1376 # Playwire embed
1377 {
1378 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1379 'info_dict': {
1380 'id': '3519514',
1381 'ext': 'mp4',
1382 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1383 'thumbnail': r're:^https?://.*\.png$',
1384 'duration': 45.115,
1385 },
1386 },
1387 # 5min embed
1388 {
1389 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1390 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1391 'info_dict': {
1392 'id': '518726732',
1393 'ext': 'mp4',
1394 'title': 'Facebook Creates "On This Day" | Crunch Report',
1395 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1396 'timestamp': 1427237531,
1397 'uploader': 'Crunch Report',
1398 'upload_date': '20150324',
1399 },
1400 'params': {
1401 # m3u8 download
1402 'skip_download': True,
1403 },
1404 },
1405 # Crooks and Liars embed
1406 {
1407 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1408 'info_dict': {
1409 'id': '8RUoRhRi',
1410 'ext': 'mp4',
1411 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1412 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1413 'timestamp': 1428207000,
1414 'upload_date': '20150405',
1415 'uploader': 'Heather',
1416 },
1417 },
1418 # Crooks and Liars external embed
1419 {
1420 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1421 'info_dict': {
1422 'id': 'MTE3MjUtMzQ2MzA',
1423 'ext': 'mp4',
1424 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1425 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1426 'timestamp': 1265032391,
1427 'upload_date': '20100201',
1428 'uploader': 'Heather',
1429 },
1430 },
1431 # NBC Sports vplayer embed
1432 {
1433 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1434 'info_dict': {
1435 'id': 'ln7x1qSThw4k',
1436 'ext': 'flv',
1437 'title': "PFT Live: New leader in the 'new-look' defense",
1438 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1439 'uploader': 'NBCU-SPORTS',
1440 'upload_date': '20140107',
1441 'timestamp': 1389118457,
1442 },
1443 'skip': 'Invalid Page URL',
1444 },
1445 # NBC News embed
1446 {
1447 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1448 'md5': '1aa589c675898ae6d37a17913cf68d66',
1449 'info_dict': {
1450 'id': 'x_dtl_oa_LettermanliftPR_160608',
1451 'ext': 'mp4',
1452 'title': 'David Letterman: A Preview',
1453 '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.',
1454 'upload_date': '20160609',
1455 'timestamp': 1465431544,
1456 'uploader': 'NBCU-NEWS',
1457 },
1458 },
1459 # UDN embed
1460 {
1461 'url': 'https://video.udn.com/news/300346',
1462 'md5': 'fd2060e988c326991037b9aff9df21a6',
1463 'info_dict': {
1464 'id': '300346',
1465 'ext': 'mp4',
1466 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1467 'thumbnail': r're:^https?://.*\.jpg$',
1468 },
1469 'params': {
1470 # m3u8 download
1471 'skip_download': True,
1472 },
1473 'expected_warnings': ['Failed to parse JSON Expecting value'],
1474 },
1475 # Brightcove URL in single quotes
1476 {
1477 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1478 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1479 'info_dict': {
1480 'id': '4255764656001',
1481 'ext': 'mp4',
1482 'title': 'SN Presents: Russell Martin, World Citizen',
1483 'description': 'To understand why he was the Toronto Blue Jaysā€™ 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.',
1484 'uploader': 'Rogers Sportsnet',
1485 'uploader_id': '1704050871',
1486 'upload_date': '20150525',
1487 'timestamp': 1432570283,
1488 },
1489 },
1490 # OnionStudios embed
1491 {
1492 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'info_dict': {
1494 'id': '2855',
1495 'ext': 'mp4',
1496 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1497 'thumbnail': r're:^https?://.*\.jpe?g$',
1498 'uploader': 'ClickHole',
1499 'uploader_id': 'clickhole',
1500 }
1501 },
1502 # SnagFilms embed
1503 {
1504 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1505 'info_dict': {
1506 'id': '74849a00-85a9-11e1-9660-123139220831',
1507 'ext': 'mp4',
1508 'title': '#whilewewatch',
1509 }
1510 },
1511 # AdobeTVVideo embed
1512 {
1513 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1514 'md5': '43662b577c018ad707a63766462b1e87',
1515 'info_dict': {
1516 'id': '2456',
1517 'ext': 'mp4',
1518 'title': 'New experience with Acrobat DC',
1519 'description': 'New experience with Acrobat DC',
1520 'duration': 248.667,
1521 },
1522 },
1523 # BrightcoveInPageEmbed embed
1524 {
1525 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1526 'info_dict': {
1527 'id': '4238694884001',
1528 'ext': 'flv',
1529 'title': 'Tabletop: Dread, Last Thoughts',
1530 'description': 'Tabletop: Dread, Last Thoughts',
1531 'duration': 51690,
1532 },
1533 },
1534 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1535 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1536 {
1537 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1538 'info_dict': {
1539 'id': '4785848093001',
1540 'ext': 'mp4',
1541 'title': 'The Cardinal Pell Interview',
1542 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1543 'uploader': 'GlobeCast Australia - GlobeStream',
1544 'uploader_id': '2733773828001',
1545 'upload_date': '20160304',
1546 'timestamp': 1457083087,
1547 },
1548 'params': {
1549 # m3u8 downloads
1550 'skip_download': True,
1551 },
1552 },
1553 {
1554 # Brightcove embed with whitespace around attribute names
1555 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1556 'info_dict': {
1557 'id': '3167554373001',
1558 'ext': 'mp4',
1559 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1560 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1561 'uploader_id': '1079349493',
1562 'upload_date': '20140207',
1563 'timestamp': 1391810548,
1564 },
1565 'params': {
1566 'skip_download': True,
1567 },
1568 },
1569 # Another form of arte.tv embed
1570 {
1571 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1572 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1573 'info_dict': {
1574 'id': '030273-562_PLUS7-F',
1575 'ext': 'mp4',
1576 'title': 'ARTE Reportage - Nulle part, en France',
1577 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1578 'upload_date': '20160409',
1579 },
1580 },
1581 # LiveLeak embed
1582 {
1583 'url': 'http://www.wykop.pl/link/3088787/',
1584 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1585 'info_dict': {
1586 'id': '874_1459135191',
1587 'ext': 'mp4',
1588 'title': 'Man shows poor quality of new apartment building',
1589 'description': 'The wall is like a sand pile.',
1590 'uploader': 'Lake8737',
1591 },
1592 'add_ie': [LiveLeakIE.ie_key()],
1593 },
1594 # Another LiveLeak embed pattern (#13336)
1595 {
1596 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1597 'info_dict': {
1598 'id': '2eb_1496309988',
1599 'ext': 'mp4',
1600 'title': 'Thief robs place where everyone was armed',
1601 'description': 'md5:694d73ee79e535953cf2488562288eee',
1602 'uploader': 'brazilwtf',
1603 },
1604 'add_ie': [LiveLeakIE.ie_key()],
1605 },
1606 # Duplicated embedded video URLs
1607 {
1608 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1609 'info_dict': {
1610 'id': '149298443_480_16c25b74_2',
1611 'ext': 'mp4',
1612 'title': 'vs. Blue Orange Spring Game',
1613 'uploader': 'www.hudl.com',
1614 },
1615 },
1616 # twitter:player:stream embed
1617 {
1618 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1619 'info_dict': {
1620 'id': 'master',
1621 'ext': 'mp4',
1622 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1623 'uploader': 'www.rtl.be',
1624 },
1625 'params': {
1626 # m3u8 downloads
1627 'skip_download': True,
1628 },
1629 },
1630 # twitter:player embed
1631 {
