]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
ce8252f6a813931da77e0d4689c4eabd9d550e52
[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 .mofosex import MofosexEmbedIE
64 from .spankwire import SpankwireIE
65 from .youporn import YouPornIE
66 from .vimeo import VimeoIE
67 from .dailymotion import DailymotionIE
68 from .dailymail import DailyMailIE
69 from .onionstudios import OnionStudiosIE
70 from .viewlift import ViewLiftEmbedIE
71 from .mtv import MTVServicesEmbeddedIE
72 from .pladform import PladformIE
73 from .videomore import VideomoreIE
74 from .webcaster import WebcasterFeedIE
75 from .googledrive import GoogleDriveIE
76 from .jwplatform import JWPlatformIE
77 from .digiteka import DigitekaIE
78 from .arkena import ArkenaIE
79 from .instagram import InstagramIE
80 from .liveleak import LiveLeakIE
81 from .threeqsdn import ThreeQSDNIE
82 from .theplatform import ThePlatformIE
83 from .kaltura import KalturaIE
84 from .eagleplatform import EaglePlatformIE
85 from .facebook import FacebookIE
86 from .soundcloud import SoundcloudEmbedIE
87 from .tunein import TuneInBaseIE
88 from .vbox7 import Vbox7IE
89 from .dbtv import DBTVIE
90 from .piksel import PikselIE
91 from .videa import VideaIE
92 from .twentymin import TwentyMinutenIE
93 from .ustream import UstreamIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
105 from .vshare import VShareIE
106 from .mediasite import MediasiteIE
107 from .springboardplatform import SpringboardPlatformIE
108 from .yapfiles import YapFilesIE
109 from .vice import ViceIE
110 from .xfileshare import XFileShareIE
111 from .cloudflarestream import CloudflareStreamIE
112 from .peertube import PeerTubeIE
113 from .teachable import TeachableIE
114 from .indavideo import IndavideoEmbedIE
115 from .apa import APAIE
116 from .foxnews import FoxNewsIE
117 from .viqeo import ViqeoIE
118 from .expressen import ExpressenIE
119 from .zype import ZypeIE
120 from .odnoklassniki import OdnoklassnikiIE
121 from .kinja import KinjaEmbedIE
122
123
124 class GenericIE(InfoExtractor):
125 IE_DESC = 'Generic downloader that works on some sites'
126 _VALID_URL = r'.*'
127 IE_NAME = 'generic'
128 _TESTS = [
129 # Direct link to a video
130 {
131 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
132 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
133 'info_dict': {
134 'id': 'trailer',
135 'ext': 'mp4',
136 'title': 'trailer',
137 'upload_date': '20100513',
138 }
139 },
140 # Direct link to media delivered compressed (until Accept-Encoding is *)
141 {
142 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
143 'md5': '128c42e68b13950268b648275386fc74',
144 'info_dict': {
145 'id': 'FictionJunction-Parallel_Hearts',
146 'ext': 'flac',
147 'title': 'FictionJunction-Parallel_Hearts',
148 'upload_date': '20140522',
149 },
150 'expected_warnings': [
151 'URL could be a direct video link, returning it as such.'
152 ],
153 'skip': 'URL invalid',
154 },
155 # Direct download with broken HEAD
156 {
157 'url': 'http://ai-radio.org:8000/radio.opus',
158 'info_dict': {
159 'id': 'radio',
160 'ext': 'opus',
161 'title': 'radio',
162 },
163 'params': {
164 'skip_download': True, # infinite live stream
165 },
166 'expected_warnings': [
167 r'501.*Not Implemented',
168 r'400.*Bad Request',
169 ],
170 },
171 # Direct link with incorrect MIME type
172 {
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'md5': '4ccbebe5f36706d85221f204d7eb5913',
175 'info_dict': {
176 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
177 'id': '5_Lennart_Poettering_-_Systemd',
178 'ext': 'webm',
179 'title': '5_Lennart_Poettering_-_Systemd',
180 'upload_date': '20141120',
181 },
182 'expected_warnings': [
183 'URL could be a direct video link, returning it as such.'
184 ]
185 },
186 # RSS feed
187 {
188 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
189 'info_dict': {
190 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
191 'title': 'Zero Punctuation',
192 'description': 're:.*groundbreaking video review series.*'
193 },
194 'playlist_mincount': 11,
195 },
196 # RSS feed with enclosure
197 {
198 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
199 'info_dict': {
200 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 'ext': 'm4v',
202 'upload_date': '20150228',
203 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
204 }
205 },
206 # RSS feed with enclosures and unsupported link URLs
207 {
208 'url': 'http://www.hellointernet.fm/podcast?format=rss',
209 'info_dict': {
210 'id': 'http://www.hellointernet.fm/podcast?format=rss',
211 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
212 'title': 'Hello Internet',
213 },
214 'playlist_mincount': 100,
215 },
216 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
217 {
218 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
219 'info_dict': {
220 'id': 'smil',
221 'ext': 'mp4',
222 'title': 'Automatics, robotics and biocybernetics',
223 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
224 'upload_date': '20130627',
225 'formats': 'mincount:16',
226 'subtitles': 'mincount:1',
227 },
228 'params': {
229 'force_generic_extractor': True,
230 'skip_download': True,
231 },
232 },
233 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
234 {
235 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
236 'info_dict': {
237 'id': 'hds',
238 'ext': 'flv',
239 'title': 'hds',
240 'formats': 'mincount:1',
241 },
242 'params': {
243 'skip_download': True,
244 },
245 },
246 # SMIL from https://www.restudy.dk/video/play/id/1637
247 {
248 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
249 'info_dict': {
250 'id': 'video_1637',
251 'ext': 'flv',
252 'title': 'video_1637',
253 'formats': 'mincount:3',
254 },
255 'params': {
256 'skip_download': True,
257 },
258 },
259 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
260 {
261 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
262 'info_dict': {
263 'id': 'smil-service',
264 'ext': 'flv',
265 'title': 'smil-service',
266 'formats': 'mincount:1',
267 },
268 'params': {
269 'skip_download': True,
270 },
271 },
272 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
273 {
274 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
275 'info_dict': {
276 'id': '4719370',
277 'ext': 'mp4',
278 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
279 'formats': 'mincount:3',
280 },
281 'params': {
282 'skip_download': True,
283 },
284 },
285 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
286 {
287 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
288 'info_dict': {
289 'id': 'mZlp2ctYIUEB',
290 'ext': 'mp4',
291 'title': 'Tikibad ontruimd wegens brand',
292 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
293 'thumbnail': r're:^https?://.*\.jpg$',
294 'duration': 33,
295 },
296 'params': {
297 'skip_download': True,
298 },
299 },
300 # MPD from http://dash-mse-test.appspot.com/media.html
301 {
302 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
303 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
304 'info_dict': {
305 'id': 'car-20120827-manifest',
306 'ext': 'mp4',
307 'title': 'car-20120827-manifest',
308 'formats': 'mincount:9',
309 'upload_date': '20130904',
310 },
311 'params': {
312 'format': 'bestvideo',
313 },
314 },
315 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
316 {
317 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
318 'info_dict': {
319 'id': 'content',
320 'ext': 'mp4',
321 'title': 'content',
322 'formats': 'mincount:8',
323 },
324 'params': {
325 # m3u8 downloads
326 'skip_download': True,
327 },
328 'skip': 'video gone',
329 },
330 # m3u8 served with Content-Type: text/plain
331 {
332 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
333 'info_dict': {
334 'id': 'index',
335 'ext': 'mp4',
336 'title': 'index',
337 'upload_date': '20140720',
338 'formats': 'mincount:11',
339 },
340 'params': {
341 # m3u8 downloads
342 'skip_download': True,
343 },
344 'skip': 'video gone',
345 },
346 # google redirect
347 {
348 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
349 'info_dict': {
350 'id': 'cmQHVoWB5FY',
351 'ext': 'mp4',
352 'upload_date': '20130224',
353 'uploader_id': 'TheVerge',
354 'description': r're:^Chris Ziegler takes a look at the\.*',
355 'uploader': 'The Verge',
356 'title': 'First Firefox OS phones side-by-side',
357 },
358 'params': {
359 'skip_download': False,
360 }
361 },
362 {
363 # redirect in Refresh HTTP header
364 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
365 'info_dict': {
366 'id': 'pO8h3EaFRdo',
367 'ext': 'mp4',
368 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
369 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
370 'upload_date': '20150917',
371 'uploader_id': 'brtvofficial',
372 'uploader': 'Boiler Room',
373 },
374 'params': {
375 'skip_download': False,
376 },
377 },
378 {
379 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
380 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
381 'info_dict': {
382 'id': '13601338388002',
383 'ext': 'mp4',
384 'uploader': 'www.hodiho.fr',
385 'title': 'R\u00e9gis plante sa Jeep',
386 }
387 },
388 # bandcamp page with custom domain
389 {
390 'add_ie': ['Bandcamp'],
391 'url': 'http://bronyrock.com/track/the-pony-mash',
392 'info_dict': {
393 'id': '3235767654',
394 'ext': 'mp3',
395 'title': 'The Pony Mash',
396 'uploader': 'M_Pallante',
397 },
398 'skip': 'There is a limit of 200 free downloads / month for the test song',
399 },
400 {
401 # embedded brightcove video
402 # it also tests brightcove videos that need to set the 'Referer'
403 # in the http requests
404 'add_ie': ['BrightcoveLegacy'],
405 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
406 'info_dict': {
407 'id': '2765128793001',
408 'ext': 'mp4',
409 'title': 'Le cours de bourse : lā€™analyse technique',
410 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
411 'uploader': 'BFM BUSINESS',
412 },
413 'params': {
414 'skip_download': True,
415 },
416 },
417 {
418 # embedded with itemprop embedURL and video id spelled as `idVideo`
419 'add_id': ['BrightcoveLegacy'],
420 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
421 'info_dict': {
422 'id': '5255628253001',
423 'ext': 'mp4',
424 'title': 'md5:37c519b1128915607601e75a87995fc0',
425 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
426 'uploader': 'BFM BUSINESS',
427 'uploader_id': '876450612001',
428 'timestamp': 1482255315,
429 'upload_date': '20161220',
430 },
431 'params': {
432 'skip_download': True,
433 },
434 },
435 {
436 # https://github.com/ytdl-org/youtube-dl/issues/2253
437 'url': 'http://bcove.me/i6nfkrc3',
438 'md5': '0ba9446db037002366bab3b3eb30c88c',
439 'info_dict': {
440 'id': '3101154703001',
441 'ext': 'mp4',
442 'title': 'Still no power',
443 'uploader': 'thestar.com',
444 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
445 },
446 'add_ie': ['BrightcoveLegacy'],
447 'skip': 'video gone',
448 },
449 {
450 'url': 'http://www.championat.com/video/football/v/87/87499.html',
451 'md5': 'fb973ecf6e4a78a67453647444222983',
452 'info_dict': {
453 'id': '3414141473001',
454 'ext': 'mp4',
455 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
456 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
457 'uploader': 'Championat',
458 },
459 },
460 {
461 # https://github.com/ytdl-org/youtube-dl/issues/3541
462 'add_ie': ['BrightcoveLegacy'],
463 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
464 'info_dict': {
465 'id': '3866516442001',
466 'ext': 'mp4',
467 'title': 'Leer mij vrouwen kennen: Aflevering 1',
468 'description': 'Leer mij vrouwen kennen: Aflevering 1',
469 'uploader': 'SBS Broadcasting',
470 },
471 'skip': 'Restricted to Netherlands',
472 'params': {
473 'skip_download': True, # m3u8 download
474 },
475 },
476 {
477 # Brightcove video in <iframe>
478 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
479 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
480 'info_dict': {
481 'id': '5360463607001',
482 'ext': 'mp4',
483 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
484 'description': 'č”åˆå›½å„æē«„åŸŗ金会äø­äøœå’ŒåŒ—非åŒŗ域大ä½æć€ä½œę›²å®¶ę‰Žå¾·Ā·čæŖę‹‰å°¼ļ¼ˆZade Diraniļ¼‰åœØ3꜈15ę—„å™åˆ©äŗšå†²ēŖēˆ†å‘7å‘Ø幓ēŗŖåæµę—„之际发åøƒäŗ†äøŗ叙利äŗšč°±å†™ēš„ę­Œę›²ć€Šåæƒč·³ć€‹ļ¼ˆHEARTBEATļ¼‰ļ¼Œäøŗ受到六幓冲ēŖå½±å“ēš„叙利äŗšå„æē«„发å‡ŗå¼ŗēƒˆå‘å–Šļ¼Œå‘¼åäø–ē•Œåšå‡ŗ共同åŠŖ力ļ¼Œä½æ叙利äŗšå„æē«„é‡ę–°čŽ·å¾—äŗ«ęœ‰ę­£åøøē«„幓ē”Ÿę“»ēš„ęƒåˆ©ć€‚',
485 'uploader': 'United Nations',
486 'uploader_id': '1362235914001',
487 'timestamp': 1489593889,
488 'upload_date': '20170315',
489 },
490 'add_ie': ['BrightcoveLegacy'],
491 },
492 {
493 # Brightcove with alternative playerID key
494 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
495 'info_dict': {
496 'id': 'nmeth.2062_SV1',
497 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
498 },
499 'playlist': [{
500 'info_dict': {
501 'id': '2228375078001',
502 'ext': 'mp4',
503 'title': 'nmeth.2062-sv1',
504 'description': 'nmeth.2062-sv1',
505 'timestamp': 1363357591,
506 'upload_date': '20130315',
507 'uploader': 'Nature Publishing Group',
508 'uploader_id': '1964492299001',
509 },
510 }],
511 },
512 {
513 # Brightcove with UUID in videoPlayer
514 'url': 'http://www8.hp.com/cn/zh/home.html',
515 'info_dict': {
516 'id': '5255815316001',
517 'ext': 'mp4',
518 'title': 'Sprocket Video - China',
519 'description': 'Sprocket Video - China',
520 'uploader': 'HP-Video Gallery',
521 'timestamp': 1482263210,
522 'upload_date': '20161220',
523 'uploader_id': '1107601872001',
524 },
525 'params': {
526 'skip_download': True, # m3u8 download
527 },
528 'skip': 'video rotates...weekly?',
529 },
530 {
531 # Brightcove:new type [2].
