]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
3c002472f795b3600c8f721e76c446f85f3f9bf5
[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 .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudEmbedIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .videopress import VideoPressIE
92 from .rutube import RutubeIE
93 from .limelight import LimelightBaseIE
94 from .anvato import AnvatoIE
95 from .washingtonpost import WashingtonPostIE
96 from .wistia import WistiaIE
97 from .mediaset import MediasetIE
98 from .joj import JojIE
99 from .megaphone import MegaphoneIE
100 from .vzaar import VzaarIE
101 from .channel9 import Channel9IE
102 from .vshare import VShareIE
103 from .mediasite import MediasiteIE
104 from .springboardplatform import SpringboardPlatformIE
105 from .yapfiles import YapFilesIE
106 from .vice import ViceIE
107 from .xfileshare import XFileShareIE
108 from .cloudflarestream import CloudflareStreamIE
109 from .peertube import PeerTubeIE
110 from .teachable import TeachableIE
111 from .indavideo import IndavideoEmbedIE
112 from .apa import APAIE
113 from .foxnews import FoxNewsIE
114 from .viqeo import ViqeoIE
115 from .expressen import ExpressenIE
116 from .zype import ZypeIE
117 from .odnoklassniki import OdnoklassnikiIE
118 from .kinja import KinjaEmbedIE
119
120
121 class GenericIE(InfoExtractor):
122 IE_DESC = 'Generic downloader that works on some sites'
123 _VALID_URL = r'.*'
124 IE_NAME = 'generic'
125 _TESTS = [
126 # Direct link to a video
127 {
128 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
129 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
130 'info_dict': {
131 'id': 'trailer',
132 'ext': 'mp4',
133 'title': 'trailer',
134 'upload_date': '20100513',
135 }
136 },
137 # Direct link to media delivered compressed (until Accept-Encoding is *)
138 {
139 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
140 'md5': '128c42e68b13950268b648275386fc74',
141 'info_dict': {
142 'id': 'FictionJunction-Parallel_Hearts',
143 'ext': 'flac',
144 'title': 'FictionJunction-Parallel_Hearts',
145 'upload_date': '20140522',
146 },
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
149 ],
150 'skip': 'URL invalid',
151 },
152 # Direct download with broken HEAD
153 {
154 'url': 'http://ai-radio.org:8000/radio.opus',
155 'info_dict': {
156 'id': 'radio',
157 'ext': 'opus',
158 'title': 'radio',
159 },
160 'params': {
161 'skip_download': True, # infinite live stream
162 },
163 'expected_warnings': [
164 r'501.*Not Implemented',
165 r'400.*Bad Request',
166 ],
167 },
168 # Direct link with incorrect MIME type
169 {
170 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
171 'md5': '4ccbebe5f36706d85221f204d7eb5913',
172 'info_dict': {
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'id': '5_Lennart_Poettering_-_Systemd',
175 'ext': 'webm',
176 'title': '5_Lennart_Poettering_-_Systemd',
177 'upload_date': '20141120',
178 },
179 'expected_warnings': [
180 'URL could be a direct video link, returning it as such.'
181 ]
182 },
183 # RSS feed
184 {
185 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
186 'info_dict': {
187 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
188 'title': 'Zero Punctuation',
189 'description': 're:.*groundbreaking video review series.*'
190 },
191 'playlist_mincount': 11,
192 },
193 # RSS feed with enclosure
194 {
195 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
196 'info_dict': {
197 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
198 'ext': 'm4v',
199 'upload_date': '20150228',
200 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 }
202 },
203 # RSS feed with enclosures and unsupported link URLs
204 {
205 'url': 'http://www.hellointernet.fm/podcast?format=rss',
206 'info_dict': {
207 'id': 'http://www.hellointernet.fm/podcast?format=rss',
208 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
209 'title': 'Hello Internet',
210 },
211 'playlist_mincount': 100,
212 },
213 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
214 {
215 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
216 'info_dict': {
217 'id': 'smil',
218 'ext': 'mp4',
219 'title': 'Automatics, robotics and biocybernetics',
220 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
221 'upload_date': '20130627',
222 'formats': 'mincount:16',
223 'subtitles': 'mincount:1',
224 },
225 'params': {
226 'force_generic_extractor': True,
227 'skip_download': True,
228 },
229 },
230 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
231 {
232 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
233 'info_dict': {
234 'id': 'hds',
235 'ext': 'flv',
236 'title': 'hds',
237 'formats': 'mincount:1',
238 },
239 'params': {
240 'skip_download': True,
241 },
242 },
243 # SMIL from https://www.restudy.dk/video/play/id/1637
244 {
245 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
246 'info_dict': {
247 'id': 'video_1637',
248 'ext': 'flv',
249 'title': 'video_1637',
250 'formats': 'mincount:3',
251 },
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
257 {
258 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
259 'info_dict': {
260 'id': 'smil-service',
261 'ext': 'flv',
262 'title': 'smil-service',
263 'formats': 'mincount:1',
264 },
265 'params': {
266 'skip_download': True,
267 },
268 },
269 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
270 {
271 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
272 'info_dict': {
273 'id': '4719370',
274 'ext': 'mp4',
275 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
276 'formats': 'mincount:3',
277 },
278 'params': {
279 'skip_download': True,
280 },
281 },
282 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
283 {
284 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
285 'info_dict': {
286 'id': 'mZlp2ctYIUEB',
287 'ext': 'mp4',
288 'title': 'Tikibad ontruimd wegens brand',
289 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
290 'thumbnail': r're:^https?://.*\.jpg$',
291 'duration': 33,
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # MPD from http://dash-mse-test.appspot.com/media.html
298 {
299 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
300 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
301 'info_dict': {
302 'id': 'car-20120827-manifest',
303 'ext': 'mp4',
304 'title': 'car-20120827-manifest',
305 'formats': 'mincount:9',
306 'upload_date': '20130904',
307 },
308 'params': {
309 'format': 'bestvideo',
310 },
311 },
312 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
313 {
314 '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',
315 'info_dict': {
316 'id': 'content',
317 'ext': 'mp4',
318 'title': 'content',
319 'formats': 'mincount:8',
320 },
321 'params': {
322 # m3u8 downloads
323 'skip_download': True,
324 },
325 'skip': 'video gone',
326 },
327 # m3u8 served with Content-Type: text/plain
328 {
329 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
330 'info_dict': {
331 'id': 'index',
332 'ext': 'mp4',
333 'title': 'index',
334 'upload_date': '20140720',
335 'formats': 'mincount:11',
336 },
337 'params': {
338 # m3u8 downloads
339 'skip_download': True,
340 },
341 'skip': 'video gone',
342 },
343 # google redirect
344 {
345 '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',
346 'info_dict': {
347 'id': 'cmQHVoWB5FY',
348 'ext': 'mp4',
349 'upload_date': '20130224',
350 'uploader_id': 'TheVerge',
351 'description': r're:^Chris Ziegler takes a look at the\.*',
352 'uploader': 'The Verge',
353 'title': 'First Firefox OS phones side-by-side',
354 },
355 'params': {
356 'skip_download': False,
357 }
358 },
359 {
360 # redirect in Refresh HTTP header
361 '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',
362 'info_dict': {
363 'id': 'pO8h3EaFRdo',
364 'ext': 'mp4',
365 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
366 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
367 'upload_date': '20150917',
368 'uploader_id': 'brtvofficial',
369 'uploader': 'Boiler Room',
370 },
371 'params': {
372 'skip_download': False,
373 },
374 },
375 {
376 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
377 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
378 'info_dict': {
379 'id': '13601338388002',
380 'ext': 'mp4',
381 'uploader': 'www.hodiho.fr',
382 'title': 'R\u00e9gis plante sa Jeep',
383 }
384 },
385 # bandcamp page with custom domain
386 {
387 'add_ie': ['Bandcamp'],
388 'url': 'http://bronyrock.com/track/the-pony-mash',
389 'info_dict': {
390 'id': '3235767654',
391 'ext': 'mp3',
392 'title': 'The Pony Mash',
393 'uploader': 'M_Pallante',
394 },
395 'skip': 'There is a limit of 200 free downloads / month for the test song',
396 },
397 {
398 # embedded brightcove video
399 # it also tests brightcove videos that need to set the 'Referer'
400 # in the http requests
401 'add_ie': ['BrightcoveLegacy'],
402 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
403 'info_dict': {
404 'id': '2765128793001',
405 'ext': 'mp4',
406 'title': 'Le cours de bourse : lā€™analyse technique',
407 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
408 'uploader': 'BFM BUSINESS',
409 },
410 'params': {
411 'skip_download': True,
412 },
413 },
414 {
415 # embedded with itemprop embedURL and video id spelled as `idVideo`
416 'add_id': ['BrightcoveLegacy'],
417 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
418 'info_dict': {
419 'id': '5255628253001',
420 'ext': 'mp4',
421 'title': 'md5:37c519b1128915607601e75a87995fc0',
422 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
423 'uploader': 'BFM BUSINESS',
424 'uploader_id': '876450612001',
425 'timestamp': 1482255315,
426 'upload_date': '20161220',
427 },
428 'params': {
429 'skip_download': True,
430 },
431 },
432 {
433 # https://github.com/ytdl-org/youtube-dl/issues/2253
434 'url': 'http://bcove.me/i6nfkrc3',
435 'md5': '0ba9446db037002366bab3b3eb30c88c',
436 'info_dict': {
437 'id': '3101154703001',
438 'ext': 'mp4',
439 'title': 'Still no power',
440 'uploader': 'thestar.com',
441 '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.',
442 },
443 'add_ie': ['BrightcoveLegacy'],
444 'skip': 'video gone',
445 },
446 {
447 'url': 'http://www.championat.com/video/football/v/87/87499.html',
448 'md5': 'fb973ecf6e4a78a67453647444222983',
449 'info_dict': {
450 'id': '3414141473001',
451 'ext': 'mp4',
452 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
453 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
454 'uploader': 'Championat',
455 },
456 },
457 {
458 # https://github.com/ytdl-org/youtube-dl/issues/3541
459 'add_ie': ['BrightcoveLegacy'],
460 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
461 'info_dict': {
462 'id': '3866516442001',
463 'ext': 'mp4',
464 'title': 'Leer mij vrouwen kennen: Aflevering 1',
465 'description': 'Leer mij vrouwen kennen: Aflevering 1',
466 'uploader': 'SBS Broadcasting',
467 },
468 'skip': 'Restricted to Netherlands',
469 'params': {
470 'skip_download': True, # m3u8 download
471 },
472 },
473 {
474 # Brightcove video in <iframe>
475 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
476 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
477 'info_dict': {
478 'id': '5360463607001',
479 'ext': 'mp4',
480 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
481 '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€‚',
482 'uploader': 'United Nations',
483 'uploader_id': '1362235914001',
484 'timestamp': 1489593889,
485 'upload_date': '20170315',
486 },
487 'add_ie': ['BrightcoveLegacy'],
488 },
489 {
490 # Brightcove with alternative playerID key
491 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
492 'info_dict': {
493 'id': 'nmeth.2062_SV1',
494 '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',
495 },
496 'playlist': [{
497 'info_dict': {
498 'id': '2228375078001',
499 'ext': 'mp4',
500 'title': 'nmeth.2062-sv1',
501 'description': 'nmeth.2062-sv1',
502 'timestamp': 1363357591,
503 'upload_date': '20130315',
504 'uploader': 'Nature Publishing Group',
505 'uploader_id': '1964492299001',
506 },
507 }],
508 },
509 {
510 # Brightcove with UUID in videoPlayer
511 'url': 'http://www8.hp.com/cn/zh/home.html',
512 'info_dict': {
513 'id': '5255815316001',
514 'ext': 'mp4',
515 'title': 'Sprocket Video - China',
516 'description': 'Sprocket Video - China',
517 'uploader': 'HP-Video Gallery',
518 'timestamp': 1482263210,
519 'upload_date': '20161220',
520 'uploader_id': '1107601872001',
521 },
522 'params': {
523 'skip_download': True, # m3u8 download
524 },
525 'skip': 'video rotates...weekly?',
526 },
527 {
528 # Brightcove:new type [2].