1632 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1633 'md5': 'a3e0df96369831de324f0778e126653c',
1634 'info_dict': {
1635 'id': '4909620399001',
1636 'ext': 'mp4',
1637 'title': 'What Do Black Holes Sound Like?',
1638 'description': 'what do black holes sound like',
1639 'upload_date': '20160524',
1640 'uploader_id': '29913724001',
1641 'timestamp': 1464107587,
1642 'uploader': 'TheAtlantic',
1643 },
1644 'add_ie': ['BrightcoveLegacy'],
1645 },
1646 # Facebook <iframe> embed
1647 {
1648 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1649 'md5': 'fbcde74f534176ecb015849146dd3aee',
1650 'info_dict': {
1651 'id': '599637780109885',
1652 'ext': 'mp4',
1653 'title': 'Facebook video #599637780109885',
1654 },
1655 },
1656 # Facebook <iframe> embed, plugin video
1657 {
1658 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1659 'info_dict': {
1660 'id': '1754168231264132',
1661 'ext': 'mp4',
1662 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1663 'uploader': 'Tariq Ramadan (official)',
1664 'timestamp': 1496758379,
1665 'upload_date': '20170606',
1666 },
1667 'params': {
1668 'skip_download': True,
1669 },
1670 },
1671 # Facebook API embed
1672 {
1673 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1674 'md5': 'a47372ee61b39a7b90287094d447d94e',
1675 'info_dict': {
1676 'id': '10153467542406923',
1677 'ext': 'mp4',
1678 'title': 'Facebook video #10153467542406923',
1679 },
1680 },
1681 # Wordpress "YouTube Video Importer" plugin
1682 {
1683 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1684 'md5': 'd16797741b560b485194eddda8121b48',
1685 'info_dict': {
1686 'id': 'HNTXWDXV9Is',
1687 'ext': 'mp4',
1688 'title': 'Blue Devils Drumline Stanford lot 2016',
1689 'upload_date': '20160627',
1690 'uploader_id': 'GENOCIDE8GENERAL10',
1691 'uploader': 'cylus cyrus',
1692 },
1693 },
1694 {
1695 # video stored on custom kaltura server
1696 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1697 'md5': '537617d06e64dfed891fa1593c4b30cc',
1698 'info_dict': {
1699 'id': '0_1iotm5bh',
1700 'ext': 'mp4',
1701 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1702 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1703 'uploader_id': 'videos.expansion@el-mundo.net',
1704 'upload_date': '20150429',
1705 'timestamp': 1430303472,
1706 },
1707 'add_ie': ['Kaltura'],
1708 },
1709 {
1710 # Non-standard Vimeo embed
1711 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1712 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1713 'info_dict': {
1714 'id': '148867247',
1715 'ext': 'mp4',
1716 'title': 'Understanding the web - Teaser',
1717 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1718 'upload_date': '20151214',
1719 'uploader': 'OpenClassrooms',
1720 'uploader_id': 'openclassrooms',
1721 },
1722 'add_ie': ['Vimeo'],
1723 },
1724 {
1725 # generic vimeo embed that requires original URL passed as Referer
1726 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1727 'only_matching': True,
1728 },
1729 {
1730 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1731 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1732 'info_dict': {
1733 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1734 'ext': 'mp4',
1735 'title': 'Big Buck Bunny',
1736 'description': 'Royalty free test video',
1737 'timestamp': 1432816365,
1738 'upload_date': '20150528',
1739 'is_live': False,
1740 },
1741 'params': {
1742 'skip_download': True,
1743 },
1744 'add_ie': [ArkenaIE.ie_key()],
1745 },
1746 {
1747 '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/',
1748 'info_dict': {
1749 'id': '1c7141f46c',
1750 'ext': 'mp4',
1751 'title': 'ŠŠ ŠšŠžŠ”ŠŖŠœ ŠžŠ¢ Š’Š—Š Š˜Š’: Š˜Š·Ń‚ŠøчŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃ‚Š°Š½Ń†Šøя Š² ŠŸŠ»Š¾Š²Š“ŠøŠ²',
1752 },
1753 'params': {
1754 'skip_download': True,
1755 },
1756 'add_ie': [Vbox7IE.ie_key()],
1757 },
1758 {
1759 # DBTV embeds
1760 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1761 'info_dict': {
1762 'id': '43254897',
1763 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1764 },
1765 'playlist_mincount': 3,
1766 },
1767 {
1768 # Videa embeds
1769 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1770 'info_dict': {
1771 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1772 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1773 },
1774 'playlist_mincount': 2,
1775 },
1776 {
1777 # 20 minuten embed
1778 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1779 'info_dict': {
1780 'id': '523629',
1781 'ext': 'mp4',
1782 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1783 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1784 },
1785 'params': {
1786 'skip_download': True,
1787 },
1788 'add_ie': [TwentyMinutenIE.ie_key()],
1789 },
1790 {
1791 # VideoPress embed
1792 'url': 'https://en.support.wordpress.com/videopress/',
1793 'info_dict': {
1794 'id': 'OcobLTqC',
1795 'ext': 'm4v',
1796 'title': 'IMG_5786',
1797 'timestamp': 1435711927,
1798 'upload_date': '20150701',
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 'add_ie': [VideoPressIE.ie_key()],
1804 },
1805 {
1806 # Rutube embed
1807 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1808 'info_dict': {
1809 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1810 'ext': 'flv',
1811 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1812 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1813 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1814 'upload_date': '20170228',
1815 'uploader_id': '996642',
1816 },
1817 'params': {
1818 'skip_download': True,
1819 },
1820 'add_ie': [RutubeIE.ie_key()],
1821 },
1822 {
1823 # ThePlatform embedded with whitespaces in URLs
1824 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1825 'only_matching': True,
1826 },
1827 {
1828 # Senate ISVP iframe https
1829 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1830 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1831 'info_dict': {
1832 'id': 'govtaff020316',
1833 'ext': 'mp4',
1834 'title': 'Integrated Senate Video Player',
1835 },
1836 'add_ie': [SenateISVPIE.ie_key()],
1837 },
1838 {
1839 # Limelight embeds (1 channel embed + 4 media embeds)
1840 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1841 'info_dict': {
1842 'id': 'FacilitatorTraining2017',
1843 'title': 'Facilitator Training 2017',
1844 },
1845 'playlist_mincount': 5,
1846 },
1847 {
1848 # Limelight embed (LimelightPlayerUtil.embed)
1849 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1850 'info_dict': {
1851 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1852 'ext': 'mp4',
1853 'title': '07448641',
1854 'timestamp': 1499890639,
1855 'upload_date': '20170712',
1856 },
1857 'params': {
1858 'skip_download': True,
1859 },
1860 'add_ie': ['LimelightMedia'],
1861 },
1862 {
1863 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1864 'info_dict': {
1865 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1866 'title': 'Standoff with Walnut Creek murder suspect ends',
1867 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1868 },
1869 'playlist_mincount': 4,
1870 },
1871 {
1872 # WashingtonPost embed
1873 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1874 'info_dict': {
1875 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1876 'ext': 'mp4',
1877 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1878 '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 ā€” and enlisted actors.',
1879 'timestamp': 1455216756,
1880 'uploader': 'The Washington Post',
1881 'upload_date': '20160211',
1882 },
1883 'add_ie': [WashingtonPostIE.ie_key()],
1884 },
1885 {
1886 # Mediaset embed