532 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
533 'md5': '2b35148fcf48da41c9fb4591650784f3',
534 'info_dict': {
535 'id': '5348741021001',
536 'ext': 'mp4',
537 'upload_date': '20170306',
538 'uploader_id': '4191638492001',
539 'timestamp': 1488769918,
540 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
541
542 },
543 },
544 {
545 # Alternative brightcove <video> attributes
546 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
547 'info_dict': {
548 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
549 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
550 },
551 'playlist': [{
552 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
553 'info_dict': {
554 'id': '5311302538001',
555 'ext': 'mp4',
556 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
557 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
558 'timestamp': 1486321708,
559 'upload_date': '20170205',
560 'uploader_id': '800000640001',
561 },
562 'only_matching': True,
563 }],
564 },
565 {
566 # Brightcove with UUID in videoPlayer
567 'url': 'http://www8.hp.com/cn/zh/home.html',
568 'info_dict': {
569 'id': '5255815316001',
570 'ext': 'mp4',
571 'title': 'Sprocket Video - China',
572 'description': 'Sprocket Video - China',
573 'uploader': 'HP-Video Gallery',
574 'timestamp': 1482263210,
575 'upload_date': '20161220',
576 'uploader_id': '1107601872001',
577 },
578 'params': {
579 'skip_download': True, # m3u8 download
580 },
581 },
582 # ooyala video
583 {
584 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
585 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
586 'info_dict': {
587 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
588 'ext': 'mp4',
589 'title': '2cc213299525360.mov', # that's what we get
590 'duration': 238.231,
591 },
592 'add_ie': ['Ooyala'],
593 },
594 {
595 # ooyala video embedded with http://player.ooyala.com/iframe.js
596 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
597 'info_dict': {
598 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
599 'ext': 'mp4',
600 'title': '"Steve Jobs: Man in the Machine" trailer',
601 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
602 'duration': 135.427,
603 },
604 'params': {
605 'skip_download': True,
606 },
607 'skip': 'movie expired',
608 },
609 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
610 {
611 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
612 'info_dict': {
613 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
614 'ext': 'mp4',
615 'title': 'Steampunk Fest Comes to Honesdale',
616 'duration': 43.276,
617 },
618 'params': {
619 'skip_download': True,
620 }
621 },
622 # embed.ly video
623 {
624 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
625 'info_dict': {
626 'id': '9ODmcdjQcHQ',
627 'ext': 'mp4',
628 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
629 'upload_date': '20140225',
630 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
631 'uploader': 'Tested',
632 'uploader_id': 'testedcom',
633 },
634 # No need to test YoutubeIE here
635 'params': {
636 'skip_download': True,
637 },
638 },
639 # funnyordie embed
640 {
641 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
642 'info_dict': {
643 'id': '18e820ec3f',
644 'ext': 'mp4',
645 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
646 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
647 },
648 # HEAD requests lead to endless 301, while GET is OK
649 'expected_warnings': ['301'],
650 },
651 # RUTV embed
652 {
653 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
654 'info_dict': {
655 'id': '776940',
656 'ext': 'mp4',
657 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
658 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
659 },
660 'params': {
661 # m3u8 download
662 'skip_download': True,
663 },
664 },
665 # TVC embed
666 {
667 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
668 'info_dict': {
669 'id': '55304',
670 'ext': 'mp4',
671 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
672 },
673 },
674 # SportBox embed
675 {
676 'url': 'http://www.vestifinance.ru/articles/25753',
677 'info_dict': {
678 'id': '25753',
679 'title': 'ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
680 },
681 'playlist': [{
682 'info_dict': {
683 'id': '370908',
684 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
685 'ext': 'mp4',
686 }
687 }, {
688 'info_dict': {
689 'id': '370905',
690 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
691 'ext': 'mp4',
692 }
693 }, {
694 'info_dict': {
695 'id': '370902',
696 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
697 'ext': 'mp4',
698 }
699 }],
700 'params': {
701 # m3u8 download
702 'skip_download': True,
703 },
704 },
705 # Myvi.ru embed
706 {
707 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
708 'info_dict': {
709 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
710 'ext': 'mp4',
711 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
712 'thumbnail': r're:^https?://.*\.jpg$',
713 'duration': 153,
714 }
715 },
716 # XHamster embed
717 {
718 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
719 'info_dict': {
720 'id': 'showthread',
721 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
722 },
723 'playlist_mincount': 7,
724 # This forum does not allow <iframe> syntaxes anymore
725 # Now HTML tags are displayed as-is
726 'skip': 'No videos on this page',
727 },
728 # Embedded TED video
729 {
730 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
731 'md5': '65fdff94098e4a607385a60c5177c638',
732 'info_dict': {
733 'id': '1969',
734 'ext': 'mp4',
735 'title': 'Hidden miracles of the natural world',
736 'uploader': 'Louie Schwartzberg',
737 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
738 }
739 },
740 # nowvideo embed hidden behind percent encoding
741 {
742 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
743 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
744 'info_dict': {
745 'id': '06e53103ca9aa',
746 'ext': 'flv',
747 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
748 'description': 'No description',
749 },
750 },
751 # arte embed
752 {
753 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
754 'md5': '7653032cbb25bf6c80d80f217055fa43',
755 'info_dict': {
756 'id': '048195-004_PLUS7-F',
757 'ext': 'flv',
758 'title': 'X:enius',
759 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
760 'upload_date': '20140320',
761 },
762 'params': {
763 'skip_download': 'Requires rtmpdump'
764 },
765 'skip': 'video gone',
766 },
767 # francetv embed
768 {
769 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
770 'info_dict': {
771 'id': 'EV_30231',
772 'ext': 'mp4',
773 'title': 'Alcaline, le concert avec Calogero',
774 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
775 'upload_date': '20150226',
776 'timestamp': 1424989860,
777 'duration': 5400,
778 },
779 'params': {
780 # m3u8 downloads
781 'skip_download': True,
782 },
783 'expected_warnings': [
784 'Forbidden'
785 ]
786 },
787 # CondƩ Nast embed
788 {
789 'url': 'http://www.wired.com/2014/04/honda-asimo/',
790 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
791 'info_dict': {
792 'id': '53501be369702d3275860000',
793 'ext': 'mp4',
794 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
795 }
796 },
797 # Dailymotion embed
798 {
799 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
800 'md5': '441aeeb82eb72c422c7f14ec533999cd',
801 'info_dict': {
802 'id': 'k2mm4bCdJ6CQ2i7c8o2',
803 'ext': 'mp4',
804 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
805 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
806 'uploader': 'Spi0n',
807 'uploader_id': 'xgditw',
808 'upload_date': '20140425',
809 'timestamp': 1398441542,
810 },
811 'add_ie': ['Dailymotion'],
812 },
813 # DailyMail embed
814 {
815 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
816 'info_dict': {
817 'id': '1495629',
818 'ext': 'mp4',
819 'title': 'Care worker punches elderly dementia patient in head 11 times',
820 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
821 },
822 'add_ie': ['DailyMail'],
823 'params': {
824 'skip_download': True,
825 },
826 },
827 # YouTube embed
828 {
829 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
830 'info_dict': {
831 'id': 'FXRb4ykk4S0',
832 'ext': 'mp4',
833 'title': 'The NBL Auction 2014',
834 'uploader': 'BADMINTON England',
835 'uploader_id': 'BADMINTONEvents',
836 'upload_date': '20140603',
837 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
838 },
839 'add_ie': ['Youtube'],
840 'params': {
841 'skip_download': True,
842 }
843 },
844 # MTVSercices embed
845 {
846 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
847 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
848 'info_dict': {
849 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
850 'ext': 'mp4',
851 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
852 'description': 'Two valets share their love for movie star Liam Neesons.',
853 'timestamp': 1349922600,
854 'upload_date': '20121011',
855 },
856 },
857 # YouTube embed via <data-embed-url="">
858 {
859 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
860 'info_dict': {
861 'id': '4vAffPZIT44',
862 'ext': 'mp4',
863 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
864 'uploader': 'Gameloft',
865 'uploader_id': 'gameloft',
866 'upload_date': '20140828',
867 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
868 },
869 'params': {
870 'skip_download': True,
871 }
872 },
873 # YouTube <object> embed
874 {
875 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
876 'md5': '516718101ec834f74318df76259fb3cc',
877 'info_dict': {
878 'id': 'msN87y-iEx0',
879 'ext': 'webm',
880 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
881 'upload_date': '20080526',
882 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
883 'uploader': 'Christopher Sykes',
884 'uploader_id': 'ChristopherJSykes',
885 },
886 'add_ie': ['Youtube'],
887 },
888 # Camtasia studio
889 {
890 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
891 'playlist': [{
892 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
893 'info_dict': {
894 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
895 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
896 'ext': 'flv',
897 'duration': 2235.90,
898 }
899 }, {
900 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
901 'info_dict': {
902 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
903 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
904 'ext': 'flv',
905 'duration': 2235.93,
906 }
907 }],
908 'info_dict': {
909 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
910 }
911 },
912 # Flowplayer
913 {
914 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
915 'md5': '9d65602bf31c6e20014319c7d07fba27',
916 'info_dict': {
917 'id': '5123ea6d5e5a7',
918 'ext': 'mp4',
919 'age_limit': 18,
920 'uploader': 'www.handjobhub.com',
921 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
922 }
923 },
924 # Multiple brightcove videos
925 # https://github.com/ytdl-org/youtube-dl/issues/2283
926 {
927 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
928 'info_dict': {
929 'id': 'always-never',
930 'title': 'Always / Never - The New Yorker',
931 },
932 'playlist_count': 3,
933 'params': {
934 'extract_flat': False,
935 'skip_download': True,
936 }
937 },
938 # MLB embed
939 {
940 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
941 'md5': '96f09a37e44da40dd083e12d9a683327',
942 'info_dict': {
943 'id': '33322633',
944 'ext': 'mp4',
945 'title': 'Ump changes call to ball',