529 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
530 'md5': '2b35148fcf48da41c9fb4591650784f3',
531 'info_dict': {
532 'id': '5348741021001',
533 'ext': 'mp4',
534 'upload_date': '20170306',
535 'uploader_id': '4191638492001',
536 'timestamp': 1488769918,
537 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
538
539 },
540 },
541 {
542 # Alternative brightcove <video> attributes
543 '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/',
544 'info_dict': {
545 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
546 '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",
547 },
548 'playlist': [{
549 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
550 'info_dict': {
551 'id': '5311302538001',
552 'ext': 'mp4',
553 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
554 '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)",
555 'timestamp': 1486321708,
556 'upload_date': '20170205',
557 'uploader_id': '800000640001',
558 },
559 'only_matching': True,
560 }],
561 },
562 {
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'info_dict': {
566 'id': '5255815316001',
567 'ext': 'mp4',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
574 },
575 'params': {
576 'skip_download': True, # m3u8 download
577 },
578 },
579 # ooyala video
580 {
581 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
582 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
583 'info_dict': {
584 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
585 'ext': 'mp4',
586 'title': '2cc213299525360.mov', # that's what we get
587 'duration': 238.231,
588 },
589 'add_ie': ['Ooyala'],
590 },
591 {
592 # ooyala video embedded with http://player.ooyala.com/iframe.js
593 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
594 'info_dict': {
595 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
596 'ext': 'mp4',
597 'title': '"Steve Jobs: Man in the Machine" trailer',
598 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
599 'duration': 135.427,
600 },
601 'params': {
602 'skip_download': True,
603 },
604 'skip': 'movie expired',
605 },
606 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
607 {
608 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
609 'info_dict': {
610 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
611 'ext': 'mp4',
612 'title': 'Steampunk Fest Comes to Honesdale',
613 'duration': 43.276,
614 },
615 'params': {
616 'skip_download': True,
617 }
618 },
619 # embed.ly video
620 {
621 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
622 'info_dict': {
623 'id': '9ODmcdjQcHQ',
624 'ext': 'mp4',
625 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
626 'upload_date': '20140225',
627 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
628 'uploader': 'Tested',
629 'uploader_id': 'testedcom',
630 },
631 # No need to test YoutubeIE here
632 'params': {
633 'skip_download': True,
634 },
635 },
636 # funnyordie embed
637 {
638 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
639 'info_dict': {
640 'id': '18e820ec3f',
641 'ext': 'mp4',
642 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
643 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
644 },
645 # HEAD requests lead to endless 301, while GET is OK
646 'expected_warnings': ['301'],
647 },
648 # RUTV embed
649 {
650 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
651 'info_dict': {
652 'id': '776940',
653 'ext': 'mp4',
654 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
655 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
656 },
657 'params': {
658 # m3u8 download
659 'skip_download': True,
660 },
661 },
662 # TVC embed
663 {
664 '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/',
665 'info_dict': {
666 'id': '55304',
667 'ext': 'mp4',
668 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
669 },
670 },
671 # SportBox embed
672 {
673 'url': 'http://www.vestifinance.ru/articles/25753',
674 'info_dict': {
675 'id': '25753',
676 '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"',
677 },
678 'playlist': [{
679 'info_dict': {
680 'id': '370908',
681 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
682 'ext': 'mp4',
683 }
684 }, {
685 'info_dict': {
686 'id': '370905',
687 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
688 'ext': 'mp4',
689 }
690 }, {
691 'info_dict': {
692 'id': '370902',
693 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
694 'ext': 'mp4',
695 }
696 }],
697 'params': {
698 # m3u8 download
699 'skip_download': True,
700 },
701 },
702 # Myvi.ru embed
703 {
704 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
705 'info_dict': {
706 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
707 'ext': 'mp4',
708 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
709 'thumbnail': r're:^https?://.*\.jpg$',
710 'duration': 153,
711 }
712 },
713 # XHamster embed
714 {
715 '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',
716 'info_dict': {
717 'id': 'showthread',
718 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
719 },
720 'playlist_mincount': 7,
721 # This forum does not allow <iframe> syntaxes anymore
722 # Now HTML tags are displayed as-is
723 'skip': 'No videos on this page',
724 },
725 # Embedded TED video
726 {
727 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
728 'md5': '65fdff94098e4a607385a60c5177c638',
729 'info_dict': {
730 'id': '1969',
731 'ext': 'mp4',
732 'title': 'Hidden miracles of the natural world',
733 'uploader': 'Louie Schwartzberg',
734 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
735 }
736 },
737 # nowvideo embed hidden behind percent encoding
738 {
739 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
740 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
741 'info_dict': {
742 'id': '06e53103ca9aa',
743 'ext': 'flv',
744 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
745 'description': 'No description',
746 },
747 },
748 # arte embed
749 {
750 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
751 'md5': '7653032cbb25bf6c80d80f217055fa43',
752 'info_dict': {
753 'id': '048195-004_PLUS7-F',
754 'ext': 'flv',
755 'title': 'X:enius',
756 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
757 'upload_date': '20140320',
758 },
759 'params': {
760 'skip_download': 'Requires rtmpdump'
761 },
762 'skip': 'video gone',
763 },
764 # francetv embed
765 {
766 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
767 'info_dict': {
768 'id': 'EV_30231',
769 'ext': 'mp4',
770 'title': 'Alcaline, le concert avec Calogero',
771 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
772 'upload_date': '20150226',
773 'timestamp': 1424989860,
774 'duration': 5400,
775 },
776 'params': {
777 # m3u8 downloads
778 'skip_download': True,
779 },
780 'expected_warnings': [
781 'Forbidden'
782 ]
783 },
784 # CondƩ Nast embed
785 {
786 'url': 'http://www.wired.com/2014/04/honda-asimo/',
787 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
788 'info_dict': {
789 'id': '53501be369702d3275860000',
790 'ext': 'mp4',
791 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
792 }
793 },
794 # Dailymotion embed
795 {
796 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
797 'md5': '441aeeb82eb72c422c7f14ec533999cd',
798 'info_dict': {
799 'id': 'k2mm4bCdJ6CQ2i7c8o2',
800 'ext': 'mp4',
801 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
802 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
803 'uploader': 'Spi0n',
804 'uploader_id': 'xgditw',
805 'upload_date': '20140425',
806 'timestamp': 1398441542,
807 },
808 'add_ie': ['Dailymotion'],
809 },
810 # DailyMail embed
811 {
812 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
813 'info_dict': {
814 'id': '1495629',
815 'ext': 'mp4',
816 'title': 'Care worker punches elderly dementia patient in head 11 times',
817 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
818 },
819 'add_ie': ['DailyMail'],
820 'params': {
821 'skip_download': True,
822 },
823 },
824 # YouTube embed
825 {
826 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
827 'info_dict': {
828 'id': 'FXRb4ykk4S0',
829 'ext': 'mp4',
830 'title': 'The NBL Auction 2014',
831 'uploader': 'BADMINTON England',
832 'uploader_id': 'BADMINTONEvents',
833 'upload_date': '20140603',
834 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
835 },
836 'add_ie': ['Youtube'],
837 'params': {
838 'skip_download': True,
839 }
840 },
841 # MTVSercices embed
842 {
843 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
844 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
845 'info_dict': {
846 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
847 'ext': 'mp4',
848 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
849 'description': 'Two valets share their love for movie star Liam Neesons.',
850 'timestamp': 1349922600,
851 'upload_date': '20121011',
852 },
853 },
854 # YouTube embed via <data-embed-url="">
855 {
856 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
857 'info_dict': {
858 'id': '4vAffPZIT44',
859 'ext': 'mp4',
860 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
861 'uploader': 'Gameloft',
862 'uploader_id': 'gameloft',
863 'upload_date': '20140828',
864 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
865 },
866 'params': {
867 'skip_download': True,
868 }
869 },
870 # YouTube <object> embed
871 {
872 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
873 'md5': '516718101ec834f74318df76259fb3cc',
874 'info_dict': {
875 'id': 'msN87y-iEx0',
876 'ext': 'webm',
877 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
878 'upload_date': '20080526',
879 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
880 'uploader': 'Christopher Sykes',
881 'uploader_id': 'ChristopherJSykes',
882 },
883 'add_ie': ['Youtube'],
884 },
885 # Camtasia studio
886 {
887 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
888 'playlist': [{
889 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
890 'info_dict': {
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
893 'ext': 'flv',
894 'duration': 2235.90,
895 }
896 }, {
897 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
898 'info_dict': {
899 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
901 'ext': 'flv',
902 'duration': 2235.93,
903 }
904 }],
905 'info_dict': {
906 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
907 }
908 },
909 # Flowplayer
910 {
911 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
912 'md5': '9d65602bf31c6e20014319c7d07fba27',
913 'info_dict': {
914 'id': '5123ea6d5e5a7',
915 'ext': 'mp4',
916 'age_limit': 18,
917 'uploader': 'www.handjobhub.com',
918 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
919 }
920 },
921 # Multiple brightcove videos
922 # https://github.com/ytdl-org/youtube-dl/issues/2283
923 {
924 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
925 'info_dict': {
926 'id': 'always-never',
927 'title': 'Always / Never - The New Yorker',
928 },
929 'playlist_count': 3,
930 'params': {
931 'extract_flat': False,
932 'skip_download': True,
933 }
934 },
935 # MLB embed
936 {
937 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
938 'md5': '96f09a37e44da40dd083e12d9a683327',
939 'info_dict': {
940 'id': '33322633',
941 'ext': 'mp4',
942 'title': 'Ump changes call to ball',
943 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
944 'duration': 48,
945 'timestamp': 1401537900,
946 'upload_date': '20140531',
947 'thumbnail': r're:^https?://.*\.jpg$',
948 },
949 },
950 # Wistia embed
951 {