1887 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1888 'info_dict': {
1889 'id': '720642',
1890 'ext': 'mp4',
1891 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 'add_ie': [MediasetIE.ie_key()],
1897 },
1898 {
1899 # JOJ.sk embeds
1900 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1901 'info_dict': {
1902 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1904 },
1905 'playlist_mincount': 5,
1906 'add_ie': [JojIE.ie_key()],
1907 },
1908 {
1909 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1910 'url': 'https://tvrain.ru/amp/418921/',
1911 'md5': 'cc00413936695987e8de148b67d14f1d',
1912 'info_dict': {
1913 'id': '418921',
1914 'ext': 'mp4',
1915 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1916 },
1917 },
1918 {
1919 # vzaar embed
1920 'url': 'http://help.vzaar.com/article/165-embedding-video',
1921 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1922 'info_dict': {
1923 'id': '8707641',
1924 'ext': 'mp4',
1925 'title': 'Building A Business Online: Principal Chairs Q & A',
1926 },
1927 },
1928 {
1929 # multiple HTML5 videos on one page
1930 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1931 'info_dict': {
1932 'id': 'keyscenarios',
1933 'title': 'Rescue Kit 14 Free Edition - Getting started',
1934 },
1935 'playlist_count': 4,
1936 },
1937 {
1938 # vshare embed
1939 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1940 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1941 'info_dict': {
1942 'id': '0f64ce6',
1943 'title': 'vl14062007715967',
1944 'ext': 'mp4',
1945 }
1946 },
1947 {
1948 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1949 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1950 'info_dict': {
1951 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1952 'ext': 'mp4',
1953 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1954 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1955 'timestamp': 1474354800,
1956 'upload_date': '20160920',
1957 }
1958 },
1959 {
1960 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1961 'info_dict': {
1962 'id': '1731611',
1963 'ext': 'mp4',
1964 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1965 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1966 'timestamp': 1516100691,
1967 'upload_date': '20180116',
1968 },
1969 'params': {
1970 'skip_download': True,
1971 },
1972 'add_ie': [SpringboardPlatformIE.ie_key()],
1973 },
1974 {
1975 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1976 'info_dict': {
1977 'id': 'uPDB5I9wfp8',
1978 'ext': 'webm',
1979 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1980 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1981 'upload_date': '20160219',
1982 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1983 'uploader_id': 'PocoyoBrazil',
1984 },
1985 'add_ie': [YoutubeIE.ie_key()],
1986 'params': {
1987 'skip_download': True,
1988 },
1989 },
1990 {
1991 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1992 'info_dict': {
1993 'id': 'vMDE4NzI1Mjgt690b',
1994 'ext': 'mp4',
1995 'title': 'ŠšŠ¾Ń‚ŃŃ‚Š°',
1996 },
1997 'add_ie': [YapFilesIE.ie_key()],
1998 'params': {
1999 'skip_download': True,
2000 },
2001 },
2002 {
2003 # CloudflareStream embed
2004 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2005 'info_dict': {
2006 'id': '31c9291ab41fac05471db4e73aa11717',
2007 'ext': 'mp4',
2008 'title': '31c9291ab41fac05471db4e73aa11717',
2009 },
2010 'add_ie': [CloudflareStreamIE.ie_key()],
2011 'params': {
2012 'skip_download': True,
2013 },
2014 },
2015 {
2016 # PeerTube embed
2017 'url': 'https://joinpeertube.org/fr/home/',
2018 'info_dict': {
2019 'id': 'home',
2020 'title': 'Reprenez le contrƓle de vos vidƩos ! #JoinPeertube',
2021 },
2022 'playlist_count': 2,
2023 },
2024 {
2025 # Indavideo embed
2026 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2027 'info_dict': {
2028 'id': '1693903',
2029 'ext': 'mp4',
2030 'title': 'ƍgy kell otthon hamburgert sĆ¼tni',
2031 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2032 'timestamp': 1426330212,
2033 'upload_date': '20150314',
2034 'uploader': 'StreetKitchen',
2035 'uploader_id': '546363',
2036 },
2037 'add_ie': [IndavideoEmbedIE.ie_key()],
2038 'params': {
2039 'skip_download': True,
2040 },
2041 },
2042 {
2043 # APA embed via JWPlatform embed
2044 'url': 'http://www.vol.at/blue-man-group/5593454',
2045 'info_dict': {
2046 'id': 'jjv85FdZ',
2047 'ext': 'mp4',
2048 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview',
2049 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2050 'thumbnail': r're:^https?://.*\.jpg$',
2051 'duration': 254,
2052 'timestamp': 1519211149,
2053 'upload_date': '20180221',
2054 },
2055 'params': {
2056 'skip_download': True,
2057 },
2058 },
2059 {
2060 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2061 'md5': 'b68d276de422ab07ee1d49388103f457',
2062 'info_dict': {
2063 'id': '83645793',
2064 'title': 'Lock up and get excited',
2065 'ext': 'mp4'
2066 },
2067 'skip': 'TODO: fix nested playlists processing in tests',
2068 },
2069 {
2070 # Viqeo embeds
2071 'url': 'https://viqeo.tv/',
2072 'info_dict': {
2073 'id': 'viqeo',
2074 'title': 'All-new video platform',
2075 },
2076 'playlist_count': 6,
2077 },
2078 {
2079 # Squarespace video embed, 2019-08-28
2080 'url': 'http://ootboxford.com',
2081 'info_dict': {
2082 'id': 'Tc7b_JGdZfw',
2083 'title': 'Out of the Blue, at Childish Things 10',
2084 'ext': 'mp4',
2085 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2086 'uploader_id': 'helendouglashouse',
2087 'uploader': 'Helen & Douglas House',
2088 'upload_date': '20140328',
2089 },
2090 'params': {
2091 'skip_download': True,
2092 },
2093 },
2094 {
2095 # Zype embed
2096 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2097 'info_dict': {
2098 'id': '5b400b834b32992a310622b9',
2099 'ext': 'mp4',
2100 'title': 'Smoky Barbecue Favorites',
2101 'thumbnail': r're:^https?://.*\.jpe?g',
2102 },
2103 'add_ie': [ZypeIE.ie_key()],
2104 'params': {
2105 'skip_download': True,
2106 },
2107 },
2108 {
2109 # videojs embed
2110 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2111 'info_dict': {
2112 'id': 'shell',
2113 'ext': 'mp4',
2114 'title': 'Š”Š¾ŃŃ‚Š°Š²Ń‰ŠøŠŗ ŠæŠøццы сŠæрŠ¾ŃŠøŠ» рŠ°Š·Ń€ŠµŃˆŠµŠ½Šøя сыŠ³Ń€Š°Ń‚ŃŒ Š½Š° фŠ¾Ń€Ń‚ŠµŠæŠøŠ°Š½Š¾',
2115 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2116 'thumbnail': r're:^https?://.*\.jpg$',
2117 },
2118 'params': {
2119 'skip_download': True,
2120 },
2121 'expected_warnings': ['Failed to download MPD manifest'],
2122 },
2123 {
2124 # DailyMotion embed with DM.player
2125 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2126 'info_dict': {
2127 'id': 'k6aKkGHd9FJs4mtJN39',
2128 'ext': 'mp4',
2129 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2130 'description': 'This video is private.',
2131 'uploader_id': 'x1jf30l',
2132 'uploader': 'beIN SPORTS USA',
2133 'upload_date': '20190528',
2134 'timestamp': 1559062971,
2135 },
2136 'params': {
2137 'skip_download': True,
2138 },
2139 },
2140 # {
2141 # # TODO: find another test
2142 # # http://schema.org/VideoObject
2143 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2144 # 'md5': '888dcf08b7ea671381f00fab74692755',
2145 # 'info_dict': {
2146 # 'id': 'nyvTSJMKId',
2147 # 'ext': 'mp4',
2148 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2149 # 'description': '#love for cats.',
2150 # 'timestamp': 1461244995,
2151 # 'upload_date': '20160421',
2152 # },
2153 # 'params': {
2154 # 'force_generic_extractor': True,
2155 # },
2156 # }
2157 ]
2158
2159 def report_following_redirect(self, new_url):
2160 """Report information extraction."""
