]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Start new release and annotate with bugs being fixed.
[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 SportBoxEmbedIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
111 from .peertube import PeerTubeIE
112 from .indavideo import IndavideoEmbedIE
113 from .apa import APAIE
114 from .foxnews import FoxNewsIE
115 from .viqeo import ViqeoIE
116 from .expressen import ExpressenIE
117
118
119 class GenericIE(InfoExtractor):
120 IE_DESC = 'Generic downloader that works on some sites'
121 _VALID_URL = r'.*'
122 IE_NAME = 'generic'
123 _TESTS = [
124 # Direct link to a video
125 {
126 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
127 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
128 'info_dict': {
129 'id': 'trailer',
130 'ext': 'mp4',
131 'title': 'trailer',
132 'upload_date': '20100513',
133 }
134 },
135 # Direct link to media delivered compressed (until Accept-Encoding is *)
136 {
137 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
138 'md5': '128c42e68b13950268b648275386fc74',
139 'info_dict': {
140 'id': 'FictionJunction-Parallel_Hearts',
141 'ext': 'flac',
142 'title': 'FictionJunction-Parallel_Hearts',
143 'upload_date': '20140522',
144 },
145 'expected_warnings': [
146 'URL could be a direct video link, returning it as such.'
147 ],
148 'skip': 'URL invalid',
149 },
150 # Direct download with broken HEAD
151 {
152 'url': 'http://ai-radio.org:8000/radio.opus',
153 'info_dict': {
154 'id': 'radio',
155 'ext': 'opus',
156 'title': 'radio',
157 },
158 'params': {
159 'skip_download': True, # infinite live stream
160 },
161 'expected_warnings': [
162 r'501.*Not Implemented',
163 r'400.*Bad Request',
164 ],
165 },
166 # Direct link with incorrect MIME type
167 {
168 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
169 'md5': '4ccbebe5f36706d85221f204d7eb5913',
170 'info_dict': {
171 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
172 'id': '5_Lennart_Poettering_-_Systemd',
173 'ext': 'webm',
174 'title': '5_Lennart_Poettering_-_Systemd',
175 'upload_date': '20141120',
176 },
177 'expected_warnings': [
178 'URL could be a direct video link, returning it as such.'
179 ]
180 },
181 # RSS feed
182 {
183 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
184 'info_dict': {
185 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
186 'title': 'Zero Punctuation',
187 'description': 're:.*groundbreaking video review series.*'
188 },
189 'playlist_mincount': 11,
190 },
191 # RSS feed with enclosure
192 {
193 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
194 'info_dict': {
195 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
196 'ext': 'm4v',
197 'upload_date': '20150228',
198 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
199 }
200 },
201 # RSS feed with enclosures and unsupported link URLs
202 {
203 'url': 'http://www.hellointernet.fm/podcast?format=rss',
204 'info_dict': {
205 'id': 'http://www.hellointernet.fm/podcast?format=rss',
206 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
207 'title': 'Hello Internet',
208 },
209 'playlist_mincount': 100,
210 },
211 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
212 {
213 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
214 'info_dict': {
215 'id': 'smil',
216 'ext': 'mp4',
217 'title': 'Automatics, robotics and biocybernetics',
218 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
219 'upload_date': '20130627',
220 'formats': 'mincount:16',
221 'subtitles': 'mincount:1',
222 },
223 'params': {
224 'force_generic_extractor': True,
225 'skip_download': True,
226 },
227 },
228 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
229 {
230 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
231 'info_dict': {
232 'id': 'hds',
233 'ext': 'flv',
234 'title': 'hds',
235 'formats': 'mincount:1',
236 },
237 'params': {
238 'skip_download': True,
239 },
240 },
241 # SMIL from https://www.restudy.dk/video/play/id/1637
242 {
243 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
244 'info_dict': {
245 'id': 'video_1637',
246 'ext': 'flv',
247 'title': 'video_1637',
248 'formats': 'mincount:3',
249 },
250 'params': {
251 'skip_download': True,
252 },
253 },
254 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
255 {
256 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
257 'info_dict': {
258 'id': 'smil-service',
259 'ext': 'flv',
260 'title': 'smil-service',
261 'formats': 'mincount:1',
262 },
263 'params': {
264 'skip_download': True,
265 },
266 },
267 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
268 {
269 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
270 'info_dict': {
271 'id': '4719370',
272 'ext': 'mp4',
273 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
274 'formats': 'mincount:3',
275 },
276 'params': {
277 'skip_download': True,
278 },
279 },
280 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
281 {
282 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
283 'info_dict': {
284 'id': 'mZlp2ctYIUEB',
285 'ext': 'mp4',
286 'title': 'Tikibad ontruimd wegens brand',
287 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
288 'thumbnail': r're:^https?://.*\.jpg$',
289 'duration': 33,
290 },
291 'params': {
292 'skip_download': True,
293 },
294 },
295 # MPD from http://dash-mse-test.appspot.com/media.html
296 {
297 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
298 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
299 'info_dict': {
300 'id': 'car-20120827-manifest',
301 'ext': 'mp4',
302 'title': 'car-20120827-manifest',
303 'formats': 'mincount:9',
304 'upload_date': '20130904',
305 },
306 'params': {
307 'format': 'bestvideo',
308 },
309 },
310 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
311 {
312 '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',
313 'info_dict': {
314 'id': 'content',
315 'ext': 'mp4',
316 'title': 'content',
317 'formats': 'mincount:8',
318 },
319 'params': {
320 # m3u8 downloads
321 'skip_download': True,
322 },
323 'skip': 'video gone',
324 },
325 # m3u8 served with Content-Type: text/plain
326 {
327 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
328 'info_dict': {
329 'id': 'index',
330 'ext': 'mp4',
331 'title': 'index',
332 'upload_date': '20140720',
333 'formats': 'mincount:11',
334 },
335 'params': {
336 # m3u8 downloads
337 'skip_download': True,
338 },
339 'skip': 'video gone',
340 },
341 # google redirect
342 {
343 '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',
344 'info_dict': {
345 'id': 'cmQHVoWB5FY',
346 'ext': 'mp4',
347 'upload_date': '20130224',
348 'uploader_id': 'TheVerge',
349 'description': r're:^Chris Ziegler takes a look at the\.*',
350 'uploader': 'The Verge',
351 'title': 'First Firefox OS phones side-by-side',
352 },
353 'params': {
354 'skip_download': False,
355 }
356 },
357 {
358 # redirect in Refresh HTTP header
359 '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',
360 'info_dict': {
361 'id': 'pO8h3EaFRdo',
362 'ext': 'mp4',
363 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
364 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
365 'upload_date': '20150917',
366 'uploader_id': 'brtvofficial',
367 'uploader': 'Boiler Room',
368 },
369 'params': {
370 'skip_download': False,
371 },
372 },
373 {
374 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
375 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
376 'info_dict': {
377 'id': '13601338388002',
378 'ext': 'mp4',
379 'uploader': 'www.hodiho.fr',
380 'title': 'R\u00e9gis plante sa Jeep',
381 }
382 },
383 # bandcamp page with custom domain
384 {
385 'add_ie': ['Bandcamp'],
386 'url': 'http://bronyrock.com/track/the-pony-mash',
387 'info_dict': {
388 'id': '3235767654',
389 'ext': 'mp3',
390 'title': 'The Pony Mash',
391 'uploader': 'M_Pallante',
392 },
393 'skip': 'There is a limit of 200 free downloads / month for the test song',
394 },
395 {
396 # embedded brightcove video
397 # it also tests brightcove videos that need to set the 'Referer'
398 # in the http requests
399 'add_ie': ['BrightcoveLegacy'],
400 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
401 'info_dict': {
402 'id': '2765128793001',
403 'ext': 'mp4',
404 'title': 'Le cours de bourse : lā€™analyse technique',
405 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
406 'uploader': 'BFM BUSINESS',
407 },
408 'params': {
409 'skip_download': True,
410 },
411 },
412 {
413 # embedded with itemprop embedURL and video id spelled as `idVideo`
414 'add_id': ['BrightcoveLegacy'],
415 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
416 'info_dict': {
417 'id': '5255628253001',
418 'ext': 'mp4',
419 'title': 'md5:37c519b1128915607601e75a87995fc0',
420 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
421 'uploader': 'BFM BUSINESS',
422 'uploader_id': '876450612001',
423 'timestamp': 1482255315,
424 'upload_date': '20161220',
425 },
426 'params': {
427 'skip_download': True,
428 },
429 },
430 {
431 # https://github.com/rg3/youtube-dl/issues/2253
432 'url': 'http://bcove.me/i6nfkrc3',
433 'md5': '0ba9446db037002366bab3b3eb30c88c',
434 'info_dict': {
435 'id': '3101154703001',
436 'ext': 'mp4',
437 'title': 'Still no power',
438 'uploader': 'thestar.com',
439 '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.',
440 },
441 'add_ie': ['BrightcoveLegacy'],
442 'skip': 'video gone',
443 },
444 {
445 'url': 'http://www.championat.com/video/football/v/87/87499.html',
446 'md5': 'fb973ecf6e4a78a67453647444222983',
447 'info_dict': {
448 'id': '3414141473001',
449 'ext': 'mp4',
450 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
451 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
452 'uploader': 'Championat',
453 },
454 },
455 {
456 # https://github.com/rg3/youtube-dl/issues/3541
457 'add_ie': ['BrightcoveLegacy'],
458 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
459 'info_dict': {
460 'id': '3866516442001',
461 'ext': 'mp4',
462 'title': 'Leer mij vrouwen kennen: Aflevering 1',
463 'description': 'Leer mij vrouwen kennen: Aflevering 1',
464 'uploader': 'SBS Broadcasting',
465 },
466 'skip': 'Restricted to Netherlands',
467 'params': {
468 'skip_download': True, # m3u8 download
469 },
470 },
471 {
472 # Brightcove video in <iframe>
473 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
474 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
475 'info_dict': {
476 'id': '5360463607001',
477 'ext': 'mp4',
478 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
479 '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€‚',
480 'uploader': 'United Nations',
481 'uploader_id': '1362235914001',
482 'timestamp': 1489593889,
483 'upload_date': '20170315',
484 },
485 'add_ie': ['BrightcoveLegacy'],
486 },
487 {
488 # Brightcove with alternative playerID key
489 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
490 'info_dict': {
491 'id': 'nmeth.2062_SV1',
492 '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',
493 },
494 'playlist': [{
495 'info_dict': {
496 'id': '2228375078001',
497 'ext': 'mp4',
498 'title': 'nmeth.2062-sv1',
499 'description': 'nmeth.2062-sv1',
500 'timestamp': 1363357591,
501 'upload_date': '20130315',
502 'uploader': 'Nature Publishing Group',
503 'uploader_id': '1964492299001',
504 },
505 }],
506 },
507 {
508 # Brightcove with UUID in videoPlayer
509 'url': 'http://www8.hp.com/cn/zh/home.html',
510 'info_dict': {
511 'id': '5255815316001',
512 'ext': 'mp4',
513 'title': 'Sprocket Video - China',
514 'description': 'Sprocket Video - China',
515 'uploader': 'HP-Video Gallery',
516 'timestamp': 1482263210,
517 'upload_date': '20161220',
518 'uploader_id': '1107601872001',
519 },
520 'params': {
521 'skip_download': True, # m3u8 download
522 },
523 'skip': 'video rotates...weekly?',
524 },
525 {
526 # Brightcove:new type [2].