952 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
953 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
954 'info_dict': {
955 'id': '6e2wtrbdaf',
956 'ext': 'mov',
957 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
958 'description': 'a Paywall Videos video from Remilon',
959 'duration': 644.072,
960 'uploader': 'study.com',
961 'timestamp': 1459678540,
962 'upload_date': '20160403',
963 'filesize': 24687186,
964 },
965 },
966 {
967 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
968 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
969 'info_dict': {
970 'id': 'uxjb0lwrcz',
971 'ext': 'mp4',
972 'title': 'Conversation about Hexagonal Rails Part 1',
973 'description': 'a Martin Fowler video from ThoughtWorks',
974 'duration': 1715.0,
975 'uploader': 'thoughtworks.wistia.com',
976 'timestamp': 1401832161,
977 'upload_date': '20140603',
978 },
979 },
980 # Wistia standard embed (async)
981 {
982 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
983 'info_dict': {
984 'id': '807fafadvk',
985 'ext': 'mp4',
986 'title': 'Drip Brennan Dunn Workshop',
987 'description': 'a JV Webinars video from getdrip-1',
988 'duration': 4986.95,
989 'timestamp': 1463607249,
990 'upload_date': '20160518',
991 },
992 'params': {
993 'skip_download': True,
994 }
995 },
996 # Soundcloud embed
997 {
998 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
999 'info_dict': {
1000 'id': '174391317',
1001 'ext': 'mp3',
1002 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1003 'uploader': 'Sophos Security',
1004 'title': 'Chet Chat 171 - Oct 29, 2014',
1005 'upload_date': '20141029',
1006 }
1007 },
1008 # Soundcloud multiple embeds
1009 {
1010 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1011 'info_dict': {
1012 'id': '52809',
1013 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
1014 },
1015 'playlist_mincount': 7,
1016 },
1017 # TuneIn station embed
1018 {
1019 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1020 'info_dict': {
1021 'id': '204146',
1022 'ext': 'mp3',
1023 'title': 'CNRV',
1024 'location': 'Paris, France',
1025 'is_live': True,
1026 },
1027 'params': {
1028 # Live stream
1029 'skip_download': True,
1030 },
1031 },
1032 # Livestream embed
1033 {
1034 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1035 'info_dict': {
1036 'id': '67864563',
1037 'ext': 'flv',
1038 'upload_date': '20141112',
1039 'title': 'Rosetta #CometLanding webcast HL 10',
1040 }
1041 },
1042 # Another Livestream embed, without 'new.' in URL
1043 {
1044 'url': 'https://www.freespeech.org/',
1045 'info_dict': {
1046 'id': '123537347',
1047 'ext': 'mp4',
1048 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1049 },
1050 'params': {
1051 # Live stream
1052 'skip_download': True,
1053 },
1054 },
1055 # LazyYT
1056 {
1057 'url': 'https://skiplagged.com/',
1058 'info_dict': {
1059 'id': 'skiplagged',
1060 'title': 'Skiplagged: The smart way to find cheap flights',
1061 },
1062 'playlist_mincount': 1,
1063 'add_ie': ['Youtube'],
1064 },
1065 # Cinchcast embed
1066 {
1067 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1068 'info_dict': {
1069 'id': '7141703',
1070 'ext': 'mp3',
1071 'upload_date': '20141126',
1072 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1073 }
1074 },
1075 # Cinerama player
1076 {
1077 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1078 'info_dict': {
1079 'id': '730m_DandD_1901_512k',
1080 'ext': 'mp4',
1081 'uploader': 'www.abc.net.au',
1082 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1083 }
1084 },
1085 # embedded viddler video
1086 {
1087 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1088 'info_dict': {
1089 'id': '4d03aad9',
1090 'ext': 'mp4',
1091 'uploader': 'deadspin',
1092 'title': 'WALL-TO-GORTAT',
1093 'timestamp': 1422285291,
1094 'upload_date': '20150126',
1095 },
1096 'add_ie': ['Viddler'],
1097 },
1098 # Libsyn embed
1099 {
1100 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1101 'info_dict': {
1102 'id': '3377616',
1103 'ext': 'mp3',
1104 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1105 'description': 'md5:601cb790edd05908957dae8aaa866465',
1106 'upload_date': '20150220',
1107 },
1108 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1109 },
1110 # jwplayer YouTube
1111 {
1112 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1113 'info_dict': {
1114 'id': 'Mrj4DVp2zeA',
1115 'ext': 'mp4',
1116 'upload_date': '20150212',
1117 'uploader': 'The National Archives UK',
1118 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1119 'uploader_id': 'NationalArchives08',
1120 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1121 },
1122 },
1123 # jwplayer rtmp
1124 {
1125 'url': 'http://www.suffolk.edu/sjc/live.php',
1126 'info_dict': {
1127 'id': 'live',
1128 'ext': 'flv',
1129 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1130 'uploader': 'www.suffolk.edu',
1131 },
1132 'params': {
1133 'skip_download': True,
1134 },
1135 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1136 },
1137 # Complex jwplayer
1138 {
1139 'url': 'http://www.indiedb.com/games/king-machine/videos',
1140 'info_dict': {
1141 'id': 'videos',
1142 'ext': 'mp4',
1143 'title': 'king machine trailer 1',
1144 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1145 'thumbnail': r're:^https?://.*\.jpg$',
1146 },
1147 },
1148 {
1149 # JWPlayer config passed as variable
1150 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1151 'info_dict': {
1152 'id': '3326530_hq',
1153 'ext': 'mp4',
1154 'title': 'ARIELE | Tube Cup',
1155 'uploader': 'www.txxx.com',
1156 'age_limit': 18,
1157 },
1158 'params': {
1159 'skip_download': True,
1160 }
1161 },
1162 {
1163 # JWPlatform iframe
1164 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1165 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1166 'info_dict': {
1167 'id': 'O0c5JcKT',
1168 'ext': 'mp4',
1169 'upload_date': '20171122',
1170 'timestamp': 1511366290,
1171 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1172 },
1173 'add_ie': [JWPlatformIE.ie_key()],
1174 },
1175 {
1176 # Video.js embed, multiple formats
1177 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1178 'info_dict': {
1179 'id': 'yygqldloqIk',
1180 'ext': 'mp4',
1181 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1182 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1183 'upload_date': '20130314',
1184 'uploader': 'PROстŠ¾Šµ3D',
1185 'uploader_id': 'PROstoe3D',
1186 },
1187 'params': {
1188 'skip_download': True,
1189 },
1190 },
1191 {
1192 # Video.js embed, single format
1193 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1194 'info_dict': {
1195 'id': 'watch',
1196 'ext': 'mp4',
1197 'title': 'Step 1 - Good Foundation',
1198 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1199 },
1200 'params': {
1201 'skip_download': True,
1202 },
1203 },
1204 # rtl.nl embed
1205 {
1206 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1207 'playlist_mincount': 5,
1208 'info_dict': {
1209 'id': 'aanslagen-kopenhagen',
1210 'title': 'Aanslagen Kopenhagen',
1211 }
1212 },
1213 # Zapiks embed
1214 {
1215 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1216 'info_dict': {
1217 'id': '118046',
1218 'ext': 'mp4',
1219 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1220 }
1221 },
1222 # Kaltura embed (different embed code)
1223 {
1224 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1225 'info_dict': {
1226 'id': '1_a52wc67y',
1227 'ext': 'flv',
1228 'upload_date': '20150127',
1229 'uploader_id': 'PremierMedia',
1230 'timestamp': int,
1231 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1232 },
1233 },
1234 # Kaltura embed with single quotes
1235 {
1236 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1237 'info_dict': {
1238 'id': '0_izeg5utt',
1239 'ext': 'mp4',
1240 'title': '35871',
1241 'timestamp': 1355743100,
1242 'upload_date': '20121217',
1243 'uploader_id': 'cplapp@learn360.com',
1244 },
1245 'add_ie': ['Kaltura'],
1246 },
1247 {
1248 # Kaltura embedded via quoted entry_id
1249 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1250 'info_dict': {
1251 'id': '0_utuok90b',
1252 'ext': 'mp4',
1253 'title': '06_matthew_brender_raj_dutt',
1254 'timestamp': 1466638791,
1255 'upload_date': '20160622',
1256 },
1257 'add_ie': ['Kaltura'],
1258 'expected_warnings': [
1259 'Could not send HEAD request'
1260 ],
1261 'params': {
1262 'skip_download': True,
1263 }
1264 },
1265 {
1266 # Kaltura embedded, some fileExt broken (#11480)
1267 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1268 'info_dict': {
1269 'id': '1_sgtvehim',
1270 'ext': 'mp4',
1271 'title': 'Our "Standard Models" of particle physics and cosmology',
1272 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1273 'timestamp': 1321158993,
1274 'upload_date': '20111113',
1275 'uploader_id': 'kps1',
1276 },
1277 'add_ie': ['Kaltura'],
1278 },
1279 {
1280 # Kaltura iframe embed
1281 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1282 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1283 'info_dict': {
1284 'id': '0_f2cfbpwy',
1285 'ext': 'mp4',
1286 'title': 'I. M. Pei: A Centennial Celebration',
1287 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1288 'upload_date': '20170403',
1289 'uploader_id': 'batchUser',
1290 'timestamp': 1491232186,
1291 },
1292 'add_ie': ['Kaltura'],
1293 },
1294 {
1295 # Kaltura iframe embed, more sophisticated
1296 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1297 'info_dict': {
1298 'id': '1_9gzouybz',
1299 'ext': 'mp4',
1300 'title': 'lecture-05sep2017',
1301 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1302 'upload_date': '20170913',
1303 'uploader_id': 'eps2',
1304 'timestamp': 1505340777,
1305 },
1306 'params': {
1307 'skip_download': True,
1308 },
1309 'add_ie': ['Kaltura'],
1310 },
1311 {
1312 # meta twitter:player
1313 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1314 'info_dict': {
1315 'id': '0_01b42zps',
1316 'ext': 'mp4',
1317 'title': 'Main Twerk (Video)',
1318 'upload_date': '20171208',
1319 'uploader_id': 'sebastian.salinas@thechive.com',
1320 'timestamp': 1512713057,
1321 },
1322 'params': {
1323 'skip_download': True,
1324 },
1325 'add_ie': ['Kaltura'],
1326 },
1327 # referrer protected EaglePlatform embed
1328 {
1329 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1330 'info_dict': {
1331 'id': '582306',
1332 'ext': 'mp4',
1333 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1334 'thumbnail': r're:^https?://.*\.jpg$',
1335 'duration': 3382,
1336 'view_count': int,
1337 },
1338 'params': {
1339 'skip_download': True,
1340 },
1341 },
1342 # ClipYou (EaglePlatform) embed (custom URL)
1343 {
1344 'url': 'http://muz-tv.ru/play/7129/',
1345 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1346 'info_dict': {
1347 'id': '12820',
1348 'ext': 'mp4',
1349 'title': "'O Sole Mio",
1350 'thumbnail': r're:^https?://.*\.jpg$',
1351 'duration': 216,
1352 'view_count': int,
1353 },
1354 'params': {
1355 'skip_download': True,
1356 },
1357 'skip': 'This video is unavailable.',
1358 },
1359 # Pladform embed
1360 {
1361 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1362 'info_dict': {
1363 'id': '100183293',
1364 'ext': 'mp4',
1365 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1366 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1367 'thumbnail': r're:^https?://.*\.jpg$',
1368 'duration': 694,
1369 'age_limit': 0,
1370 },
1371 'skip': 'HTTP Error 404: Not Found',
1372 },
1373 # Playwire embed
1374 {