2161 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2162
2163 def _extract_rss(self, url, video_id, doc):
2164 playlist_title = doc.find('./channel/title').text
2165 playlist_desc_el = doc.find('./channel/description')
2166 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2167
2168 entries = []
2169 for it in doc.findall('./channel/item'):
2170 next_url = None
2171 enclosure_nodes = it.findall('./enclosure')
2172 for e in enclosure_nodes:
2173 next_url = e.attrib.get('url')
2174 if next_url:
2175 break
2176
2177 if not next_url:
2178 next_url = xpath_text(it, 'link', fatal=False)
2179
2180 if not next_url:
2181 continue
2182
2183 entries.append({
2184 '_type': 'url_transparent',
2185 'url': next_url,
2186 'title': it.find('title').text,
2187 })
2188
2189 return {
2190 '_type': 'playlist',
2191 'id': url,
2192 'title': playlist_title,
2193 'description': playlist_desc,
2194 'entries': entries,
2195 }
2196
2197 def _extract_camtasia(self, url, video_id, webpage):
2198 """ Returns None if no camtasia video can be found. """
2199
2200 camtasia_cfg = self._search_regex(
2201 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2202 webpage, 'camtasia configuration file', default=None)
2203 if camtasia_cfg is None:
2204 return None
2205
2206 title = self._html_search_meta('DC.title', webpage, fatal=True)
2207
2208 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2209 camtasia_cfg = self._download_xml(
2210 camtasia_url, video_id,
2211 note='Downloading camtasia configuration',
2212 errnote='Failed to download camtasia configuration')
2213 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2214
2215 entries = []
2216 for n in fileset_node.getchildren():
2217 url_n = n.find('./uri')
2218 if url_n is None:
2219 continue
2220
2221 entries.append({
2222 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2223 'title': '%s - %s' % (title, n.tag),
2224 'url': compat_urlparse.urljoin(url, url_n.text),
2225 'duration': float_or_none(n.find('./duration').text),
2226 })
2227
2228 return {
2229 '_type': 'playlist',
2230 'entries': entries,
2231 'title': title,
2232 }
2233
2234 def _real_extract(self, url):
2235 if url.startswith('//'):
2236 return self.url_result(self.http_scheme() + url)
2237
2238 parsed_url = compat_urlparse.urlparse(url)
2239 if not parsed_url.scheme:
2240 default_search = self._downloader.params.get('default_search')
2241 if default_search is None:
2242 default_search = 'fixup_error'
2243
2244 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2245 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2246 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2247 return self.url_result('http://' + url)
2248 elif default_search != 'fixup_error':
2249 if default_search == 'auto_warning':
2250 if re.match(r'^(?:url|URL)$', url):
2251 raise ExtractorError(
2252 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2253 expected=True)
2254 else:
2255 self._downloader.report_warning(
2256 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2257 return self.url_result('ytsearch:' + url)
2258
2259 if default_search in ('error', 'fixup_error'):
2260 raise ExtractorError(
2261 '%r is not a valid URL. '
2262 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2263 % (url, url), expected=True)
2264 else:
2265 if ':' not in default_search:
2266 default_search += ':'
2267 return self.url_result(default_search + url)
2268
2269 url, smuggled_data = unsmuggle_url(url)
2270 force_videoid = None
2271 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2272 if smuggled_data and 'force_videoid' in smuggled_data:
2273 force_videoid = smuggled_data['force_videoid']
2274 video_id = force_videoid
2275 else:
2276 video_id = self._generic_id(url)
2277
2278 self.to_screen('%s: Requesting header' % video_id)
2279
2280 head_req = HEADRequest(url)
2281 head_response = self._request_webpage(
2282 head_req, video_id,
2283 note=False, errnote='Could not send HEAD request to %s' % url,
2284 fatal=False)
2285
2286 if head_response is not False:
2287 # Check for redirect
2288 new_url = compat_str(head_response.geturl())
2289 if url != new_url:
2290 self.report_following_redirect(new_url)
2291 if force_videoid:
2292 new_url = smuggle_url(
2293 new_url, {'force_videoid': force_videoid})
2294 return self.url_result(new_url)
2295
2296 full_response = None
2297 if head_response is False:
2298 request = sanitized_Request(url)
2299 request.add_header('Accept-Encoding', '*')
2300 full_response = self._request_webpage(request, video_id)
2301 head_response = full_response
2302
2303 info_dict = {
2304 'id': video_id,
2305 'title': self._generic_title(url),
2306 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2307 }
2308
2309 # Check for direct link to a video
2310 content_type = head_response.headers.get('Content-Type', '').lower()
2311 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2312 if m:
2313 format_id = compat_str(m.group('format_id'))
2314 if format_id.endswith('mpegurl'):
2315 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2316 elif format_id == 'f4m':
2317 formats = self._extract_f4m_formats(url, video_id)
2318 else:
2319 formats = [{
2320 'format_id': format_id,
2321 'url': url,
2322 'vcodec': 'none' if m.group('type') == 'audio' else None
2323 }]
2324 info_dict['direct'] = True
2325 self._sort_formats(formats)
2326 info_dict['formats'] = formats
2327 return info_dict
2328
2329 if not self._downloader.params.get('test', False) and not is_intentional:
2330 force = self._downloader.params.get('force_generic_extractor', False)
2331 self._downloader.report_warning(
2332 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2333
2334 if not full_response:
2335 request = sanitized_Request(url)
2336 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2337 # making it impossible to download only chunk of the file (yet we need only 512kB to
2338 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2339 # that will always result in downloading the whole file that is not desirable.
2340 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2341 # to accept raw bytes and being able to download only a chunk.
2342 # It may probably better to solve this by checking Content-Type for application/octet-stream
2343 # after HEAD request finishes, but not sure if we can rely on this.
2344 request.add_header('Accept-Encoding', '*')
2345 full_response = self._request_webpage(request, video_id)
2346
2347 first_bytes = full_response.read(512)
2348
2349 # Is it an M3U playlist?
2350 if first_bytes.startswith(b'#EXTM3U'):
2351 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2352 self._sort_formats(info_dict['formats'])
2353 return info_dict
2354
2355 # Maybe it's a direct link to a video?
2356 # Be careful not to download the whole thing!
2357 if not is_html(first_bytes):
2358 self._downloader.report_warning(
2359 'URL could be a direct video link, returning it as such.')
2360 info_dict.update({
2361 'direct': True,
2362 'url': url,
2363 })
2364 return info_dict
2365
2366 webpage = self._webpage_read_content(
2367 full_response, url, video_id, prefix=first_bytes)
2368
2369 self.report_extraction(video_id)
2370
2371 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2372 try:
2373 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2374 if doc.tag == 'rss':
2375 return self._extract_rss(url, video_id, doc)
2376 elif doc.tag == 'SmoothStreamingMedia':
2377 info_dict['formats'] = self._parse_ism_formats(doc, url)
2378 self._sort_formats(info_dict['formats'])
2379 return info_dict
2380 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2381 smil = self._parse_smil(doc, url, video_id)
2382 self._sort_formats(smil['formats'])
2383 return smil
2384 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2385 return self.playlist_result(
2386 self._parse_xspf(
2387 doc, video_id, xspf_url=url,
2388 xspf_base_url=compat_str(full_response.geturl())),
2389 video_id)
2390 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2391 info_dict['formats'] = self._parse_mpd_formats(
2392 doc,
2393 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2394 mpd_url=url)
2395 self._sort_formats(info_dict['formats'])
2396 return info_dict
2397 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2398 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2399 self._sort_formats(info_dict['formats'])
2400 return info_dict
2401 except compat_xml_parse_error:
2402 pass
2403
2404 # Is it a Camtasia project?
