]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
c108d4a8a4e9a31d6b931d39c8a6233e75be1b0d
[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_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 js_to_json,
24 orderedSet,
25 sanitized_Request,
26 smuggle_url,
27 unescapeHTML,
28 unified_strdate,
29 unsmuggle_url,
30 UnsupportedError,
31 xpath_text,
32 )
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
35 BrightcoveLegacyIE,
36 BrightcoveNewIE,
37 )
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
56 DailymotionIE,
57 DailymotionCloudIE,
58 )
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87 from .rutube import RutubeIE
88 from .limelight import LimelightBaseIE
89 from .anvato import AnvatoIE
90 from .washingtonpost import WashingtonPostIE
91 from .wistia import WistiaIE
92 from .mediaset import MediasetIE
93
94
95 class GenericIE(InfoExtractor):
96 IE_DESC = 'Generic downloader that works on some sites'
97 _VALID_URL = r'.*'
98 IE_NAME = 'generic'
99 _TESTS = [
100 # Direct link to a video
101 {
102 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
103 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
104 'info_dict': {
105 'id': 'trailer',
106 'ext': 'mp4',
107 'title': 'trailer',
108 'upload_date': '20100513',
109 }
110 },
111 # Direct link to media delivered compressed (until Accept-Encoding is *)
112 {
113 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
114 'md5': '128c42e68b13950268b648275386fc74',
115 'info_dict': {
116 'id': 'FictionJunction-Parallel_Hearts',
117 'ext': 'flac',
118 'title': 'FictionJunction-Parallel_Hearts',
119 'upload_date': '20140522',
120 },
121 'expected_warnings': [
122 'URL could be a direct video link, returning it as such.'
123 ],
124 'skip': 'URL invalid',
125 },
126 # Direct download with broken HEAD
127 {
128 'url': 'http://ai-radio.org:8000/radio.opus',
129 'info_dict': {
130 'id': 'radio',
131 'ext': 'opus',
132 'title': 'radio',
133 },
134 'params': {
135 'skip_download': True, # infinite live stream
136 },
137 'expected_warnings': [
138 r'501.*Not Implemented',
139 r'400.*Bad Request',
140 ],
141 },
142 # Direct link with incorrect MIME type
143 {
144 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
145 'md5': '4ccbebe5f36706d85221f204d7eb5913',
146 'info_dict': {
147 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
148 'id': '5_Lennart_Poettering_-_Systemd',
149 'ext': 'webm',
150 'title': '5_Lennart_Poettering_-_Systemd',
151 'upload_date': '20141120',
152 },
153 'expected_warnings': [
154 'URL could be a direct video link, returning it as such.'
155 ]
156 },
157 # RSS feed
158 {
159 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
160 'info_dict': {
161 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
162 'title': 'Zero Punctuation',
163 'description': 're:.*groundbreaking video review series.*'
164 },
165 'playlist_mincount': 11,
166 },
167 # RSS feed with enclosure
168 {
169 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
170 'info_dict': {
171 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
172 'ext': 'm4v',
173 'upload_date': '20150228',
174 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
175 }
176 },
177 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
178 {
179 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
180 'info_dict': {
181 'id': 'smil',
182 'ext': 'mp4',
183 'title': 'Automatics, robotics and biocybernetics',
184 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
185 'upload_date': '20130627',
186 'formats': 'mincount:16',
187 'subtitles': 'mincount:1',
188 },
189 'params': {
190 'force_generic_extractor': True,
191 'skip_download': True,
192 },
193 },
194 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
195 {
196 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
197 'info_dict': {
198 'id': 'hds',
199 'ext': 'flv',
200 'title': 'hds',
201 'formats': 'mincount:1',
202 },
203 'params': {
204 'skip_download': True,
205 },
206 },
207 # SMIL from https://www.restudy.dk/video/play/id/1637
208 {
209 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
210 'info_dict': {
211 'id': 'video_1637',
212 'ext': 'flv',
213 'title': 'video_1637',
214 'formats': 'mincount:3',
215 },
216 'params': {
217 'skip_download': True,
218 },
219 },
220 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
221 {
222 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
223 'info_dict': {
224 'id': 'smil-service',
225 'ext': 'flv',
226 'title': 'smil-service',
227 'formats': 'mincount:1',
228 },
229 'params': {
230 'skip_download': True,
231 },
232 },
233 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
234 {
235 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
236 'info_dict': {
237 'id': '4719370',
238 'ext': 'mp4',
239 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
240 'formats': 'mincount:3',
241 },
242 'params': {
243 'skip_download': True,
244 },
245 },
246 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
247 {
248 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
249 'info_dict': {
250 'id': 'mZlp2ctYIUEB',
251 'ext': 'mp4',
252 'title': 'Tikibad ontruimd wegens brand',
253 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
254 'thumbnail': r're:^https?://.*\.jpg$',
255 'duration': 33,
256 },
257 'params': {
258 'skip_download': True,
259 },
260 },
261 # MPD from http://dash-mse-test.appspot.com/media.html
262 {
263 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
264 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
265 'info_dict': {
266 'id': 'car-20120827-manifest',
267 'ext': 'mp4',
268 'title': 'car-20120827-manifest',
269 'formats': 'mincount:9',
270 'upload_date': '20130904',
271 },
272 'params': {
273 'format': 'bestvideo',
274 },
275 },
276 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
277 {
278 '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',
279 'info_dict': {
280 'id': 'content',