946 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
947 'duration': 48,
948 'timestamp': 1401537900,
949 'upload_date': '20140531',
950 'thumbnail': r're:^https?://.*\.jpg$',
951 },
952 },
953 # Wistia embed
954 {
955 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
956 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
957 'info_dict': {
958 'id': '6e2wtrbdaf',
959 'ext': 'mov',
960 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
961 'description': 'a Paywall Videos video from Remilon',
962 'duration': 644.072,
963 'uploader': 'study.com',
964 'timestamp': 1459678540,
965 'upload_date': '20160403',
966 'filesize': 24687186,
967 },
968 },
969 {
970 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
971 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
972 'info_dict': {
973 'id': 'uxjb0lwrcz',
974 'ext': 'mp4',
975 'title': 'Conversation about Hexagonal Rails Part 1',
976 'description': 'a Martin Fowler video from ThoughtWorks',
977 'duration': 1715.0,
978 'uploader': 'thoughtworks.wistia.com',
979 'timestamp': 1401832161,
980 'upload_date': '20140603',
981 },
982 },
983 # Wistia standard embed (async)
984 {
985 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
986 'info_dict': {
987 'id': '807fafadvk',
988 'ext': 'mp4',
989 'title': 'Drip Brennan Dunn Workshop',
990 'description': 'a JV Webinars video from getdrip-1',
991 'duration': 4986.95,
992 'timestamp': 1463607249,
993 'upload_date': '20160518',
994 },
995 'params': {
996 'skip_download': True,
997 }
998 },
999 # Soundcloud embed
1000 {
1001 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1002 'info_dict': {
1003 'id': '174391317',
1004 'ext': 'mp3',
1005 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1006 'uploader': 'Sophos Security',
1007 'title': 'Chet Chat 171 - Oct 29, 2014',
1008 'upload_date': '20141029',
1009 }
1010 },
1011 # Soundcloud multiple embeds
1012 {
1013 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1014 'info_dict': {
1015 'id': '52809',
1016 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
1017 },
1018 'playlist_mincount': 7,
1019 },
1020 # TuneIn station embed
1021 {
1022 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1023 'info_dict': {
1024 'id': '204146',
1025 'ext': 'mp3',
1026 'title': 'CNRV',
1027 'location': 'Paris, France',
1028 'is_live': True,
1029 },
1030 'params': {
1031 # Live stream
1032 'skip_download': True,
1033 },
1034 },
1035 # Livestream embed
1036 {
1037 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1038 'info_dict': {
1039 'id': '67864563',
1040 'ext': 'flv',
1041 'upload_date': '20141112',
1042 'title': 'Rosetta #CometLanding webcast HL 10',
1043 }
1044 },
1045 # Another Livestream embed, without 'new.' in URL
1046 {
1047 'url': 'https://www.freespeech.org/',
1048 'info_dict': {
1049 'id': '123537347',
1050 'ext': 'mp4',
1051 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1052 },
1053 'params': {
1054 # Live stream
1055 'skip_download': True,
1056 },
1057 },
1058 # LazyYT
1059 {
1060 'url': 'https://skiplagged.com/',
1061 'info_dict': {
1062 'id': 'skiplagged',
1063 'title': 'Skiplagged: The smart way to find cheap flights',
1064 },
1065 'playlist_mincount': 1,
1066 'add_ie': ['Youtube'],
1067 },
1068 # Cinchcast embed
1069 {
1070 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1071 'info_dict': {
1072 'id': '7141703',
1073 'ext': 'mp3',
1074 'upload_date': '20141126',
1075 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1076 }
1077 },
1078 # Cinerama player
1079 {
1080 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1081 'info_dict': {
1082 'id': '730m_DandD_1901_512k',
1083 'ext': 'mp4',
1084 'uploader': 'www.abc.net.au',
1085 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1086 }
1087 },
1088 # embedded viddler video
1089 {
1090 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1091 'info_dict': {
1092 'id': '4d03aad9',
1093 'ext': 'mp4',
1094 'uploader': 'deadspin',
1095 'title': 'WALL-TO-GORTAT',
1096 'timestamp': 1422285291,
1097 'upload_date': '20150126',
1098 },
1099 'add_ie': ['Viddler'],
1100 },
1101 # Libsyn embed
1102 {
1103 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1104 'info_dict': {
1105 'id': '3377616',
1106 'ext': 'mp3',
1107 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1108 'description': 'md5:601cb790edd05908957dae8aaa866465',
1109 'upload_date': '20150220',
1110 },
1111 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1112 },
1113 # jwplayer YouTube
1114 {
1115 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1116 'info_dict': {
1117 'id': 'Mrj4DVp2zeA',
1118 'ext': 'mp4',
1119 'upload_date': '20150212',
1120 'uploader': 'The National Archives UK',
1121 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1122 'uploader_id': 'NationalArchives08',
1123 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1124 },
1125 },
1126 # jwplayer rtmp
1127 {
1128 'url': 'http://www.suffolk.edu/sjc/live.php',
1129 'info_dict': {
1130 'id': 'live',
1131 'ext': 'flv',
1132 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1133 'uploader': 'www.suffolk.edu',
1134 },
1135 'params': {
1136 'skip_download': True,
1137 },
1138 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1139 },
1140 # Complex jwplayer
1141 {
1142 'url': 'http://www.indiedb.com/games/king-machine/videos',
1143 'info_dict': {
1144 'id': 'videos',
1145 'ext': 'mp4',
1146 'title': 'king machine trailer 1',
1147 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1148 'thumbnail': r're:^https?://.*\.jpg$',
1149 },
1150 },
1151 {
1152 # JWPlayer config passed as variable
1153 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1154 'info_dict': {
1155 'id': '3326530_hq',
1156 'ext': 'mp4',
1157 'title': 'ARIELE | Tube Cup',
1158 'uploader': 'www.txxx.com',
1159 'age_limit': 18,
1160 },
1161 'params': {
1162 'skip_download': True,
1163 }
1164 },
1165 {
1166 # JWPlatform iframe
1167 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1168 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1169 'info_dict': {
1170 'id': 'O0c5JcKT',
1171 'ext': 'mp4',
1172 'upload_date': '20171122',
1173 'timestamp': 1511366290,
1174 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1175 },
1176 'add_ie': [JWPlatformIE.ie_key()],
1177 },
1178 {
1179 # Video.js embed, multiple formats
1180 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1181 'info_dict': {
1182 'id': 'yygqldloqIk',
1183 'ext': 'mp4',
1184 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1185 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1186 'upload_date': '20130314',
1187 'uploader': 'PROстŠ¾Šµ3D',
1188 'uploader_id': 'PROstoe3D',
1189 },
1190 'params': {
1191 'skip_download': True,
1192 },
1193 },
1194 {
1195 # Video.js embed, single format
1196 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1197 'info_dict': {
1198 'id': 'watch',
1199 'ext': 'mp4',
1200 'title': 'Step 1 - Good Foundation',
1201 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1202 },
1203 'params': {
1204 'skip_download': True,
1205 },
1206 },
1207 # rtl.nl embed
1208 {
1209 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1210 'playlist_mincount': 5,
1211 'info_dict': {
1212 'id': 'aanslagen-kopenhagen',
1213 'title': 'Aanslagen Kopenhagen',
1214 }
1215 },
1216 # Zapiks embed
1217 {
1218 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1219 'info_dict': {
1220 'id': '118046',
1221 'ext': 'mp4',
1222 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1223 }
1224 },
1225 # Kaltura embed (different embed code)
1226 {
1227 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1228 'info_dict': {
1229 'id': '1_a52wc67y',
1230 'ext': 'flv',
1231 'upload_date': '20150127',
1232 'uploader_id': 'PremierMedia',
1233 'timestamp': int,
1234 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1235 },
1236 },
1237 # Kaltura embed with single quotes
1238 {
1239 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1240 'info_dict': {
1241 'id': '0_izeg5utt',
1242 'ext': 'mp4',
1243 'title': '35871',
1244 'timestamp': 1355743100,
1245 'upload_date': '20121217',
1246 'uploader_id': 'cplapp@learn360.com',
1247 },
1248 'add_ie': ['Kaltura'],
1249 },
1250 {
1251 # Kaltura embedded via quoted entry_id
1252 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1253 'info_dict': {
1254 'id': '0_utuok90b',
1255 'ext': 'mp4',
1256 'title': '06_matthew_brender_raj_dutt',
1257 'timestamp': 1466638791,
1258 'upload_date': '20160622',
1259 },
1260 'add_ie': ['Kaltura'],
1261 'expected_warnings': [
1262 'Could not send HEAD request'
1263 ],
1264 'params': {
1265 'skip_download': True,
1266 }
1267 },
1268 {
1269 # Kaltura embedded, some fileExt broken (#11480)
1270 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1271 'info_dict': {
1272 'id': '1_sgtvehim',
1273 'ext': 'mp4',
1274 'title': 'Our "Standard Models" of particle physics and cosmology',
1275 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1276 'timestamp': 1321158993,
1277 'upload_date': '20111113',
1278 'uploader_id': 'kps1',
1279 },
1280 'add_ie': ['Kaltura'],
1281 },
1282 {
1283 # Kaltura iframe embed
1284 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1285 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1286 'info_dict': {
1287 'id': '0_f2cfbpwy',
1288 'ext': 'mp4',
1289 'title': 'I. M. Pei: A Centennial Celebration',
1290 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1291 'upload_date': '20170403',
1292 'uploader_id': 'batchUser',
1293 'timestamp': 1491232186,
1294 },
1295 'add_ie': ['Kaltura'],
1296 },
1297 {
1298 # Kaltura iframe embed, more sophisticated
1299 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1300 'info_dict': {
1301 'id': '1_9gzouybz',
1302 'ext': 'mp4',
1303 'title': 'lecture-05sep2017',
1304 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1305 'upload_date': '20170913',
1306 'uploader_id': 'eps2',
1307 'timestamp': 1505340777,
1308 },
1309 'params': {
1310 'skip_download': True,
1311 },
1312 'add_ie': ['Kaltura'],
1313 },
1314 {
1315 # meta twitter:player
1316 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1317 'info_dict': {
1318 'id': '0_01b42zps',
1319 'ext': 'mp4',
1320 'title': 'Main Twerk (Video)',
1321 'upload_date': '20171208',
1322 'uploader_id': 'sebastian.salinas@thechive.com',
1323 'timestamp': 1512713057,
1324 },
1325 'params': {
1326 'skip_download': True,
1327 },
1328 'add_ie': ['Kaltura'],
1329 },
1330 # referrer protected EaglePlatform embed
1331 {
1332 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1333 'info_dict': {
1334 'id': '582306',
1335 'ext': 'mp4',
1336 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1337 'thumbnail': r're:^https?://.*\.jpg$',
1338 'duration': 3382,
1339 'view_count': int,
1340 },
1341 'params': {
1342 'skip_download': True,
1343 },
1344 },
1345 # ClipYou (EaglePlatform) embed (custom URL)
1346 {
1347 'url': 'http://muz-tv.ru/play/7129/',
1348 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1349 'info_dict': {
1350 'id': '12820',
1351 'ext': 'mp4',
1352 'title': "'O Sole Mio",
1353 'thumbnail': r're:^https?://.*\.jpg$',
1354 'duration': 216,
1355 'view_count': int,
1356 },
1357 'params': {
1358 'skip_download': True,
1359 },
1360 'skip': 'This video is unavailable.',
1361 },
1362 # Pladform embed
1363 {
1364 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1365 'info_dict': {
1366 'id': '100183293',
1367 'ext': 'mp4',
1368 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1369 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1370 'thumbnail': r're:^https?://.*\.jpg$',