2405 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2406 if camtasia_res is not None:
2407 return camtasia_res
2408
2409 # Sometimes embedded video player is hidden behind percent encoding
2410 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2411 # Unescaping the whole page allows to handle those cases in a generic way
2412 webpage = compat_urllib_parse_unquote(webpage)
2413
2414 # Unescape squarespace embeds to be detected by generic extractor,
2415 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2416 webpage = re.sub(
2417 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2418 lambda x: unescapeHTML(x.group(0)), webpage)
2419
2420 # it's tempting to parse this further, but you would
2421 # have to take into account all the variations like
2422 # Video Title - Site Name
2423 # Site Name | Video Title
2424 # Video Title - Tagline | Site Name
2425 # and so on and so forth; it's just not practical
2426 video_title = self._og_search_title(
2427 webpage, default=None) or self._html_search_regex(
2428 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2429 default='video')
2430
2431 # Try to detect age limit automatically
2432 age_limit = self._rta_search(webpage)
2433 # And then there are the jokers who advertise that they use RTA,
2434 # but actually don't.
2435 AGE_LIMIT_MARKERS = [
2436 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2437 ]
2438 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2439 age_limit = 18
2440
2441 # video uploader is domain name
2442 video_uploader = self._search_regex(
2443 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2444
2445 video_description = self._og_search_description(webpage, default=None)
2446 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2447
2448 info_dict.update({
2449 'title': video_title,
2450 'description': video_description,
2451 'thumbnail': video_thumbnail,
2452 'age_limit': age_limit,
2453 })
2454
2455 # Look for Brightcove Legacy Studio embeds
2456 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2457 if bc_urls:
2458 entries = [{
2459 '_type': 'url',
2460 'url': smuggle_url(bc_url, {'Referer': url}),
2461 'ie_key': 'BrightcoveLegacy'
2462 } for bc_url in bc_urls]
2463
2464 return {
2465 '_type': 'playlist',
2466 'title': video_title,
2467 'id': video_id,
2468 'entries': entries,
2469 }
2470
2471 # Look for Brightcove New Studio embeds
2472 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2473 if bc_urls:
2474 return self.playlist_from_matches(
2475 bc_urls, video_id, video_title,
2476 getter=lambda x: smuggle_url(x, {'referrer': url}),
2477 ie='BrightcoveNew')
2478
2479 # Look for Nexx embeds
2480 nexx_urls = NexxIE._extract_urls(webpage)
2481 if nexx_urls:
2482 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2483
2484 # Look for Nexx iFrame embeds
2485 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2486 if nexx_embed_urls:
2487 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2488
2489 # Look for ThePlatform embeds
2490 tp_urls = ThePlatformIE._extract_urls(webpage)
2491 if tp_urls:
2492 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2493
2494 # Look for Vessel embeds
2495 vessel_urls = VesselIE._extract_urls(webpage)
2496 if vessel_urls:
2497 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2498
2499 # Look for embedded rtl.nl player
2500 matches = re.findall(
2501 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2502 webpage)
2503 if matches:
2504 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2505
2506 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2507 if vimeo_urls:
2508 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2509
2510 vid_me_embed_url = self._search_regex(
2511 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2512 webpage, 'vid.me embed', default=None)
2513 if vid_me_embed_url is not None:
2514 return self.url_result(vid_me_embed_url, 'Vidme')
2515
2516 # Look for YouTube embeds
2517 youtube_urls = YoutubeIE._extract_urls(webpage)
2518 if youtube_urls:
2519 return self.playlist_from_matches(
2520 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2521
2522 matches = DailymotionIE._extract_urls(webpage)
2523 if matches:
2524 return self.playlist_from_matches(matches, video_id, video_title)
2525
2526 # Look for embedded Dailymotion playlist player (#3822)
2527 m = re.search(
2528 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2529 if m:
2530 playlists = re.findall(
2531 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2532 if playlists:
2533 return self.playlist_from_matches(
2534 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2535
2536 # Look for DailyMail embeds
2537 dailymail_urls = DailyMailIE._extract_urls(webpage)
2538 if dailymail_urls:
2539 return self.playlist_from_matches(
2540 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2541
2542 # Look for embedded Wistia player
2543 wistia_url = WistiaIE._extract_url(webpage)
2544 if wistia_url:
2545 return {
2546 '_type': 'url_transparent',
2547 'url': self._proto_relative_url(wistia_url),
2548 'ie_key': WistiaIE.ie_key(),
2549 'uploader': video_uploader,
2550 }
2551
2552 # Look for SVT player
2553 svt_url = SVTIE._extract_url(webpage)
2554 if svt_url:
2555 return self.url_result(svt_url, 'SVT')
2556
2557 # Look for Bandcamp pages with custom domain
2558 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2559 if mobj is not None:
2560 burl = unescapeHTML(mobj.group(1))
2561 # Don't set the extractor because it can be a track url or an album
2562 return self.url_result(burl)
2563
2564 # Look for embedded Vevo player
2565 mobj = re.search(
2566 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2567 if mobj is not None:
2568 return self.url_result(mobj.group('url'))
2569
2570 # Look for embedded Viddler player
2571 mobj = re.search(
2572 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2573 webpage)
2574 if mobj is not None:
2575 return self.url_result(mobj.group('url'))
2576
2577 # Look for NYTimes player
2578 mobj = re.search(
2579 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2580 webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'))
2583
2584 # Look for Libsyn player
2585 mobj = re.search(
2586 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2587 if mobj is not None:
2588 return self.url_result(mobj.group('url'))
2589
2590 # Look for Ooyala videos
2591 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2592 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2593 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2594 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2595 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2596 if mobj is not None:
2597 embed_token = self._search_regex(
2598 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2599 webpage, 'ooyala embed token', default=None)
2600 return OoyalaIE._build_url_result(smuggle_url(
2601 mobj.group('ec'), {
2602 'domain': url,
2603 'embed_token': embed_token,
2604 }))
2605
2606 # Look for multiple Ooyala embeds on SBN network websites
2607 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2608 if mobj is not None:
2609 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2610 if embeds:
2611 return self.playlist_from_matches(
2612 embeds, video_id, video_title,
2613 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2614
2615 # Look for Aparat videos
2616 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2617 if mobj is not None:
2618 return self.url_result(mobj.group(1), 'Aparat')
2619
2620 # Look for MPORA videos
2621 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2622 if mobj is not None:
2623 return self.url_result(mobj.group(1), 'Mpora')
2624
2625 # Look for embedded Facebook player
2626 facebook_urls = FacebookIE._extract_urls(webpage)
2627 if facebook_urls:
2628 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2629
2630 # Look for embedded VK player
2631 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2632 if mobj is not None:
2633 return self.url_result(mobj.group('url'), 'VK')
2634
2635 # Look for embedded Odnoklassniki player
2636 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2637 if mobj is not None:
2638 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2639
2640 # Look for embedded ivi player
2641 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2642 if mobj is not None:
2643 return self.url_result(mobj.group('url'), 'Ivi')
2644
2645 # Look for embedded Huffington Post player
2646 mobj = re.search(
2647 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'), 'HuffPost')
2650
2651 # Look for embed.ly
2652 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2653 if mobj is not None:
2654 return self.url_result(mobj.group('url'))
2655 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2656 if mobj is not None:
2657 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2658
2659 # Look for funnyordie embed
2660 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2661 if matches:
2662 return self.playlist_from_matches(
2663 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2664
2665 # Look for BBC iPlayer embed
2666 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2667 if matches:
2668 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2669
2670 # Look for embedded RUTV player
2671 rutv_url = RUTVIE._extract_url(webpage)
2672 if rutv_url:
2673 return self.url_result(rutv_url, 'RUTV')
2674
2675 # Look for embedded TVC player
2676 tvc_url = TVCIE._extract_url(webpage)
2677 if tvc_url:
2678 return self.url_result(tvc_url, 'TVC')
2679
2680 # Look for embedded SportBox player
2681 sportbox_urls = SportBoxIE._extract_urls(webpage)
2682 if sportbox_urls:
2683 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2684
2685 # Look for embedded XHamster player
2686 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2687 if xhamster_urls:
2688 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2689
2690 # Look for embedded TNAFlixNetwork player
2691 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2692 if tnaflix_urls:
2693 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2694
2695 # Look for embedded PornHub player
2696 pornhub_urls = PornHubIE._extract_urls(webpage)
2697 if pornhub_urls:
2698 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2699
2700 # Look for embedded DrTuber player
2701 drtuber_urls = DrTuberIE._extract_urls(webpage)
2702 if drtuber_urls:
2703 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2704
2705 # Look for embedded RedTube player
2706 redtube_urls = RedTubeIE._extract_urls(webpage)
2707 if redtube_urls:
2708 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2709
2710 # Look for embedded Tube8 player
2711 tube8_urls = Tube8IE._extract_urls(webpage)
2712 if tube8_urls:
2713 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2714
2715 # Look for embedded Tvigle player
2716 mobj = re.search(
2717 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2718 if mobj is not None:
2719 return self.url_result(mobj.group('url'), 'Tvigle')
2720
2721 # Look for embedded TED player
2722 mobj = re.search(
2723 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2724 if mobj is not None:
2725 return self.url_result(mobj.group('url'), 'TED')
2726
2727 # Look for embedded Ustream videos
2728 ustream_url = UstreamIE._extract_url(webpage)
2729 if ustream_url:
2730 return self.url_result(ustream_url, UstreamIE.ie_key())
2731
2732 # Look for embedded arte.tv player
2733 mobj = re.search(
2734 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2735 webpage)
2736 if mobj is not None:
2737 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2738
2739 # Look for embedded francetv player
2740 mobj = re.search(
2741 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2742 webpage)
2743 if mobj is not None:
2744 return self.url_result(mobj.group('url'))
2745
2746 # Look for embedded smotri.com player
2747 smotri_url = SmotriIE._extract_url(webpage)
2748 if smotri_url:
2749 return self.url_result(smotri_url, 'Smotri')
2750
2751 # Look for embedded Myvi.ru player
2752 myvi_url = MyviIE._extract_url(webpage)
2753 if myvi_url:
2754 return self.url_result(myvi_url)
2755
2756 # Look for embedded soundcloud player
2757 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2758 if soundcloud_urls:
2759 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2760
2761 # Look for tunein player
2762 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2763 if tunein_urls:
2764 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2765
2766 # Look for embedded mtvservices player
2767 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2768 if mtvservices_url:
2769 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2770
2771 # Look for embedded yahoo player
2772 mobj = re.search(
2773 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2774 webpage)
2775 if mobj is not None:
2776 return self.url_result(mobj.group('url'), 'Yahoo')
2777
2778 # Look for embedded sbs.com.au player
2779 mobj = re.search(
2780 r'''(?x)
2781 (?:
2782 <meta\s+property="og:video"\s+content=|
2783 <iframe[^>]+?src=
2784 )
2785 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2786 webpage)
2787 if mobj is not None:
2788 return self.url_result(mobj.group('url'), 'SBS')
2789
2790 # Look for embedded Cinchcast player
2791 mobj = re.search(
2792 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2793 webpage)
2794 if mobj is not None:
2795 return self.url_result(mobj.group('url'), 'Cinchcast')
2796
2797 mobj = re.search(
2798 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2799 webpage)
2800 if not mobj:
2801 mobj = re.search(
2802 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2803 webpage)
2804 if mobj is not None:
2805 return self.url_result(mobj.group('url'), 'MLB')
2806
2807 mobj = re.search(
2808 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2809 webpage)
2810 if mobj is not None:
2811 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2812
2813 mobj = re.search(
2814 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2815 webpage)
2816 if mobj is not None:
2817 return self.url_result(mobj.group('url'), 'Livestream')
2818
2819 # Look for Zapiks embed
2820 mobj = re.search(
2821 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2822 if mobj is not None:
2823 return self.url_result(mobj.group('url'), 'Zapiks')
2824
2825 # Look for Kaltura embeds
2826 kaltura_url = KalturaIE._extract_url(webpage)
2827 if kaltura_url:
2828 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2829
2830 # Look for EaglePlatform embeds
2831 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2832 if eagleplatform_url:
2833 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2834
2835 # Look for ClipYou (uses EaglePlatform) embeds
2836 mobj = re.search(
2837 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2838 if mobj is not None:
2839 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2840
2841 # Look for Pladform embeds
2842 pladform_url = PladformIE._extract_url(webpage)
2843 if pladform_url:
2844 return self.url_result(pladform_url)
2845
2846 # Look for Videomore embeds
2847 videomore_url = VideomoreIE._extract_url(webpage)
2848 if videomore_url:
2849 return self.url_result(videomore_url)
2850
2851 # Look for Webcaster embeds
2852 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2853 if webcaster_url:
2854 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2855
2856 # Look for Playwire embeds
2857 mobj = re.search(
2858 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2859 if mobj is not None:
2860 return self.url_result(mobj.group('url'))
2861
2862 # Look for 5min embeds
2863 mobj = re.search(
2864 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2865 if mobj is not None:
2866 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2867
2868 # Look for Crooks and Liars embeds
2869 mobj = re.search(
2870 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2871 if mobj is not None:
2872 return self.url_result(mobj.group('url'))
2873
2874 # Look for NBC Sports VPlayer embeds
2875 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2876 if nbc_sports_url:
2877 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2878
2879 # Look for NBC News embeds
2880 nbc_news_embed_url = re.search(
2881 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2882 if nbc_news_embed_url:
2883 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2884
2885 # Look for Google Drive embeds
2886 google_drive_url = GoogleDriveIE._extract_url(webpage)
2887 if google_drive_url:
2888 return self.url_result(google_drive_url, 'GoogleDrive')
2889
2890 # Look for UDN embeds
2891 mobj = re.search(
2892 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2893 if mobj is not None:
2894 return self.url_result(
2895 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2896
2897 # Look for Senate ISVP iframe
2898 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2899 if senate_isvp_url:
2900 return self.url_result(senate_isvp_url, 'SenateISVP')
2901
2902 # Look for OnionStudios embeds
2903 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2904 if onionstudios_url:
2905 return self.url_result(onionstudios_url)
2906
2907 # Look for ViewLift embeds
2908 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2909 if viewlift_url:
2910 return self.url_result(viewlift_url)
2911
2912 # Look for JWPlatform embeds
2913 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2914 if jwplatform_urls:
2915 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2916
2917 # Look for Digiteka embeds
2918 digiteka_url = DigitekaIE._extract_url(webpage)
2919 if digiteka_url:
2920 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2921
2922 # Look for Arkena embeds
2923 arkena_url = ArkenaIE._extract_url(webpage)
2924 if arkena_url:
2925 return self.url_result(arkena_url, ArkenaIE.ie_key())
2926
2927 # Look for Piksel embeds
2928 piksel_url = PikselIE._extract_url(webpage)
2929 if piksel_url:
2930 return self.url_result(piksel_url, PikselIE.ie_key())
2931
2932 # Look for Limelight embeds
2933 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2934 if limelight_urls:
2935 return self.playlist_result(
2936 limelight_urls, video_id, video_title, video_description)
2937
2938 # Look for Anvato embeds
2939 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2940 if anvato_urls:
2941 return self.playlist_result(
2942 anvato_urls, video_id, video_title, video_description)
2943
2944 # Look for AdobeTVVideo embeds
2945 mobj = re.search(
2946 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2947 webpage)
2948 if mobj is not None:
2949 return self.url_result(
2950 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2951 'AdobeTVVideo')
2952
2953 # Look for Vine embeds
2954 mobj = re.search(
2955 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2956 webpage)
2957 if mobj is not None:
2958 return self.url_result(
2959 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2960
2961 # Look for VODPlatform embeds
2962 mobj = re.search(
2963 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2964 webpage)
2965 if mobj is not None:
2966 return self.url_result(
2967 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2968
2969 # Look for Mangomolo embeds
2970 mobj = re.search(
2971 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2972 (?:
2973 video\?.*?\bid=(?P<video_id>\d+)|
2974 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2975 ).+?)\1''', webpage)
2976 if mobj is not None:
2977 info = {
2978 '_type': 'url_transparent',
2979 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2980 'title': video_title,
2981 'description': video_description,
2982 'thumbnail': video_thumbnail,
2983 'uploader': video_uploader,
2984 }
2985 video_id = mobj.group('video_id')
2986 if video_id:
2987 info.update({
2988 'ie_key': 'MangomoloVideo',
2989 'id': video_id,
2990 })
2991 else:
2992 info.update({
2993 'ie_key': 'MangomoloLive',
2994 'id': mobj.group('channel_id'),
2995 })
2996 return info
2997
2998 # Look for Instagram embeds
2999 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3000 if instagram_embed_url is not None:
3001 return self.url_result(
3002 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3003
3004 # Look for LiveLeak embeds
3005 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3006 if liveleak_urls:
3007 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3008
3009 # Look for 3Q SDN embeds
3010 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3011 if threeqsdn_url:
3012 return {
3013 '_type': 'url_transparent',
3014 'ie_key': ThreeQSDNIE.ie_key(),
3015 'url': self._proto_relative_url(threeqsdn_url),
3016 'title': video_title,
3017 'description': video_description,
3018 'thumbnail': video_thumbnail,
3019 'uploader': video_uploader,
3020 }
3021
3022 # Look for VBOX7 embeds
3023 vbox7_url = Vbox7IE._extract_url(webpage)
3024 if vbox7_url:
3025 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3026
3027 # Look for DBTV embeds
3028 dbtv_urls = DBTVIE._extract_urls(webpage)
3029 if dbtv_urls:
3030 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3031
3032 # Look for Videa embeds
3033 videa_urls = VideaIE._extract_urls(webpage)
3034 if videa_urls:
3035 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3036
3037 # Look for 20 minuten embeds
3038 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3039 if twentymin_urls:
3040 return self.playlist_from_matches(
3041 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3042
3043 # Look for Openload embeds
3044 openload_urls = OpenloadIE._extract_urls(webpage)
3045 if openload_urls:
3046 return self.playlist_from_matches(
3047 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3048
3049 # Look for Verystream embeds
3050 verystream_urls = VerystreamIE._extract_urls(webpage)
3051 if verystream_urls:
3052 return self.playlist_from_matches(
3053 verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key())
3054
3055 # Look for VideoPress embeds
3056 videopress_urls = VideoPressIE._extract_urls(webpage)
3057 if videopress_urls:
3058 return self.playlist_from_matches(
3059 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3060
3061 # Look for Rutube embeds
3062 rutube_urls = RutubeIE._extract_urls(webpage)
3063 if rutube_urls:
3064 return self.playlist_from_matches(
3065 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3066
3067 # Look for WashingtonPost embeds
3068 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3069 if wapo_urls:
3070 return self.playlist_from_matches(
3071 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3072
3073 # Look for Mediaset embeds
3074 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3075 if mediaset_urls:
3076 return self.playlist_from_matches(
3077 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3078
3079 # Look for JOJ.sk embeds
3080 joj_urls = JojIE._extract_urls(webpage)
3081 if joj_urls:
3082 return self.playlist_from_matches(
3083 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3084
3085 # Look for megaphone.fm embeds
3086 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3087 if mpfn_urls:
3088 return self.playlist_from_matches(
3089 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3090
3091 # Look for vzaar embeds
3092 vzaar_urls = VzaarIE._extract_urls(webpage)
3093 if vzaar_urls:
3094 return self.playlist_from_matches(
3095 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3096
3097 channel9_urls = Channel9IE._extract_urls(webpage)
3098 if channel9_urls:
3099 return self.playlist_from_matches(
3100 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3101
3102 vshare_urls = VShareIE._extract_urls(webpage)
3103 if vshare_urls:
3104 return self.playlist_from_matches(
3105 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3106
3107 # Look for Mediasite embeds
3108 mediasite_urls = MediasiteIE._extract_urls(webpage)
3109 if mediasite_urls:
3110 entries = [
3111 self.url_result(smuggle_url(
3112 compat_urlparse.urljoin(url, mediasite_url),
3113 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3114 for mediasite_url in mediasite_urls]
3115 return self.playlist_result(entries, video_id, video_title)
3116
3117 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3118 if springboardplatform_urls:
3119 return self.playlist_from_matches(
3120 springboardplatform_urls, video_id, video_title,
3121 ie=SpringboardPlatformIE.ie_key())
3122
3123 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3124 if yapfiles_urls:
3125 return self.playlist_from_matches(
3126 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3127
3128 vice_urls = ViceIE._extract_urls(webpage)
3129 if vice_urls:
3130 return self.playlist_from_matches(
3131 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3132
3133 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3134 if xfileshare_urls:
3135 return self.playlist_from_matches(
3136 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3137
3138 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3139 if cloudflarestream_urls:
3140 return self.playlist_from_matches(
3141 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3142
3143 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3144 if peertube_urls:
3145 return self.playlist_from_matches(
3146 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3147
3148 teachable_url = TeachableIE._extract_url(webpage, url)
3149 if teachable_url:
3150 return self.url_result(teachable_url)
3151
3152 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3153 if indavideo_urls:
3154 return self.playlist_from_matches(
3155 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3156
3157 apa_urls = APAIE._extract_urls(webpage)
3158 if apa_urls:
3159 return self.playlist_from_matches(
3160 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3161
3162 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3163 if foxnews_urls:
3164 return self.playlist_from_matches(
3165 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3166
3167 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3168 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3169 webpage)]
3170 if sharevideos_urls:
3171 return self.playlist_from_matches(
3172 sharevideos_urls, video_id, video_title)
3173
3174 viqeo_urls = ViqeoIE._extract_urls(webpage)
3175 if viqeo_urls:
3176 return self.playlist_from_matches(
3177 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3178
3179 expressen_urls = ExpressenIE._extract_urls(webpage)