527 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
528 'md5': '2b35148fcf48da41c9fb4591650784f3',
529 'info_dict': {
530 'id': '5348741021001',
531 'ext': 'mp4',
532 'upload_date': '20170306',
533 'uploader_id': '4191638492001',
534 'timestamp': 1488769918,
535 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
536
537 },
538 },
539 {
540 # Alternative brightcove <video> attributes
541 '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/',
542 'info_dict': {
543 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
544 '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",
545 },
546 'playlist': [{
547 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
548 'info_dict': {
549 'id': '5311302538001',
550 'ext': 'mp4',
551 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
552 '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)",
553 'timestamp': 1486321708,
554 'upload_date': '20170205',
555 'uploader_id': '800000640001',
556 },
557 'only_matching': True,
558 }],
559 },
560 {
561 # Brightcove with UUID in videoPlayer
562 'url': 'http://www8.hp.com/cn/zh/home.html',
563 'info_dict': {
564 'id': '5255815316001',
565 'ext': 'mp4',
566 'title': 'Sprocket Video - China',
567 'description': 'Sprocket Video - China',
568 'uploader': 'HP-Video Gallery',
569 'timestamp': 1482263210,
570 'upload_date': '20161220',
571 'uploader_id': '1107601872001',
572 },
573 'params': {
574 'skip_download': True, # m3u8 download
575 },
576 },
577 # ooyala video
578 {
579 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
580 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
581 'info_dict': {
582 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
583 'ext': 'mp4',
584 'title': '2cc213299525360.mov', # that's what we get
585 'duration': 238.231,
586 },
587 'add_ie': ['Ooyala'],
588 },
589 {
590 # ooyala video embedded with http://player.ooyala.com/iframe.js
591 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
592 'info_dict': {
593 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
594 'ext': 'mp4',
595 'title': '"Steve Jobs: Man in the Machine" trailer',
596 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
597 'duration': 135.427,
598 },
599 'params': {
600 'skip_download': True,
601 },
602 'skip': 'movie expired',
603 },
604 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
605 {
606 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
607 'info_dict': {
608 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
609 'ext': 'mp4',
610 'title': 'Steampunk Fest Comes to Honesdale',
611 'duration': 43.276,
612 },
613 'params': {
614 'skip_download': True,
615 }
616 },
617 # embed.ly video
618 {
619 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
620 'info_dict': {
621 'id': '9ODmcdjQcHQ',
622 'ext': 'mp4',
623 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
624 'upload_date': '20140225',
625 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
626 'uploader': 'Tested',
627 'uploader_id': 'testedcom',
628 },
629 # No need to test YoutubeIE here
630 'params': {
631 'skip_download': True,
632 },
633 },
634 # funnyordie embed
635 {
636 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
637 'info_dict': {
638 'id': '18e820ec3f',
639 'ext': 'mp4',
640 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
641 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
642 },
643 # HEAD requests lead to endless 301, while GET is OK
644 'expected_warnings': ['301'],
645 },
646 # RUTV embed
647 {
648 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
649 'info_dict': {
650 'id': '776940',
651 'ext': 'mp4',
652 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
653 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
654 },
655 'params': {
656 # m3u8 download
657 'skip_download': True,
658 },
659 },
660 # TVC embed
661 {
662 '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/',
663 'info_dict': {
664 'id': '55304',
665 'ext': 'mp4',
666 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
667 },
668 },
669 # SportBox embed
670 {
671 'url': 'http://www.vestifinance.ru/articles/25753',
672 'info_dict': {
673 'id': '25753',
674 '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"',
675 },
676 'playlist': [{
677 'info_dict': {
678 'id': '370908',
679 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
680 'ext': 'mp4',
681 }
682 }, {
683 'info_dict': {
684 'id': '370905',
685 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
686 'ext': 'mp4',
687 }
688 }, {
689 'info_dict': {
690 'id': '370902',
691 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
692 'ext': 'mp4',
693 }
694 }],
695 'params': {
696 # m3u8 download
697 'skip_download': True,
698 },
699 },
700 # Myvi.ru embed
701 {
702 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
703 'info_dict': {
704 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
705 'ext': 'mp4',
706 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
707 'thumbnail': r're:^https?://.*\.jpg$',
708 'duration': 153,
709 }
710 },
711 # XHamster embed
712 {
713 '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',
714 'info_dict': {
715 'id': 'showthread',
716 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
717 },
718 'playlist_mincount': 7,
719 # This forum does not allow <iframe> syntaxes anymore
720 # Now HTML tags are displayed as-is
721 'skip': 'No videos on this page',
722 },
723 # Embedded TED video
724 {
725 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
726 'md5': '65fdff94098e4a607385a60c5177c638',
727 'info_dict': {
728 'id': '1969',
729 'ext': 'mp4',
730 'title': 'Hidden miracles of the natural world',
731 'uploader': 'Louie Schwartzberg',
732 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
733 }
734 },
735 # nowvideo embed hidden behind percent encoding
736 {
737 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
738 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
739 'info_dict': {
740 'id': '06e53103ca9aa',
741 'ext': 'flv',
742 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
743 'description': 'No description',
744 },
745 },
746 # arte embed
747 {
748 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
749 'md5': '7653032cbb25bf6c80d80f217055fa43',
750 'info_dict': {
751 'id': '048195-004_PLUS7-F',
752 'ext': 'flv',
753 'title': 'X:enius',
754 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
755 'upload_date': '20140320',
756 },
757 'params': {
758 'skip_download': 'Requires rtmpdump'
759 },
760 'skip': 'video gone',
761 },
762 # francetv embed
763 {
764 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
765 'info_dict': {
766 'id': 'EV_30231',
767 'ext': 'mp4',
768 'title': 'Alcaline, le concert avec Calogero',
769 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
770 'upload_date': '20150226',
771 'timestamp': 1424989860,
772 'duration': 5400,
773 },
774 'params': {
775 # m3u8 downloads
776 'skip_download': True,
777 },
778 'expected_warnings': [
779 'Forbidden'
780 ]
781 },
782 # CondƩ Nast embed
783 {
784 'url': 'http://www.wired.com/2014/04/honda-asimo/',
785 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
786 'info_dict': {
787 'id': '53501be369702d3275860000',
788 'ext': 'mp4',
789 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
790 }
791 },
792 # Dailymotion embed
793 {
794 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
795 'md5': '441aeeb82eb72c422c7f14ec533999cd',
796 'info_dict': {
797 'id': 'k2mm4bCdJ6CQ2i7c8o2',
798 'ext': 'mp4',
799 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
800 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
801 'uploader': 'Spi0n',
802 'uploader_id': 'xgditw',
803 'upload_date': '20140425',
804 'timestamp': 1398441542,
805 },
806 'add_ie': ['Dailymotion'],
807 },
808 # DailyMail embed
809 {
810 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
811 'info_dict': {
812 'id': '1495629',
813 'ext': 'mp4',
814 'title': 'Care worker punches elderly dementia patient in head 11 times',
815 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
816 },
817 'add_ie': ['DailyMail'],
818 'params': {
819 'skip_download': True,
820 },
821 },
822 # YouTube embed
823 {
824 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
825 'info_dict': {
826 'id': 'FXRb4ykk4S0',
827 'ext': 'mp4',
828 'title': 'The NBL Auction 2014',
829 'uploader': 'BADMINTON England',
830 'uploader_id': 'BADMINTONEvents',
831 'upload_date': '20140603',
832 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
833 },
834 'add_ie': ['Youtube'],
835 'params': {
836 'skip_download': True,
837 }
838 },
839 # MTVSercices embed
840 {
841 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
842 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
843 'info_dict': {
844 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
845 'ext': 'mp4',
846 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
847 'description': 'Two valets share their love for movie star Liam Neesons.',
848 'timestamp': 1349922600,
849 'upload_date': '20121011',
850 },
851 },
852 # YouTube embed via <data-embed-url="">
853 {
854 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
855 'info_dict': {
856 'id': '4vAffPZIT44',
857 'ext': 'mp4',
858 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
859 'uploader': 'Gameloft',
860 'uploader_id': 'gameloft',
861 'upload_date': '20140828',
862 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
863 },
864 'params': {
865 'skip_download': True,
866 }
867 },
868 # YouTube <object> embed
869 {
870 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
871 'md5': '516718101ec834f74318df76259fb3cc',
872 'info_dict': {
873 'id': 'msN87y-iEx0',
874 'ext': 'webm',
875 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
876 'upload_date': '20080526',
877 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
878 'uploader': 'Christopher Sykes',
879 'uploader_id': 'ChristopherJSykes',
880 },
881 'add_ie': ['Youtube'],
882 },
883 # Camtasia studio
884 {
885 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
886 'playlist': [{
887 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
888 'info_dict': {
889 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
890 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
891 'ext': 'flv',
892 'duration': 2235.90,
893 }
894 }, {
895 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
896 'info_dict': {
897 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
898 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
899 'ext': 'flv',
900 'duration': 2235.93,
901 }
902 }],
903 'info_dict': {
904 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
905 }
906 },
907 # Flowplayer
908 {
909 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
910 'md5': '9d65602bf31c6e20014319c7d07fba27',
911 'info_dict': {
912 'id': '5123ea6d5e5a7',
913 'ext': 'mp4',
914 'age_limit': 18,
915 'uploader': 'www.handjobhub.com',
916 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
917 }
918 },
919 # Multiple brightcove videos
920 # https://github.com/rg3/youtube-dl/issues/2283
921 {
922 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
923 'info_dict': {
924 'id': 'always-never',
925 'title': 'Always / Never - The New Yorker',
926 },
927 'playlist_count': 3,
928 'params': {
929 'extract_flat': False,
930 'skip_download': True,
931 }
932 },
933 # MLB embed
934 {
935 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
936 'md5': '96f09a37e44da40dd083e12d9a683327',
937 'info_dict': {
938 'id': '33322633',
939 'ext': 'mp4',
940 'title': 'Ump changes call to ball',
941 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
942 'duration': 48,
943 'timestamp': 1401537900,
944 'upload_date': '20140531',
945 'thumbnail': r're:^https?://.*\.jpg$',
946 },
947 },
948 # Wistia embed
949 {
950 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
951 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
952 'info_dict': {
953 'id': '6e2wtrbdaf',
954 'ext': 'mov',
955 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
956 'description': 'a Paywall Videos video from Remilon',
957 'duration': 644.072,
958 'uploader': 'study.com',
959 'timestamp': 1459678540,
960 'upload_date': '20160403',
961 'filesize': 24687186,
962 },
963 },
964 {
965 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
966 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
967 'info_dict': {
968 'id': 'uxjb0lwrcz',
969 'ext': 'mp4',
970 'title': 'Conversation about Hexagonal Rails Part 1',
971 'description': 'a Martin Fowler video from ThoughtWorks',
972 'duration': 1715.0,
973 'uploader': 'thoughtworks.wistia.com',
974 'timestamp': 1401832161,
975 'upload_date': '20140603',
976 },
977 },