1375 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1376 'info_dict': {
1377 'id': '3519514',
1378 'ext': 'mp4',
1379 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1380 'thumbnail': r're:^https?://.*\.png$',
1381 'duration': 45.115,
1382 },
1383 },
1384 # 5min embed
1385 {
1386 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1387 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1388 'info_dict': {
1389 'id': '518726732',
1390 'ext': 'mp4',
1391 'title': 'Facebook Creates "On This Day" | Crunch Report',
1392 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1393 'timestamp': 1427237531,
1394 'uploader': 'Crunch Report',
1395 'upload_date': '20150324',
1396 },
1397 'params': {
1398 # m3u8 download
1399 'skip_download': True,
1400 },
1401 },
1402 # Crooks and Liars embed
1403 {
1404 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1405 'info_dict': {
1406 'id': '8RUoRhRi',
1407 'ext': 'mp4',
1408 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1409 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1410 'timestamp': 1428207000,
1411 'upload_date': '20150405',
1412 'uploader': 'Heather',
1413 },
1414 },
1415 # Crooks and Liars external embed
1416 {
1417 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1418 'info_dict': {
1419 'id': 'MTE3MjUtMzQ2MzA',
1420 'ext': 'mp4',
1421 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1422 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1423 'timestamp': 1265032391,
1424 'upload_date': '20100201',
1425 'uploader': 'Heather',
1426 },
1427 },
1428 # NBC Sports vplayer embed
1429 {
1430 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1431 'info_dict': {
1432 'id': 'ln7x1qSThw4k',
1433 'ext': 'flv',
1434 'title': "PFT Live: New leader in the 'new-look' defense",
1435 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1436 'uploader': 'NBCU-SPORTS',
1437 'upload_date': '20140107',
1438 'timestamp': 1389118457,
1439 },
1440 'skip': 'Invalid Page URL',
1441 },
1442 # NBC News embed
1443 {
1444 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1445 'md5': '1aa589c675898ae6d37a17913cf68d66',
1446 'info_dict': {
1447 'id': 'x_dtl_oa_LettermanliftPR_160608',
1448 'ext': 'mp4',
1449 'title': 'David Letterman: A Preview',
1450 '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.',
1451 'upload_date': '20160609',
1452 'timestamp': 1465431544,
1453 'uploader': 'NBCU-NEWS',
1454 },
1455 },
1456 # UDN embed
1457 {
1458 'url': 'https://video.udn.com/news/300346',
1459 'md5': 'fd2060e988c326991037b9aff9df21a6',
1460 'info_dict': {
1461 'id': '300346',
1462 'ext': 'mp4',
1463 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1464 'thumbnail': r're:^https?://.*\.jpg$',
1465 },
1466 'params': {
1467 # m3u8 download
1468 'skip_download': True,
1469 },
1470 'expected_warnings': ['Failed to parse JSON Expecting value'],
1471 },
1472 # Brightcove URL in single quotes
1473 {
1474 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1475 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1476 'info_dict': {
1477 'id': '4255764656001',
1478 'ext': 'mp4',
1479 'title': 'SN Presents: Russell Martin, World Citizen',
1480 '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.',
1481 'uploader': 'Rogers Sportsnet',
1482 'uploader_id': '1704050871',
1483 'upload_date': '20150525',
1484 'timestamp': 1432570283,
1485 },
1486 },
1487 # Kinja embed
1488 {
1489 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1490 'info_dict': {
1491 'id': '106351',
1492 'ext': 'mp4',
1493 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1494 'description': 'Migrated from OnionStudios',
1495 'thumbnail': r're:^https?://.*\.jpe?g$',
1496 'uploader': 'clickhole',
1497 'upload_date': '20150527',
1498 'timestamp': 1432744860,
1499 }
1500 },
1501 # SnagFilms embed
1502 {
1503 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1504 'info_dict': {
1505 'id': '74849a00-85a9-11e1-9660-123139220831',
1506 'ext': 'mp4',
1507 'title': '#whilewewatch',
1508 }
1509 },
1510 # AdobeTVVideo embed
1511 {
1512 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1513 'md5': '43662b577c018ad707a63766462b1e87',
1514 'info_dict': {
1515 'id': '2456',
1516 'ext': 'mp4',
1517 'title': 'New experience with Acrobat DC',
1518 'description': 'New experience with Acrobat DC',
1519 'duration': 248.667,
1520 },
1521 },
1522 # BrightcoveInPageEmbed embed
1523 {
1524 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1525 'info_dict': {
1526 'id': '4238694884001',
1527 'ext': 'flv',
1528 'title': 'Tabletop: Dread, Last Thoughts',
1529 'description': 'Tabletop: Dread, Last Thoughts',
1530 'duration': 51690,
1531 },
1532 },
1533 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1534 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1535 {
1536 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1537 'info_dict': {
1538 'id': '4785848093001',
1539 'ext': 'mp4',
1540 'title': 'The Cardinal Pell Interview',
1541 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1542 'uploader': 'GlobeCast Australia - GlobeStream',
1543 'uploader_id': '2733773828001',
1544 'upload_date': '20160304',
1545 'timestamp': 1457083087,
1546 },
1547 'params': {
1548 # m3u8 downloads
1549 'skip_download': True,
1550 },
1551 },
1552 {
1553 # Brightcove embed with whitespace around attribute names
1554 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1555 'info_dict': {
1556 'id': '3167554373001',
1557 'ext': 'mp4',
1558 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1559 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1560 'uploader_id': '1079349493',
1561 'upload_date': '20140207',
1562 'timestamp': 1391810548,
1563 },
1564 'params': {
1565 'skip_download': True,
1566 },
1567 },
1568 # Another form of arte.tv embed
1569 {
1570 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1571 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1572 'info_dict': {
1573 'id': '030273-562_PLUS7-F',
1574 'ext': 'mp4',
1575 'title': 'ARTE Reportage - Nulle part, en France',
1576 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1577 'upload_date': '20160409',
1578 },
1579 },
1580 # LiveLeak embed
1581 {
1582 'url': 'http://www.wykop.pl/link/3088787/',
1583 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1584 'info_dict': {
1585 'id': '874_1459135191',
1586 'ext': 'mp4',
1587 'title': 'Man shows poor quality of new apartment building',
1588 'description': 'The wall is like a sand pile.',
1589 'uploader': 'Lake8737',
1590 },
1591 'add_ie': [LiveLeakIE.ie_key()],
1592 },
1593 # Another LiveLeak embed pattern (#13336)
1594 {
1595 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1596 'info_dict': {
1597 'id': '2eb_1496309988',
1598 'ext': 'mp4',
1599 'title': 'Thief robs place where everyone was armed',
1600 'description': 'md5:694d73ee79e535953cf2488562288eee',
1601 'uploader': 'brazilwtf',
1602 },
1603 'add_ie': [LiveLeakIE.ie_key()],
1604 },
1605 # Duplicated embedded video URLs
1606 {
1607 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1608 'info_dict': {
1609 'id': '149298443_480_16c25b74_2',
1610 'ext': 'mp4',
1611 'title': 'vs. Blue Orange Spring Game',
1612 'uploader': 'www.hudl.com',
1613 },
1614 },
1615 # twitter:player:stream embed
1616 {
1617 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1618 'info_dict': {
1619 'id': 'master',
1620 'ext': 'mp4',
1621 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1622 'uploader': 'www.rtl.be',
1623 },
1624 'params': {
1625 # m3u8 downloads
1626 'skip_download': True,
1627 },
1628 },
1629 # twitter:player embed
1630 {
1631 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1632 'md5': 'a3e0df96369831de324f0778e126653c',
1633 'info_dict': {
1634 'id': '4909620399001',
1635 'ext': 'mp4',
1636 'title': 'What Do Black Holes Sound Like?',
1637 'description': 'what do black holes sound like',
1638 'upload_date': '20160524',
1639 'uploader_id': '29913724001',
1640 'timestamp': 1464107587,
1641 'uploader': 'TheAtlantic',
1642 },
1643 'add_ie': ['BrightcoveLegacy'],
1644 },
1645 # Facebook <iframe> embed
1646 {
1647 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1648 'md5': 'fbcde74f534176ecb015849146dd3aee',
1649 'info_dict': {
1650 'id': '599637780109885',
1651 'ext': 'mp4',
1652 'title': 'Facebook video #599637780109885',
1653 },
1654 },
1655 # Facebook <iframe> embed, plugin video
1656 {
1657 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1658 'info_dict': {
1659 'id': '1754168231264132',
1660 'ext': 'mp4',
1661 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1662 'uploader': 'Tariq Ramadan (official)',
1663 'timestamp': 1496758379,
1664 'upload_date': '20170606',
1665 },
1666 'params': {
1667 'skip_download': True,
1668 },
1669 },
1670 # Facebook API embed
1671 {
1672 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1673 'md5': 'a47372ee61b39a7b90287094d447d94e',
1674 'info_dict': {
1675 'id': '10153467542406923',
1676 'ext': 'mp4',
1677 'title': 'Facebook video #10153467542406923',
1678 },
1679 },
1680 # Wordpress "YouTube Video Importer" plugin
1681 {
1682 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1683 'md5': 'd16797741b560b485194eddda8121b48',
1684 'info_dict': {
1685 'id': 'HNTXWDXV9Is',
1686 'ext': 'mp4',
1687 'title': 'Blue Devils Drumline Stanford lot 2016',
1688 'upload_date': '20160627',
1689 'uploader_id': 'GENOCIDE8GENERAL10',
1690 'uploader': 'cylus cyrus',
1691 },
1692 },
1693 {
1694 # video stored on custom kaltura server
1695 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1696 'md5': '537617d06e64dfed891fa1593c4b30cc',
1697 'info_dict': {
1698 'id': '0_1iotm5bh',
1699 'ext': 'mp4',
1700 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1701 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1702 'uploader_id': 'videos.expansion@el-mundo.net',
1703 'upload_date': '20150429',
1704 'timestamp': 1430303472,
1705 },
1706 'add_ie': ['Kaltura'],
1707 },
1708 {
1709 # Non-standard Vimeo embed
1710 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1711 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1712 'info_dict': {
1713 'id': '148867247',
1714 'ext': 'mp4',
1715 'title': 'Understanding the web - Teaser',
1716 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1717 'upload_date': '20151214',
1718 'uploader': 'OpenClassrooms',
1719 'uploader_id': 'openclassrooms',
1720 },
1721 'add_ie': ['Vimeo'],
1722 },
1723 {
1724 # generic vimeo embed that requires original URL passed as Referer
1725 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1726 'only_matching': True,
1727 },
1728 {
1729 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1730 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1731 'info_dict': {
1732 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1733 'ext': 'mp4',
1734 'title': 'Big Buck Bunny',
1735 'description': 'Royalty free test video',
1736 'timestamp': 1432816365,
1737 'upload_date': '20150528',
1738 'is_live': False,
1739 },
1740 'params': {
1741 'skip_download': True,
1742 },
1743 'add_ie': [ArkenaIE.ie_key()],
1744 },
1745 {
1746 '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/',
1747 'info_dict': {
1748 'id': '1c7141f46c',
1749 'ext': 'mp4',
1750 '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',
1751 },
1752 'params': {
1753 'skip_download': True,
1754 },
1755 'add_ie': [Vbox7IE.ie_key()],
1756 },
1757 {
1758 # DBTV embeds
1759 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1760 'info_dict': {