1371 'duration': 694,
1372 'age_limit': 0,
1373 },
1374 'skip': 'HTTP Error 404: Not Found',
1375 },
1376 # Playwire embed
1377 {
1378 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1379 'info_dict': {
1380 'id': '3519514',
1381 'ext': 'mp4',
1382 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1383 'thumbnail': r're:^https?://.*\.png$',
1384 'duration': 45.115,
1385 },
1386 },
1387 # 5min embed
1388 {
1389 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1390 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1391 'info_dict': {
1392 'id': '518726732',
1393 'ext': 'mp4',
1394 'title': 'Facebook Creates "On This Day" | Crunch Report',
1395 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1396 'timestamp': 1427237531,
1397 'uploader': 'Crunch Report',
1398 'upload_date': '20150324',
1399 },
1400 'params': {
1401 # m3u8 download
1402 'skip_download': True,
1403 },
1404 },
1405 # Crooks and Liars embed
1406 {
1407 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1408 'info_dict': {
1409 'id': '8RUoRhRi',
1410 'ext': 'mp4',
1411 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1412 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1413 'timestamp': 1428207000,
1414 'upload_date': '20150405',
1415 'uploader': 'Heather',
1416 },
1417 },
1418 # Crooks and Liars external embed
1419 {
1420 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1421 'info_dict': {
1422 'id': 'MTE3MjUtMzQ2MzA',
1423 'ext': 'mp4',
1424 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1425 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1426 'timestamp': 1265032391,
1427 'upload_date': '20100201',
1428 'uploader': 'Heather',
1429 },
1430 },
1431 # NBC Sports vplayer embed
1432 {
1433 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1434 'info_dict': {
1435 'id': 'ln7x1qSThw4k',
1436 'ext': 'flv',
1437 'title': "PFT Live: New leader in the 'new-look' defense",
1438 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1439 'uploader': 'NBCU-SPORTS',
1440 'upload_date': '20140107',
1441 'timestamp': 1389118457,
1442 },
1443 'skip': 'Invalid Page URL',
1444 },
1445 # NBC News embed
1446 {
1447 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1448 'md5': '1aa589c675898ae6d37a17913cf68d66',
1449 'info_dict': {
1450 'id': 'x_dtl_oa_LettermanliftPR_160608',
1451 'ext': 'mp4',
1452 'title': 'David Letterman: A Preview',
1453 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1454 'upload_date': '20160609',
1455 'timestamp': 1465431544,
1456 'uploader': 'NBCU-NEWS',
1457 },
1458 },
1459 # UDN embed
1460 {
1461 'url': 'https://video.udn.com/news/300346',
1462 'md5': 'fd2060e988c326991037b9aff9df21a6',
1463 'info_dict': {
1464 'id': '300346',
1465 'ext': 'mp4',
1466 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1467 'thumbnail': r're:^https?://.*\.jpg$',
1468 },
1469 'params': {
1470 # m3u8 download
1471 'skip_download': True,
1472 },
1473 'expected_warnings': ['Failed to parse JSON Expecting value'],
1474 },
1475 # Brightcove URL in single quotes
1476 {
1477 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1478 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1479 'info_dict': {
1480 'id': '4255764656001',
1481 'ext': 'mp4',
1482 'title': 'SN Presents: Russell Martin, World Citizen',
1483 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1484 'uploader': 'Rogers Sportsnet',
1485 'uploader_id': '1704050871',
1486 'upload_date': '20150525',
1487 'timestamp': 1432570283,
1488 },
1489 },
1490 # Kinja embed
1491 {
1492 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'info_dict': {
1494 'id': '106351',
1495 'ext': 'mp4',
1496 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1497 'description': 'Migrated from OnionStudios',
1498 'thumbnail': r're:^https?://.*\.jpe?g$',
1499 'uploader': 'clickhole',
1500 'upload_date': '20150527',
1501 'timestamp': 1432744860,
1502 }
1503 },
1504 # SnagFilms embed
1505 {
1506 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1507 'info_dict': {
1508 'id': '74849a00-85a9-11e1-9660-123139220831',
1509 'ext': 'mp4',
1510 'title': '#whilewewatch',
1511 }
1512 },
1513 # AdobeTVVideo embed
1514 {
1515 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1516 'md5': '43662b577c018ad707a63766462b1e87',
1517 'info_dict': {
1518 'id': '2456',
1519 'ext': 'mp4',
1520 'title': 'New experience with Acrobat DC',
1521 'description': 'New experience with Acrobat DC',
1522 'duration': 248.667,
1523 },
1524 },
1525 # BrightcoveInPageEmbed embed
1526 {
1527 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1528 'info_dict': {
1529 'id': '4238694884001',
1530 'ext': 'flv',
1531 'title': 'Tabletop: Dread, Last Thoughts',
1532 'description': 'Tabletop: Dread, Last Thoughts',
1533 'duration': 51690,
1534 },
1535 },
1536 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1537 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1538 {
1539 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1540 'info_dict': {
1541 'id': '4785848093001',
1542 'ext': 'mp4',
1543 'title': 'The Cardinal Pell Interview',
1544 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1545 'uploader': 'GlobeCast Australia - GlobeStream',
1546 'uploader_id': '2733773828001',
1547 'upload_date': '20160304',
1548 'timestamp': 1457083087,
1549 },
1550 'params': {
1551 # m3u8 downloads
1552 'skip_download': True,
1553 },
1554 },
1555 {
1556 # Brightcove embed with whitespace around attribute names
1557 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1558 'info_dict': {
1559 'id': '3167554373001',
1560 'ext': 'mp4',
1561 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1562 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1563 'uploader_id': '1079349493',
1564 'upload_date': '20140207',
1565 'timestamp': 1391810548,
1566 },
1567 'params': {
1568 'skip_download': True,
1569 },
1570 },
1571 # Another form of arte.tv embed
1572 {
1573 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1574 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1575 'info_dict': {
1576 'id': '030273-562_PLUS7-F',
1577 'ext': 'mp4',
1578 'title': 'ARTE Reportage - Nulle part, en France',
1579 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1580 'upload_date': '20160409',
1581 },
1582 },
1583 # LiveLeak embed
1584 {
1585 'url': 'http://www.wykop.pl/link/3088787/',
1586 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1587 'info_dict': {
1588 'id': '874_1459135191',
1589 'ext': 'mp4',
1590 'title': 'Man shows poor quality of new apartment building',
1591 'description': 'The wall is like a sand pile.',
1592 'uploader': 'Lake8737',
1593 },
1594 'add_ie': [LiveLeakIE.ie_key()],
1595 },
1596 # Another LiveLeak embed pattern (#13336)
1597 {
1598 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1599 'info_dict': {
1600 'id': '2eb_1496309988',
1601 'ext': 'mp4',
1602 'title': 'Thief robs place where everyone was armed',
1603 'description': 'md5:694d73ee79e535953cf2488562288eee',
1604 'uploader': 'brazilwtf',
1605 },
1606 'add_ie': [LiveLeakIE.ie_key()],
1607 },
1608 # Duplicated embedded video URLs
1609 {
1610 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1611 'info_dict': {
1612 'id': '149298443_480_16c25b74_2',
1613 'ext': 'mp4',
1614 'title': 'vs. Blue Orange Spring Game',
1615 'uploader': 'www.hudl.com',
1616 },
1617 },
1618 # twitter:player:stream embed
1619 {
1620 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1621 'info_dict': {
1622 'id': 'master',
1623 'ext': 'mp4',
1624 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1625 'uploader': 'www.rtl.be',
1626 },
1627 'params': {
1628 # m3u8 downloads
1629 'skip_download': True,
1630 },
1631 },
1632 # twitter:player embed
1633 {
1634 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1635 'md5': 'a3e0df96369831de324f0778e126653c',
1636 'info_dict': {
1637 'id': '4909620399001',
1638 'ext': 'mp4',
1639 'title': 'What Do Black Holes Sound Like?',
1640 'description': 'what do black holes sound like',
1641 'upload_date': '20160524',
1642 'uploader_id': '29913724001',
1643 'timestamp': 1464107587,
1644 'uploader': 'TheAtlantic',
1645 },
1646 'add_ie': ['BrightcoveLegacy'],
1647 },
1648 # Facebook <iframe> embed
1649 {
1650 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1651 'md5': 'fbcde74f534176ecb015849146dd3aee',
1652 'info_dict': {
1653 'id': '599637780109885',
1654 'ext': 'mp4',
1655 'title': 'Facebook video #599637780109885',
1656 },
1657 },
1658 # Facebook <iframe> embed, plugin video
1659 {
1660 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1661 'info_dict': {
1662 'id': '1754168231264132',
1663 'ext': 'mp4',
1664 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1665 'uploader': 'Tariq Ramadan (official)',
1666 'timestamp': 1496758379,
1667 'upload_date': '20170606',
1668 },
1669 'params': {
1670 'skip_download': True,
1671 },
1672 },
1673 # Facebook API embed
1674 {
1675 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1676 'md5': 'a47372ee61b39a7b90287094d447d94e',
1677 'info_dict': {
1678 'id': '10153467542406923',
1679 'ext': 'mp4',
1680 'title': 'Facebook video #10153467542406923',
1681 },
1682 },
1683 # Wordpress "YouTube Video Importer" plugin
1684 {
1685 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1686 'md5': 'd16797741b560b485194eddda8121b48',
1687 'info_dict': {
1688 'id': 'HNTXWDXV9Is',
1689 'ext': 'mp4',
1690 'title': 'Blue Devils Drumline Stanford lot 2016',
1691 'upload_date': '20160627',
1692 'uploader_id': 'GENOCIDE8GENERAL10',
1693 'uploader': 'cylus cyrus',
1694 },
1695 },
1696 {
1697 # video stored on custom kaltura server
1698 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1699 'md5': '537617d06e64dfed891fa1593c4b30cc',
1700 'info_dict': {
1701 'id': '0_1iotm5bh',
1702 'ext': 'mp4',
1703 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1704 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1705 'uploader_id': 'videos.expansion@el-mundo.net',
1706 'upload_date': '20150429',
1707 'timestamp': 1430303472,
1708 },
1709 'add_ie': ['Kaltura'],
1710 },
1711 {
1712 # Non-standard Vimeo embed
1713 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1714 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1715 'info_dict': {
1716 'id': '148867247',
1717 'ext': 'mp4',
1718 'title': 'Understanding the web - Teaser',
1719 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1720 'upload_date': '20151214',
1721 'uploader': 'OpenClassrooms',
1722 'uploader_id': 'openclassrooms',
1723 },
1724 'add_ie': ['Vimeo'],
1725 },
1726 {
1727 # generic vimeo embed that requires original URL passed as Referer
1728 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1729 'only_matching': True,
1730 },
1731 {
1732 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1733 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1734 'info_dict': {
1735 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1736 'ext': 'mp4',
1737 'title': 'Big Buck Bunny',
1738 'description': 'Royalty free test video',
1739 'timestamp': 1432816365,
1740 'upload_date': '20150528',
1741 'is_live': False,
1742 },
1743 'params': {
1744 'skip_download': True,
1745 },
1746 'add_ie': [ArkenaIE.ie_key()],
1747 },
1748 {
1749 '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/',
1750 'info_dict': {
1751 'id': '1c7141f46c',
1752 'ext': 'mp4',
1753 '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',
1754 },
1755 'params': {
1756 'skip_download': True,
1757 },
1758 'add_ie': [Vbox7IE.ie_key()],
1759 },
1760 {
1761 # DBTV embeds