281 'ext': 'mp4',
282 'title': 'content',
283 'formats': 'mincount:8',
284 },
285 'params': {
286 # m3u8 downloads
287 'skip_download': True,
288 },
289 'skip': 'video gone',
290 },
291 # m3u8 served with Content-Type: text/plain
292 {
293 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
294 'info_dict': {
295 'id': 'index',
296 'ext': 'mp4',
297 'title': 'index',
298 'upload_date': '20140720',
299 'formats': 'mincount:11',
300 },
301 'params': {
302 # m3u8 downloads
303 'skip_download': True,
304 },
305 'skip': 'video gone',
306 },
307 # google redirect
308 {
309 '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',
310 'info_dict': {
311 'id': 'cmQHVoWB5FY',
312 'ext': 'mp4',
313 'upload_date': '20130224',
314 'uploader_id': 'TheVerge',
315 'description': r're:^Chris Ziegler takes a look at the\.*',
316 'uploader': 'The Verge',
317 'title': 'First Firefox OS phones side-by-side',
318 },
319 'params': {
320 'skip_download': False,
321 }
322 },
323 {
324 # redirect in Refresh HTTP header
325 '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',
326 'info_dict': {
327 'id': 'pO8h3EaFRdo',
328 'ext': 'mp4',
329 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
330 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
331 'upload_date': '20150917',
332 'uploader_id': 'brtvofficial',
333 'uploader': 'Boiler Room',
334 },
335 'params': {
336 'skip_download': False,
337 },
338 },
339 {
340 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
341 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
342 'info_dict': {
343 'id': '13601338388002',
344 'ext': 'mp4',
345 'uploader': 'www.hodiho.fr',
346 'title': 'R\u00e9gis plante sa Jeep',
347 }
348 },
349 # bandcamp page with custom domain
350 {
351 'add_ie': ['Bandcamp'],
352 'url': 'http://bronyrock.com/track/the-pony-mash',
353 'info_dict': {
354 'id': '3235767654',
355 'ext': 'mp3',
356 'title': 'The Pony Mash',
357 'uploader': 'M_Pallante',
358 },
359 'skip': 'There is a limit of 200 free downloads / month for the test song',
360 },
361 {
362 # embedded brightcove video
363 # it also tests brightcove videos that need to set the 'Referer'
364 # in the http requests
365 'add_ie': ['BrightcoveLegacy'],
366 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
367 'info_dict': {
368 'id': '2765128793001',
369 'ext': 'mp4',
370 'title': 'Le cours de bourse : lā€™analyse technique',
371 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
372 'uploader': 'BFM BUSINESS',
373 },
374 'params': {
375 'skip_download': True,
376 },
377 },
378 {
379 # embedded with itemprop embedURL and video id spelled as `idVideo`
380 'add_id': ['BrightcoveLegacy'],
381 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
382 'info_dict': {
383 'id': '5255628253001',
384 'ext': 'mp4',
385 'title': 'md5:37c519b1128915607601e75a87995fc0',
386 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
387 'uploader': 'BFM BUSINESS',
388 'uploader_id': '876450612001',
389 'timestamp': 1482255315,
390 'upload_date': '20161220',
391 },
392 'params': {
393 'skip_download': True,
394 },
395 },
396 {
397 # https://github.com/rg3/youtube-dl/issues/2253
398 'url': 'http://bcove.me/i6nfkrc3',
399 'md5': '0ba9446db037002366bab3b3eb30c88c',
400 'info_dict': {
401 'id': '3101154703001',
402 'ext': 'mp4',
403 'title': 'Still no power',
404 'uploader': 'thestar.com',
405 '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.',
406 },
407 'add_ie': ['BrightcoveLegacy'],
408 'skip': 'video gone',
409 },
410 {
411 'url': 'http://www.championat.com/video/football/v/87/87499.html',
412 'md5': 'fb973ecf6e4a78a67453647444222983',
413 'info_dict': {
414 'id': '3414141473001',
415 'ext': 'mp4',
416 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
417 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
418 'uploader': 'Championat',
419 },
420 },
421 {
422 # https://github.com/rg3/youtube-dl/issues/3541
423 'add_ie': ['BrightcoveLegacy'],
424 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
425 'info_dict': {
426 'id': '3866516442001',
427 'ext': 'mp4',
428 'title': 'Leer mij vrouwen kennen: Aflevering 1',
429 'description': 'Leer mij vrouwen kennen: Aflevering 1',
430 'uploader': 'SBS Broadcasting',
431 },
432 'skip': 'Restricted to Netherlands',
433 'params': {
434 'skip_download': True, # m3u8 download
435 },
436 },
437 {
438 # Brightcove video in <iframe>
439 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
440 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
441 'info_dict': {
442 'id': '5360463607001',
443 'ext': 'mp4',
444 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
445 '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€‚',
446 'uploader': 'United Nations',
447 'uploader_id': '1362235914001',
448 'timestamp': 1489593889,
449 'upload_date': '20170315',
450 },
451 'add_ie': ['BrightcoveLegacy'],
452 },
453 {
454 # Brightcove with alternative playerID key
455 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
456 'info_dict': {
457 'id': 'nmeth.2062_SV1',
458 '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',
459 },
460 'playlist': [{
461 'info_dict': {
462 'id': '2228375078001',
463 'ext': 'mp4',
464 'title': 'nmeth.2062-sv1',
465 'description': 'nmeth.2062-sv1',
466 'timestamp': 1363357591,
467 'upload_date': '20130315',
468 'uploader': 'Nature Publishing Group',
469 'uploader_id': '1964492299001',
470 },
471 }],
472 },
473 {
474 # Brightcove with UUID in videoPlayer
475 'url': 'http://www8.hp.com/cn/zh/home.html',
476 'info_dict': {
477 'id': '5255815316001',
478 'ext': 'mp4',
479 'title': 'Sprocket Video - China',
480 'description': 'Sprocket Video - China',
481 'uploader': 'HP-Video Gallery',
482 'timestamp': 1482263210,
483 'upload_date': '20161220',
484 'uploader_id': '1107601872001',
485 },
486 'params': {
487 'skip_download': True, # m3u8 download
488 },
489 'skip': 'video rotates...weekly?',
490 },
491 {
492 # Brightcove:new type [2].