1761 'id': '43254897',
1762 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1763 },
1764 'playlist_mincount': 3,
1765 },
1766 {
1767 # Videa embeds
1768 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1769 'info_dict': {
1770 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1771 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1772 },
1773 'playlist_mincount': 2,
1774 },
1775 {
1776 # 20 minuten embed
1777 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1778 'info_dict': {
1779 'id': '523629',
1780 'ext': 'mp4',
1781 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1782 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1783 },
1784 'params': {
1785 'skip_download': True,
1786 },
1787 'add_ie': [TwentyMinutenIE.ie_key()],
1788 },
1789 {
1790 # VideoPress embed
1791 'url': 'https://en.support.wordpress.com/videopress/',
1792 'info_dict': {
1793 'id': 'OcobLTqC',
1794 'ext': 'm4v',
1795 'title': 'IMG_5786',
1796 'timestamp': 1435711927,
1797 'upload_date': '20150701',
1798 },
1799 'params': {
1800 'skip_download': True,
1801 },
1802 'add_ie': [VideoPressIE.ie_key()],
1803 },
1804 {
1805 # Rutube embed
1806 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1807 'info_dict': {
1808 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1809 'ext': 'flv',
1810 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1811 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1812 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1813 'upload_date': '20170228',
1814 'uploader_id': '996642',
1815 },
1816 'params': {
1817 'skip_download': True,
1818 },
1819 'add_ie': [RutubeIE.ie_key()],
1820 },
1821 {
1822 # ThePlatform embedded with whitespaces in URLs
1823 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1824 'only_matching': True,
1825 },
1826 {
1827 # Senate ISVP iframe https
1828 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1829 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1830 'info_dict': {
1831 'id': 'govtaff020316',
1832 'ext': 'mp4',
1833 'title': 'Integrated Senate Video Player',
1834 },
1835 'add_ie': [SenateISVPIE.ie_key()],
1836 },
1837 {
1838 # Limelight embeds (1 channel embed + 4 media embeds)
1839 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1840 'info_dict': {
1841 'id': 'FacilitatorTraining2017',
1842 'title': 'Facilitator Training 2017',
1843 },
1844 'playlist_mincount': 5,
1845 },
1846 {
1847 # Limelight embed (LimelightPlayerUtil.embed)
1848 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1849 'info_dict': {
1850 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1851 'ext': 'mp4',
1852 'title': '07448641',
1853 'timestamp': 1499890639,
1854 'upload_date': '20170712',
1855 },
1856 'params': {
1857 'skip_download': True,
1858 },
1859 'add_ie': ['LimelightMedia'],
1860 },
1861 {
1862 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1863 'info_dict': {
1864 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1865 'title': 'Standoff with Walnut Creek murder suspect ends',
1866 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1867 },
1868 'playlist_mincount': 4,
1869 },
1870 {
1871 # WashingtonPost embed
1872 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1873 'info_dict': {
1874 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1875 'ext': 'mp4',
1876 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1877 '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.',
1878 'timestamp': 1455216756,
1879 'uploader': 'The Washington Post',
1880 'upload_date': '20160211',
1881 },
1882 'add_ie': [WashingtonPostIE.ie_key()],
1883 },
1884 {
1885 # Mediaset embed
1886 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1887 'info_dict': {
1888 'id': '720642',
1889 'ext': 'mp4',
1890 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1891 },
1892 'params': {
1893 'skip_download': True,
1894 },
1895 'add_ie': [MediasetIE.ie_key()],
1896 },
1897 {
1898 # JOJ.sk embeds
1899 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1900 'info_dict': {
1901 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1902 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1903 },
1904 'playlist_mincount': 5,
1905 'add_ie': [JojIE.ie_key()],
1906 },
1907 {
1908 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1909 'url': 'https://tvrain.ru/amp/418921/',
1910 'md5': 'cc00413936695987e8de148b67d14f1d',
1911 'info_dict': {
1912 'id': '418921',
1913 'ext': 'mp4',
1914 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1915 },
1916 },
1917 {
1918 # vzaar embed
1919 'url': 'http://help.vzaar.com/article/165-embedding-video',
1920 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1921 'info_dict': {
1922 'id': '8707641',
1923 'ext': 'mp4',
1924 'title': 'Building A Business Online: Principal Chairs Q & A',
1925 },
1926 },
1927 {
1928 # multiple HTML5 videos on one page
1929 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1930 'info_dict': {
1931 'id': 'keyscenarios',
1932 'title': 'Rescue Kit 14 Free Edition - Getting started',
1933 },
1934 'playlist_count': 4,
1935 },
1936 {
1937 # vshare embed
1938 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1939 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1940 'info_dict': {
1941 'id': '0f64ce6',
1942 'title': 'vl14062007715967',
1943 'ext': 'mp4',
1944 }
1945 },
1946 {
1947 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1948 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1949 'info_dict': {
1950 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1951 'ext': 'mp4',
1952 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1953 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1954 'timestamp': 1474354800,
1955 'upload_date': '20160920',
1956 }
1957 },
1958 {
1959 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1960 'info_dict': {
1961 'id': '1731611',
1962 'ext': 'mp4',
1963 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1964 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1965 'timestamp': 1516100691,
1966 'upload_date': '20180116',
1967 },
1968 'params': {
1969 'skip_download': True,
1970 },
1971 'add_ie': [SpringboardPlatformIE.ie_key()],
1972 },
1973 {
1974 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1975 'info_dict': {
1976 'id': 'uPDB5I9wfp8',
1977 'ext': 'webm',
1978 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1979 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1980 'upload_date': '20160219',
1981 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1982 'uploader_id': 'PocoyoBrazil',
1983 },
1984 'add_ie': [YoutubeIE.ie_key()],
1985 'params': {
1986 'skip_download': True,
1987 },
1988 },
1989 {
1990 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1991 'info_dict': {
1992 'id': 'vMDE4NzI1Mjgt690b',
1993 'ext': 'mp4',
1994 'title': 'ŠšŠ¾Ń‚ŃŃ‚Š°',
1995 },
1996 'add_ie': [YapFilesIE.ie_key()],
1997 'params': {
1998 'skip_download': True,
1999 },
2000 },
2001 {
2002 # CloudflareStream embed
2003 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2004 'info_dict': {
2005 'id': '31c9291ab41fac05471db4e73aa11717',
2006 'ext': 'mp4',
2007 'title': '31c9291ab41fac05471db4e73aa11717',
2008 },
2009 'add_ie': [CloudflareStreamIE.ie_key()],
2010 'params': {
2011 'skip_download': True,
2012 },
2013 },
2014 {
2015 # PeerTube embed
2016 'url': 'https://joinpeertube.org/fr/home/',
2017 'info_dict': {
2018 'id': 'home',
2019 'title': 'Reprenez le contrƓle de vos vidƩos ! #JoinPeertube',
2020 },
2021 'playlist_count': 2,
2022 },
2023 {
2024 # Indavideo embed
2025 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2026 'info_dict': {
2027 'id': '1693903',
2028 'ext': 'mp4',
2029 'title': 'ƍgy kell otthon hamburgert sĆ¼tni',
2030 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2031 'timestamp': 1426330212,
2032 'upload_date': '20150314',
2033 'uploader': 'StreetKitchen',
2034 'uploader_id': '546363',
2035 },
2036 'add_ie': [IndavideoEmbedIE.ie_key()],
2037 'params': {
2038 'skip_download': True,
2039 },
2040 },
2041 {
2042 # APA embed via JWPlatform embed
2043 'url': 'http://www.vol.at/blue-man-group/5593454',
2044 'info_dict': {
2045 'id': 'jjv85FdZ',
2046 'ext': 'mp4',
2047 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview',
2048 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2049 'thumbnail': r're:^https?://.*\.jpg$',
2050 'duration': 254,
2051 'timestamp': 1519211149,
2052 'upload_date': '20180221',
2053 },
2054 'params': {
2055 'skip_download': True,
2056 },
2057 },
2058 {
2059 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2060 'md5': 'b68d276de422ab07ee1d49388103f457',
2061 'info_dict': {
2062 'id': '83645793',
2063 'title': 'Lock up and get excited',
2064 'ext': 'mp4'
2065 },
2066 'skip': 'TODO: fix nested playlists processing in tests',
2067 },
2068 {
2069 # Viqeo embeds
2070 'url': 'https://viqeo.tv/',
2071 'info_dict': {
2072 'id': 'viqeo',
2073 'title': 'All-new video platform',
2074 },
2075 'playlist_count': 6,
2076 },
2077 {
2078 # Squarespace video embed, 2019-08-28
2079 'url': 'http://ootboxford.com',
2080 'info_dict': {
2081 'id': 'Tc7b_JGdZfw',
2082 'title': 'Out of the Blue, at Childish Things 10',
2083 'ext': 'mp4',
2084 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2085 'uploader_id': 'helendouglashouse',
2086 'uploader': 'Helen & Douglas House',
2087 'upload_date': '20140328',
2088 },
2089 'params': {
2090 'skip_download': True,
2091 },
2092 },
2093 {
2094 # Zype embed
2095 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2096 'info_dict': {
2097 'id': '5b400b834b32992a310622b9',
2098 'ext': 'mp4',
2099 'title': 'Smoky Barbecue Favorites',
2100 'thumbnail': r're:^https?://.*\.jpe?g',
2101 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2102 'upload_date': '20170909',
2103 'timestamp': 1504915200,
2104 },
2105 'add_ie': [ZypeIE.ie_key()],
2106 'params': {
2107 'skip_download': True,
2108 },
2109 },
2110 {
2111 # videojs embed
2112 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2113 'info_dict': {
2114 'id': 'shell',
2115 'ext': 'mp4',
2116 'title': 'Š”Š¾ŃŃ‚Š°Š²Ń‰ŠøŠŗ ŠæŠøццы сŠæрŠ¾ŃŠøŠ» рŠ°Š·Ń€ŠµŃˆŠµŠ½Šøя сыŠ³Ń€Š°Ń‚ŃŒ Š½Š° фŠ¾Ń€Ń‚ŠµŠæŠøŠ°Š½Š¾',
2117 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2118 'thumbnail': r're:^https?://.*\.jpg$',
2119 },
2120 'params': {
2121 'skip_download': True,
2122 },
2123 'expected_warnings': ['Failed to download MPD manifest'],
2124 },
2125 {
2126 # DailyMotion embed with DM.player
2127 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2128 'info_dict': {
2129 'id': 'k6aKkGHd9FJs4mtJN39',
2130 'ext': 'mp4',
2131 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2132 'description': 'This video is private.',
2133 'uploader_id': 'x1jf30l',
2134 'uploader': 'beIN SPORTS USA',
2135 'upload_date': '20190528',
2136 'timestamp': 1559062971,
2137 },
2138 'params': {
2139 'skip_download': True,
2140 },
2141 },
2142 # {
2143 # # TODO: find another test
2144 # # http://schema.org/VideoObject
2145 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2146 # 'md5': '888dcf08b7ea671381f00fab74692755',
2147 # 'info_dict': {
2148 # 'id': 'nyvTSJMKId',
2149 # 'ext': 'mp4',
2150 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2151 # 'description': '#love for cats.',
2152 # 'timestamp': 1461244995,
2153 # 'upload_date': '20160421',
2154 # },
2155 # 'params': {
2156 # 'force_generic_extractor': True,
2157 # },
2158 # }
2159 ]
2160
2161 def report_following_redirect(self, new_url):
2162 """Report information extraction."""