1762 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1763 'info_dict': {
1764 'id': '43254897',
1765 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1766 },
1767 'playlist_mincount': 3,
1768 },
1769 {
1770 # Videa embeds
1771 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1772 'info_dict': {
1773 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1774 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1775 },
1776 'playlist_mincount': 2,
1777 },
1778 {
1779 # 20 minuten embed
1780 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1781 'info_dict': {
1782 'id': '523629',
1783 'ext': 'mp4',
1784 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1785 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1786 },
1787 'params': {
1788 'skip_download': True,
1789 },
1790 'add_ie': [TwentyMinutenIE.ie_key()],
1791 },
1792 {
1793 # VideoPress embed
1794 'url': 'https://en.support.wordpress.com/videopress/',
1795 'info_dict': {
1796 'id': 'OcobLTqC',
1797 'ext': 'm4v',
1798 'title': 'IMG_5786',
1799 'timestamp': 1435711927,
1800 'upload_date': '20150701',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 },
1805 'add_ie': [VideoPressIE.ie_key()],
1806 },
1807 {
1808 # Rutube embed
1809 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1810 'info_dict': {
1811 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1812 'ext': 'flv',
1813 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1814 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1815 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1816 'upload_date': '20170228',
1817 'uploader_id': '996642',
1818 },
1819 'params': {
1820 'skip_download': True,
1821 },
1822 'add_ie': [RutubeIE.ie_key()],
1823 },
1824 {
1825 # ThePlatform embedded with whitespaces in URLs
1826 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1827 'only_matching': True,
1828 },
1829 {
1830 # Senate ISVP iframe https
1831 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1832 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1833 'info_dict': {
1834 'id': 'govtaff020316',
1835 'ext': 'mp4',
1836 'title': 'Integrated Senate Video Player',
1837 },
1838 'add_ie': [SenateISVPIE.ie_key()],
1839 },
1840 {
1841 # Limelight embeds (1 channel embed + 4 media embeds)
1842 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1843 'info_dict': {
1844 'id': 'FacilitatorTraining2017',
1845 'title': 'Facilitator Training 2017',
1846 },
1847 'playlist_mincount': 5,
1848 },
1849 {
1850 # Limelight embed (LimelightPlayerUtil.embed)
1851 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1852 'info_dict': {
1853 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1854 'ext': 'mp4',
1855 'title': '07448641',
1856 'timestamp': 1499890639,
1857 'upload_date': '20170712',
1858 },
1859 'params': {
1860 'skip_download': True,
1861 },
1862 'add_ie': ['LimelightMedia'],
1863 },
1864 {
1865 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1866 'info_dict': {
1867 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1868 'title': 'Standoff with Walnut Creek murder suspect ends',
1869 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1870 },
1871 'playlist_mincount': 4,
1872 },
1873 {
1874 # WashingtonPost embed
1875 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1876 'info_dict': {
1877 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1878 'ext': 'mp4',
1879 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1880 '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.',
1881 'timestamp': 1455216756,
1882 'uploader': 'The Washington Post',
1883 'upload_date': '20160211',
1884 },
1885 'add_ie': [WashingtonPostIE.ie_key()],
1886 },
1887 {
1888 # Mediaset embed
1889 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1890 'info_dict': {
1891 'id': '720642',
1892 'ext': 'mp4',
1893 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1894 },
1895 'params': {
1896 'skip_download': True,
1897 },
1898 'add_ie': [MediasetIE.ie_key()],
1899 },
1900 {
1901 # JOJ.sk embeds
1902 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'info_dict': {
1904 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1905 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1906 },
1907 'playlist_mincount': 5,
1908 'add_ie': [JojIE.ie_key()],
1909 },
1910 {
1911 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1912 'url': 'https://tvrain.ru/amp/418921/',
1913 'md5': 'cc00413936695987e8de148b67d14f1d',
1914 'info_dict': {
1915 'id': '418921',
1916 'ext': 'mp4',
1917 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1918 },
1919 },
1920 {
1921 # vzaar embed
1922 'url': 'http://help.vzaar.com/article/165-embedding-video',
1923 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1924 'info_dict': {
1925 'id': '8707641',
1926 'ext': 'mp4',
1927 'title': 'Building A Business Online: Principal Chairs Q & A',
1928 },
1929 },
1930 {
1931 # multiple HTML5 videos on one page
1932 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1933 'info_dict': {
1934 'id': 'keyscenarios',
1935 'title': 'Rescue Kit 14 Free Edition - Getting started',
1936 },
1937 'playlist_count': 4,
1938 },
1939 {
1940 # vshare embed
1941 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1942 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1943 'info_dict': {
1944 'id': '0f64ce6',
1945 'title': 'vl14062007715967',
1946 'ext': 'mp4',
1947 }
1948 },
1949 {
1950 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1951 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1952 'info_dict': {
1953 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1954 'ext': 'mp4',
1955 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1956 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1957 'timestamp': 1474354800,
1958 'upload_date': '20160920',
1959 }
1960 },
1961 {
1962 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1963 'info_dict': {
1964 'id': '1731611',
1965 'ext': 'mp4',
1966 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1967 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1968 'timestamp': 1516100691,
1969 'upload_date': '20180116',
1970 },
1971 'params': {
1972 'skip_download': True,
1973 },
1974 'add_ie': [SpringboardPlatformIE.ie_key()],
1975 },
1976 {
1977 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1978 'info_dict': {
1979 'id': 'uPDB5I9wfp8',
1980 'ext': 'webm',
1981 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1982 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1983 'upload_date': '20160219',
1984 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1985 'uploader_id': 'PocoyoBrazil',
1986 },
1987 'add_ie': [YoutubeIE.ie_key()],
1988 'params': {
1989 'skip_download': True,
1990 },
1991 },
1992 {
1993 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1994 'info_dict': {
1995 'id': 'vMDE4NzI1Mjgt690b',
1996 'ext': 'mp4',
1997 'title': 'ŠšŠ¾Ń‚ŃŃ‚Š°',
1998 },
1999 'add_ie': [YapFilesIE.ie_key()],
2000 'params': {
2001 'skip_download': True,
2002 },
2003 },
2004 {
2005 # CloudflareStream embed
2006 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2007 'info_dict': {
2008 'id': '31c9291ab41fac05471db4e73aa11717',
2009 'ext': 'mp4',
2010 'title': '31c9291ab41fac05471db4e73aa11717',
2011 },
2012 'add_ie': [CloudflareStreamIE.ie_key()],
2013 'params': {
2014 'skip_download': True,
2015 },
2016 },
2017 {
2018 # PeerTube embed
2019 'url': 'https://joinpeertube.org/fr/home/',
2020 'info_dict': {
2021 'id': 'home',
2022 'title': 'Reprenez le contrƓle de vos vidƩos ! #JoinPeertube',
2023 },
2024 'playlist_count': 2,
2025 },
2026 {
2027 # Indavideo embed
2028 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2029 'info_dict': {
2030 'id': '1693903',
2031 'ext': 'mp4',
2032 'title': 'ƍgy kell otthon hamburgert sĆ¼tni',
2033 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2034 'timestamp': 1426330212,
2035 'upload_date': '20150314',
2036 'uploader': 'StreetKitchen',
2037 'uploader_id': '546363',
2038 },
2039 'add_ie': [IndavideoEmbedIE.ie_key()],
2040 'params': {
2041 'skip_download': True,
2042 },
2043 },
2044 {
2045 # APA embed via JWPlatform embed
2046 'url': 'http://www.vol.at/blue-man-group/5593454',
2047 'info_dict': {
2048 'id': 'jjv85FdZ',
2049 'ext': 'mp4',
2050 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview',
2051 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2052 'thumbnail': r're:^https?://.*\.jpg$',
2053 'duration': 254,
2054 'timestamp': 1519211149,
2055 'upload_date': '20180221',
2056 },
2057 'params': {
2058 'skip_download': True,
2059 },
2060 },
2061 {
2062 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2063 'md5': 'b68d276de422ab07ee1d49388103f457',
2064 'info_dict': {
2065 'id': '83645793',
2066 'title': 'Lock up and get excited',
2067 'ext': 'mp4'
2068 },
2069 'skip': 'TODO: fix nested playlists processing in tests',
2070 },
2071 {
2072 # Viqeo embeds
2073 'url': 'https://viqeo.tv/',
2074 'info_dict': {
2075 'id': 'viqeo',
2076 'title': 'All-new video platform',
2077 },
2078 'playlist_count': 6,
2079 },
2080 {
2081 # Squarespace video embed, 2019-08-28
2082 'url': 'http://ootboxford.com',
2083 'info_dict': {
2084 'id': 'Tc7b_JGdZfw',
2085 'title': 'Out of the Blue, at Childish Things 10',
2086 'ext': 'mp4',
2087 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2088 'uploader_id': 'helendouglashouse',
2089 'uploader': 'Helen & Douglas House',
2090 'upload_date': '20140328',
2091 },
2092 'params': {
2093 'skip_download': True,
2094 },
2095 },
2096 {
2097 # Zype embed
2098 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2099 'info_dict': {
2100 'id': '5b400b834b32992a310622b9',
2101 'ext': 'mp4',
2102 'title': 'Smoky Barbecue Favorites',
2103 'thumbnail': r're:^https?://.*\.jpe?g',
2104 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2105 'upload_date': '20170909',
2106 'timestamp': 1504915200,
2107 },
2108 'add_ie': [ZypeIE.ie_key()],
2109 'params': {
2110 'skip_download': True,
2111 },
2112 },
2113 {
2114 # videojs embed
2115 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2116 'info_dict': {
2117 'id': 'shell',
2118 'ext': 'mp4',
2119 'title': 'Š”Š¾ŃŃ‚Š°Š²Ń‰ŠøŠŗ ŠæŠøццы сŠæрŠ¾ŃŠøŠ» рŠ°Š·Ń€ŠµŃˆŠµŠ½Šøя сыŠ³Ń€Š°Ń‚ŃŒ Š½Š° фŠ¾Ń€Ń‚ŠµŠæŠøŠ°Š½Š¾',
2120 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2121 'thumbnail': r're:^https?://.*\.jpg$',
2122 },
2123 'params': {
2124 'skip_download': True,
2125 },
2126 'expected_warnings': ['Failed to download MPD manifest'],
2127 },
2128 {
2129 # DailyMotion embed with DM.player
2130 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2131 'info_dict': {
2132 'id': 'k6aKkGHd9FJs4mtJN39',
2133 'ext': 'mp4',
2134 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2135 'description': 'This video is private.',
2136 'uploader_id': 'x1jf30l',
2137 'uploader': 'beIN SPORTS USA',
2138 'upload_date': '20190528',
2139 'timestamp': 1559062971,
2140 },
2141 'params': {
2142 'skip_download': True,
2143 },
2144 },
2145 # {
2146 # # TODO: find another test
2147 # # http://schema.org/VideoObject
2148 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2149 # 'md5': '888dcf08b7ea671381f00fab74692755',
2150 # 'info_dict': {
2151 # 'id': 'nyvTSJMKId',
2152 # 'ext': 'mp4',
2153 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2154 # 'description': '#love for cats.',
2155 # 'timestamp': 1461244995,
2156 # 'upload_date': '20160421',
2157 # },
2158 # 'params': {
2159 # 'force_generic_extractor': True,
2160 # },
2161 # }
2162 ]
2163
2164 def report_following_redirect(self, new_url):
2165 """Report information extraction."""