493 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
494 'md5': '2b35148fcf48da41c9fb4591650784f3',
495 'info_dict': {
496 'id': '5348741021001',
497 'ext': 'mp4',
498 'upload_date': '20170306',
499 'uploader_id': '4191638492001',
500 'timestamp': 1488769918,
501 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
502
503 },
504 },
505 {
506 # Alternative brightcove <video> attributes
507 '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/',
508 'info_dict': {
509 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
510 '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",
511 },
512 'playlist': [{
513 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
514 'info_dict': {
515 'id': '5311302538001',
516 'ext': 'mp4',
517 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
518 '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)",
519 'timestamp': 1486321708,
520 'upload_date': '20170205',
521 'uploader_id': '800000640001',
522 },
523 'only_matching': True,
524 }],
525 },
526 {
527 # Brightcove with UUID in videoPlayer
528 'url': 'http://www8.hp.com/cn/zh/home.html',
529 'info_dict': {
530 'id': '5255815316001',
531 'ext': 'mp4',
532 'title': 'Sprocket Video - China',
533 'description': 'Sprocket Video - China',
534 'uploader': 'HP-Video Gallery',
535 'timestamp': 1482263210,
536 'upload_date': '20161220',
537 'uploader_id': '1107601872001',
538 },
539 'params': {
540 'skip_download': True, # m3u8 download
541 },
542 },
543 # ooyala video
544 {
545 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
546 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
547 'info_dict': {
548 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
549 'ext': 'mp4',
550 'title': '2cc213299525360.mov', # that's what we get
551 'duration': 238.231,
552 },
553 'add_ie': ['Ooyala'],
554 },
555 {
556 # ooyala video embedded with http://player.ooyala.com/iframe.js
557 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
558 'info_dict': {
559 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
560 'ext': 'mp4',
561 'title': '"Steve Jobs: Man in the Machine" trailer',
562 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
563 'duration': 135.427,
564 },
565 'params': {
566 'skip_download': True,
567 },
568 'skip': 'movie expired',
569 },
570 # embed.ly video
571 {
572 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
573 'info_dict': {
574 'id': '9ODmcdjQcHQ',
575 'ext': 'mp4',
576 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
577 'upload_date': '20140225',
578 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
579 'uploader': 'Tested',
580 'uploader_id': 'testedcom',
581 },
582 # No need to test YoutubeIE here
583 'params': {
584 'skip_download': True,
585 },
586 },
587 # funnyordie embed
588 {
589 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
590 'info_dict': {
591 'id': '18e820ec3f',
592 'ext': 'mp4',
593 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
594 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
595 },
596 # HEAD requests lead to endless 301, while GET is OK
597 'expected_warnings': ['301'],
598 },
599 # RUTV embed
600 {
601 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
602 'info_dict': {
603 'id': '776940',
604 'ext': 'mp4',
605 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
606 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
607 },
608 'params': {
609 # m3u8 download
610 'skip_download': True,
611 },
612 },
613 # TVC embed
614 {
615 '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/',
616 'info_dict': {
617 'id': '55304',
618 'ext': 'mp4',
619 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
620 },
621 },
622 # SportBox embed
623 {
624 'url': 'http://www.vestifinance.ru/articles/25753',
625 'info_dict': {
626 'id': '25753',
627 '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"',
628 },
629 'playlist': [{
630 'info_dict': {
631 'id': '370908',
632 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
633 'ext': 'mp4',
634 }
635 }, {
636 'info_dict': {
637 'id': '370905',
638 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
639 'ext': 'mp4',
640 }
641 }, {
642 'info_dict': {
643 'id': '370902',
644 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
645 'ext': 'mp4',
646 }
647 }],
648 'params': {
649 # m3u8 download
650 'skip_download': True,
651 },
652 },
653 # Myvi.ru embed
654 {
655 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
656 'info_dict': {
657 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
658 'ext': 'mp4',
659 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
660 'thumbnail': r're:^https?://.*\.jpg$',
661 'duration': 153,
662 }
663 },
664 # XHamster embed
665 {
666 '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',
667 'info_dict': {
668 'id': 'showthread',
669 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
670 },
671 'playlist_mincount': 7,
672 # This forum does not allow <iframe> syntaxes anymore
673 # Now HTML tags are displayed as-is
674 'skip': 'No videos on this page',
675 },
676 # Embedded TED video
677 {
678 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
679 'md5': '65fdff94098e4a607385a60c5177c638',
680 'info_dict': {
681 'id': '1969',
682 'ext': 'mp4',
683 'title': 'Hidden miracles of the natural world',
684 'uploader': 'Louie Schwartzberg',
685 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
686 }
687 },
688 # nowvideo embed hidden behind percent encoding
689 {
690 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
691 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
692 'info_dict': {
693 'id': '06e53103ca9aa',
694 'ext': 'flv',
695 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
696 'description': 'No description',
697 },
698 },
699 # arte embed
700 {
701 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
702 'md5': '7653032cbb25bf6c80d80f217055fa43',
703 'info_dict': {
704 'id': '048195-004_PLUS7-F',
705 'ext': 'flv',
706 'title': 'X:enius',
707 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
708 'upload_date': '20140320',
709 },
710 'params': {
711 'skip_download': 'Requires rtmpdump'
712 },
713 'skip': 'video gone',
714 },
715 # francetv embed
716 {
717 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
718 'info_dict': {
719 'id': 'EV_30231',
720 'ext': 'mp4',
721 'title': 'Alcaline, le concert avec Calogero',
722 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
723 'upload_date': '20150226',
724 'timestamp': 1424989860,
725 'duration': 5400,
726 },
727 'params': {
728 # m3u8 downloads
729 'skip_download': True,
730 },
731 'expected_warnings': [
732 'Forbidden'
733 ]
734 },
735 # CondƩ Nast embed
736 {
737 'url': 'http://www.wired.com/2014/04/honda-asimo/',
738 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
739 'info_dict': {
740 'id': '53501be369702d3275860000',
741 'ext': 'mp4',
742 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
743 }
744 },
745 # Dailymotion embed
746 {
747 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
748 'md5': '441aeeb82eb72c422c7f14ec533999cd',
749 'info_dict': {
750 'id': 'k2mm4bCdJ6CQ2i7c8o2',
751 'ext': 'mp4',