978 # Wistia standard embed (async)
979 {
980 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
981 'info_dict': {
982 'id': '807fafadvk',
983 'ext': 'mp4',
984 'title': 'Drip Brennan Dunn Workshop',
985 'description': 'a JV Webinars video from getdrip-1',
986 'duration': 4986.95,
987 'timestamp': 1463607249,
988 'upload_date': '20160518',
989 },
990 'params': {
991 'skip_download': True,
992 }
993 },
994 # Soundcloud embed
995 {
996 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
997 'info_dict': {
998 'id': '174391317',
999 'ext': 'mp3',
1000 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1001 'uploader': 'Sophos Security',
1002 'title': 'Chet Chat 171 - Oct 29, 2014',
1003 'upload_date': '20141029',
1004 }
1005 },
1006 # Soundcloud multiple embeds
1007 {
1008 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1009 'info_dict': {
1010 'id': '52809',
1011 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
1012 },
1013 'playlist_mincount': 7,
1014 },
1015 # TuneIn station embed
1016 {
1017 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1018 'info_dict': {
1019 'id': '204146',
1020 'ext': 'mp3',
1021 'title': 'CNRV',
1022 'location': 'Paris, France',
1023 'is_live': True,
1024 },
1025 'params': {
1026 # Live stream
1027 'skip_download': True,
1028 },
1029 },
1030 # Livestream embed
1031 {
1032 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1033 'info_dict': {
1034 'id': '67864563',
1035 'ext': 'flv',
1036 'upload_date': '20141112',
1037 'title': 'Rosetta #CometLanding webcast HL 10',
1038 }
1039 },
1040 # Another Livestream embed, without 'new.' in URL
1041 {
1042 'url': 'https://www.freespeech.org/',
1043 'info_dict': {
1044 'id': '123537347',
1045 'ext': 'mp4',
1046 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1047 },
1048 'params': {
1049 # Live stream
1050 'skip_download': True,
1051 },
1052 },
1053 # LazyYT
1054 {
1055 'url': 'https://skiplagged.com/',
1056 'info_dict': {
1057 'id': 'skiplagged',
1058 'title': 'Skiplagged: The smart way to find cheap flights',
1059 },
1060 'playlist_mincount': 1,
1061 'add_ie': ['Youtube'],
1062 },
1063 # Cinchcast embed
1064 {
1065 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1066 'info_dict': {
1067 'id': '7141703',
1068 'ext': 'mp3',
1069 'upload_date': '20141126',
1070 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1071 }
1072 },
1073 # Cinerama player
1074 {
1075 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1076 'info_dict': {
1077 'id': '730m_DandD_1901_512k',
1078 'ext': 'mp4',
1079 'uploader': 'www.abc.net.au',
1080 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1081 }
1082 },
1083 # embedded viddler video
1084 {
1085 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1086 'info_dict': {
1087 'id': '4d03aad9',
1088 'ext': 'mp4',
1089 'uploader': 'deadspin',
1090 'title': 'WALL-TO-GORTAT',
1091 'timestamp': 1422285291,
1092 'upload_date': '20150126',
1093 },
1094 'add_ie': ['Viddler'],
1095 },
1096 # Libsyn embed
1097 {
1098 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1099 'info_dict': {
1100 'id': '3377616',
1101 'ext': 'mp3',
1102 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1103 'description': 'md5:601cb790edd05908957dae8aaa866465',
1104 'upload_date': '20150220',
1105 },
1106 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1107 },
1108 # jwplayer YouTube
1109 {
1110 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1111 'info_dict': {
1112 'id': 'Mrj4DVp2zeA',
1113 'ext': 'mp4',
1114 'upload_date': '20150212',
1115 'uploader': 'The National Archives UK',
1116 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1117 'uploader_id': 'NationalArchives08',
1118 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1119 },
1120 },
1121 # jwplayer rtmp
1122 {
1123 'url': 'http://www.suffolk.edu/sjc/live.php',
1124 'info_dict': {
1125 'id': 'live',
1126 'ext': 'flv',
1127 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1128 'uploader': 'www.suffolk.edu',
1129 },
1130 'params': {
1131 'skip_download': True,
1132 },
1133 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1134 },
1135 # Complex jwplayer
1136 {
1137 'url': 'http://www.indiedb.com/games/king-machine/videos',
1138 'info_dict': {
1139 'id': 'videos',
1140 'ext': 'mp4',
1141 'title': 'king machine trailer 1',
1142 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1143 'thumbnail': r're:^https?://.*\.jpg$',
1144 },
1145 },
1146 {
1147 # JWPlayer config passed as variable
1148 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1149 'info_dict': {
1150 'id': '3326530_hq',
1151 'ext': 'mp4',
1152 'title': 'ARIELE | Tube Cup',
1153 'uploader': 'www.txxx.com',
1154 'age_limit': 18,
1155 },
1156 'params': {
1157 'skip_download': True,
1158 }
1159 },
1160 {
1161 # JWPlatform iframe
1162 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1163 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1164 'info_dict': {
1165 'id': 'O0c5JcKT',
1166 'ext': 'mp4',
1167 'upload_date': '20171122',
1168 'timestamp': 1511366290,
1169 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1170 },
1171 'add_ie': [JWPlatformIE.ie_key()],
1172 },
1173 {
1174 # Video.js embed, multiple formats
1175 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1176 'info_dict': {
1177 'id': 'yygqldloqIk',
1178 'ext': 'mp4',
1179 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1180 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1181 'upload_date': '20130314',
1182 'uploader': 'PROстŠ¾Šµ3D',
1183 'uploader_id': 'PROstoe3D',
1184 },
1185 'params': {
1186 'skip_download': True,
1187 },
1188 },
1189 {
1190 # Video.js embed, single format
1191 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1192 'info_dict': {
1193 'id': 'watch',
1194 'ext': 'mp4',
1195 'title': 'Step 1 - Good Foundation',
1196 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1197 },
1198 'params': {
1199 'skip_download': True,
1200 },
1201 },
1202 # rtl.nl embed
1203 {
1204 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1205 'playlist_mincount': 5,
1206 'info_dict': {
1207 'id': 'aanslagen-kopenhagen',
1208 'title': 'Aanslagen Kopenhagen',
1209 }
1210 },
1211 # Zapiks embed
1212 {
1213 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1214 'info_dict': {
1215 'id': '118046',
1216 'ext': 'mp4',
1217 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1218 }
1219 },
1220 # Kaltura embed (different embed code)
1221 {
1222 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1223 'info_dict': {
1224 'id': '1_a52wc67y',
1225 'ext': 'flv',
1226 'upload_date': '20150127',
1227 'uploader_id': 'PremierMedia',
1228 'timestamp': int,
1229 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1230 },
1231 },
1232 # Kaltura embed with single quotes
1233 {
1234 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1235 'info_dict': {
1236 'id': '0_izeg5utt',
1237 'ext': 'mp4',
1238 'title': '35871',
1239 'timestamp': 1355743100,
1240 'upload_date': '20121217',
1241 'uploader_id': 'cplapp@learn360.com',
1242 },
1243 'add_ie': ['Kaltura'],
1244 },
1245 {
1246 # Kaltura embedded via quoted entry_id
1247 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1248 'info_dict': {
1249 'id': '0_utuok90b',
1250 'ext': 'mp4',
1251 'title': '06_matthew_brender_raj_dutt',
1252 'timestamp': 1466638791,
1253 'upload_date': '20160622',
1254 },
1255 'add_ie': ['Kaltura'],
1256 'expected_warnings': [
1257 'Could not send HEAD request'
1258 ],
1259 'params': {
1260 'skip_download': True,
1261 }
1262 },
1263 {
1264 # Kaltura embedded, some fileExt broken (#11480)
1265 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1266 'info_dict': {
1267 'id': '1_sgtvehim',
1268 'ext': 'mp4',
1269 'title': 'Our "Standard Models" of particle physics and cosmology',
1270 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1271 'timestamp': 1321158993,
1272 'upload_date': '20111113',
1273 'uploader_id': 'kps1',
1274 },
1275 'add_ie': ['Kaltura'],
1276 },
1277 {
1278 # Kaltura iframe embed
1279 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1280 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1281 'info_dict': {
1282 'id': '0_f2cfbpwy',
1283 'ext': 'mp4',
1284 'title': 'I. M. Pei: A Centennial Celebration',
1285 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1286 'upload_date': '20170403',
1287 'uploader_id': 'batchUser',
1288 'timestamp': 1491232186,
1289 },
1290 'add_ie': ['Kaltura'],
1291 },
1292 {
1293 # Kaltura iframe embed, more sophisticated
1294 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1295 'info_dict': {
1296 'id': '1_9gzouybz',
1297 'ext': 'mp4',
1298 'title': 'lecture-05sep2017',
1299 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1300 'upload_date': '20170913',
1301 'uploader_id': 'eps2',
1302 'timestamp': 1505340777,
1303 },
1304 'params': {
1305 'skip_download': True,
1306 },
1307 'add_ie': ['Kaltura'],
1308 },
1309 {
1310 # meta twitter:player
1311 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1312 'info_dict': {
1313 'id': '0_01b42zps',
1314 'ext': 'mp4',
1315 'title': 'Main Twerk (Video)',
1316 'upload_date': '20171208',
1317 'uploader_id': 'sebastian.salinas@thechive.com',
1318 'timestamp': 1512713057,
1319 },
1320 'params': {
1321 'skip_download': True,
1322 },
1323 'add_ie': ['Kaltura'],
1324 },
1325 # referrer protected EaglePlatform embed
1326 {
1327 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1328 'info_dict': {
1329 'id': '582306',
1330 'ext': 'mp4',
1331 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1332 'thumbnail': r're:^https?://.*\.jpg$',
1333 'duration': 3382,
1334 'view_count': int,
1335 },
1336 'params': {
1337 'skip_download': True,
1338 },
1339 },
1340 # ClipYou (EaglePlatform) embed (custom URL)
1341 {
1342 'url': 'http://muz-tv.ru/play/7129/',
1343 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1344 'info_dict': {
1345 'id': '12820',
1346 'ext': 'mp4',
1347 'title': "'O Sole Mio",
1348 'thumbnail': r're:^https?://.*\.jpg$',
1349 'duration': 216,
1350 'view_count': int,
1351 },
1352 'params': {
1353 'skip_download': True,
1354 },
1355 'skip': 'This video is unavailable.',
1356 },
1357 # Pladform embed
1358 {
1359 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1360 'info_dict': {
1361 'id': '100183293',
1362 'ext': 'mp4',
1363 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1364 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1365 'thumbnail': r're:^https?://.*\.jpg$',
1366 'duration': 694,
1367 'age_limit': 0,
1368 },
1369 'skip': 'HTTP Error 404: Not Found',
1370 },
1371 # Playwire embed
1372 {
1373 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1374 'info_dict': {
1375 'id': '3519514',
1376 'ext': 'mp4',
1377 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1378 'thumbnail': r're:^https?://.*\.png$',
1379 'duration': 45.115,
1380 },
1381 },
1382 # 5min embed
1383 {
1384 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1385 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1386 'info_dict': {
1387 'id': '518726732',
1388 'ext': 'mp4',
1389 'title': 'Facebook Creates "On This Day" | Crunch Report',
1390 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1391 'timestamp': 1427237531,
1392 'uploader': 'Crunch Report',
1393 'upload_date': '20150324',
1394 },
1395 'params': {
1396 # m3u8 download
1397 'skip_download': True,
1398 },
1399 },
1400 # Crooks and Liars embed
1401 {
1402 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1403 'info_dict': {
1404 'id': '8RUoRhRi',
1405 'ext': 'mp4',
1406 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1407 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1408 'timestamp': 1428207000,
1409 'upload_date': '20150405',
1410 'uploader': 'Heather',
1411 },
1412 },
1413 # Crooks and Liars external embed
1414 {
1415 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1416 'info_dict': {
1417 'id': 'MTE3MjUtMzQ2MzA',
1418 'ext': 'mp4',
1419 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1420 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1421 'timestamp': 1265032391,
1422 'upload_date': '20100201',
1423 'uploader': 'Heather',
1424 },
1425 },
1426 # NBC Sports vplayer embed
1427 {
1428 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1429 'info_dict': {
1430 'id': 'ln7x1qSThw4k',
1431 'ext': 'flv',
1432 'title': "PFT Live: New leader in the 'new-look' defense",
1433 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1434 'uploader': 'NBCU-SPORTS',
1435 'upload_date': '20140107',
1436 'timestamp': 1389118457,
1437 },
1438 'skip': 'Invalid Page URL',
1439 },
1440 # NBC News embed
1441 {
1442 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1443 'md5': '1aa589c675898ae6d37a17913cf68d66',