2166 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2167
2168 def _extract_rss(self, url, video_id, doc):
2169 playlist_title = doc.find('./channel/title').text
2170 playlist_desc_el = doc.find('./channel/description')
2171 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2172
2173 entries = []
2174 for it in doc.findall('./channel/item'):
2175 next_url = None
2176 enclosure_nodes = it.findall('./enclosure')
2177 for e in enclosure_nodes:
2178 next_url = e.attrib.get('url')
2179 if next_url:
2180 break
2181
2182 if not next_url:
2183 next_url = xpath_text(it, 'link', fatal=False)
2184
2185 if not next_url:
2186 continue
2187
2188 entries.append({
2189 '_type': 'url_transparent',
2190 'url': next_url,
2191 'title': it.find('title').text,
2192 })
2193
2194 return {
2195 '_type': 'playlist',
2196 'id': url,
2197 'title': playlist_title,
2198 'description': playlist_desc,
2199 'entries': entries,
2200 }
2201
2202 def _extract_camtasia(self, url, video_id, webpage):
2203 """ Returns None if no camtasia video can be found. """
2204
2205 camtasia_cfg = self._search_regex(
2206 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2207 webpage, 'camtasia configuration file', default=None)
2208 if camtasia_cfg is None:
2209 return None
2210
2211 title = self._html_search_meta('DC.title', webpage, fatal=True)
2212
2213 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2214 camtasia_cfg = self._download_xml(
2215 camtasia_url, video_id,
2216 note='Downloading camtasia configuration',
2217 errnote='Failed to download camtasia configuration')
2218 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2219
2220 entries = []
2221 for n in fileset_node.getchildren():
2222 url_n = n.find('./uri')
2223 if url_n is None:
2224 continue
2225
2226 entries.append({
2227 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2228 'title': '%s - %s' % (title, n.tag),
2229 'url': compat_urlparse.urljoin(url, url_n.text),
2230 'duration': float_or_none(n.find('./duration').text),
2231 })
2232
2233 return {
2234 '_type': 'playlist',
2235 'entries': entries,
2236 'title': title,
2237 }
2238
2239 def _real_extract(self, url):
2240 if url.startswith('//'):
2241 return self.url_result(self.http_scheme() + url)
2242
2243 parsed_url = compat_urlparse.urlparse(url)
2244 if not parsed_url.scheme:
2245 default_search = self._downloader.params.get('default_search')
2246 if default_search is None:
2247 default_search = 'fixup_error'
2248
2249 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2250 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2251 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2252 return self.url_result('http://' + url)
2253 elif default_search != 'fixup_error':
2254 if default_search == 'auto_warning':
2255 if re.match(r'^(?:url|URL)$', url):
2256 raise ExtractorError(
2257 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2258 expected=True)
2259 else:
2260 self._downloader.report_warning(
2261 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2262 return self.url_result('ytsearch:' + url)
2263
2264 if default_search in ('error', 'fixup_error'):
2265 raise ExtractorError(
2266 '%r is not a valid URL. '
2267 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2268 % (url, url), expected=True)
2269 else:
2270 if ':' not in default_search:
2271 default_search += ':'
2272 return self.url_result(default_search + url)
2273
2274 url, smuggled_data = unsmuggle_url(url)
2275 force_videoid = None
2276 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2277 if smuggled_data and 'force_videoid' in smuggled_data:
2278 force_videoid = smuggled_data['force_videoid']
2279 video_id = force_videoid
2280 else:
2281 video_id = self._generic_id(url)
2282
2283 self.to_screen('%s: Requesting header' % video_id)
2284
2285 head_req = HEADRequest(url)
2286 head_response = self._request_webpage(
2287 head_req, video_id,
2288 note=False, errnote='Could not send HEAD request to %s' % url,
2289 fatal=False)
2290
2291 if head_response is not False:
2292 # Check for redirect
2293 new_url = head_response.geturl()
2294 if url != new_url:
2295 self.report_following_redirect(new_url)
2296 if force_videoid:
2297 new_url = smuggle_url(
2298 new_url, {'force_videoid': force_videoid})
2299 return self.url_result(new_url)
2300
2301 full_response = None
2302 if head_response is False:
2303 request = sanitized_Request(url)
2304 request.add_header('Accept-Encoding', '*')
2305 full_response = self._request_webpage(request, video_id)
2306 head_response = full_response
2307
2308 info_dict = {
2309 'id': video_id,
2310 'title': self._generic_title(url),
2311 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2312 }
2313
2314 # Check for direct link to a video
2315 content_type = head_response.headers.get('Content-Type', '').lower()
2316 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2317 if m:
2318 format_id = compat_str(m.group('format_id'))
2319 if format_id.endswith('mpegurl'):
2320 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2321 elif format_id == 'f4m':
2322 formats = self._extract_f4m_formats(url, video_id)
2323 else:
2324 formats = [{
2325 'format_id': format_id,
2326 'url': url,
2327 'vcodec': 'none' if m.group('type') == 'audio' else None
2328 }]
2329 info_dict['direct'] = True
2330 self._sort_formats(formats)
2331 info_dict['formats'] = formats
2332 return info_dict
2333
2334 if not self._downloader.params.get('test', False) and not is_intentional:
2335 force = self._downloader.params.get('force_generic_extractor', False)
2336 self._downloader.report_warning(
2337 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2338
2339 if not full_response:
2340 request = sanitized_Request(url)
2341 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2342 # making it impossible to download only chunk of the file (yet we need only 512kB to
2343 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2344 # that will always result in downloading the whole file that is not desirable.
2345 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2346 # to accept raw bytes and being able to download only a chunk.
2347 # It may probably better to solve this by checking Content-Type for application/octet-stream
2348 # after HEAD request finishes, but not sure if we can rely on this.
2349 request.add_header('Accept-Encoding', '*')
2350 full_response = self._request_webpage(request, video_id)
2351
2352 first_bytes = full_response.read(512)
2353
2354 # Is it an M3U playlist?
2355 if first_bytes.startswith(b'#EXTM3U'):
2356 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2357 self._sort_formats(info_dict['formats'])
2358 return info_dict
2359
2360 # Maybe it's a direct link to a video?
2361 # Be careful not to download the whole thing!
2362 if not is_html(first_bytes):
2363 self._downloader.report_warning(
2364 'URL could be a direct video link, returning it as such.')
2365 info_dict.update({
2366 'direct': True,
2367 'url': url,
2368 })
2369 return info_dict
2370
2371 webpage = self._webpage_read_content(
2372 full_response, url, video_id, prefix=first_bytes)
2373
2374 self.report_extraction(video_id)
2375
2376 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2377 try:
2378 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2379 if doc.tag == 'rss':
2380 return self._extract_rss(url, video_id, doc)
2381 elif doc.tag == 'SmoothStreamingMedia':
2382 info_dict['formats'] = self._parse_ism_formats(doc, url)
2383 self._sort_formats(info_dict['formats'])
2384 return info_dict
2385 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2386 smil = self._parse_smil(doc, url, video_id)
2387 self._sort_formats(smil['formats'])
2388 return smil
2389 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2390 return self.playlist_result(
2391 self._parse_xspf(
2392 doc, video_id, xspf_url=url,
2393 xspf_base_url=full_response.geturl()),
2394 video_id)
2395 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2396 info_dict['formats'] = self._parse_mpd_formats(
2397 doc,
2398 mpd_base_url=full_response.geturl().rpartition('/')[0],
2399 mpd_url=url)
2400 self._sort_formats(info_dict['formats'])
2401 return info_dict
2402 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2403 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2404 self._sort_formats(info_dict['formats'])
2405 return info_dict
2406 except compat_xml_parse_error:
2407 pass
2408
2409 # Is it a Camtasia project?
2410 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2411 if camtasia_res is not None:
2412 return camtasia_res
2413
2414 # Sometimes embedded video player is hidden behind percent encoding
2415 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2416 # Unescaping the whole page allows to handle those cases in a generic way
2417 webpage = compat_urllib_parse_unquote(webpage)
2418
2419 # Unescape squarespace embeds to be detected by generic extractor,
2420 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2421 webpage = re.sub(
2422 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2423 lambda x: unescapeHTML(x.group(0)), webpage)
2424
2425 # it's tempting to parse this further, but you would
2426 # have to take into account all the variations like
2427 # Video Title - Site Name
2428 # Site Name | Video Title
2429 # Video Title - Tagline | Site Name
2430 # and so on and so forth; it's just not practical
2431 video_title = self._og_search_title(
2432 webpage, default=None) or self._html_search_regex(
2433 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2434 default='video')
2435
2436 # Try to detect age limit automatically
2437 age_limit = self._rta_search(webpage)
2438 # And then there are the jokers who advertise that they use RTA,
2439 # but actually don't.
2440 AGE_LIMIT_MARKERS = [
2441 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2442 ]
2443 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2444 age_limit = 18
2445
2446 # video uploader is domain name
2447 video_uploader = self._search_regex(
2448 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2449
2450 video_description = self._og_search_description(webpage, default=None)
2451 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2452
2453 info_dict.update({
2454 'title': video_title,
2455 'description': video_description,
2456 'thumbnail': video_thumbnail,
2457 'age_limit': age_limit,
2458 })
2459
2460 # Look for Brightcove Legacy Studio embeds
2461 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2462 if bc_urls:
2463 entries = [{
2464 '_type': 'url',
2465 'url': smuggle_url(bc_url, {'Referer': url}),
2466 'ie_key': 'BrightcoveLegacy'
2467 } for bc_url in bc_urls]
2468
2469 return {
2470 '_type': 'playlist',
2471 'title': video_title,
2472 'id': video_id,
2473 'entries': entries,
2474 }
2475
2476 # Look for Brightcove New Studio embeds
2477 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2478 if bc_urls:
2479 return self.playlist_from_matches(
2480 bc_urls, video_id, video_title,
2481 getter=lambda x: smuggle_url(x, {'referrer': url}),
2482 ie='BrightcoveNew')
2483
2484 # Look for Nexx embeds
2485 nexx_urls = NexxIE._extract_urls(webpage)
2486 if nexx_urls:
2487 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2488
2489 # Look for Nexx iFrame embeds
2490 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2491 if nexx_embed_urls:
2492 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2493
2494 # Look for ThePlatform embeds
2495 tp_urls = ThePlatformIE._extract_urls(webpage)
2496 if tp_urls:
2497 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2498
2499 # Look for embedded rtl.nl player
2500 matches = re.findall(
2501 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2502 webpage)
2503 if matches:
2504 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2505
2506 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2507 if vimeo_urls:
2508 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2509
2510 vid_me_embed_url = self._search_regex(
2511 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2512 webpage, 'vid.me embed', default=None)
2513 if vid_me_embed_url is not None:
2514 return self.url_result(vid_me_embed_url, 'Vidme')
2515
2516 # Look for YouTube embeds
2517 youtube_urls = YoutubeIE._extract_urls(webpage)
2518 if youtube_urls:
2519 return self.playlist_from_matches(
2520 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2521
2522 matches = DailymotionIE._extract_urls(webpage)
2523 if matches:
2524 return self.playlist_from_matches(matches, video_id, video_title)
2525
2526 # Look for embedded Dailymotion playlist player (#3822)
2527 m = re.search(
2528 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2529 if m:
2530 playlists = re.findall(
2531 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2532 if playlists:
2533 return self.playlist_from_matches(
2534 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2535
2536 # Look for DailyMail embeds
2537 dailymail_urls = DailyMailIE._extract_urls(webpage)
2538 if dailymail_urls:
2539 return self.playlist_from_matches(
2540 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2541
2542 # Look for Teachable embeds, must be before Wistia
2543 teachable_url = TeachableIE._extract_url(webpage, url)
2544 if teachable_url:
2545 return self.url_result(teachable_url)
2546
2547 # Look for embedded Wistia player
2548 wistia_urls = WistiaIE._extract_urls(webpage)
2549 if wistia_urls:
2550 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2551 for entry in playlist['entries']:
2552 entry.update({
2553 '_type': 'url_transparent',
2554 'uploader': video_uploader,
2555 })
2556 return playlist
2557
2558 # Look for SVT player
2559 svt_url = SVTIE._extract_url(webpage)
2560 if svt_url:
2561 return self.url_result(svt_url, 'SVT')
2562
2563 # Look for Bandcamp pages with custom domain
2564 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2565 if mobj is not None:
2566 burl = unescapeHTML(mobj.group(1))
2567 # Don't set the extractor because it can be a track url or an album
2568 return self.url_result(burl)
2569
2570 # Look for embedded Vevo player
2571 mobj = re.search(
2572 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2573 if mobj is not None:
2574 return self.url_result(mobj.group('url'))
2575
2576 # Look for embedded Viddler player
2577 mobj = re.search(
2578 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2579 webpage)
2580 if mobj is not None:
2581 return self.url_result(mobj.group('url'))
2582
2583 # Look for NYTimes player
2584 mobj = re.search(
2585 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2586 webpage)
2587 if mobj is not None:
2588 return self.url_result(mobj.group('url'))
2589
2590 # Look for Libsyn player