752 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
753 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
754 'uploader': 'Spi0n',
755 'uploader_id': 'xgditw',
756 'upload_date': '20140425',
757 'timestamp': 1398441542,
758 },
759 'add_ie': ['Dailymotion'],
760 },
761 # YouTube embed
762 {
763 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
764 'info_dict': {
765 'id': 'FXRb4ykk4S0',
766 'ext': 'mp4',
767 'title': 'The NBL Auction 2014',
768 'uploader': 'BADMINTON England',
769 'uploader_id': 'BADMINTONEvents',
770 'upload_date': '20140603',
771 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
772 },
773 'add_ie': ['Youtube'],
774 'params': {
775 'skip_download': True,
776 }
777 },
778 # MTVSercices embed
779 {
780 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
781 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
782 'info_dict': {
783 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
784 'ext': 'mp4',
785 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
786 'description': 'Two valets share their love for movie star Liam Neesons.',
787 'timestamp': 1349922600,
788 'upload_date': '20121011',
789 },
790 },
791 # YouTube embed via <data-embed-url="">
792 {
793 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
794 'info_dict': {
795 'id': '4vAffPZIT44',
796 'ext': 'mp4',
797 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
798 'uploader': 'Gameloft',
799 'uploader_id': 'gameloft',
800 'upload_date': '20140828',
801 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
802 },
803 'params': {
804 'skip_download': True,
805 }
806 },
807 # YouTube <object> embed
808 {
809 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
810 'md5': '516718101ec834f74318df76259fb3cc',
811 'info_dict': {
812 'id': 'msN87y-iEx0',
813 'ext': 'webm',
814 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
815 'upload_date': '20080526',
816 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
817 'uploader': 'Christopher Sykes',
818 'uploader_id': 'ChristopherJSykes',
819 },
820 'add_ie': ['Youtube'],
821 },
822 # Camtasia studio
823 {
824 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
825 'playlist': [{
826 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
827 'info_dict': {
828 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
829 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
830 'ext': 'flv',
831 'duration': 2235.90,
832 }
833 }, {
834 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
835 'info_dict': {
836 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
837 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
838 'ext': 'flv',
839 'duration': 2235.93,
840 }
841 }],
842 'info_dict': {
843 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
844 }
845 },
846 # Flowplayer
847 {
848 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
849 'md5': '9d65602bf31c6e20014319c7d07fba27',
850 'info_dict': {
851 'id': '5123ea6d5e5a7',
852 'ext': 'mp4',
853 'age_limit': 18,
854 'uploader': 'www.handjobhub.com',
855 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
856 }
857 },
858 # Multiple brightcove videos
859 # https://github.com/rg3/youtube-dl/issues/2283
860 {
861 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
862 'info_dict': {
863 'id': 'always-never',
864 'title': 'Always / Never - The New Yorker',
865 },
866 'playlist_count': 3,
867 'params': {
868 'extract_flat': False,
869 'skip_download': True,
870 }
871 },
872 # MLB embed
873 {
874 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
875 'md5': '96f09a37e44da40dd083e12d9a683327',
876 'info_dict': {
877 'id': '33322633',
878 'ext': 'mp4',
879 'title': 'Ump changes call to ball',
880 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
881 'duration': 48,
882 'timestamp': 1401537900,
883 'upload_date': '20140531',
884 'thumbnail': r're:^https?://.*\.jpg$',
885 },
886 },
887 # Wistia embed
888 {
889 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
890 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
891 'info_dict': {
892 'id': '6e2wtrbdaf',
893 'ext': 'mov',
894 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
895 'description': 'a Paywall Videos video from Remilon',
896 'duration': 644.072,
897 'uploader': 'study.com',
898 'timestamp': 1459678540,
899 'upload_date': '20160403',
900 'filesize': 24687186,
901 },
902 },
903 {
904 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
905 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
906 'info_dict': {
907 'id': 'uxjb0lwrcz',
908 'ext': 'mp4',
909 'title': 'Conversation about Hexagonal Rails Part 1',
910 'description': 'a Martin Fowler video from ThoughtWorks',
911 'duration': 1715.0,
912 'uploader': 'thoughtworks.wistia.com',
913 'timestamp': 1401832161,
914 'upload_date': '20140603',
915 },
916 },
917 # Wistia standard embed (async)
918 {
919 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
920 'info_dict': {
921 'id': '807fafadvk',
922 'ext': 'mp4',
923 'title': 'Drip Brennan Dunn Workshop',
924 'description': 'a JV Webinars video from getdrip-1',
925 'duration': 4986.95,
926 'timestamp': 1463607249,
927 'upload_date': '20160518',
928 },
929 'params': {
930 'skip_download': True,
931 }
932 },
933 # Soundcloud embed
934 {
935 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
936 'info_dict': {
937 'id': '174391317',
938 'ext': 'mp3',
939 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
940 'uploader': 'Sophos Security',
941 'title': 'Chet Chat 171 - Oct 29, 2014',
942 'upload_date': '20141029',
943 }
944 },
945 # Soundcloud multiple embeds
946 {
947 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
948 'info_dict': {
949 'id': '52809',
950 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
951 },
952 'playlist_mincount': 7,
953 },
954 # TuneIn station embed
955 {
956 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
957 'info_dict': {
958 'id': '204146',
959 'ext': 'mp3',
960 'title': 'CNRV',
961 'location': 'Paris, France',
962 'is_live': True,
963 },
964 'params': {
965 # Live stream
966 'skip_download': True,
967 },
968 },
969 # Livestream embed
970 {
971 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
972 'info_dict': {
973 'id': '67864563',
974 'ext': 'flv',
975 'upload_date': '20141112',
976 'title': 'Rosetta #CometLanding webcast HL 10',
977 }
978 },
979 # Another Livestream embed, without 'new.' in URL
980 {
981 'url': 'https://www.freespeech.org/',
982 'info_dict': {
983 'id': '123537347',
984 'ext': 'mp4',
985 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
986 },
987 'params': {
988 # Live stream
989 'skip_download': True,
990 },
991 },
992 # LazyYT
993 {
994 'url': 'https://skiplagged.com/',
995 'info_dict': {
996 'id': 'skiplagged',
997 'title': 'Skiplagged: The smart way to find cheap flights',
998 },
999 'playlist_mincount': 1,
1000 'add_ie': ['Youtube'],
1001 },
1002 # Cinchcast embed
1003 {
1004 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1005 'info_dict': {
1006 'id': '7141703',
1007 'ext': 'mp3',
1008 'upload_date': '20141126',
1009 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1010 }
1011 },
1012 # Cinerama player