1444 'info_dict': {
1445 'id': 'x_dtl_oa_LettermanliftPR_160608',
1446 'ext': 'mp4',
1447 'title': 'David Letterman: A Preview',
1448 '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.',
1449 'upload_date': '20160609',
1450 'timestamp': 1465431544,
1451 'uploader': 'NBCU-NEWS',
1452 },
1453 },
1454 # UDN embed
1455 {
1456 'url': 'https://video.udn.com/news/300346',
1457 'md5': 'fd2060e988c326991037b9aff9df21a6',
1458 'info_dict': {
1459 'id': '300346',
1460 'ext': 'mp4',
1461 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1462 'thumbnail': r're:^https?://.*\.jpg$',
1463 },
1464 'params': {
1465 # m3u8 download
1466 'skip_download': True,
1467 },
1468 'expected_warnings': ['Failed to parse JSON Expecting value'],
1469 },
1470 # Brightcove URL in single quotes
1471 {
1472 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1473 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1474 'info_dict': {
1475 'id': '4255764656001',
1476 'ext': 'mp4',
1477 'title': 'SN Presents: Russell Martin, World Citizen',
1478 '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.',
1479 'uploader': 'Rogers Sportsnet',
1480 'uploader_id': '1704050871',
1481 'upload_date': '20150525',
1482 'timestamp': 1432570283,
1483 },
1484 },
1485 # OnionStudios embed
1486 {
1487 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1488 'info_dict': {
1489 'id': '2855',
1490 'ext': 'mp4',
1491 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1492 'thumbnail': r're:^https?://.*\.jpe?g$',
1493 'uploader': 'ClickHole',
1494 'uploader_id': 'clickhole',
1495 }
1496 },
1497 # SnagFilms embed
1498 {
1499 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1500 'info_dict': {
1501 'id': '74849a00-85a9-11e1-9660-123139220831',
1502 'ext': 'mp4',
1503 'title': '#whilewewatch',
1504 }
1505 },
1506 # AdobeTVVideo embed
1507 {
1508 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1509 'md5': '43662b577c018ad707a63766462b1e87',
1510 'info_dict': {
1511 'id': '2456',
1512 'ext': 'mp4',
1513 'title': 'New experience with Acrobat DC',
1514 'description': 'New experience with Acrobat DC',
1515 'duration': 248.667,
1516 },
1517 },
1518 # BrightcoveInPageEmbed embed
1519 {
1520 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1521 'info_dict': {
1522 'id': '4238694884001',
1523 'ext': 'flv',
1524 'title': 'Tabletop: Dread, Last Thoughts',
1525 'description': 'Tabletop: Dread, Last Thoughts',
1526 'duration': 51690,
1527 },
1528 },
1529 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1530 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1531 {
1532 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1533 'info_dict': {
1534 'id': '4785848093001',
1535 'ext': 'mp4',
1536 'title': 'The Cardinal Pell Interview',
1537 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1538 'uploader': 'GlobeCast Australia - GlobeStream',
1539 'uploader_id': '2733773828001',
1540 'upload_date': '20160304',
1541 'timestamp': 1457083087,
1542 },
1543 'params': {
1544 # m3u8 downloads
1545 'skip_download': True,
1546 },
1547 },
1548 {
1549 # Brightcove embed with whitespace around attribute names
1550 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1551 'info_dict': {
1552 'id': '3167554373001',
1553 'ext': 'mp4',
1554 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1555 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1556 'uploader_id': '1079349493',
1557 'upload_date': '20140207',
1558 'timestamp': 1391810548,
1559 },
1560 'params': {
1561 'skip_download': True,
1562 },
1563 },
1564 # Another form of arte.tv embed
1565 {
1566 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1567 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1568 'info_dict': {
1569 'id': '030273-562_PLUS7-F',
1570 'ext': 'mp4',
1571 'title': 'ARTE Reportage - Nulle part, en France',
1572 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1573 'upload_date': '20160409',
1574 },
1575 },
1576 # LiveLeak embed
1577 {
1578 'url': 'http://www.wykop.pl/link/3088787/',
1579 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1580 'info_dict': {
1581 'id': '874_1459135191',
1582 'ext': 'mp4',
1583 'title': 'Man shows poor quality of new apartment building',
1584 'description': 'The wall is like a sand pile.',
1585 'uploader': 'Lake8737',
1586 },
1587 'add_ie': [LiveLeakIE.ie_key()],
1588 },
1589 # Another LiveLeak embed pattern (#13336)
1590 {
1591 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1592 'info_dict': {
1593 'id': '2eb_1496309988',
1594 'ext': 'mp4',
1595 'title': 'Thief robs place where everyone was armed',
1596 'description': 'md5:694d73ee79e535953cf2488562288eee',
1597 'uploader': 'brazilwtf',
1598 },
1599 'add_ie': [LiveLeakIE.ie_key()],
1600 },
1601 # Duplicated embedded video URLs
1602 {
1603 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1604 'info_dict': {
1605 'id': '149298443_480_16c25b74_2',
1606 'ext': 'mp4',
1607 'title': 'vs. Blue Orange Spring Game',
1608 'uploader': 'www.hudl.com',
1609 },
1610 },
1611 # twitter:player:stream embed
1612 {
1613 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1614 'info_dict': {
1615 'id': 'master',
1616 'ext': 'mp4',
1617 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1618 'uploader': 'www.rtl.be',
1619 },
1620 'params': {
1621 # m3u8 downloads
1622 'skip_download': True,
1623 },
1624 },
1625 # twitter:player embed
1626 {
1627 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1628 'md5': 'a3e0df96369831de324f0778e126653c',
1629 'info_dict': {
1630 'id': '4909620399001',
1631 'ext': 'mp4',
1632 'title': 'What Do Black Holes Sound Like?',
1633 'description': 'what do black holes sound like',
1634 'upload_date': '20160524',
1635 'uploader_id': '29913724001',
1636 'timestamp': 1464107587,
1637 'uploader': 'TheAtlantic',
1638 },
1639 'add_ie': ['BrightcoveLegacy'],
1640 },
1641 # Facebook <iframe> embed
1642 {
1643 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1644 'md5': 'fbcde74f534176ecb015849146dd3aee',
1645 'info_dict': {
1646 'id': '599637780109885',
1647 'ext': 'mp4',
1648 'title': 'Facebook video #599637780109885',
1649 },
1650 },
1651 # Facebook <iframe> embed, plugin video
1652 {
1653 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1654 'info_dict': {
1655 'id': '1754168231264132',
1656 'ext': 'mp4',
1657 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1658 'uploader': 'Tariq Ramadan (official)',
1659 'timestamp': 1496758379,
1660 'upload_date': '20170606',
1661 },
1662 'params': {
1663 'skip_download': True,
1664 },
1665 },
1666 # Facebook API embed
1667 {
1668 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1669 'md5': 'a47372ee61b39a7b90287094d447d94e',
1670 'info_dict': {
1671 'id': '10153467542406923',
1672 'ext': 'mp4',
1673 'title': 'Facebook video #10153467542406923',
1674 },
1675 },
1676 # Wordpress "YouTube Video Importer" plugin
1677 {
1678 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1679 'md5': 'd16797741b560b485194eddda8121b48',
1680 'info_dict': {
1681 'id': 'HNTXWDXV9Is',
1682 'ext': 'mp4',
1683 'title': 'Blue Devils Drumline Stanford lot 2016',
1684 'upload_date': '20160627',
1685 'uploader_id': 'GENOCIDE8GENERAL10',
1686 'uploader': 'cylus cyrus',
1687 },
1688 },
1689 {
1690 # video stored on custom kaltura server
1691 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1692 'md5': '537617d06e64dfed891fa1593c4b30cc',
1693 'info_dict': {
1694 'id': '0_1iotm5bh',
1695 'ext': 'mp4',
1696 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1697 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1698 'uploader_id': 'videos.expansion@el-mundo.net',
1699 'upload_date': '20150429',
1700 'timestamp': 1430303472,
1701 },
1702 'add_ie': ['Kaltura'],
1703 },
1704 {
1705 # Non-standard Vimeo embed
1706 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1707 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1708 'info_dict': {
1709 'id': '148867247',
1710 'ext': 'mp4',
1711 'title': 'Understanding the web - Teaser',
1712 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1713 'upload_date': '20151214',
1714 'uploader': 'OpenClassrooms',
1715 'uploader_id': 'openclassrooms',
1716 },
1717 'add_ie': ['Vimeo'],
1718 },
1719 {
1720 # generic vimeo embed that requires original URL passed as Referer
1721 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1722 'only_matching': True,
1723 },
1724 {
1725 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1726 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1727 'info_dict': {
1728 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1729 'ext': 'mp4',
1730 'title': 'Big Buck Bunny',
1731 'description': 'Royalty free test video',
1732 'timestamp': 1432816365,
1733 'upload_date': '20150528',
1734 'is_live': False,
1735 },
1736 'params': {
1737 'skip_download': True,
1738 },
1739 'add_ie': [ArkenaIE.ie_key()],
1740 },
1741 {
1742 '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/',
1743 'info_dict': {
1744 'id': '1c7141f46c',
1745 'ext': 'mp4',
1746 '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',
1747 },
1748 'params': {
1749 'skip_download': True,
1750 },
1751 'add_ie': [Vbox7IE.ie_key()],
1752 },
1753 {
1754 # DBTV embeds
1755 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1756 'info_dict': {
1757 'id': '43254897',
1758 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1759 },
1760 'playlist_mincount': 3,
1761 },
1762 {
1763 # Videa embeds
1764 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1765 'info_dict': {
1766 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1767 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1768 },
1769 'playlist_mincount': 2,
1770 },
1771 {
1772 # 20 minuten embed
1773 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1774 'info_dict': {
1775 'id': '523629',
1776 'ext': 'mp4',
1777 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1778 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1779 },
1780 'params': {
1781 'skip_download': True,
1782 },
1783 'add_ie': [TwentyMinutenIE.ie_key()],
1784 },
1785 {
1786 # VideoPress embed
1787 'url': 'https://en.support.wordpress.com/videopress/',
1788 'info_dict': {
1789 'id': 'OcobLTqC',
1790 'ext': 'm4v',
1791 'title': 'IMG_5786',
1792 'timestamp': 1435711927,
1793 'upload_date': '20150701',
1794 },
1795 'params': {
1796 'skip_download': True,
1797 },
1798 'add_ie': [VideoPressIE.ie_key()],
1799 },
1800 {
1801 # Rutube embed
1802 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1803 'info_dict': {
1804 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1805 'ext': 'flv',
1806 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1807 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1808 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1809 'upload_date': '20170228',
1810 'uploader_id': '996642',
1811 },
1812 'params': {
1813 'skip_download': True,
1814 },
1815 'add_ie': [RutubeIE.ie_key()],
1816 },
1817 {
1818 # ThePlatform embedded with whitespaces in URLs
1819 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1820 'only_matching': True,
1821 },
1822 {
1823 # Senate ISVP iframe https
1824 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1825 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1826 'info_dict': {
1827 'id': 'govtaff020316',
1828 'ext': 'mp4',
1829 'title': 'Integrated Senate Video Player',
1830 },
1831 'add_ie': [SenateISVPIE.ie_key()],
1832 },
1833 {
1834 # Limelight embeds (1 channel embed + 4 media embeds)
1835 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1836 'info_dict': {
1837 'id': 'FacilitatorTraining2017',
1838 'title': 'Facilitator Training 2017',
1839 },
1840 'playlist_mincount': 5,
1841 },
1842 {
1843 # Limelight embed (LimelightPlayerUtil.embed)
1844 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1845 'info_dict': {
1846 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1847 'ext': 'mp4',
1848 'title': '07448641',
1849 'timestamp': 1499890639,
1850 'upload_date': '20170712',
1851 },
1852 'params': {
1853 'skip_download': True,
1854 },
1855 'add_ie': ['LimelightMedia'],
1856 },
1857 {
1858 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1859 'info_dict': {
1860 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1861 'title': 'Standoff with Walnut Creek murder suspect ends',
1862 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1863 },
1864 'playlist_mincount': 4,
1865 },
1866 {
1867 # WashingtonPost embed
1868 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1869 'info_dict': {
1870 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1871 'ext': 'mp4',
1872 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1873 '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.',