2163 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2164
2165 def _extract_rss(self, url, video_id, doc):
2166 playlist_title = doc.find('./channel/title').text
2167 playlist_desc_el = doc.find('./channel/description')
2168 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2169
2170 entries = []
2171 for it in doc.findall('./channel/item'):
2172 next_url = None
2173 enclosure_nodes = it.findall('./enclosure')
2174 for e in enclosure_nodes:
2175 next_url = e.attrib.get('url')
2176 if next_url:
2177 break
2178
2179 if not next_url:
2180 next_url = xpath_text(it, 'link', fatal=False)
2181
2182 if not next_url:
2183 continue
2184
2185 entries.append({
2186 '_type': 'url_transparent',
2187 'url': next_url,
2188 'title': it.find('title').text,
2189 })
2190
2191 return {
2192 '_type': 'playlist',
2193 'id': url,
2194 'title': playlist_title,
2195 'description': playlist_desc,
2196 'entries': entries,
2197 }
2198
2199 def _extract_camtasia(self, url, video_id, webpage):
2200 """ Returns None if no camtasia video can be found. """
2201
2202 camtasia_cfg = self._search_regex(
2203 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2204 webpage, 'camtasia configuration file', default=None)
2205 if camtasia_cfg is None:
2206 return None
2207
2208 title = self._html_search_meta('DC.title', webpage, fatal=True)
2209
2210 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2211 camtasia_cfg = self._download_xml(
2212 camtasia_url, video_id,
2213 note='Downloading camtasia configuration',
2214 errnote='Failed to download camtasia configuration')
2215 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2216
2217 entries = []
2218 for n in fileset_node.getchildren():
2219 url_n = n.find('./uri')
2220 if url_n is None:
2221 continue
2222
2223 entries.append({
2224 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2225 'title': '%s - %s' % (title, n.tag),
2226 'url': compat_urlparse.urljoin(url, url_n.text),
2227 'duration': float_or_none(n.find('./duration').text),
2228 })
2229
2230 return {
2231 '_type': 'playlist',
2232 'entries': entries,
2233 'title': title,
2234 }
2235
2236 def _real_extract(self, url):
2237 if url.startswith('//'):
2238 return self.url_result(self.http_scheme() + url)
2239
2240 parsed_url = compat_urlparse.urlparse(url)
2241 if not parsed_url.scheme:
2242 default_search = self._downloader.params.get('default_search')
2243 if default_search is None:
2244 default_search = 'fixup_error'
2245
2246 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2247 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2248 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2249 return self.url_result('http://' + url)
2250 elif default_search != 'fixup_error':
2251 if default_search == 'auto_warning':
2252 if re.match(r'^(?:url|URL)$', url):
2253 raise ExtractorError(
2254 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2255 expected=True)
2256 else:
2257 self._downloader.report_warning(
2258 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2259 return self.url_result('ytsearch:' + url)
2260
2261 if default_search in ('error', 'fixup_error'):
2262 raise ExtractorError(
2263 '%r is not a valid URL. '
2264 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2265 % (url, url), expected=True)
2266 else:
2267 if ':' not in default_search:
2268 default_search += ':'
2269 return self.url_result(default_search + url)
2270
2271 url, smuggled_data = unsmuggle_url(url)
2272 force_videoid = None
2273 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2274 if smuggled_data and 'force_videoid' in smuggled_data:
2275 force_videoid = smuggled_data['force_videoid']
2276 video_id = force_videoid
2277 else:
2278 video_id = self._generic_id(url)
2279
2280 self.to_screen('%s: Requesting header' % video_id)
2281
2282 head_req = HEADRequest(url)
2283 head_response = self._request_webpage(
2284 head_req, video_id,
2285 note=False, errnote='Could not send HEAD request to %s' % url,
2286 fatal=False)
2287
2288 if head_response is not False:
2289 # Check for redirect
2290 new_url = compat_str(head_response.geturl())
2291 if url != new_url:
2292 self.report_following_redirect(new_url)
2293 if force_videoid:
2294 new_url = smuggle_url(
2295 new_url, {'force_videoid': force_videoid})
2296 return self.url_result(new_url)
2297
2298 full_response = None
2299 if head_response is False:
2300 request = sanitized_Request(url)
2301 request.add_header('Accept-Encoding', '*')
2302 full_response = self._request_webpage(request, video_id)
2303 head_response = full_response
2304
2305 info_dict = {
2306 'id': video_id,
2307 'title': self._generic_title(url),
2308 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2309 }
2310
2311 # Check for direct link to a video
2312 content_type = head_response.headers.get('Content-Type', '').lower()
2313 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2314 if m:
2315 format_id = compat_str(m.group('format_id'))
2316 if format_id.endswith('mpegurl'):
2317 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2318 elif format_id == 'f4m':
2319 formats = self._extract_f4m_formats(url, video_id)
2320 else:
2321 formats = [{
2322 'format_id': format_id,
2323 'url': url,
2324 'vcodec': 'none' if m.group('type') == 'audio' else None
2325 }]
2326 info_dict['direct'] = True
2327 self._sort_formats(formats)
2328 info_dict['formats'] = formats
2329 return info_dict
2330
2331 if not self._downloader.params.get('test', False) and not is_intentional:
2332 force = self._downloader.params.get('force_generic_extractor', False)
2333 self._downloader.report_warning(
2334 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2335
2336 if not full_response:
2337 request = sanitized_Request(url)
2338 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2339 # making it impossible to download only chunk of the file (yet we need only 512kB to
2340 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2341 # that will always result in downloading the whole file that is not desirable.
2342 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2343 # to accept raw bytes and being able to download only a chunk.
2344 # It may probably better to solve this by checking Content-Type for application/octet-stream
2345 # after HEAD request finishes, but not sure if we can rely on this.
2346 request.add_header('Accept-Encoding', '*')
2347 full_response = self._request_webpage(request, video_id)
2348
2349 first_bytes = full_response.read(512)
2350
2351 # Is it an M3U playlist?
2352 if first_bytes.startswith(b'#EXTM3U'):
2353 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2354 self._sort_formats(info_dict['formats'])
2355 return info_dict
2356
2357 # Maybe it's a direct link to a video?
2358 # Be careful not to download the whole thing!
2359 if not is_html(first_bytes):
2360 self._downloader.report_warning(
2361 'URL could be a direct video link, returning it as such.')
2362 info_dict.update({
2363 'direct': True,
2364 'url': url,
2365 })
2366 return info_dict
2367
2368 webpage = self._webpage_read_content(
2369 full_response, url, video_id, prefix=first_bytes)
2370
2371 self.report_extraction(video_id)
2372
2373 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2374 try:
2375 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2376 if doc.tag == 'rss':
2377 return self._extract_rss(url, video_id, doc)
2378 elif doc.tag == 'SmoothStreamingMedia':
2379 info_dict['formats'] = self._parse_ism_formats(doc, url)
2380 self._sort_formats(info_dict['formats'])
2381 return info_dict
2382 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2383 smil = self._parse_smil(doc, url, video_id)
2384 self._sort_formats(smil['formats'])
2385 return smil
2386 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2387 return self.playlist_result(
2388 self._parse_xspf(
2389 doc, video_id, xspf_url=url,
2390 xspf_base_url=compat_str(full_response.geturl())),
2391 video_id)
2392 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2393 info_dict['formats'] = self._parse_mpd_formats(
2394 doc,
2395 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2396 mpd_url=url)
2397 self._sort_formats(info_dict['formats'])
2398 return info_dict
2399 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2400 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2401 self._sort_formats(info_dict['formats'])
2402 return info_dict
2403 except compat_xml_parse_error:
2404 pass
2405
2406 # Is it a Camtasia project?
2407 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2408 if camtasia_res is not None:
2409 return camtasia_res
2410
2411 # Sometimes embedded video player is hidden behind percent encoding
2412 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2413 # Unescaping the whole page allows to handle those cases in a generic way
2414 webpage = compat_urllib_parse_unquote(webpage)
2415
2416 # Unescape squarespace embeds to be detected by generic extractor,
2417 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2418 webpage = re.sub(
2419 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2420 lambda x: unescapeHTML(x.group(0)), webpage)
2421
2422 # it's tempting to parse this further, but you would
2423 # have to take into account all the variations like
2424 # Video Title - Site Name
2425 # Site Name | Video Title
2426 # Video Title - Tagline | Site Name
2427 # and so on and so forth; it's just not practical
2428 video_title = self._og_search_title(
2429 webpage, default=None) or self._html_search_regex(
2430 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2431 default='video')
2432
2433 # Try to detect age limit automatically
2434 age_limit = self._rta_search(webpage)
2435 # And then there are the jokers who advertise that they use RTA,
2436 # but actually don't.
2437 AGE_LIMIT_MARKERS = [
2438 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2439 ]
2440 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2441 age_limit = 18
2442
2443 # video uploader is domain name
2444 video_uploader = self._search_regex(
2445 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2446
2447 video_description = self._og_search_description(webpage, default=None)
2448 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2449
2450 info_dict.update({
2451 'title': video_title,
2452 'description': video_description,
2453 'thumbnail': video_thumbnail,
2454 'age_limit': age_limit,
2455 })
2456
2457 # Look for Brightcove Legacy Studio embeds
2458 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2459 if bc_urls:
2460 entries = [{
2461 '_type': 'url',
2462 'url': smuggle_url(bc_url, {'Referer': url}),
2463 'ie_key': 'BrightcoveLegacy'
2464 } for bc_url in bc_urls]
2465
2466 return {
2467 '_type': 'playlist',
2468 'title': video_title,
2469 'id': video_id,
2470 'entries': entries,
2471 }
2472
2473 # Look for Brightcove New Studio embeds
2474 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2475 if bc_urls:
2476 return self.playlist_from_matches(
2477 bc_urls, video_id, video_title,
2478 getter=lambda x: smuggle_url(x, {'referrer': url}),
2479 ie='BrightcoveNew')
2480
2481 # Look for Nexx embeds
2482 nexx_urls = NexxIE._extract_urls(webpage)
2483 if nexx_urls:
2484 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2485
2486 # Look for Nexx iFrame embeds
2487 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2488 if nexx_embed_urls:
2489 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2490
2491 # Look for ThePlatform embeds
2492 tp_urls = ThePlatformIE._extract_urls(webpage)
2493 if tp_urls:
2494 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2495
2496 # Look for embedded rtl.nl player
2497 matches = re.findall(
2498 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2499 webpage)
2500 if matches:
2501 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2502
2503 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2504 if vimeo_urls:
2505 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2506
2507 vid_me_embed_url = self._search_regex(
2508 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2509 webpage, 'vid.me embed', default=None)
2510 if vid_me_embed_url is not None:
2511 return self.url_result(vid_me_embed_url, 'Vidme')
2512
2513 # Look for YouTube embeds
2514 youtube_urls = YoutubeIE._extract_urls(webpage)
2515 if youtube_urls:
2516 return self.playlist_from_matches(
2517 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2518
2519 matches = DailymotionIE._extract_urls(webpage)
2520 if matches:
2521 return self.playlist_from_matches(matches, video_id, video_title)
2522
2523 # Look for embedded Dailymotion playlist player (#3822)
2524 m = re.search(
2525 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2526 if m:
2527 playlists = re.findall(
2528 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2529 if playlists:
2530 return self.playlist_from_matches(
2531 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2532
2533 # Look for DailyMail embeds
2534 dailymail_urls = DailyMailIE._extract_urls(webpage)
2535 if dailymail_urls:
2536 return self.playlist_from_matches(
2537 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2538
2539 # Look for embedded Wistia player
2540 wistia_url = WistiaIE._extract_url(webpage)
2541 if wistia_url:
2542 return {
2543 '_type': 'url_transparent',
2544 'url': self._proto_relative_url(wistia_url),
2545 'ie_key': WistiaIE.ie_key(),
2546 'uploader': video_uploader,
2547 }
2548
2549 # Look for SVT player
2550 svt_url = SVTIE._extract_url(webpage)
2551 if svt_url:
2552 return self.url_result(svt_url, 'SVT')
2553
2554 # Look for Bandcamp pages with custom domain
2555 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2556 if mobj is not None:
2557 burl = unescapeHTML(mobj.group(1))
2558 # Don't set the extractor because it can be a track url or an album
2559 return self.url_result(burl)
2560
2561 # Look for embedded Vevo player
2562 mobj = re.search(
2563 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2564 if mobj is not None:
2565 return self.url_result(mobj.group('url'))
2566
2567 # Look for embedded Viddler player
2568 mobj = re.search(
2569 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2570 webpage)
2571 if mobj is not None:
2572 return self.url_result(mobj.group('url'))
2573
2574 # Look for NYTimes player
2575 mobj = re.search(
2576 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2577 webpage)
2578 if mobj is not None:
2579 return self.url_result(mobj.group('url'))
2580
2581 # Look for Libsyn player
2582 mobj = re.search(