1013 {
1014 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1015 'info_dict': {
1016 'id': '730m_DandD_1901_512k',
1017 'ext': 'mp4',
1018 'uploader': 'www.abc.net.au',
1019 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1020 }
1021 },
1022 # embedded viddler video
1023 {
1024 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1025 'info_dict': {
1026 'id': '4d03aad9',
1027 'ext': 'mp4',
1028 'uploader': 'deadspin',
1029 'title': 'WALL-TO-GORTAT',
1030 'timestamp': 1422285291,
1031 'upload_date': '20150126',
1032 },
1033 'add_ie': ['Viddler'],
1034 },
1035 # Libsyn embed
1036 {
1037 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1038 'info_dict': {
1039 'id': '3377616',
1040 'ext': 'mp3',
1041 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1042 'description': 'md5:601cb790edd05908957dae8aaa866465',
1043 'upload_date': '20150220',
1044 },
1045 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1046 },
1047 # jwplayer YouTube
1048 {
1049 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1050 'info_dict': {
1051 'id': 'Mrj4DVp2zeA',
1052 'ext': 'mp4',
1053 'upload_date': '20150212',
1054 'uploader': 'The National Archives UK',
1055 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1056 'uploader_id': 'NationalArchives08',
1057 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1058 },
1059 },
1060 # jwplayer rtmp
1061 {
1062 'url': 'http://www.suffolk.edu/sjc/',
1063 'info_dict': {
1064 'id': 'sjclive',
1065 'ext': 'flv',
1066 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1067 'uploader': 'www.suffolk.edu',
1068 },
1069 'params': {
1070 'skip_download': True,
1071 }
1072 },
1073 # Complex jwplayer
1074 {
1075 'url': 'http://www.indiedb.com/games/king-machine/videos',
1076 'info_dict': {
1077 'id': 'videos',
1078 'ext': 'mp4',
1079 'title': 'king machine trailer 1',
1080 'thumbnail': r're:^https?://.*\.jpg$',
1081 },
1082 },
1083 {
1084 # JWPlayer config passed as variable
1085 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1086 'info_dict': {
1087 'id': '3326530_hq',
1088 'ext': 'mp4',
1089 'title': 'ARIELE | Tube Cup',
1090 'uploader': 'www.txxx.com',
1091 'age_limit': 18,
1092 },
1093 'params': {
1094 'skip_download': True,
1095 }
1096 },
1097 # rtl.nl embed
1098 {
1099 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1100 'playlist_mincount': 5,
1101 'info_dict': {
1102 'id': 'aanslagen-kopenhagen',
1103 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1104 }
1105 },
1106 # Zapiks embed
1107 {
1108 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1109 'info_dict': {
1110 'id': '118046',
1111 'ext': 'mp4',
1112 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1113 }
1114 },
1115 # Kaltura embed (different embed code)
1116 {
1117 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1118 'info_dict': {
1119 'id': '1_a52wc67y',
1120 'ext': 'flv',
1121 'upload_date': '20150127',
1122 'uploader_id': 'PremierMedia',
1123 'timestamp': int,
1124 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1125 },
1126 },
1127 # Kaltura embed with single quotes
1128 {
1129 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1130 'info_dict': {
1131 'id': '0_izeg5utt',
1132 'ext': 'mp4',
1133 'title': '35871',
1134 'timestamp': 1355743100,
1135 'upload_date': '20121217',
1136 'uploader_id': 'batchUser',
1137 },
1138 'add_ie': ['Kaltura'],
1139 },
1140 {
1141 # Kaltura embedded via quoted entry_id
1142 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1143 'info_dict': {
1144 'id': '0_utuok90b',
1145 'ext': 'mp4',
1146 'title': '06_matthew_brender_raj_dutt',
1147 'timestamp': 1466638791,
1148 'upload_date': '20160622',
1149 },
1150 'add_ie': ['Kaltura'],
1151 'expected_warnings': [
1152 'Could not send HEAD request'
1153 ],
1154 'params': {
1155 'skip_download': True,
1156 }
1157 },
1158 {
1159 # Kaltura embedded, some fileExt broken (#11480)
1160 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1161 'info_dict': {
1162 'id': '1_sgtvehim',
1163 'ext': 'mp4',
1164 'title': 'Our "Standard Models" of particle physics and cosmology',
1165 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1166 'timestamp': 1321158993,
1167 'upload_date': '20111113',
1168 'uploader_id': 'kps1',
1169 },
1170 'add_ie': ['Kaltura'],
1171 },
1172 {
1173 # Kaltura iframe embed
1174 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1175 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1176 'info_dict': {
1177 'id': '0_f2cfbpwy',
1178 'ext': 'mp4',
1179 'title': 'I. M. Pei: A Centennial Celebration',
1180 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1181 'upload_date': '20170403',
1182 'uploader_id': 'batchUser',
1183 'timestamp': 1491232186,
1184 },
1185 'add_ie': ['Kaltura'],
1186 },
1187 # Eagle.Platform embed (generic URL)
1188 {
1189 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1190 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1191 'info_dict': {
1192 'id': '227304',
1193 'ext': 'mp4',
1194 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1195 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1196 'thumbnail': r're:^https?://.*\.jpg$',
1197 'duration': 87,
1198 'view_count': int,
1199 'age_limit': 0,
1200 },
1201 },
1202 # ClipYou (Eagle.Platform) embed (custom URL)
1203 {
1204 'url': 'http://muz-tv.ru/play/7129/',
1205 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1206 'info_dict': {
1207 'id': '12820',
1208 'ext': 'mp4',
1209 'title': "'O Sole Mio",
1210 'thumbnail': r're:^https?://.*\.jpg$',
1211 'duration': 216,
1212 'view_count': int,
1213 },
1214 },
1215 # Pladform embed
1216 {
1217 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1218 'info_dict': {
1219 'id': '100183293',
1220 'ext': 'mp4',
1221 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1222 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1223 'thumbnail': r're:^https?://.*\.jpg$',
1224 'duration': 694,
1225 'age_limit': 0,
1226 },
1227 },
1228 # Playwire embed
1229 {
1230 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1231 'info_dict': {
1232 'id': '3519514',
1233 'ext': 'mp4',
1234 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1235 'thumbnail': r're:^https?://.*\.png$',
1236 'duration': 45.115,
1237 },
1238 },
1239 # 5min embed
1240 {
1241 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1242 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1243 'info_dict': {
1244 'id': '518726732',
1245 'ext': 'mp4',
1246 'title': 'Facebook Creates "On This Day" | Crunch Report',
1247 },
1248 },
1249 # SVT embed
1250 {
1251 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1252 'info_dict': {
1253 'id': '2900353',
1254 'ext': 'flv',
1255 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1256 'duration': 27,
1257 'age_limit': 0,
1258 },
1259 },
1260 # Crooks and Liars embed
1261 {
1262 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1263 'info_dict': {
1264 'id': '8RUoRhRi',
1265 'ext': 'mp4',
1266 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1267 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1268 'timestamp': 1428207000,
1269 'upload_date': '20150405',
1270 'uploader': 'Heather',