1874 'timestamp': 1455216756,
1875 'uploader': 'The Washington Post',
1876 'upload_date': '20160211',
1877 },
1878 'add_ie': [WashingtonPostIE.ie_key()],
1879 },
1880 {
1881 # Mediaset embed
1882 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1883 'info_dict': {
1884 'id': '720642',
1885 'ext': 'mp4',
1886 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1887 },
1888 'params': {
1889 'skip_download': True,
1890 },
1891 'add_ie': [MediasetIE.ie_key()],
1892 },
1893 {
1894 # JOJ.sk embeds
1895 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1896 'info_dict': {
1897 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1898 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1899 },
1900 'playlist_mincount': 5,
1901 'add_ie': [JojIE.ie_key()],
1902 },
1903 {
1904 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1905 'url': 'https://tvrain.ru/amp/418921/',
1906 'md5': 'cc00413936695987e8de148b67d14f1d',
1907 'info_dict': {
1908 'id': '418921',
1909 'ext': 'mp4',
1910 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1911 },
1912 },
1913 {
1914 # vzaar embed
1915 'url': 'http://help.vzaar.com/article/165-embedding-video',
1916 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1917 'info_dict': {
1918 'id': '8707641',
1919 'ext': 'mp4',
1920 'title': 'Building A Business Online: Principal Chairs Q & A',
1921 },
1922 },
1923 {
1924 # multiple HTML5 videos on one page
1925 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1926 'info_dict': {
1927 'id': 'keyscenarios',
1928 'title': 'Rescue Kit 14 Free Edition - Getting started',
1929 },
1930 'playlist_count': 4,
1931 },
1932 {
1933 # vshare embed
1934 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1935 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1936 'info_dict': {
1937 'id': '0f64ce6',
1938 'title': 'vl14062007715967',
1939 'ext': 'mp4',
1940 }
1941 },
1942 {
1943 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1944 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1945 'info_dict': {
1946 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1947 'ext': 'mp4',
1948 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1949 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1950 'timestamp': 1474354800,
1951 'upload_date': '20160920',
1952 }
1953 },
1954 {
1955 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1956 'info_dict': {
1957 'id': '1731611',
1958 'ext': 'mp4',
1959 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1960 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1961 'timestamp': 1516100691,
1962 'upload_date': '20180116',
1963 },
1964 'params': {
1965 'skip_download': True,
1966 },
1967 'add_ie': [SpringboardPlatformIE.ie_key()],
1968 },
1969 {
1970 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1971 'info_dict': {
1972 'id': 'uPDB5I9wfp8',
1973 'ext': 'webm',
1974 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1975 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1976 'upload_date': '20160219',
1977 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1978 'uploader_id': 'PocoyoBrazil',
1979 },
1980 'add_ie': [YoutubeIE.ie_key()],
1981 'params': {
1982 'skip_download': True,
1983 },
1984 },
1985 {
1986 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1987 'info_dict': {
1988 'id': 'vMDE4NzI1Mjgt690b',
1989 'ext': 'mp4',
1990 'title': 'ŠšŠ¾Ń‚ŃŃ‚Š°',
1991 },
1992 'add_ie': [YapFilesIE.ie_key()],
1993 'params': {
1994 'skip_download': True,
1995 },
1996 },
1997 {
1998 # CloudflareStream embed
1999 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2000 'info_dict': {
2001 'id': '31c9291ab41fac05471db4e73aa11717',
2002 'ext': 'mp4',
2003 'title': '31c9291ab41fac05471db4e73aa11717',
2004 },
2005 'add_ie': [CloudflareStreamIE.ie_key()],
2006 'params': {
2007 'skip_download': True,
2008 },
2009 },
2010 {
2011 # PeerTube embed
2012 'url': 'https://joinpeertube.org/fr/home/',
2013 'info_dict': {
2014 'id': 'home',
2015 'title': 'Reprenez le contrƓle de vos vidƩos ! #JoinPeertube',
2016 },
2017 'playlist_count': 2,
2018 },
2019 {
2020 # Indavideo embed
2021 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2022 'info_dict': {
2023 'id': '1693903',
2024 'ext': 'mp4',
2025 'title': 'ƍgy kell otthon hamburgert sĆ¼tni',
2026 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2027 'timestamp': 1426330212,
2028 'upload_date': '20150314',
2029 'uploader': 'StreetKitchen',
2030 'uploader_id': '546363',
2031 },
2032 'add_ie': [IndavideoEmbedIE.ie_key()],
2033 'params': {
2034 'skip_download': True,
2035 },
2036 },
2037 {
2038 # APA embed via JWPlatform embed
2039 'url': 'http://www.vol.at/blue-man-group/5593454',
2040 'info_dict': {
2041 'id': 'jjv85FdZ',
2042 'ext': 'mp4',
2043 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview',
2044 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2045 'thumbnail': r're:^https?://.*\.jpg$',
2046 'duration': 254,
2047 'timestamp': 1519211149,
2048 'upload_date': '20180221',
2049 },
2050 'params': {
2051 'skip_download': True,
2052 },
2053 },
2054 {
2055 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2056 'md5': 'b68d276de422ab07ee1d49388103f457',
2057 'info_dict': {
2058 'id': '83645793',
2059 'title': 'Lock up and get excited',
2060 'ext': 'mp4'
2061 },
2062 'skip': 'TODO: fix nested playlists processing in tests',
2063 },
2064 {
2065 # Viqeo embeds
2066 'url': 'https://viqeo.tv/',
2067 'info_dict': {
2068 'id': 'viqeo',
2069 'title': 'All-new video platform',
2070 },
2071 'playlist_count': 6,
2072 },
2073 {
2074 # videojs embed
2075 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2076 'info_dict': {
2077 'id': 'shell',
2078 'ext': 'mp4',
2079 'title': 'Š”Š¾ŃŃ‚Š°Š²Ń‰ŠøŠŗ ŠæŠøццы сŠæрŠ¾ŃŠøŠ» рŠ°Š·Ń€ŠµŃˆŠµŠ½Šøя сыŠ³Ń€Š°Ń‚ŃŒ Š½Š° фŠ¾Ń€Ń‚ŠµŠæŠøŠ°Š½Š¾',
2080 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2081 'thumbnail': r're:^https?://.*\.jpg$',
2082 },
2083 'params': {
2084 'skip_download': True,
2085 },
2086 'expected_warnings': ['Failed to download MPD manifest'],
2087 },
2088 # {
2089 # # TODO: find another test
2090 # # http://schema.org/VideoObject
2091 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2092 # 'md5': '888dcf08b7ea671381f00fab74692755',
2093 # 'info_dict': {
2094 # 'id': 'nyvTSJMKId',
2095 # 'ext': 'mp4',
2096 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2097 # 'description': '#love for cats.',
2098 # 'timestamp': 1461244995,
2099 # 'upload_date': '20160421',
2100 # },
2101 # 'params': {
2102 # 'force_generic_extractor': True,
2103 # },
2104 # }
2105 ]
2106
2107 def report_following_redirect(self, new_url):
2108 """Report information extraction."""
2109 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2110
2111 def _extract_rss(self, url, video_id, doc):
2112 playlist_title = doc.find('./channel/title').text
2113 playlist_desc_el = doc.find('./channel/description')
2114 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2115
2116 entries = []
2117 for it in doc.findall('./channel/item'):
2118 next_url = None
2119 enclosure_nodes = it.findall('./enclosure')
2120 for e in enclosure_nodes:
2121 next_url = e.attrib.get('url')
2122 if next_url:
2123 break
2124
2125 if not next_url:
2126 next_url = xpath_text(it, 'link', fatal=False)
2127
2128 if not next_url:
2129 continue
2130
2131 entries.append({
2132 '_type': 'url_transparent',
2133 'url': next_url,
2134 'title': it.find('title').text,
2135 })
2136
2137 return {
2138 '_type': 'playlist',
2139 'id': url,
2140 'title': playlist_title,
2141 'description': playlist_desc,
2142 'entries': entries,
2143 }
2144
2145 def _extract_camtasia(self, url, video_id, webpage):
2146 """ Returns None if no camtasia video can be found. """
2147
2148 camtasia_cfg = self._search_regex(
2149 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2150 webpage, 'camtasia configuration file', default=None)
2151 if camtasia_cfg is None:
2152 return None
2153
2154 title = self._html_search_meta('DC.title', webpage, fatal=True)
2155
2156 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2157 camtasia_cfg = self._download_xml(
2158 camtasia_url, video_id,
2159 note='Downloading camtasia configuration',
2160 errnote='Failed to download camtasia configuration')
2161 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2162
2163 entries = []
2164 for n in fileset_node.getchildren():
2165 url_n = n.find('./uri')
2166 if url_n is None:
2167 continue
2168
2169 entries.append({
2170 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2171 'title': '%s - %s' % (title, n.tag),
2172 'url': compat_urlparse.urljoin(url, url_n.text),
2173 'duration': float_or_none(n.find('./duration').text),
2174 })
2175
2176 return {
2177 '_type': 'playlist',
2178 'entries': entries,
2179 'title': title,
2180 }
2181
2182 def _real_extract(self, url):
2183 if url.startswith('//'):
2184 return {
2185 '_type': 'url',
2186 'url': self.http_scheme() + url,
2187 }
2188
2189 parsed_url = compat_urlparse.urlparse(url)
2190 if not parsed_url.scheme:
2191 default_search = self._downloader.params.get('default_search')
2192 if default_search is None:
2193 default_search = 'fixup_error'
2194
2195 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2196 if '/' in url:
2197 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2198 return self.url_result('http://' + url)
2199 elif default_search != 'fixup_error':
2200 if default_search == 'auto_warning':
2201 if re.match(r'^(?:url|URL)$', url):
2202 raise ExtractorError(
2203 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2204 expected=True)
2205 else:
2206 self._downloader.report_warning(
2207 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2208 return self.url_result('ytsearch:' + url)
2209
2210 if default_search in ('error', 'fixup_error'):
2211 raise ExtractorError(
2212 '%r is not a valid URL. '
2213 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2214 % (url, url), expected=True)
2215 else:
2216 if ':' not in default_search:
2217 default_search += ':'
2218 return self.url_result(default_search + url)
2219
2220 url, smuggled_data = unsmuggle_url(url)
2221 force_videoid = None
2222 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2223 if smuggled_data and 'force_videoid' in smuggled_data:
2224 force_videoid = smuggled_data['force_videoid']
2225 video_id = force_videoid
2226 else:
2227 video_id = self._generic_id(url)
2228
2229 self.to_screen('%s: Requesting header' % video_id)
2230
2231 head_req = HEADRequest(url)
2232 head_response = self._request_webpage(
2233 head_req, video_id,
2234 note=False, errnote='Could not send HEAD request to %s' % url,
2235 fatal=False)
2236
2237 if head_response is not False:
2238 # Check for redirect
2239 new_url = compat_str(head_response.geturl())
2240 if url != new_url:
2241 self.report_following_redirect(new_url)
2242 if force_videoid:
2243 new_url = smuggle_url(
2244 new_url, {'force_videoid': force_videoid})
2245 return self.url_result(new_url)
2246
2247 full_response = None
2248 if head_response is False:
2249 request = sanitized_Request(url)
2250 request.add_header('Accept-Encoding', '*')
2251 full_response = self._request_webpage(request, video_id)
2252 head_response = full_response
2253
2254 info_dict = {
2255 'id': video_id,
2256 'title': self._generic_title(url),
2257 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2258 }
2259
2260 # Check for direct link to a video
2261 content_type = head_response.headers.get('Content-Type', '').lower()
2262 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2263 if m:
2264 format_id = compat_str(m.group('format_id'))
2265 if format_id.endswith('mpegurl'):
2266 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2267 elif format_id == 'f4m':
2268 formats = self._extract_f4m_formats(url, video_id)
2269 else:
2270 formats = [{
2271 'format_id': format_id,
2272 'url': url,
2273 'vcodec': 'none' if m.group('type') == 'audio' else None
2274 }]
2275 info_dict['direct'] = True
2276 self._sort_formats(formats)
2277 info_dict['formats'] = formats
2278 return info_dict
2279
2280 if not self._downloader.params.get('test', False) and not is_intentional:
2281 force = self._downloader.params.get('force_generic_extractor', False)
2282 self._downloader.report_warning(
2283 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2284
2285 if not full_response:
2286 request = sanitized_Request(url)
2287 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2288 # making it impossible to download only chunk of the file (yet we need only 512kB to
2289 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2290 # that will always result in downloading the whole file that is not desirable.