3180 if expressen_urls:
3181 return self.playlist_from_matches(
3182 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3183
3184 zype_urls = ZypeIE._extract_urls(webpage)
3185 if zype_urls:
3186 return self.playlist_from_matches(
3187 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3188
3189 # Look for HTML5 media
3190 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3191 if entries:
3192 if len(entries) == 1:
3193 entries[0].update({
3194 'id': video_id,
3195 'title': video_title,
3196 })
3197 else:
3198 for num, entry in enumerate(entries, start=1):
3199 entry.update({
3200 'id': '%s-%s' % (video_id, num),
3201 'title': '%s (%d)' % (video_title, num),
3202 })
3203 for entry in entries:
3204 self._sort_formats(entry['formats'])
3205 return self.playlist_result(entries, video_id, video_title)
3206
3207 jwplayer_data = self._find_jwplayer_data(
3208 webpage, video_id, transform_source=js_to_json)
3209 if jwplayer_data:
3210 try:
3211 info = self._parse_jwplayer_data(
3212 jwplayer_data, video_id, require_title=False, base_url=url)
3213 return merge_dicts(info, info_dict)
3214 except ExtractorError:
3215 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3216 pass
3217
3218 # Video.js embed
3219 mobj = re.search(
3220 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3221 webpage)
3222 if mobj is not None:
3223 sources = self._parse_json(
3224 mobj.group(1), video_id, transform_source=js_to_json,
3225 fatal=False) or []
3226 if not isinstance(sources, list):
3227 sources = [sources]
3228 formats = []
3229 for source in sources:
3230 src = source.get('src')
3231 if not src or not isinstance(src, compat_str):
3232 continue
3233 src = compat_urlparse.urljoin(url, src)
3234 src_type = source.get('type')
3235 if isinstance(src_type, compat_str):
3236 src_type = src_type.lower()
3237 ext = determine_ext(src).lower()
3238 if src_type == 'video/youtube':
3239 return self.url_result(src, YoutubeIE.ie_key())
3240 if src_type == 'application/dash+xml' or ext == 'mpd':
3241 formats.extend(self._extract_mpd_formats(
3242 src, video_id, mpd_id='dash', fatal=False))
3243 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3244 formats.extend(self._extract_m3u8_formats(
3245 src, video_id, 'mp4', entry_protocol='m3u8_native',
3246 m3u8_id='hls', fatal=False))
3247 else:
3248 formats.append({
3249 'url': src,
3250 'ext': (mimetype2ext(src_type)
3251 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3252 })
3253 if formats:
3254 self._sort_formats(formats)
3255 info_dict['formats'] = formats
3256 return info_dict
3257
3258 # Looking for http://schema.org/VideoObject
3259 json_ld = self._search_json_ld(
3260 webpage, video_id, default={}, expected_type='VideoObject')
3261 if json_ld.get('url'):
3262 return merge_dicts(json_ld, info_dict)
3263
3264 def check_video(vurl):
3265 if YoutubeIE.suitable(vurl):
3266 return True
3267 if RtmpIE.suitable(vurl):
3268 return True
3269 vpath = compat_urlparse.urlparse(vurl).path
3270 vext = determine_ext(vpath)
3271 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3272
3273 def filter_video(urls):
3274 return list(filter(check_video, urls))
3275
3276 # Start with something easy: JW Player in SWFObject
3277 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3278 if not found:
3279 # Look for gorilla-vid style embedding
3280 found = filter_video(re.findall(r'''(?sx)
3281 (?:
3282 jw_plugins|
3283 JWPlayerOptions|
3284 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3285 )
3286 .*?
3287 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3288 if not found:
3289 # Broaden the search a little bit
3290 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3291 if not found:
3292 # Broaden the findall a little bit: JWPlayer JS loader
3293 found = filter_video(re.findall(
3294 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3295 if not found:
3296 # Flow player
3297 found = filter_video(re.findall(r'''(?xs)
3298 flowplayer\("[^"]+",\s*
3299 \{[^}]+?\}\s*,
3300 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3301 ["']?url["']?\s*:\s*["']([^"']+)["']
3302 ''', webpage))
3303 if not found:
3304 # Cinerama player
3305 found = re.findall(
3306 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3307 if not found:
3308 # Try to find twitter cards info
3309 # twitter:player:stream should be checked before twitter:player since
3310 # it is expected to contain a raw stream (see
3311 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3312 found = filter_video(re.findall(
3313 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3314 if not found:
3315 # We look for Open Graph info:
3316 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3317 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3318 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3319 if m_video_type is not None:
3320 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3321 if not found:
3322 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3323 found = re.search(
3324 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3325 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3326 webpage)
3327 if not found:
3328 # Look also in Refresh HTTP header
3329 refresh_header = head_response.headers.get('Refresh')
3330 if refresh_header:
3331 # In python 2 response HTTP headers are bytestrings
3332 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3333 refresh_header = refresh_header.decode('iso-8859-1')
3334 found = re.search(REDIRECT_REGEX, refresh_header)
3335 if found:
3336 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3337 if new_url != url:
3338 self.report_following_redirect(new_url)
3339 return {
3340 '_type': 'url',
3341 'url': new_url,
3342 }
3343 else:
3344 found = None
3345
3346 if not found:
3347 # twitter:player is a https URL to iframe player that may or may not
3348 # be supported by youtube-dl thus this is checked the very last (see
3349 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3350 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3351 if embed_url and embed_url != url:
3352 return self.url_result(embed_url)
3353
3354 if not found:
3355 raise UnsupportedError(url)
3356
3357 entries = []
3358 for video_url in orderedSet(found):
3359 video_url = unescapeHTML(video_url)
3360 video_url = video_url.replace('\\/', '/')
3361 video_url = compat_urlparse.urljoin(url, video_url)
3362 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3363
3364 # Sometimes, jwplayer extraction will result in a YouTube URL
3365 if YoutubeIE.suitable(video_url):
3366 entries.append(self.url_result(video_url, 'Youtube'))
3367 continue
3368
3369 # here's a fun little line of code for you:
3370 video_id = os.path.splitext(video_id)[0]
3371
3372 entry_info_dict = {
3373 'id': video_id,
3374 'uploader': video_uploader,
3375 'title': video_title,
3376 'age_limit': age_limit,
3377 }
3378
3379 if RtmpIE.suitable(video_url):
3380 entry_info_dict.update({
3381 '_type': 'url_transparent',
3382 'ie_key': RtmpIE.ie_key(),
3383 'url': video_url,
3384 })
3385 entries.append(entry_info_dict)
3386 continue
3387
3388 ext = determine_ext(video_url)
3389 if ext == 'smil':
3390 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3391 elif ext == 'xspf':
3392 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3393 elif ext == 'm3u8':
3394 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3395 elif ext == 'mpd':
3396 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3397 elif ext == 'f4m':
3398 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3399 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3400 # Just matching .ism/manifest is not enough to be reliably sure
3401 # whether it's actually an ISM manifest or some other streaming
3402 # manifest since there are various streaming URL formats
3403 # possible (see [1]) as well as some other shenanigans like
3404 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3405 # so on.
3406 # Thus the most reasonable way to solve this is to delegate
3407 # to generic extractor in order to look into the contents of
3408 # the manifest itself.
3409 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3410 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3411 entry_info_dict = self.url_result(
3412 smuggle_url(video_url, {'to_generic': True}),
3413 GenericIE.ie_key())
3414 else:
3415 entry_info_dict['url'] = video_url
3416
3417 if entry_info_dict.get('formats'):
3418 self._sort_formats(entry_info_dict['formats'])
3419
3420 entries.append(entry_info_dict)
3421
3422 if len(entries) == 1:
3423 return entries[0]
3424 else:
3425 for num, e in enumerate(entries, start=1):
3426 # 'url' results don't have a title
3427 if e.get('title') is not None:
3428 e['title'] = '%s (%d)' % (e['title'], num)
3429 return {
3430 '_type': 'playlist',
3431 'entries': entries,
3432 }