1271 },
1272 },
1273 # Crooks and Liars external embed
1274 {
1275 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1276 'info_dict': {
1277 'id': 'MTE3MjUtMzQ2MzA',
1278 'ext': 'mp4',
1279 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1280 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1281 'timestamp': 1265032391,
1282 'upload_date': '20100201',
1283 'uploader': 'Heather',
1284 },
1285 },
1286 # NBC Sports vplayer embed
1287 {
1288 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1289 'info_dict': {
1290 'id': 'ln7x1qSThw4k',
1291 'ext': 'flv',
1292 'title': "PFT Live: New leader in the 'new-look' defense",
1293 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1294 'uploader': 'NBCU-SPORTS',
1295 'upload_date': '20140107',
1296 'timestamp': 1389118457,
1297 },
1298 },
1299 # NBC News embed
1300 {
1301 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1302 'md5': '1aa589c675898ae6d37a17913cf68d66',
1303 'info_dict': {
1304 'id': '701714499682',
1305 'ext': 'mp4',
1306 'title': 'PREVIEW: On Assignment: David Letterman',
1307 '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.',
1308 },
1309 },
1310 # UDN embed
1311 {
1312 'url': 'https://video.udn.com/news/300346',
1313 'md5': 'fd2060e988c326991037b9aff9df21a6',
1314 'info_dict': {
1315 'id': '300346',
1316 'ext': 'mp4',
1317 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1318 'thumbnail': r're:^https?://.*\.jpg$',
1319 },
1320 'params': {
1321 # m3u8 download
1322 'skip_download': True,
1323 },
1324 },
1325 # Ooyala embed
1326 {
1327 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1328 'info_dict': {
1329 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1330 'ext': 'mp4',
1331 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1332 'title': 'This is what separates the Excel masters from the wannabes',
1333 'duration': 191.933,
1334 },
1335 'params': {
1336 # m3u8 downloads
1337 'skip_download': True,
1338 }
1339 },
1340 # Brightcove URL in single quotes
1341 {
1342 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1343 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1344 'info_dict': {
1345 'id': '4255764656001',
1346 'ext': 'mp4',
1347 'title': 'SN Presents: Russell Martin, World Citizen',
1348 '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.',
1349 'uploader': 'Rogers Sportsnet',
1350 'uploader_id': '1704050871',
1351 'upload_date': '20150525',
1352 'timestamp': 1432570283,
1353 },
1354 },
1355 # Dailymotion Cloud video
1356 {
1357 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1358 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1359 'info_dict': {
1360 'id': 'x2uy8t3',
1361 'ext': 'mp4',
1362 'title': 'Sauvons les abeilles ! - Le dƩbat',
1363 'description': 'md5:d9082128b1c5277987825d684939ca26',
1364 'thumbnail': r're:^https?://.*\.jpe?g$',
1365 'timestamp': 1434970506,
1366 'upload_date': '20150622',
1367 'uploader': 'Public SĆ©nat',
1368 'uploader_id': 'xa9gza',
1369 }
1370 },
1371 # OnionStudios embed
1372 {
1373 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1374 'info_dict': {
1375 'id': '2855',
1376 'ext': 'mp4',
1377 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1378 'thumbnail': r're:^https?://.*\.jpe?g$',
1379 'uploader': 'ClickHole',
1380 'uploader_id': 'clickhole',
1381 }
1382 },
1383 # SnagFilms embed
1384 {
1385 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1386 'info_dict': {
1387 'id': '74849a00-85a9-11e1-9660-123139220831',
1388 'ext': 'mp4',
1389 'title': '#whilewewatch',
1390 }
1391 },
1392 # AdobeTVVideo embed
1393 {
1394 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1395 'md5': '43662b577c018ad707a63766462b1e87',
1396 'info_dict': {
1397 'id': '2456',
1398 'ext': 'mp4',
1399 'title': 'New experience with Acrobat DC',
1400 'description': 'New experience with Acrobat DC',
1401 'duration': 248.667,
1402 },
1403 },
1404 # BrightcoveInPageEmbed embed
1405 {
1406 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1407 'info_dict': {
1408 'id': '4238694884001',
1409 'ext': 'flv',
1410 'title': 'Tabletop: Dread, Last Thoughts',
1411 'description': 'Tabletop: Dread, Last Thoughts',
1412 'duration': 51690,
1413 },
1414 },
1415 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1416 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1417 {
1418 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1419 'info_dict': {
1420 'id': '4785848093001',
1421 'ext': 'mp4',
1422 'title': 'The Cardinal Pell Interview',
1423 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1424 'uploader': 'GlobeCast Australia - GlobeStream',
1425 'uploader_id': '2733773828001',
1426 'upload_date': '20160304',
1427 'timestamp': 1457083087,
1428 },
1429 'params': {
1430 # m3u8 downloads
1431 'skip_download': True,
1432 },
1433 },
1434 {
1435 # Brightcove embed with whitespace around attribute names
1436 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1437 'info_dict': {
1438 'id': '3167554373001',
1439 'ext': 'mp4',
1440 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1441 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1442 'uploader_id': '1079349493',
1443 'upload_date': '20140207',
1444 'timestamp': 1391810548,
1445 },
1446 'params': {
1447 'skip_download': True,
1448 },
1449 },
1450 # Another form of arte.tv embed
1451 {
1452 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1453 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1454 'info_dict': {
1455 'id': '030273-562_PLUS7-F',
1456 'ext': 'mp4',
1457 'title': 'ARTE Reportage - Nulle part, en France',
1458 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1459 'upload_date': '20160409',
1460 },
1461 },
1462 # LiveLeak embed
1463 {
1464 'url': 'http://www.wykop.pl/link/3088787/',
1465 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1466 'info_dict': {
1467 'id': '874_1459135191',
1468 'ext': 'mp4',
1469 'title': 'Man shows poor quality of new apartment building',
1470 'description': 'The wall is like a sand pile.',
1471 'uploader': 'Lake8737',
1472 }
1473 },
1474 # Duplicated embedded video URLs
1475 {
1476 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1477 'info_dict': {
1478 'id': '149298443_480_16c25b74_2',
1479 'ext': 'mp4',
1480 'title': 'vs. Blue Orange Spring Game',
1481 'uploader': 'www.hudl.com',
1482 },
1483 },
1484 # twitter:player:stream embed
1485 {
1486 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1487 'info_dict': {
1488 'id': 'master',
1489 'ext': 'mp4',
1490 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1491 'uploader': 'www.rtl.be',
1492 },
1493 'params': {
1494 # m3u8 downloads
1495 'skip_download': True,
1496 },
1497 },
1498 # twitter:player embed
1499 {
1500 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1501 'md5': 'a3e0df96369831de324f0778e126653c',
1502 'info_dict': {
1503 'id': '4909620399001',
1504 'ext': 'mp4',
1505 'title': 'What Do Black Holes Sound Like?',
1506 'description': 'what do black holes sound like',
1507 'upload_date': '20160524',
1508 'uploader_id': '29913724001',
1509 'timestamp': 1464107587,
1510 'uploader': 'TheAtlantic',
1511 },
1512 'add_ie': ['BrightcoveLegacy'],
1513 },