2291 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2292 # to accept raw bytes and being able to download only a chunk.
2293 # It may probably better to solve this by checking Content-Type for application/octet-stream
2294 # after HEAD request finishes, but not sure if we can rely on this.
2295 request.add_header('Accept-Encoding', '*')
2296 full_response = self._request_webpage(request, video_id)
2297
2298 first_bytes = full_response.read(512)
2299
2300 # Is it an M3U playlist?
2301 if first_bytes.startswith(b'#EXTM3U'):
2302 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2303 self._sort_formats(info_dict['formats'])
2304 return info_dict
2305
2306 # Maybe it's a direct link to a video?
2307 # Be careful not to download the whole thing!
2308 if not is_html(first_bytes):
2309 self._downloader.report_warning(
2310 'URL could be a direct video link, returning it as such.')
2311 info_dict.update({
2312 'direct': True,
2313 'url': url,
2314 })
2315 return info_dict
2316
2317 webpage = self._webpage_read_content(
2318 full_response, url, video_id, prefix=first_bytes)
2319
2320 self.report_extraction(video_id)
2321
2322 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2323 try:
2324 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2325 if doc.tag == 'rss':
2326 return self._extract_rss(url, video_id, doc)
2327 elif doc.tag == 'SmoothStreamingMedia':
2328 info_dict['formats'] = self._parse_ism_formats(doc, url)
2329 self._sort_formats(info_dict['formats'])
2330 return info_dict
2331 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2332 smil = self._parse_smil(doc, url, video_id)
2333 self._sort_formats(smil['formats'])
2334 return smil
2335 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2336 return self.playlist_result(
2337 self._parse_xspf(
2338 doc, video_id, xspf_url=url,
2339 xspf_base_url=compat_str(full_response.geturl())),
2340 video_id)
2341 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2342 info_dict['formats'] = self._parse_mpd_formats(
2343 doc,
2344 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2345 mpd_url=url)
2346 self._sort_formats(info_dict['formats'])
2347 return info_dict
2348 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2349 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2350 self._sort_formats(info_dict['formats'])
2351 return info_dict
2352 except compat_xml_parse_error:
2353 pass
2354
2355 # Is it a Camtasia project?
2356 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2357 if camtasia_res is not None:
2358 return camtasia_res
2359
2360 # Sometimes embedded video player is hidden behind percent encoding
2361 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2362 # Unescaping the whole page allows to handle those cases in a generic way
2363 webpage = compat_urllib_parse_unquote(webpage)
2364
2365 # it's tempting to parse this further, but you would
2366 # have to take into account all the variations like
2367 # Video Title - Site Name
2368 # Site Name | Video Title
2369 # Video Title - Tagline | Site Name
2370 # and so on and so forth; it's just not practical
2371 video_title = self._og_search_title(
2372 webpage, default=None) or self._html_search_regex(
2373 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2374 default='video')
2375
2376 # Try to detect age limit automatically
2377 age_limit = self._rta_search(webpage)
2378 # And then there are the jokers who advertise that they use RTA,
2379 # but actually don't.
2380 AGE_LIMIT_MARKERS = [
2381 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2382 ]
2383 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2384 age_limit = 18
2385
2386 # video uploader is domain name
2387 video_uploader = self._search_regex(
2388 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2389
2390 video_description = self._og_search_description(webpage, default=None)
2391 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2392
2393 info_dict.update({
2394 'title': video_title,
2395 'description': video_description,
2396 'thumbnail': video_thumbnail,
2397 'age_limit': age_limit,
2398 })
2399
2400 # Look for Brightcove Legacy Studio embeds
2401 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2402 if bc_urls:
2403 entries = [{
2404 '_type': 'url',
2405 'url': smuggle_url(bc_url, {'Referer': url}),
2406 'ie_key': 'BrightcoveLegacy'
2407 } for bc_url in bc_urls]
2408
2409 return {
2410 '_type': 'playlist',
2411 'title': video_title,
2412 'id': video_id,
2413 'entries': entries,
2414 }
2415
2416 # Look for Brightcove New Studio embeds
2417 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2418 if bc_urls:
2419 return self.playlist_from_matches(
2420 bc_urls, video_id, video_title,
2421 getter=lambda x: smuggle_url(x, {'referrer': url}),
2422 ie='BrightcoveNew')
2423
2424 # Look for Nexx embeds
2425 nexx_urls = NexxIE._extract_urls(webpage)
2426 if nexx_urls:
2427 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2428
2429 # Look for Nexx iFrame embeds
2430 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2431 if nexx_embed_urls:
2432 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2433
2434 # Look for ThePlatform embeds
2435 tp_urls = ThePlatformIE._extract_urls(webpage)
2436 if tp_urls:
2437 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2438
2439 # Look for Vessel embeds
2440 vessel_urls = VesselIE._extract_urls(webpage)
2441 if vessel_urls:
2442 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2443
2444 # Look for embedded rtl.nl player
2445 matches = re.findall(
2446 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2447 webpage)
2448 if matches:
2449 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2450
2451 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2452 if vimeo_urls:
2453 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2454
2455 vid_me_embed_url = self._search_regex(
2456 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2457 webpage, 'vid.me embed', default=None)
2458 if vid_me_embed_url is not None:
2459 return self.url_result(vid_me_embed_url, 'Vidme')
2460
2461 # Look for YouTube embeds
2462 youtube_urls = YoutubeIE._extract_urls(webpage)
2463 if youtube_urls:
2464 return self.playlist_from_matches(
2465 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2466
2467 matches = DailymotionIE._extract_urls(webpage)
2468 if matches:
2469 return self.playlist_from_matches(matches, video_id, video_title)
2470
2471 # Look for embedded Dailymotion playlist player (#3822)
2472 m = re.search(
2473 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2474 if m:
2475 playlists = re.findall(
2476 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2477 if playlists:
2478 return self.playlist_from_matches(
2479 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2480
2481 # Look for DailyMail embeds
2482 dailymail_urls = DailyMailIE._extract_urls(webpage)
2483 if dailymail_urls:
2484 return self.playlist_from_matches(
2485 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2486
2487 # Look for embedded Wistia player
2488 wistia_url = WistiaIE._extract_url(webpage)
2489 if wistia_url:
2490 return {
2491 '_type': 'url_transparent',
2492 'url': self._proto_relative_url(wistia_url),
2493 'ie_key': WistiaIE.ie_key(),
2494 'uploader': video_uploader,
2495 }
2496
2497 # Look for SVT player
2498 svt_url = SVTIE._extract_url(webpage)
2499 if svt_url:
2500 return self.url_result(svt_url, 'SVT')
2501
2502 # Look for Bandcamp pages with custom domain
2503 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2504 if mobj is not None:
2505 burl = unescapeHTML(mobj.group(1))
2506 # Don't set the extractor because it can be a track url or an album
2507 return self.url_result(burl)
2508
2509 # Look for embedded Vevo player
2510 mobj = re.search(
2511 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2512 if mobj is not None:
2513 return self.url_result(mobj.group('url'))
2514
2515 # Look for embedded Viddler player
2516 mobj = re.search(
2517 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2518 webpage)
2519 if mobj is not None:
2520 return self.url_result(mobj.group('url'))
2521
2522 # Look for NYTimes player
2523 mobj = re.search(
2524 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2525 webpage)
2526 if mobj is not None:
2527 return self.url_result(mobj.group('url'))
2528
2529 # Look for Libsyn player
2530 mobj = re.search(
2531 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'))
2534
2535 # Look for Ooyala videos
2536 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2537 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2538 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2539 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2540 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2541 if mobj is not None:
2542 embed_token = self._search_regex(
2543 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2544 webpage, 'ooyala embed token', default=None)
2545 return OoyalaIE._build_url_result(smuggle_url(
2546 mobj.group('ec'), {
2547 'domain': url,
2548 'embed_token': embed_token,
2549 }))
2550
2551 # Look for multiple Ooyala embeds on SBN network websites
2552 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2553 if mobj is not None:
2554 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2555 if embeds:
2556 return self.playlist_from_matches(
2557 embeds, video_id, video_title,
2558 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2559
2560 # Look for Aparat videos
2561 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2562 if mobj is not None:
2563 return self.url_result(mobj.group(1), 'Aparat')
2564
2565 # Look for MPORA videos
2566 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2567 if mobj is not None:
2568 return self.url_result(mobj.group(1), 'Mpora')
2569
2570 # Look for embedded NovaMov-based player
2571 mobj = re.search(
2572 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2573 (?P<url>http://(?:(?:embed|www)\.)?