2583 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2584 if mobj is not None:
2585 return self.url_result(mobj.group('url'))
2586
2587 # Look for Ooyala videos
2588 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2589 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2590 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2591 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2592 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2593 if mobj is not None:
2594 embed_token = self._search_regex(
2595 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2596 webpage, 'ooyala embed token', default=None)
2597 return OoyalaIE._build_url_result(smuggle_url(
2598 mobj.group('ec'), {
2599 'domain': url,
2600 'embed_token': embed_token,
2601 }))
2602
2603 # Look for multiple Ooyala embeds on SBN network websites
2604 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2605 if mobj is not None:
2606 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2607 if embeds:
2608 return self.playlist_from_matches(
2609 embeds, video_id, video_title,
2610 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2611
2612 # Look for Aparat videos
2613 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2614 if mobj is not None:
2615 return self.url_result(mobj.group(1), 'Aparat')
2616
2617 # Look for MPORA videos
2618 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2619 if mobj is not None:
2620 return self.url_result(mobj.group(1), 'Mpora')
2621
2622 # Look for embedded Facebook player
2623 facebook_urls = FacebookIE._extract_urls(webpage)
2624 if facebook_urls:
2625 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2626
2627 # Look for embedded VK player
2628 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2629 if mobj is not None:
2630 return self.url_result(mobj.group('url'), 'VK')
2631
2632 # Look for embedded Odnoklassniki player
2633 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2634 if odnoklassniki_url:
2635 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2636
2637 # Look for embedded ivi player
2638 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2639 if mobj is not None:
2640 return self.url_result(mobj.group('url'), 'Ivi')
2641
2642 # Look for embedded Huffington Post player
2643 mobj = re.search(
2644 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2645 if mobj is not None:
2646 return self.url_result(mobj.group('url'), 'HuffPost')
2647
2648 # Look for embed.ly
2649 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2650 if mobj is not None:
2651 return self.url_result(mobj.group('url'))
2652 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2653 if mobj is not None:
2654 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2655
2656 # Look for funnyordie embed
2657 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2658 if matches:
2659 return self.playlist_from_matches(
2660 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2661
2662 # Look for BBC iPlayer embed
2663 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2664 if matches:
2665 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2666
2667 # Look for embedded RUTV player
2668 rutv_url = RUTVIE._extract_url(webpage)
2669 if rutv_url:
2670 return self.url_result(rutv_url, 'RUTV')
2671
2672 # Look for embedded TVC player
2673 tvc_url = TVCIE._extract_url(webpage)
2674 if tvc_url:
2675 return self.url_result(tvc_url, 'TVC')
2676
2677 # Look for embedded SportBox player
2678 sportbox_urls = SportBoxIE._extract_urls(webpage)
2679 if sportbox_urls:
2680 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2681
2682 # Look for embedded XHamster player
2683 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2684 if xhamster_urls:
2685 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2686
2687 # Look for embedded TNAFlixNetwork player
2688 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2689 if tnaflix_urls:
2690 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2691
2692 # Look for embedded PornHub player
2693 pornhub_urls = PornHubIE._extract_urls(webpage)
2694 if pornhub_urls:
2695 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2696
2697 # Look for embedded DrTuber player
2698 drtuber_urls = DrTuberIE._extract_urls(webpage)
2699 if drtuber_urls:
2700 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2701
2702 # Look for embedded RedTube player
2703 redtube_urls = RedTubeIE._extract_urls(webpage)
2704 if redtube_urls:
2705 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2706
2707 # Look for embedded Tube8 player
2708 tube8_urls = Tube8IE._extract_urls(webpage)
2709 if tube8_urls:
2710 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2711
2712 # Look for embedded Tvigle player
2713 mobj = re.search(
2714 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2715 if mobj is not None:
2716 return self.url_result(mobj.group('url'), 'Tvigle')
2717
2718 # Look for embedded TED player
2719 mobj = re.search(
2720 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2721 if mobj is not None:
2722 return self.url_result(mobj.group('url'), 'TED')
2723
2724 # Look for embedded Ustream videos
2725 ustream_url = UstreamIE._extract_url(webpage)
2726 if ustream_url:
2727 return self.url_result(ustream_url, UstreamIE.ie_key())
2728
2729 # Look for embedded arte.tv player
2730 mobj = re.search(
2731 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2732 webpage)
2733 if mobj is not None:
2734 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2735
2736 # Look for embedded francetv player
2737 mobj = re.search(
2738 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2739 webpage)
2740 if mobj is not None:
2741 return self.url_result(mobj.group('url'))
2742
2743 # Look for embedded smotri.com player
2744 smotri_url = SmotriIE._extract_url(webpage)
2745 if smotri_url:
2746 return self.url_result(smotri_url, 'Smotri')
2747
2748 # Look for embedded Myvi.ru player
2749 myvi_url = MyviIE._extract_url(webpage)
2750 if myvi_url:
2751 return self.url_result(myvi_url)
2752
2753 # Look for embedded soundcloud player
2754 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2755 if soundcloud_urls:
2756 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2757
2758 # Look for tunein player
2759 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2760 if tunein_urls:
2761 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2762
2763 # Look for embedded mtvservices player
2764 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2765 if mtvservices_url:
2766 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2767
2768 # Look for embedded yahoo player
2769 mobj = re.search(
2770 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2771 webpage)
2772 if mobj is not None:
2773 return self.url_result(mobj.group('url'), 'Yahoo')
2774
2775 # Look for embedded sbs.com.au player
2776 mobj = re.search(
2777 r'''(?x)
2778 (?:
2779 <meta\s+property="og:video"\s+content=|
2780 <iframe[^>]+?src=
2781 )
2782 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2783 webpage)
2784 if mobj is not None:
2785 return self.url_result(mobj.group('url'), 'SBS')
2786
2787 # Look for embedded Cinchcast player
2788 mobj = re.search(
2789 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2790 webpage)
2791 if mobj is not None:
2792 return self.url_result(mobj.group('url'), 'Cinchcast')
2793
2794 mobj = re.search(
2795 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2796 webpage)
2797 if not mobj:
2798 mobj = re.search(
2799 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2800 webpage)
2801 if mobj is not None:
2802 return self.url_result(mobj.group('url'), 'MLB')
2803
2804 mobj = re.search(
2805 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2806 webpage)
2807 if mobj is not None:
2808 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2809
2810 mobj = re.search(
2811 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2812 webpage)
2813 if mobj is not None:
2814 return self.url_result(mobj.group('url'), 'Livestream')
2815
2816 # Look for Zapiks embed
2817 mobj = re.search(
2818 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2819 if mobj is not None:
2820 return self.url_result(mobj.group('url'), 'Zapiks')
2821
2822 # Look for Kaltura embeds
2823 kaltura_url = KalturaIE._extract_url(webpage)
2824 if kaltura_url:
2825 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2826
2827 # Look for EaglePlatform embeds
2828 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2829 if eagleplatform_url:
2830 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2831
2832 # Look for ClipYou (uses EaglePlatform) embeds
2833 mobj = re.search(
2834 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2835 if mobj is not None:
2836 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2837
2838 # Look for Pladform embeds
2839 pladform_url = PladformIE._extract_url(webpage)
2840 if pladform_url:
2841 return self.url_result(pladform_url)
2842
2843 # Look for Videomore embeds
2844 videomore_url = VideomoreIE._extract_url(webpage)
2845 if videomore_url:
2846 return self.url_result(videomore_url)
2847
2848 # Look for Webcaster embeds
2849 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2850 if webcaster_url:
2851 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2852
2853 # Look for Playwire embeds
2854 mobj = re.search(
2855 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2856 if mobj is not None:
2857 return self.url_result(mobj.group('url'))
2858
2859 # Look for 5min embeds
2860 mobj = re.search(
2861 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2862 if mobj is not None:
2863 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2864
2865 # Look for Crooks and Liars embeds
2866 mobj = re.search(
2867 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2868 if mobj is not None:
2869 return self.url_result(mobj.group('url'))
2870
2871 # Look for NBC Sports VPlayer embeds
2872 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2873 if nbc_sports_url:
2874 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2875
2876 # Look for NBC News embeds
2877 nbc_news_embed_url = re.search(
2878 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2879 if nbc_news_embed_url:
2880 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2881
2882 # Look for Google Drive embeds
2883 google_drive_url = GoogleDriveIE._extract_url(webpage)
2884 if google_drive_url:
2885 return self.url_result(google_drive_url, 'GoogleDrive')
2886
2887 # Look for UDN embeds
2888 mobj = re.search(
2889 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2890 if mobj is not None:
2891 return self.url_result(
2892 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2893
2894 # Look for Senate ISVP iframe
2895 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2896 if senate_isvp_url:
2897 return self.url_result(senate_isvp_url, 'SenateISVP')
2898
2899 # Look for Kinja embeds
2900 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2901 if kinja_embed_urls:
2902 return self.playlist_from_matches(
2903 kinja_embed_urls, video_id, video_title)
2904
2905 # Look for OnionStudios embeds
2906 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2907 if onionstudios_url:
2908 return self.url_result(onionstudios_url)
2909
2910 # Look for ViewLift embeds
2911 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2912 if viewlift_url:
2913 return self.url_result(viewlift_url)
2914
2915 # Look for JWPlatform embeds
2916 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2917 if jwplatform_urls:
2918 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2919
2920 # Look for Digiteka embeds
2921 digiteka_url = DigitekaIE._extract_url(webpage)
2922 if digiteka_url:
2923 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2924
2925 # Look for Arkena embeds
2926 arkena_url = ArkenaIE._extract_url(webpage)
2927 if arkena_url:
2928 return self.url_result(arkena_url, ArkenaIE.ie_key())
2929
2930 # Look for Piksel embeds
2931 piksel_url = PikselIE._extract_url(webpage)
2932 if piksel_url:
2933 return self.url_result(piksel_url, PikselIE.ie_key())
2934
2935 # Look for Limelight embeds
2936 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2937 if limelight_urls:
2938 return self.playlist_result(
2939 limelight_urls, video_id, video_title, video_description)
2940
2941 # Look for Anvato embeds
2942 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2943 if anvato_urls:
2944 return self.playlist_result(
2945 anvato_urls, video_id, video_title, video_description)
2946
2947 # Look for AdobeTVVideo embeds
2948 mobj = re.search(
2949 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2950 webpage)
2951 if mobj is not None:
2952 return self.url_result(
2953 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2954 'AdobeTVVideo')
2955
2956 # Look for Vine embeds
2957 mobj = re.search(
2958 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2959 webpage)
2960 if mobj is not None:
2961 return self.url_result(
2962 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2963
2964 # Look for VODPlatform embeds
2965 mobj = re.search(
2966 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
2967 webpage)
2968 if mobj is not None:
2969 return self.url_result(
2970 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2971
2972 # Look for Mangomolo embeds
2973 mobj = re.search(
2974 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
2975 (?:
2976 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
2977 player\.mangomolo\.com/v1
2978 )/
2979 (?:
2980 video\?.*?\bid=(?P<video_id>\d+)|
2981 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2982 ).+?)\1''', webpage)
2983 if mobj is not None:
2984 info = {
2985 '_type': 'url_transparent',
2986 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2987 'title': video_title,
2988 'description': video_description,
2989 'thumbnail': video_thumbnail,
2990 'uploader': video_uploader,
2991 }
2992 video_id = mobj.group('video_id')
2993 if video_id:
2994 info.update({
2995 'ie_key': 'MangomoloVideo',
2996 'id': video_id,
2997 })
2998 else:
2999 info.update({
3000 'ie_key': 'MangomoloLive',
3001 'id': mobj.group('channel_id'),
3002 })
3003 return info
3004
3005 # Look for Instagram embeds
3006 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3007 if instagram_embed_url is not None:
3008 return self.url_result(
3009 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3010
3011 # Look for LiveLeak embeds
3012 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3013 if liveleak_urls:
3014 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3015
3016 # Look for 3Q SDN embeds
3017 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3018 if threeqsdn_url:
3019 return {
3020 '_type': 'url_transparent',
3021 'ie_key': ThreeQSDNIE.ie_key(),
3022 'url': self._proto_relative_url(threeqsdn_url),
3023 'title': video_title,
3024 'description': video_description,
3025 'thumbnail': video_thumbnail,
3026 'uploader': video_uploader,
3027 }
3028
3029 # Look for VBOX7 embeds
3030 vbox7_url = Vbox7IE._extract_url(webpage)
3031 if vbox7_url:
3032 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3033
3034 # Look for DBTV embeds
3035 dbtv_urls = DBTVIE._extract_urls(webpage)
3036 if dbtv_urls:
3037 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3038
3039 # Look for Videa embeds
3040 videa_urls = VideaIE._extract_urls(webpage)
3041 if videa_urls:
3042 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3043
3044 # Look for 20 minuten embeds
3045 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3046 if twentymin_urls:
3047 return self.playlist_from_matches(
3048 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3049
3050 # Look for VideoPress embeds
3051 videopress_urls = VideoPressIE._extract_urls(webpage)
3052 if videopress_urls:
3053 return self.playlist_from_matches(
3054 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3055
3056 # Look for Rutube embeds
3057 rutube_urls = RutubeIE._extract_urls(webpage)
3058 if rutube_urls:
3059 return self.playlist_from_matches(
3060 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3061
3062 # Look for WashingtonPost embeds
3063 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3064 if wapo_urls:
3065 return self.playlist_from_matches(
3066 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3067
3068 # Look for Mediaset embeds
3069 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3070 if mediaset_urls:
3071 return self.playlist_from_matches(
3072 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3073
3074 # Look for JOJ.sk embeds
3075 joj_urls = JojIE._extract_urls(webpage)
3076 if joj_urls:
3077 return self.playlist_from_matches(
3078 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3079
3080 # Look for megaphone.fm embeds
3081 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3082 if mpfn_urls:
3083 return self.playlist_from_matches(
3084 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3085
3086 # Look for vzaar embeds
3087 vzaar_urls = VzaarIE._extract_urls(webpage)
3088 if vzaar_urls:
3089 return self.playlist_from_matches(
3090 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3091
3092 channel9_urls = Channel9IE._extract_urls(webpage)
3093 if channel9_urls:
3094 return self.playlist_from_matches(
3095 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3096
3097 vshare_urls = VShareIE._extract_urls(webpage)
3098 if vshare_urls:
3099 return self.playlist_from_matches(
3100 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3101
3102 # Look for Mediasite embeds
3103 mediasite_urls = MediasiteIE._extract_urls(webpage)
3104 if mediasite_urls:
3105 entries = [
3106 self.url_result(smuggle_url(
3107 compat_urlparse.urljoin(url, mediasite_url),
3108 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3109 for mediasite_url in mediasite_urls]
3110 return self.playlist_result(entries, video_id, video_title)
3111
3112 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3113 if springboardplatform_urls:
3114 return self.playlist_from_matches(
3115 springboardplatform_urls, video_id, video_title,
3116 ie=SpringboardPlatformIE.ie_key())
3117
3118 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3119 if yapfiles_urls:
3120 return self.playlist_from_matches(
3121 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3122
3123 vice_urls = ViceIE._extract_urls(webpage)
3124 if vice_urls:
3125 return self.playlist_from_matches(
3126 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3127
3128 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3129 if xfileshare_urls:
3130 return self.playlist_from_matches(
3131 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3132
3133 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3134 if cloudflarestream_urls:
3135 return self.playlist_from_matches(
3136 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3137
3138 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3139 if peertube_urls:
3140 return self.playlist_from_matches(
3141 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3142
3143 teachable_url = TeachableIE._extract_url(webpage, url)
3144 if teachable_url:
3145 return self.url_result(teachable_url)
3146
3147 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3148 if indavideo_urls:
3149 return self.playlist_from_matches(
3150 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3151
3152 apa_urls = APAIE._extract_urls(webpage)
3153 if apa_urls:
3154 return self.playlist_from_matches(
3155 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3156
3157 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3158 if foxnews_urls:
3159 return self.playlist_from_matches(
3160 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3161
3162 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3163 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3164 webpage)]
3165 if sharevideos_urls:
3166 return self.playlist_from_matches(
3167 sharevideos_urls, video_id, video_title)
3168
3169 viqeo_urls = ViqeoIE._extract_urls(webpage)
3170 if viqeo_urls:
3171 return self.playlist_from_matches(
3172 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3173
3174 expressen_urls = ExpressenIE._extract_urls(webpage)
3175 if expressen_urls:
3176 return self.playlist_from_matches(
3177 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3178
3179 zype_urls = ZypeIE._extract_urls(webpage)
3180 if zype_urls:
3181 return self.playlist_from_matches(
3182 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3183
3184 # Look for HTML5 media
3185 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3186 if entries:
3187 if len(entries) == 1:
3188 entries[0].update({
3189 'id': video_id,
3190 'title': video_title,
3191 })
3192 else:
3193 for num, entry in enumerate(entries, start=1):
3194 entry.update({
3195 'id': '%s-%s' % (video_id, num),
3196 'title': '%s (%d)' % (video_title, num),
3197 })
3198 for entry in entries:
3199 self._sort_formats(entry['formats'])
3200 return self.playlist_result(entries, video_id, video_title)
3201
3202 jwplayer_data = self._find_jwplayer_data(
3203 webpage, video_id, transform_source=js_to_json)
3204 if jwplayer_data:
3205 try:
3206 info = self._parse_jwplayer_data(
3207 jwplayer_data, video_id, require_title=False, base_url=url)
3208 return merge_dicts(info, info_dict)
3209 except ExtractorError:
3210 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3211 pass
3212
3213 # Video.js embed
3214 mobj = re.search(
3215 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3216 webpage)
3217 if mobj is not None:
3218 sources = self._parse_json(
3219 mobj.group(1), video_id, transform_source=js_to_json,
3220 fatal=False) or []
3221 if not isinstance(sources, list):
3222 sources = [sources]
3223 formats = []
3224 for source in sources:
3225 src = source.get('src')
3226 if not src or not isinstance(src, compat_str):
3227 continue
3228 src = compat_urlparse.urljoin(url, src)
3229 src_type = source.get('type')
3230 if isinstance(src_type, compat_str):
3231 src_type = src_type.lower()
3232 ext = determine_ext(src).lower()
3233 if src_type == 'video/youtube':
3234 return self.url_result(src, YoutubeIE.ie_key())
3235 if src_type == 'application/dash+xml' or ext == 'mpd':
3236 formats.extend(self._extract_mpd_formats(
3237 src, video_id, mpd_id='dash', fatal=False))
3238 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3239 formats.extend(self._extract_m3u8_formats(
3240 src, video_id, 'mp4', entry_protocol='m3u8_native',
3241 m3u8_id='hls', fatal=False))
3242 else:
3243 formats.append({
3244 'url': src,
3245 'ext': (mimetype2ext(src_type)
3246 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3247 })
3248 if formats:
3249 self._sort_formats(formats)
3250 info_dict['formats'] = formats
3251 return info_dict
3252
3253 # Looking for http://schema.org/VideoObject
3254 json_ld = self._search_json_ld(
3255 webpage, video_id, default={}, expected_type='VideoObject')
3256 if json_ld.get('url'):
3257 return merge_dicts(json_ld, info_dict)
3258
3259 def check_video(vurl):
3260 if YoutubeIE.suitable(vurl):
3261 return True
3262 if RtmpIE.suitable(vurl):
3263 return True
3264 vpath = compat_urlparse.urlparse(vurl).path
3265 vext = determine_ext(vpath)
3266 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3267
3268 def filter_video(urls):
3269 return list(filter(check_video, urls))
3270
3271 # Start with something easy: JW Player in SWFObject
3272 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3273 if not found:
3274 # Look for gorilla-vid style embedding
3275 found = filter_video(re.findall(r'''(?sx)
3276 (?:
3277 jw_plugins|
3278 JWPlayerOptions|
3279 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3280 )
3281 .*?
3282 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3283 if not found:
3284 # Broaden the search a little bit
3285 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3286 if not found:
3287 # Broaden the findall a little bit: JWPlayer JS loader
3288 found = filter_video(re.findall(
3289 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3290 if not found:
3291 # Flow player
3292 found = filter_video(re.findall(r'''(?xs)
3293 flowplayer\("[^"]+",\s*
3294 \{[^}]+?\}\s*,
3295 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3296 ["']?url["']?\s*:\s*["']([^"']+)["']
3297 ''', webpage))
3298 if not found:
3299 # Cinerama player
3300 found = re.findall(
3301 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3302 if not found:
3303 # Try to find twitter cards info
3304 # twitter:player:stream should be checked before twitter:player since
3305 # it is expected to contain a raw stream (see
3306 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3307 found = filter_video(re.findall(
3308 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3309 if not found:
3310 # We look for Open Graph info:
3311 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3312 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3313 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3314 if m_video_type is not None:
3315 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3316 if not found:
3317 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3318 found = re.search(
3319 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3320 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3321 webpage)
3322 if not found:
3323 # Look also in Refresh HTTP header
3324 refresh_header = head_response.headers.get('Refresh')
3325 if refresh_header:
3326 # In python 2 response HTTP headers are bytestrings
3327 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3328 refresh_header = refresh_header.decode('iso-8859-1')
3329 found = re.search(REDIRECT_REGEX, refresh_header)
3330 if found:
3331 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3332 if new_url != url:
3333 self.report_following_redirect(new_url)
3334 return {
3335 '_type': 'url',
3336 'url': new_url,
3337 }
3338 else:
3339 found = None
3340
3341 if not found:
3342 # twitter:player is a https URL to iframe player that may or may not
3343 # be supported by youtube-dl thus this is checked the very last (see
3344 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3345 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3346 if embed_url and embed_url != url:
3347 return self.url_result(embed_url)
3348
3349 if not found:
3350 raise UnsupportedError(url)
3351
3352 entries = []
3353 for video_url in orderedSet(found):
3354 video_url = unescapeHTML(video_url)
3355 video_url = video_url.replace('\\/', '/')
3356 video_url = compat_urlparse.urljoin(url, video_url)
3357 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3358
3359 # Sometimes, jwplayer extraction will result in a YouTube URL
3360 if YoutubeIE.suitable(video_url):
3361 entries.append(self.url_result(video_url, 'Youtube'))
3362 continue
3363
3364 # here's a fun little line of code for you:
3365 video_id = os.path.splitext(video_id)[0]
3366
3367 entry_info_dict = {
3368 'id': video_id,
3369 'uploader': video_uploader,
3370 'title': video_title,
3371 'age_limit': age_limit,
3372 }
3373
3374 if RtmpIE.suitable(video_url):
3375 entry_info_dict.update({
3376 '_type': 'url_transparent',
3377 'ie_key': RtmpIE.ie_key(),
3378 'url': video_url,
3379 })
3380 entries.append(entry_info_dict)
3381 continue
3382
3383 ext = determine_ext(video_url)
3384 if ext == 'smil':
3385 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3386 elif ext == 'xspf':
3387 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3388 elif ext == 'm3u8':
3389 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3390 elif ext == 'mpd':
3391 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3392 elif ext == 'f4m':
3393 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3394 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3395 # Just matching .ism/manifest is not enough to be reliably sure
3396 # whether it's actually an ISM manifest or some other streaming
3397 # manifest since there are various streaming URL formats
3398 # possible (see [1]) as well as some other shenanigans like
3399 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3400 # so on.
3401 # Thus the most reasonable way to solve this is to delegate
3402 # to generic extractor in order to look into the contents of
3403 # the manifest itself.
3404 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3405 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3406 entry_info_dict = self.url_result(
3407 smuggle_url(video_url, {'to_generic': True}),
3408 GenericIE.ie_key())
3409 else:
3410 entry_info_dict['url'] = video_url
3411
3412 if entry_info_dict.get('formats'):
3413 self._sort_formats(entry_info_dict['formats'])
3414
3415 entries.append(entry_info_dict)
3416
3417 if len(entries) == 1:
3418 return entries[0]
3419 else:
3420 for num, e in enumerate(entries, start=1):
3421 # 'url' results don't have a title
3422 if e.get('title') is not None:
3423 e['title'] = '%s (%d)' % (e['title'], num)
3424 return {
3425 '_type': 'playlist',
3426 'entries': entries,
3427 }