1514 # Facebook <iframe> embed
1515 {
1516 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1517 'md5': 'fbcde74f534176ecb015849146dd3aee',
1518 'info_dict': {
1519 'id': '599637780109885',
1520 'ext': 'mp4',
1521 'title': 'Facebook video #599637780109885',
1522 },
1523 },
1524 # Facebook API embed
1525 {
1526 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1527 'md5': 'a47372ee61b39a7b90287094d447d94e',
1528 'info_dict': {
1529 'id': '10153467542406923',
1530 'ext': 'mp4',
1531 'title': 'Facebook video #10153467542406923',
1532 },
1533 },
1534 # Wordpress "YouTube Video Importer" plugin
1535 {
1536 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1537 'md5': 'd16797741b560b485194eddda8121b48',
1538 'info_dict': {
1539 'id': 'HNTXWDXV9Is',
1540 'ext': 'mp4',
1541 'title': 'Blue Devils Drumline Stanford lot 2016',
1542 'upload_date': '20160627',
1543 'uploader_id': 'GENOCIDE8GENERAL10',
1544 'uploader': 'cylus cyrus',
1545 },
1546 },
1547 {
1548 # video stored on custom kaltura server
1549 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1550 'md5': '537617d06e64dfed891fa1593c4b30cc',
1551 'info_dict': {
1552 'id': '0_1iotm5bh',
1553 'ext': 'mp4',
1554 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1555 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1556 'uploader_id': 'videos.expansion@el-mundo.net',
1557 'upload_date': '20150429',
1558 'timestamp': 1430303472,
1559 },
1560 'add_ie': ['Kaltura'],
1561 },
1562 {
1563 # Non-standard Vimeo embed
1564 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1565 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1566 'info_dict': {
1567 'id': '148867247',
1568 'ext': 'mp4',
1569 'title': 'Understanding the web - Teaser',
1570 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1571 'upload_date': '20151214',
1572 'uploader': 'OpenClassrooms',
1573 'uploader_id': 'openclassrooms',
1574 },
1575 'add_ie': ['Vimeo'],
1576 },
1577 {
1578 # generic vimeo embed that requires original URL passed as Referer
1579 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1580 'only_matching': True,
1581 },
1582 {
1583 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1584 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1585 'info_dict': {
1586 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1587 'ext': 'mp4',
1588 'title': 'Big Buck Bunny',
1589 'description': 'Royalty free test video',
1590 'timestamp': 1432816365,
1591 'upload_date': '20150528',
1592 'is_live': False,
1593 },
1594 'params': {
1595 'skip_download': True,
1596 },
1597 'add_ie': [ArkenaIE.ie_key()],
1598 },
1599 {
1600 '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/',
1601 'info_dict': {
1602 'id': '1c7141f46c',
1603 'ext': 'mp4',
1604 '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',
1605 },
1606 'params': {
1607 'skip_download': True,
1608 },
1609 'add_ie': [Vbox7IE.ie_key()],
1610 },
1611 {
1612 # DBTV embeds
1613 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1614 'info_dict': {
1615 'id': '43254897',
1616 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1617 },
1618 'playlist_mincount': 3,
1619 },
1620 {
1621 # Videa embeds
1622 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1623 'info_dict': {
1624 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1625 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1626 },
1627 'playlist_mincount': 2,
1628 },
1629 {
1630 # 20 minuten embed
1631 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1632 'info_dict': {
1633 'id': '523629',
1634 'ext': 'mp4',
1635 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1636 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1637 },
1638 'params': {
1639 'skip_download': True,
1640 },
1641 'add_ie': [TwentyMinutenIE.ie_key()],
1642 },
1643 {
1644 # VideoPress embed
1645 'url': 'https://en.support.wordpress.com/videopress/',
1646 'info_dict': {
1647 'id': 'OcobLTqC',
1648 'ext': 'm4v',
1649 'title': 'IMG_5786',
1650 'timestamp': 1435711927,
1651 'upload_date': '20150701',
1652 },
1653 'params': {
1654 'skip_download': True,
1655 },
1656 'add_ie': [VideoPressIE.ie_key()],
1657 },
1658 {
1659 # Rutube embed
1660 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1661 'info_dict': {
1662 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1663 'ext': 'flv',
1664 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1665 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1666 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1667 'upload_date': '20170228',
1668 'uploader_id': '996642',
1669 },
1670 'params': {
1671 'skip_download': True,
1672 },
1673 'add_ie': [RutubeIE.ie_key()],
1674 },
1675 {
1676 # ThePlatform embedded with whitespaces in URLs
1677 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1678 'only_matching': True,
1679 },
1680 {
1681 # Senate ISVP iframe https
1682 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1683 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1684 'info_dict': {
1685 'id': 'govtaff020316',
1686 'ext': 'mp4',
1687 'title': 'Integrated Senate Video Player',
1688 },
1689 'add_ie': [SenateISVPIE.ie_key()],
1690 },
1691 {
1692 # Limelight embeds (1 channel embed + 4 media embeds)
1693 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1694 'info_dict': {
1695 'id': 'FacilitatorTraining2017',
1696 'title': 'Facilitator Training 2017',
1697 },
1698 'playlist_mincount': 5,
1699 },
1700 {
1701 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1702 'info_dict': {
1703 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1704 'title': 'Standoff with Walnut Creek murder suspect ends',
1705 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1706 },
1707 'playlist_mincount': 4,
1708 },
1709 {
1710 # WashingtonPost embed
1711 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1712 'info_dict': {
1713 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1714 'ext': 'mp4',
1715 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1716 '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.',
1717 'timestamp': 1455216756,
1718 'uploader': 'The Washington Post',
1719 'upload_date': '20160211',
1720 },
1721 'add_ie': [WashingtonPostIE.ie_key()],
1722 },
1723 {
1724 # Mediaset embed
1725 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1726 'info_dict': {
1727 'id': '720642',
1728 'ext': 'mp4',
1729 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1730 },
1731 'params': {
1732 'skip_download': True,
1733 },
1734 'add_ie': [MediasetIE.ie_key()],
1735 },
1736 # {
1737 # # TODO: find another test
1738 # # http://schema.org/VideoObject
1739 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1740 # 'md5': '888dcf08b7ea671381f00fab74692755',
1741 # 'info_dict': {
1742 # 'id': 'nyvTSJMKId',
1743 # 'ext': 'mp4',
1744 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1745 # 'description': '#love for cats.',
1746 # 'timestamp': 1461244995,
1747 # 'upload_date': '20160421',
1748 # },
1749 # 'params': {
1750 # 'force_generic_extractor': True,
1751 # },
1752 # }
1753 ]
1754
1755 def report_following_redirect(self, new_url):
1756 """Report information extraction."""