2574 (?:novamov\.com|
2575 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2576 videoweed\.(?:es|com)|
2577 movshare\.(?:net|sx|ag)|
2578 divxstage\.(?:eu|net|ch|co|at|ag))
2579 /embed\.php.+?)\1''', webpage)
2580 if mobj is not None:
2581 return self.url_result(mobj.group('url'))
2582
2583 # Look for embedded Facebook player
2584 facebook_urls = FacebookIE._extract_urls(webpage)
2585 if facebook_urls:
2586 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2587
2588 # Look for embedded VK player
2589 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2590 if mobj is not None:
2591 return self.url_result(mobj.group('url'), 'VK')
2592
2593 # Look for embedded Odnoklassniki player
2594 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2595 if mobj is not None:
2596 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2597
2598 # Look for embedded ivi player
2599 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2600 if mobj is not None:
2601 return self.url_result(mobj.group('url'), 'Ivi')
2602
2603 # Look for embedded Huffington Post player
2604 mobj = re.search(
2605 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2606 if mobj is not None:
2607 return self.url_result(mobj.group('url'), 'HuffPost')
2608
2609 # Look for embed.ly
2610 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2611 if mobj is not None:
2612 return self.url_result(mobj.group('url'))
2613 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2614 if mobj is not None:
2615 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2616
2617 # Look for funnyordie embed
2618 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2619 if matches:
2620 return self.playlist_from_matches(
2621 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2622
2623 # Look for BBC iPlayer embed
2624 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2625 if matches:
2626 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2627
2628 # Look for embedded RUTV player
2629 rutv_url = RUTVIE._extract_url(webpage)
2630 if rutv_url:
2631 return self.url_result(rutv_url, 'RUTV')
2632
2633 # Look for embedded TVC player
2634 tvc_url = TVCIE._extract_url(webpage)
2635 if tvc_url:
2636 return self.url_result(tvc_url, 'TVC')
2637
2638 # Look for embedded SportBox player
2639 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2640 if sportbox_urls:
2641 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2642
2643 # Look for embedded XHamster player
2644 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2645 if xhamster_urls:
2646 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2647
2648 # Look for embedded TNAFlixNetwork player
2649 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2650 if tnaflix_urls:
2651 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2652
2653 # Look for embedded PornHub player
2654 pornhub_urls = PornHubIE._extract_urls(webpage)
2655 if pornhub_urls:
2656 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2657
2658 # Look for embedded DrTuber player
2659 drtuber_urls = DrTuberIE._extract_urls(webpage)
2660 if drtuber_urls:
2661 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2662
2663 # Look for embedded RedTube player
2664 redtube_urls = RedTubeIE._extract_urls(webpage)
2665 if redtube_urls:
2666 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2667
2668 # Look for embedded Tube8 player
2669 tube8_urls = Tube8IE._extract_urls(webpage)
2670 if tube8_urls:
2671 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2672
2673 # Look for embedded Tvigle player
2674 mobj = re.search(
2675 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2676 if mobj is not None:
2677 return self.url_result(mobj.group('url'), 'Tvigle')
2678
2679 # Look for embedded TED player
2680 mobj = re.search(
2681 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2682 if mobj is not None:
2683 return self.url_result(mobj.group('url'), 'TED')
2684
2685 # Look for embedded Ustream videos
2686 ustream_url = UstreamIE._extract_url(webpage)
2687 if ustream_url:
2688 return self.url_result(ustream_url, UstreamIE.ie_key())
2689
2690 # Look for embedded arte.tv player
2691 mobj = re.search(
2692 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2693 webpage)
2694 if mobj is not None:
2695 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2696
2697 # Look for embedded francetv player
2698 mobj = re.search(
2699 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2700 webpage)
2701 if mobj is not None:
2702 return self.url_result(mobj.group('url'))
2703
2704 # Look for embedded smotri.com player
2705 smotri_url = SmotriIE._extract_url(webpage)
2706 if smotri_url:
2707 return self.url_result(smotri_url, 'Smotri')
2708
2709 # Look for embedded Myvi.ru player
2710 myvi_url = MyviIE._extract_url(webpage)
2711 if myvi_url:
2712 return self.url_result(myvi_url)
2713
2714 # Look for embedded soundcloud player
2715 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2716 if soundcloud_urls:
2717 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2718
2719 # Look for tunein player
2720 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2721 if tunein_urls:
2722 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2723
2724 # Look for embedded mtvservices player
2725 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2726 if mtvservices_url:
2727 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2728
2729 # Look for embedded yahoo player
2730 mobj = re.search(
2731 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2732 webpage)
2733 if mobj is not None:
2734 return self.url_result(mobj.group('url'), 'Yahoo')
2735
2736 # Look for embedded sbs.com.au player
2737 mobj = re.search(
2738 r'''(?x)
2739 (?:
2740 <meta\s+property="og:video"\s+content=|
2741 <iframe[^>]+?src=
2742 )
2743 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2744 webpage)
2745 if mobj is not None:
2746 return self.url_result(mobj.group('url'), 'SBS')
2747
2748 # Look for embedded Cinchcast player
2749 mobj = re.search(
2750 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2751 webpage)
2752 if mobj is not None:
2753 return self.url_result(mobj.group('url'), 'Cinchcast')
2754
2755 mobj = re.search(
2756 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2757 webpage)
2758 if not mobj:
2759 mobj = re.search(
2760 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2761 webpage)
2762 if mobj is not None:
2763 return self.url_result(mobj.group('url'), 'MLB')
2764
2765 mobj = re.search(
2766 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2767 webpage)
2768 if mobj is not None:
2769 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2770
2771 mobj = re.search(
2772 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2773 webpage)
2774 if mobj is not None:
2775 return self.url_result(mobj.group('url'), 'Livestream')
2776
2777 # Look for Zapiks embed
2778 mobj = re.search(
2779 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2780 if mobj is not None:
2781 return self.url_result(mobj.group('url'), 'Zapiks')
2782
2783 # Look for Kaltura embeds
2784 kaltura_url = KalturaIE._extract_url(webpage)
2785 if kaltura_url:
2786 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2787
2788 # Look for EaglePlatform embeds
2789 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2790 if eagleplatform_url:
2791 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2792
2793 # Look for ClipYou (uses EaglePlatform) embeds
2794 mobj = re.search(
2795 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2796 if mobj is not None:
2797 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2798
2799 # Look for Pladform embeds
2800 pladform_url = PladformIE._extract_url(webpage)
2801 if pladform_url:
2802 return self.url_result(pladform_url)
2803
2804 # Look for Videomore embeds
2805 videomore_url = VideomoreIE._extract_url(webpage)
2806 if videomore_url:
2807 return self.url_result(videomore_url)
2808
2809 # Look for Webcaster embeds
2810 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2811 if webcaster_url:
2812 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2813
2814 # Look for Playwire embeds
2815 mobj = re.search(
2816 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2817 if mobj is not None:
2818 return self.url_result(mobj.group('url'))
2819
2820 # Look for 5min embeds
2821 mobj = re.search(
2822 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2823 if mobj is not None:
2824 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2825
2826 # Look for Crooks and Liars embeds
2827 mobj = re.search(
2828 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2829 if mobj is not None:
2830 return self.url_result(mobj.group('url'))
2831
2832 # Look for NBC Sports VPlayer embeds
2833 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2834 if nbc_sports_url:
2835 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2836
2837 # Look for NBC News embeds
2838 nbc_news_embed_url = re.search(
2839 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2840 if nbc_news_embed_url:
2841 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2842
2843 # Look for Google Drive embeds
2844 google_drive_url = GoogleDriveIE._extract_url(webpage)
2845 if google_drive_url:
2846 return self.url_result(google_drive_url, 'GoogleDrive')
2847
2848 # Look for UDN embeds
2849 mobj = re.search(
2850 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2851 if mobj is not None:
2852 return self.url_result(
2853 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2854
2855 # Look for Senate ISVP iframe
2856 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2857 if senate_isvp_url:
2858 return self.url_result(senate_isvp_url, 'SenateISVP')
2859
2860 # Look for OnionStudios embeds
2861 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2862 if onionstudios_url:
2863 return self.url_result(onionstudios_url)
2864
2865 # Look for ViewLift embeds
2866 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2867 if viewlift_url:
2868 return self.url_result(viewlift_url)
2869
2870 # Look for JWPlatform embeds
2871 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2872 if jwplatform_urls:
2873 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2874
2875 # Look for Digiteka embeds
2876 digiteka_url = DigitekaIE._extract_url(webpage)
2877 if digiteka_url:
2878 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2879
2880 # Look for Arkena embeds
2881 arkena_url = ArkenaIE._extract_url(webpage)
2882 if arkena_url:
2883 return self.url_result(arkena_url, ArkenaIE.ie_key())
2884
2885 # Look for Piksel embeds
2886 piksel_url = PikselIE._extract_url(webpage)
2887 if piksel_url:
2888 return self.url_result(piksel_url, PikselIE.ie_key())
2889
2890 # Look for Limelight embeds
2891 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2892 if limelight_urls:
2893 return self.playlist_result(
2894 limelight_urls, video_id, video_title, video_description)
2895
2896 # Look for Anvato embeds
2897 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2898 if anvato_urls:
2899 return self.playlist_result(
2900 anvato_urls, video_id, video_title, video_description)
2901
2902 # Look for AdobeTVVideo embeds
2903 mobj = re.search(
2904 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2905 webpage)
2906 if mobj is not None:
2907 return self.url_result(
2908 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2909 'AdobeTVVideo')
2910
2911 # Look for Vine embeds
2912 mobj = re.search(
2913 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2914 webpage)
2915 if mobj is not None:
2916 return self.url_result(
2917 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2918
2919 # Look for VODPlatform embeds
2920 mobj = re.search(
2921 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2922 webpage)
2923 if mobj is not None:
2924 return self.url_result(
2925 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2926
2927 # Look for Mangomolo embeds
2928 mobj = re.search(
2929 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2930 (?:
2931 video\?.*?\bid=(?P<video_id>\d+)|
2932 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2933 ).+?)\1''', webpage)
2934 if mobj is not None:
2935 info = {
2936 '_type': 'url_transparent',
2937 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2938 'title': video_title,
2939 'description': video_description,
2940 'thumbnail': video_thumbnail,
2941 'uploader': video_uploader,
2942 }
2943 video_id = mobj.group('video_id')
2944 if video_id:
2945 info.update({
2946 'ie_key': 'MangomoloVideo',
2947 'id': video_id,
2948 })
2949 else:
2950 info.update({
2951 'ie_key': 'MangomoloLive',
2952 'id': mobj.group('channel_id'),
2953 })
2954 return info
2955
2956 # Look for Instagram embeds
2957 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2958 if instagram_embed_url is not None:
2959 return self.url_result(
2960 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2961
2962 # Look for LiveLeak embeds
2963 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2964 if liveleak_urls:
2965 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2966
2967 # Look for 3Q SDN embeds
2968 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2969 if threeqsdn_url:
2970 return {
2971 '_type': 'url_transparent',
2972 'ie_key': ThreeQSDNIE.ie_key(),
2973 'url': self._proto_relative_url(threeqsdn_url),
2974 'title': video_title,
2975 'description': video_description,
2976 'thumbnail': video_thumbnail,
2977 'uploader': video_uploader,
2978 }
2979
2980 # Look for VBOX7 embeds
2981 vbox7_url = Vbox7IE._extract_url(webpage)
2982 if vbox7_url:
2983 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2984
2985 # Look for DBTV embeds
2986 dbtv_urls = DBTVIE._extract_urls(webpage)