2591 mobj = re.search(
2592 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2593 if mobj is not None:
2594 return self.url_result(mobj.group('url'))
2595
2596 # Look for Ooyala videos
2597 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2598 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2599 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2600 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2601 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2602 if mobj is not None:
2603 embed_token = self._search_regex(
2604 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2605 webpage, 'ooyala embed token', default=None)
2606 return OoyalaIE._build_url_result(smuggle_url(
2607 mobj.group('ec'), {
2608 'domain': url,
2609 'embed_token': embed_token,
2610 }))
2611
2612 # Look for multiple Ooyala embeds on SBN network websites
2613 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2614 if mobj is not None:
2615 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2616 if embeds:
2617 return self.playlist_from_matches(
2618 embeds, video_id, video_title,
2619 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2620
2621 # Look for Aparat videos
2622 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2623 if mobj is not None:
2624 return self.url_result(mobj.group(1), 'Aparat')
2625
2626 # Look for MPORA videos
2627 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2628 if mobj is not None:
2629 return self.url_result(mobj.group(1), 'Mpora')
2630
2631 # Look for embedded Facebook player
2632 facebook_urls = FacebookIE._extract_urls(webpage)
2633 if facebook_urls:
2634 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2635
2636 # Look for embedded VK player
2637 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2638 if mobj is not None:
2639 return self.url_result(mobj.group('url'), 'VK')
2640
2641 # Look for embedded Odnoklassniki player
2642 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2643 if odnoklassniki_url:
2644 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2645
2646 # Look for embedded ivi player
2647 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'), 'Ivi')
2650
2651 # Look for embedded Huffington Post player
2652 mobj = re.search(
2653 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2654 if mobj is not None:
2655 return self.url_result(mobj.group('url'), 'HuffPost')
2656
2657 # Look for embed.ly
2658 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2659 if mobj is not None:
2660 return self.url_result(mobj.group('url'))
2661 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2662 if mobj is not None:
2663 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2664
2665 # Look for funnyordie embed
2666 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2667 if matches:
2668 return self.playlist_from_matches(
2669 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2670
2671 # Look for BBC iPlayer embed
2672 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2673 if matches:
2674 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2675
2676 # Look for embedded RUTV player
2677 rutv_url = RUTVIE._extract_url(webpage)
2678 if rutv_url:
2679 return self.url_result(rutv_url, 'RUTV')
2680
2681 # Look for embedded TVC player
2682 tvc_url = TVCIE._extract_url(webpage)
2683 if tvc_url:
2684 return self.url_result(tvc_url, 'TVC')
2685
2686 # Look for embedded SportBox player
2687 sportbox_urls = SportBoxIE._extract_urls(webpage)
2688 if sportbox_urls:
2689 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2690
2691 # Look for embedded XHamster player
2692 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2693 if xhamster_urls:
2694 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2695
2696 # Look for embedded TNAFlixNetwork player
2697 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2698 if tnaflix_urls:
2699 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2700
2701 # Look for embedded PornHub player
2702 pornhub_urls = PornHubIE._extract_urls(webpage)
2703 if pornhub_urls:
2704 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2705
2706 # Look for embedded DrTuber player
2707 drtuber_urls = DrTuberIE._extract_urls(webpage)
2708 if drtuber_urls:
2709 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2710
2711 # Look for embedded RedTube player
2712 redtube_urls = RedTubeIE._extract_urls(webpage)
2713 if redtube_urls:
2714 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2715
2716 # Look for embedded Tube8 player
2717 tube8_urls = Tube8IE._extract_urls(webpage)
2718 if tube8_urls:
2719 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2720
2721 # Look for embedded Mofosex player
2722 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2723 if mofosex_urls:
2724 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2725
2726 # Look for embedded Spankwire player
2727 spankwire_urls = SpankwireIE._extract_urls(webpage)
2728 if spankwire_urls:
2729 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2730
2731 # Look for embedded YouPorn player
2732 youporn_urls = YouPornIE._extract_urls(webpage)
2733 if youporn_urls:
2734 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2735
2736 # Look for embedded Tvigle player
2737 mobj = re.search(
2738 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2739 if mobj is not None:
2740 return self.url_result(mobj.group('url'), 'Tvigle')
2741
2742 # Look for embedded TED player
2743 mobj = re.search(
2744 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2745 if mobj is not None:
2746 return self.url_result(mobj.group('url'), 'TED')
2747
2748 # Look for embedded Ustream videos
2749 ustream_url = UstreamIE._extract_url(webpage)
2750 if ustream_url:
2751 return self.url_result(ustream_url, UstreamIE.ie_key())
2752
2753 # Look for embedded arte.tv player
2754 mobj = re.search(
2755 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2756 webpage)
2757 if mobj is not None:
2758 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2759
2760 # Look for embedded francetv player
2761 mobj = re.search(
2762 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2763 webpage)
2764 if mobj is not None:
2765 return self.url_result(mobj.group('url'))
2766
2767 # Look for embedded smotri.com player
2768 smotri_url = SmotriIE._extract_url(webpage)
2769 if smotri_url:
2770 return self.url_result(smotri_url, 'Smotri')
2771
2772 # Look for embedded Myvi.ru player
2773 myvi_url = MyviIE._extract_url(webpage)
2774 if myvi_url:
2775 return self.url_result(myvi_url)
2776
2777 # Look for embedded soundcloud player
2778 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2779 if soundcloud_urls:
2780 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2781
2782 # Look for tunein player
2783 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2784 if tunein_urls:
2785 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2786
2787 # Look for embedded mtvservices player
2788 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2789 if mtvservices_url:
2790 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2791
2792 # Look for embedded yahoo player
2793 mobj = re.search(
2794 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2795 webpage)
2796 if mobj is not None:
2797 return self.url_result(mobj.group('url'), 'Yahoo')
2798
2799 # Look for embedded sbs.com.au player
2800 mobj = re.search(
2801 r'''(?x)
2802 (?:
2803 <meta\s+property="og:video"\s+content=|
2804 <iframe[^>]+?src=
2805 )
2806 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2807 webpage)
2808 if mobj is not None:
2809 return self.url_result(mobj.group('url'), 'SBS')
2810
2811 # Look for embedded Cinchcast player
2812 mobj = re.search(
2813 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2814 webpage)
2815 if mobj is not None:
2816 return self.url_result(mobj.group('url'), 'Cinchcast')
2817
2818 mobj = re.search(
2819 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2820 webpage)
2821 if not mobj:
2822 mobj = re.search(
2823 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2824 webpage)
2825 if mobj is not None:
2826 return self.url_result(mobj.group('url'), 'MLB')
2827
2828 mobj = re.search(
2829 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2830 webpage)
2831 if mobj is not None:
2832 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2833
2834 mobj = re.search(
2835 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2836 webpage)
2837 if mobj is not None:
2838 return self.url_result(mobj.group('url'), 'Livestream')
2839
2840 # Look for Zapiks embed
2841 mobj = re.search(
2842 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2843 if mobj is not None:
2844 return self.url_result(mobj.group('url'), 'Zapiks')
2845
2846 # Look for Kaltura embeds
2847 kaltura_url = KalturaIE._extract_url(webpage)
2848 if kaltura_url:
2849 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2850
2851 # Look for EaglePlatform embeds
2852 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2853 if eagleplatform_url:
2854 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2855
2856 # Look for ClipYou (uses EaglePlatform) embeds
2857 mobj = re.search(
2858 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2859 if mobj is not None:
2860 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2861
2862 # Look for Pladform embeds
2863 pladform_url = PladformIE._extract_url(webpage)
2864 if pladform_url:
2865 return self.url_result(pladform_url)
2866
2867 # Look for Videomore embeds
2868 videomore_url = VideomoreIE._extract_url(webpage)
2869 if videomore_url:
2870 return self.url_result(videomore_url)
2871
2872 # Look for Webcaster embeds
2873 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2874 if webcaster_url:
2875 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2876
2877 # Look for Playwire embeds
2878 mobj = re.search(
2879 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2880 if mobj is not None:
2881 return self.url_result(mobj.group('url'))
2882
2883 # Look for 5min embeds
2884 mobj = re.search(
2885 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2886 if mobj is not None:
2887 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2888
2889 # Look for Crooks and Liars embeds
2890 mobj = re.search(
2891 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2892 if mobj is not None:
2893 return self.url_result(mobj.group('url'))
2894
2895 # Look for NBC Sports VPlayer embeds
2896 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2897 if nbc_sports_url:
2898 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2899
2900 # Look for NBC News embeds
2901 nbc_news_embed_url = re.search(
2902 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2903 if nbc_news_embed_url:
2904 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2905
2906 # Look for Google Drive embeds
2907 google_drive_url = GoogleDriveIE._extract_url(webpage)
2908 if google_drive_url:
2909 return self.url_result(google_drive_url, 'GoogleDrive')
2910
2911 # Look for UDN embeds
2912 mobj = re.search(
2913 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2914 if mobj is not None:
2915 return self.url_result(
2916 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2917
2918 # Look for Senate ISVP iframe
2919 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2920 if senate_isvp_url:
2921 return self.url_result(senate_isvp_url, 'SenateISVP')
2922
2923 # Look for Kinja embeds
2924 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2925 if kinja_embed_urls:
2926 return self.playlist_from_matches(
2927 kinja_embed_urls, video_id, video_title)
2928
2929 # Look for OnionStudios embeds
2930 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2931 if onionstudios_url:
2932 return self.url_result(onionstudios_url)
2933
2934 # Look for ViewLift embeds
2935 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2936 if viewlift_url:
2937 return self.url_result(viewlift_url)
2938
2939 # Look for JWPlatform embeds
2940 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2941 if jwplatform_urls:
2942 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2943
2944 # Look for Digiteka embeds
2945 digiteka_url = DigitekaIE._extract_url(webpage)
2946 if digiteka_url:
2947 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2948
2949 # Look for Arkena embeds
2950 arkena_url = ArkenaIE._extract_url(webpage)
2951 if arkena_url:
2952 return self.url_result(arkena_url, ArkenaIE.ie_key())
2953
2954 # Look for Piksel embeds
2955 piksel_url = PikselIE._extract_url(webpage)
2956 if piksel_url:
2957 return self.url_result(piksel_url, PikselIE.ie_key())
2958
2959 # Look for Limelight embeds
2960 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2961 if limelight_urls:
2962 return self.playlist_result(
2963 limelight_urls, video_id, video_title, video_description)
2964
2965 # Look for Anvato embeds
2966 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2967 if anvato_urls:
2968 return self.playlist_result(
2969 anvato_urls, video_id, video_title, video_description)
2970
2971 # Look for AdobeTVVideo embeds
2972 mobj = re.search(
2973 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2974 webpage)
2975 if mobj is not None:
2976 return self.url_result(
2977 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2978 'AdobeTVVideo')
2979
2980 # Look for Vine embeds
2981 mobj = re.search(
2982 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2983 webpage)
2984 if mobj is not None:
2985 return self.url_result(
2986 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2987
2988 # Look for VODPlatform embeds
2989 mobj = re.search(
2990 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
2991 webpage)
2992 if mobj is not None:
2993 return self.url_result(
2994 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2995
2996 # Look for Mangomolo embeds
2997 mobj = re.search(
2998 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
2999 (?:
3000 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3001 player\.mangomolo\.com/v1
3002 )/
3003 (?:
3004 video\?.*?\bid=(?P<video_id>\d+)|
3005 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3006 ).+?)\1''', webpage)
3007 if mobj is not None:
3008 info = {
3009 '_type': 'url_transparent',
3010 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3011 'title': video_title,
3012 'description': video_description,
3013 'thumbnail': video_thumbnail,
3014 'uploader': video_uploader,
3015 }
3016 video_id = mobj.group('video_id')
3017 if video_id:
3018 info.update({
3019 'ie_key': 'MangomoloVideo',
3020 'id': video_id,
3021 })
3022 else:
3023 info.update({
3024 'ie_key': 'MangomoloLive',
3025 'id': mobj.group('channel_id'),
3026 })
3027 return info
3028