2987 if dbtv_urls:
2988 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2989
2990 # Look for Videa embeds
2991 videa_urls = VideaIE._extract_urls(webpage)
2992 if videa_urls:
2993 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2994
2995 # Look for 20 minuten embeds
2996 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2997 if twentymin_urls:
2998 return self.playlist_from_matches(
2999 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3000
3001 # Look for Openload embeds
3002 openload_urls = OpenloadIE._extract_urls(webpage)
3003 if openload_urls:
3004 return self.playlist_from_matches(
3005 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3006
3007 # Look for VideoPress embeds
3008 videopress_urls = VideoPressIE._extract_urls(webpage)
3009 if videopress_urls:
3010 return self.playlist_from_matches(
3011 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3012
3013 # Look for Rutube embeds
3014 rutube_urls = RutubeIE._extract_urls(webpage)
3015 if rutube_urls:
3016 return self.playlist_from_matches(
3017 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3018
3019 # Look for WashingtonPost embeds
3020 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3021 if wapo_urls:
3022 return self.playlist_from_matches(
3023 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3024
3025 # Look for Mediaset embeds
3026 mediaset_urls = MediasetIE._extract_urls(webpage)
3027 if mediaset_urls:
3028 return self.playlist_from_matches(
3029 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3030
3031 # Look for JOJ.sk embeds
3032 joj_urls = JojIE._extract_urls(webpage)
3033 if joj_urls:
3034 return self.playlist_from_matches(
3035 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3036
3037 # Look for megaphone.fm embeds
3038 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3039 if mpfn_urls:
3040 return self.playlist_from_matches(
3041 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3042
3043 # Look for vzaar embeds
3044 vzaar_urls = VzaarIE._extract_urls(webpage)
3045 if vzaar_urls:
3046 return self.playlist_from_matches(
3047 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3048
3049 channel9_urls = Channel9IE._extract_urls(webpage)
3050 if channel9_urls:
3051 return self.playlist_from_matches(
3052 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3053
3054 vshare_urls = VShareIE._extract_urls(webpage)
3055 if vshare_urls:
3056 return self.playlist_from_matches(
3057 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3058
3059 # Look for Mediasite embeds
3060 mediasite_urls = MediasiteIE._extract_urls(webpage)
3061 if mediasite_urls:
3062 entries = [
3063 self.url_result(smuggle_url(
3064 compat_urlparse.urljoin(url, mediasite_url),
3065 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3066 for mediasite_url in mediasite_urls]
3067 return self.playlist_result(entries, video_id, video_title)
3068
3069 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3070 if springboardplatform_urls:
3071 return self.playlist_from_matches(
3072 springboardplatform_urls, video_id, video_title,
3073 ie=SpringboardPlatformIE.ie_key())
3074
3075 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3076 if yapfiles_urls:
3077 return self.playlist_from_matches(
3078 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3079
3080 vice_urls = ViceIE._extract_urls(webpage)
3081 if vice_urls:
3082 return self.playlist_from_matches(
3083 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3084
3085 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3086 if xfileshare_urls:
3087 return self.playlist_from_matches(
3088 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3089
3090 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3091 if cloudflarestream_urls:
3092 return self.playlist_from_matches(
3093 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3094
3095 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3096 if peertube_urls:
3097 return self.playlist_from_matches(
3098 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3099
3100 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3101 if indavideo_urls:
3102 return self.playlist_from_matches(
3103 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3104
3105 apa_urls = APAIE._extract_urls(webpage)
3106 if apa_urls:
3107 return self.playlist_from_matches(
3108 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3109
3110 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3111 if foxnews_urls:
3112 return self.playlist_from_matches(
3113 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3114
3115 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3116 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3117 webpage)]
3118 if sharevideos_urls:
3119 return self.playlist_from_matches(
3120 sharevideos_urls, video_id, video_title)
3121
3122 viqeo_urls = ViqeoIE._extract_urls(webpage)
3123 if viqeo_urls:
3124 return self.playlist_from_matches(
3125 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3126
3127 expressen_urls = ExpressenIE._extract_urls(webpage)
3128 if expressen_urls:
3129 return self.playlist_from_matches(
3130 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3131
3132 # Look for HTML5 media
3133 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3134 if entries:
3135 if len(entries) == 1:
3136 entries[0].update({
3137 'id': video_id,
3138 'title': video_title,
3139 })
3140 else:
3141 for num, entry in enumerate(entries, start=1):
3142 entry.update({
3143 'id': '%s-%s' % (video_id, num),
3144 'title': '%s (%d)' % (video_title, num),
3145 })
3146 for entry in entries:
3147 self._sort_formats(entry['formats'])
3148 return self.playlist_result(entries, video_id, video_title)
3149
3150 jwplayer_data = self._find_jwplayer_data(
3151 webpage, video_id, transform_source=js_to_json)
3152 if jwplayer_data:
3153 try:
3154 info = self._parse_jwplayer_data(
3155 jwplayer_data, video_id, require_title=False, base_url=url)
3156 return merge_dicts(info, info_dict)
3157 except ExtractorError:
3158 # See https://github.com/rg3/youtube-dl/pull/16735
3159 pass
3160
3161 # Video.js embed
3162 mobj = re.search(
3163 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3164 webpage)
3165 if mobj is not None:
3166 sources = self._parse_json(
3167 mobj.group(1), video_id, transform_source=js_to_json,
3168 fatal=False) or []
3169 if not isinstance(sources, list):
3170 sources = [sources]
3171 formats = []
3172 for source in sources:
3173 src = source.get('src')
3174 if not src or not isinstance(src, compat_str):
3175 continue
3176 src = compat_urlparse.urljoin(url, src)
3177 src_type = source.get('type')
3178 if isinstance(src_type, compat_str):
3179 src_type = src_type.lower()
3180 ext = determine_ext(src).lower()
3181 if src_type == 'video/youtube':
3182 return self.url_result(src, YoutubeIE.ie_key())
3183 if src_type == 'application/dash+xml' or ext == 'mpd':
3184 formats.extend(self._extract_mpd_formats(
3185 src, video_id, mpd_id='dash', fatal=False))
3186 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3187 formats.extend(self._extract_m3u8_formats(
3188 src, video_id, 'mp4', entry_protocol='m3u8_native',
3189 m3u8_id='hls', fatal=False))
3190 else:
3191 formats.append({
3192 'url': src,
3193 'ext': (mimetype2ext(src_type) or
3194 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3195 })
3196 if formats:
3197 self._sort_formats(formats)
3198 info_dict['formats'] = formats
3199 return info_dict
3200
3201 # Looking for http://schema.org/VideoObject
3202 json_ld = self._search_json_ld(
3203 webpage, video_id, default={}, expected_type='VideoObject')
3204 if json_ld.get('url'):
3205 return merge_dicts(json_ld, info_dict)
3206
3207 def check_video(vurl):
3208 if YoutubeIE.suitable(vurl):
3209 return True
3210 if RtmpIE.suitable(vurl):
3211 return True
3212 vpath = compat_urlparse.urlparse(vurl).path
3213 vext = determine_ext(vpath)
3214 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3215
3216 def filter_video(urls):
3217 return list(filter(check_video, urls))
3218
3219 # Start with something easy: JW Player in SWFObject
3220 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3221 if not found:
3222 # Look for gorilla-vid style embedding
3223 found = filter_video(re.findall(r'''(?sx)
3224 (?:
3225 jw_plugins|
3226 JWPlayerOptions|
3227 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3228 )
3229 .*?
3230 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3231 if not found:
3232 # Broaden the search a little bit
3233 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3234 if not found:
3235 # Broaden the findall a little bit: JWPlayer JS loader
3236 found = filter_video(re.findall(
3237 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3238 if not found:
3239 # Flow player
3240 found = filter_video(re.findall(r'''(?xs)
3241 flowplayer\("[^"]+",\s*
3242 \{[^}]+?\}\s*,
3243 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3244 ["']?url["']?\s*:\s*["']([^"']+)["']
3245 ''', webpage))
3246 if not found:
3247 # Cinerama player
3248 found = re.findall(
3249 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3250 if not found:
3251 # Try to find twitter cards info
3252 # twitter:player:stream should be checked before twitter:player since
3253 # it is expected to contain a raw stream (see
3254 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3255 found = filter_video(re.findall(
3256 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3257 if not found:
3258 # We look for Open Graph info:
3259 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3260 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3261 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3262 if m_video_type is not None:
3263 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3264 if not found:
3265 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3266 found = re.search(
3267 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3268 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3269 webpage)
3270 if not found:
3271 # Look also in Refresh HTTP header
3272 refresh_header = head_response.headers.get('Refresh')
3273 if refresh_header:
3274 # In python 2 response HTTP headers are bytestrings
3275 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3276 refresh_header = refresh_header.decode('iso-8859-1')
3277 found = re.search(REDIRECT_REGEX, refresh_header)
3278 if found:
3279 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3280 if new_url != url:
3281 self.report_following_redirect(new_url)
3282 return {
3283 '_type': 'url',
3284 'url': new_url,
3285 }
3286 else:
3287 found = None
3288
3289 if not found:
3290 # twitter:player is a https URL to iframe player that may or may not
3291 # be supported by youtube-dl thus this is checked the very last (see
3292 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3293 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3294 if embed_url and embed_url != url:
3295 return self.url_result(embed_url)
3296
3297 if not found:
3298 raise UnsupportedError(url)
3299
3300 entries = []
3301 for video_url in orderedSet(found):
3302 video_url = unescapeHTML(video_url)
3303 video_url = video_url.replace('\\/', '/')
3304 video_url = compat_urlparse.urljoin(url, video_url)
3305 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3306
3307 # Sometimes, jwplayer extraction will result in a YouTube URL
3308 if YoutubeIE.suitable(video_url):
3309 entries.append(self.url_result(video_url, 'Youtube'))
3310 continue
3311
3312 # here's a fun little line of code for you:
3313 video_id = os.path.splitext(video_id)[0]
3314
3315 entry_info_dict = {
3316 'id': video_id,
3317 'uploader': video_uploader,
3318 'title': video_title,
3319 'age_limit': age_limit,
3320 }
3321
3322 if RtmpIE.suitable(video_url):
3323 entry_info_dict.update({
3324 '_type': 'url_transparent',
3325 'ie_key': RtmpIE.ie_key(),
3326 'url': video_url,
3327 })
3328 entries.append(entry_info_dict)
3329 continue
3330
3331 ext = determine_ext(video_url)
3332 if ext == 'smil':
3333 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3334 elif ext == 'xspf':
3335 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3336 elif ext == 'm3u8':
3337 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3338 elif ext == 'mpd':
3339 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3340 elif ext == 'f4m':
3341 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3342 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3343 # Just matching .ism/manifest is not enough to be reliably sure
3344 # whether it's actually an ISM manifest or some other streaming
3345 # manifest since there are various streaming URL formats
3346 # possible (see [1]) as well as some other shenanigans like
3347 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3348 # so on.
3349 # Thus the most reasonable way to solve this is to delegate
3350 # to generic extractor in order to look into the contents of
3351 # the manifest itself.
3352 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3353 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3354 entry_info_dict = self.url_result(
3355 smuggle_url(video_url, {'to_generic': True}),
3356 GenericIE.ie_key())
3357 else:
3358 entry_info_dict['url'] = video_url
3359
3360 if entry_info_dict.get('formats'):
3361 self._sort_formats(entry_info_dict['formats'])
3362
3363 entries.append(entry_info_dict)
3364
3365 if len(entries) == 1:
3366 return entries[0]
3367 else:
3368 for num, e in enumerate(entries, start=1):
3369 # 'url' results don't have a title
3370 if e.get('title') is not None:
3371 e['title'] = '%s (%d)' % (e['title'], num)
3372 return {
3373 '_type': 'playlist',
3374 'entries': entries,
3375 }