3029 # Look for Instagram embeds
3030 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3031 if instagram_embed_url is not None:
3032 return self.url_result(
3033 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3034
3035 # Look for LiveLeak embeds
3036 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3037 if liveleak_urls:
3038 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3039
3040 # Look for 3Q SDN embeds
3041 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3042 if threeqsdn_url:
3043 return {
3044 '_type': 'url_transparent',
3045 'ie_key': ThreeQSDNIE.ie_key(),
3046 'url': self._proto_relative_url(threeqsdn_url),
3047 'title': video_title,
3048 'description': video_description,
3049 'thumbnail': video_thumbnail,
3050 'uploader': video_uploader,
3051 }
3052
3053 # Look for VBOX7 embeds
3054 vbox7_url = Vbox7IE._extract_url(webpage)
3055 if vbox7_url:
3056 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3057
3058 # Look for DBTV embeds
3059 dbtv_urls = DBTVIE._extract_urls(webpage)
3060 if dbtv_urls:
3061 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3062
3063 # Look for Videa embeds
3064 videa_urls = VideaIE._extract_urls(webpage)
3065 if videa_urls:
3066 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3067
3068 # Look for 20 minuten embeds
3069 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3070 if twentymin_urls:
3071 return self.playlist_from_matches(
3072 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3073
3074 # Look for VideoPress embeds
3075 videopress_urls = VideoPressIE._extract_urls(webpage)
3076 if videopress_urls:
3077 return self.playlist_from_matches(
3078 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3079
3080 # Look for Rutube embeds
3081 rutube_urls = RutubeIE._extract_urls(webpage)
3082 if rutube_urls:
3083 return self.playlist_from_matches(
3084 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3085
3086 # Look for WashingtonPost embeds
3087 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3088 if wapo_urls:
3089 return self.playlist_from_matches(
3090 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3091
3092 # Look for Mediaset embeds
3093 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3094 if mediaset_urls:
3095 return self.playlist_from_matches(
3096 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3097
3098 # Look for JOJ.sk embeds
3099 joj_urls = JojIE._extract_urls(webpage)
3100 if joj_urls:
3101 return self.playlist_from_matches(
3102 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3103
3104 # Look for megaphone.fm embeds
3105 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3106 if mpfn_urls:
3107 return self.playlist_from_matches(
3108 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3109
3110 # Look for vzaar embeds
3111 vzaar_urls = VzaarIE._extract_urls(webpage)
3112 if vzaar_urls:
3113 return self.playlist_from_matches(
3114 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3115
3116 channel9_urls = Channel9IE._extract_urls(webpage)
3117 if channel9_urls:
3118 return self.playlist_from_matches(
3119 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3120
3121 vshare_urls = VShareIE._extract_urls(webpage)
3122 if vshare_urls:
3123 return self.playlist_from_matches(
3124 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3125
3126 # Look for Mediasite embeds
3127 mediasite_urls = MediasiteIE._extract_urls(webpage)
3128 if mediasite_urls:
3129 entries = [
3130 self.url_result(smuggle_url(
3131 compat_urlparse.urljoin(url, mediasite_url),
3132 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3133 for mediasite_url in mediasite_urls]
3134 return self.playlist_result(entries, video_id, video_title)
3135
3136 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3137 if springboardplatform_urls:
3138 return self.playlist_from_matches(
3139 springboardplatform_urls, video_id, video_title,
3140 ie=SpringboardPlatformIE.ie_key())
3141
3142 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3143 if yapfiles_urls:
3144 return self.playlist_from_matches(
3145 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3146
3147 vice_urls = ViceIE._extract_urls(webpage)
3148 if vice_urls:
3149 return self.playlist_from_matches(
3150 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3151
3152 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3153 if xfileshare_urls:
3154 return self.playlist_from_matches(
3155 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3156
3157 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3158 if cloudflarestream_urls:
3159 return self.playlist_from_matches(
3160 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3161
3162 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3163 if peertube_urls:
3164 return self.playlist_from_matches(
3165 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3166
3167 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3168 if indavideo_urls:
3169 return self.playlist_from_matches(
3170 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3171
3172 apa_urls = APAIE._extract_urls(webpage)
3173 if apa_urls:
3174 return self.playlist_from_matches(
3175 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3176
3177 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3178 if foxnews_urls:
3179 return self.playlist_from_matches(
3180 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3181
3182 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3183 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3184 webpage)]
3185 if sharevideos_urls:
3186 return self.playlist_from_matches(
3187 sharevideos_urls, video_id, video_title)
3188
3189 viqeo_urls = ViqeoIE._extract_urls(webpage)
3190 if viqeo_urls:
3191 return self.playlist_from_matches(
3192 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3193
3194 expressen_urls = ExpressenIE._extract_urls(webpage)
3195 if expressen_urls:
3196 return self.playlist_from_matches(
3197 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3198
3199 zype_urls = ZypeIE._extract_urls(webpage)
3200 if zype_urls:
3201 return self.playlist_from_matches(
3202 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3203
3204 # Look for HTML5 media
3205 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3206 if entries:
3207 if len(entries) == 1:
3208 entries[0].update({
3209 'id': video_id,
3210 'title': video_title,
3211 })
3212 else:
3213 for num, entry in enumerate(entries, start=1):
3214 entry.update({
3215 'id': '%s-%s' % (video_id, num),
3216 'title': '%s (%d)' % (video_title, num),
3217 })
3218 for entry in entries:
3219 self._sort_formats(entry['formats'])
3220 return self.playlist_result(entries, video_id, video_title)
3221
3222 jwplayer_data = self._find_jwplayer_data(
3223 webpage, video_id, transform_source=js_to_json)
3224 if jwplayer_data:
3225 try:
3226 info = self._parse_jwplayer_data(
3227 jwplayer_data, video_id, require_title=False, base_url=url)
3228 return merge_dicts(info, info_dict)
3229 except ExtractorError:
3230 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3231 pass
3232
3233 # Video.js embed
3234 mobj = re.search(
3235 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3236 webpage)
3237 if mobj is not None:
3238 sources = self._parse_json(
3239 mobj.group(1), video_id, transform_source=js_to_json,
3240 fatal=False) or []
3241 if not isinstance(sources, list):
3242 sources = [sources]
3243 formats = []
3244 for source in sources:
3245 src = source.get('src')
3246 if not src or not isinstance(src, compat_str):
3247 continue
3248 src = compat_urlparse.urljoin(url, src)
3249 src_type = source.get('type')
3250 if isinstance(src_type, compat_str):
3251 src_type = src_type.lower()
3252 ext = determine_ext(src).lower()
3253 if src_type == 'video/youtube':
3254 return self.url_result(src, YoutubeIE.ie_key())
3255 if src_type == 'application/dash+xml' or ext == 'mpd':
3256 formats.extend(self._extract_mpd_formats(
3257 src, video_id, mpd_id='dash', fatal=False))
3258 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3259 formats.extend(self._extract_m3u8_formats(
3260 src, video_id, 'mp4', entry_protocol='m3u8_native',
3261 m3u8_id='hls', fatal=False))
3262 else:
3263 formats.append({
3264 'url': src,
3265 'ext': (mimetype2ext(src_type)
3266 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3267 })
3268 if formats:
3269 self._sort_formats(formats)
3270 info_dict['formats'] = formats
3271 return info_dict
3272
3273 # Looking for http://schema.org/VideoObject
3274 json_ld = self._search_json_ld(
3275 webpage, video_id, default={}, expected_type='VideoObject')
3276 if json_ld.get('url'):
3277 return merge_dicts(json_ld, info_dict)
3278
3279 def check_video(vurl):
3280 if YoutubeIE.suitable(vurl):
3281 return True
3282 if RtmpIE.suitable(vurl):
3283 return True
3284 vpath = compat_urlparse.urlparse(vurl).path
3285 vext = determine_ext(vpath)
3286 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3287
3288 def filter_video(urls):
3289 return list(filter(check_video, urls))
3290
3291 # Start with something easy: JW Player in SWFObject
3292 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3293 if not found:
3294 # Look for gorilla-vid style embedding
3295 found = filter_video(re.findall(r'''(?sx)
3296 (?:
3297 jw_plugins|
3298 JWPlayerOptions|
3299 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3300 )
3301 .*?
3302 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3303 if not found:
3304 # Broaden the search a little bit
3305 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3306 if not found:
3307 # Broaden the findall a little bit: JWPlayer JS loader
3308 found = filter_video(re.findall(
3309 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3310 if not found:
3311 # Flow player
3312 found = filter_video(re.findall(r'''(?xs)
3313 flowplayer\("[^"]+",\s*
3314 \{[^}]+?\}\s*,
3315 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3316 ["']?url["']?\s*:\s*["']([^"']+)["']
3317 ''', webpage))
3318 if not found:
3319 # Cinerama player
3320 found = re.findall(
3321 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3322 if not found:
3323 # Try to find twitter cards info
3324 # twitter:player:stream should be checked before twitter:player since
3325 # it is expected to contain a raw stream (see
3326 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3327 found = filter_video(re.findall(
3328 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3329 if not found:
3330 # We look for Open Graph info:
3331 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3332 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3333 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3334 if m_video_type is not None:
3335 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3336 if not found:
3337 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3338 found = re.search(
3339 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3340 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3341 webpage)
3342 if not found:
3343 # Look also in Refresh HTTP header
3344 refresh_header = head_response.headers.get('Refresh')
3345 if refresh_header:
3346 # In python 2 response HTTP headers are bytestrings
3347 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3348 refresh_header = refresh_header.decode('iso-8859-1')
3349 found = re.search(REDIRECT_REGEX, refresh_header)
3350 if found:
3351 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3352 if new_url != url:
3353 self.report_following_redirect(new_url)
3354 return {
3355 '_type': 'url',
3356 'url': new_url,
3357 }
3358 else:
3359 found = None
3360
3361 if not found:
3362 # twitter:player is a https URL to iframe player that may or may not
3363 # be supported by youtube-dl thus this is checked the very last (see
3364 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3365 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3366 if embed_url and embed_url != url:
3367 return self.url_result(embed_url)
3368
3369 if not found:
3370 raise UnsupportedError(url)
3371
3372 entries = []
3373 for video_url in orderedSet(found):
3374 video_url = unescapeHTML(video_url)
3375 video_url = video_url.replace('\\/', '/')
3376 video_url = compat_urlparse.urljoin(url, video_url)
3377 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3378
3379 # Sometimes, jwplayer extraction will result in a YouTube URL
3380 if YoutubeIE.suitable(video_url):
3381 entries.append(self.url_result(video_url, 'Youtube'))
3382 continue
3383
3384 # here's a fun little line of code for you:
3385 video_id = os.path.splitext(video_id)[0]
3386
3387 entry_info_dict = {
3388 'id': video_id,
3389 'uploader': video_uploader,
3390 'title': video_title,
3391 'age_limit': age_limit,
3392 }
3393
3394 if RtmpIE.suitable(video_url):
3395 entry_info_dict.update({
3396 '_type': 'url_transparent',
3397 'ie_key': RtmpIE.ie_key(),
3398 'url': video_url,
3399 })
3400 entries.append(entry_info_dict)
3401 continue
3402
3403 ext = determine_ext(video_url)
3404 if ext == 'smil':
3405 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3406 elif ext == 'xspf':
3407 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3408 elif ext == 'm3u8':
3409 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3410 elif ext == 'mpd':
3411 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3412 elif ext == 'f4m':
3413 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3414 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3415 # Just matching .ism/manifest is not enough to be reliably sure
3416 # whether it's actually an ISM manifest or some other streaming
3417 # manifest since there are various streaming URL formats
3418 # possible (see [1]) as well as some other shenanigans like
3419 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3420 # so on.
3421 # Thus the most reasonable way to solve this is to delegate
3422 # to generic extractor in order to look into the contents of
3423 # the manifest itself.
3424 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3425 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3426 entry_info_dict = self.url_result(
3427 smuggle_url(video_url, {'to_generic': True}),
3428 GenericIE.ie_key())
3429 else:
3430 entry_info_dict['url'] = video_url
3431
3432 if entry_info_dict.get('formats'):
3433 self._sort_formats(entry_info_dict['formats'])
3434
3435 entries.append(entry_info_dict)
3436
3437 if len(entries) == 1:
3438 return entries[0]
3439 else:
3440 for num, e in enumerate(entries, start=1):
3441 # 'url' results don't have a title
3442 if e.get('title') is not None:
3443 e['title'] = '%s (%d)' % (e['title'], num)
3444 return {
3445 '_type': 'playlist',
3446 'entries': entries,
3447 }