1757 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1758
1759 def _extract_rss(self, url, video_id, doc):
1760 playlist_title = doc.find('./channel/title').text
1761 playlist_desc_el = doc.find('./channel/description')
1762 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1763
1764 entries = []
1765 for it in doc.findall('./channel/item'):
1766 next_url = xpath_text(it, 'link', fatal=False)
1767 if not next_url:
1768 enclosure_nodes = it.findall('./enclosure')
1769 for e in enclosure_nodes:
1770 next_url = e.attrib.get('url')
1771 if next_url:
1772 break
1773
1774 if not next_url:
1775 continue
1776
1777 entries.append({
1778 '_type': 'url_transparent',
1779 'url': next_url,
1780 'title': it.find('title').text,
1781 })
1782
1783 return {
1784 '_type': 'playlist',
1785 'id': url,
1786 'title': playlist_title,
1787 'description': playlist_desc,
1788 'entries': entries,
1789 }
1790
1791 def _extract_camtasia(self, url, video_id, webpage):
1792 """ Returns None if no camtasia video can be found. """
1793
1794 camtasia_cfg = self._search_regex(
1795 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1796 webpage, 'camtasia configuration file', default=None)
1797 if camtasia_cfg is None:
1798 return None
1799
1800 title = self._html_search_meta('DC.title', webpage, fatal=True)
1801
1802 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1803 camtasia_cfg = self._download_xml(
1804 camtasia_url, video_id,
1805 note='Downloading camtasia configuration',
1806 errnote='Failed to download camtasia configuration')
1807 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1808
1809 entries = []
1810 for n in fileset_node.getchildren():
1811 url_n = n.find('./uri')
1812 if url_n is None:
1813 continue
1814
1815 entries.append({
1816 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1817 'title': '%s - %s' % (title, n.tag),
1818 'url': compat_urlparse.urljoin(url, url_n.text),
1819 'duration': float_or_none(n.find('./duration').text),
1820 })
1821
1822 return {
1823 '_type': 'playlist',
1824 'entries': entries,
1825 'title': title,
1826 }
1827
1828 def _real_extract(self, url):
1829 if url.startswith('//'):
1830 return {
1831 '_type': 'url',
1832 'url': self.http_scheme() + url,
1833 }
1834
1835 parsed_url = compat_urlparse.urlparse(url)
1836 if not parsed_url.scheme:
1837 default_search = self._downloader.params.get('default_search')
1838 if default_search is None:
1839 default_search = 'fixup_error'
1840
1841 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1842 if '/' in url:
1843 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1844 return self.url_result('http://' + url)
1845 elif default_search != 'fixup_error':
1846 if default_search == 'auto_warning':
1847 if re.match(r'^(?:url|URL)$', url):
1848 raise ExtractorError(
1849 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1850 expected=True)
1851 else:
1852 self._downloader.report_warning(
1853 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1854 return self.url_result('ytsearch:' + url)
1855
1856 if default_search in ('error', 'fixup_error'):
1857 raise ExtractorError(
1858 '%r is not a valid URL. '
1859 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1860 % (url, url), expected=True)
1861 else:
1862 if ':' not in default_search:
1863 default_search += ':'
1864 return self.url_result(default_search + url)
1865
1866 url, smuggled_data = unsmuggle_url(url)
1867 force_videoid = None
1868 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1869 if smuggled_data and 'force_videoid' in smuggled_data:
1870 force_videoid = smuggled_data['force_videoid']
1871 video_id = force_videoid
1872 else:
1873 video_id = self._generic_id(url)
1874
1875 self.to_screen('%s: Requesting header' % video_id)
1876
1877 head_req = HEADRequest(url)
1878 head_response = self._request_webpage(
1879 head_req, video_id,
1880 note=False, errnote='Could not send HEAD request to %s' % url,
1881 fatal=False)
1882
1883 if head_response is not False:
1884 # Check for redirect
1885 new_url = head_response.geturl()
1886 if url != new_url:
1887 self.report_following_redirect(new_url)
1888 if force_videoid:
1889 new_url = smuggle_url(
1890 new_url, {'force_videoid': force_videoid})
1891 return self.url_result(new_url)
1892
1893 full_response = None
1894 if head_response is False:
1895 request = sanitized_Request(url)
1896 request.add_header('Accept-Encoding', '*')
1897 full_response = self._request_webpage(request, video_id)
1898 head_response = full_response
1899
1900 info_dict = {
1901 'id': video_id,
1902 'title': self._generic_title(url),
1903 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1904 }
1905
1906 # Check for direct link to a video
1907 content_type = head_response.headers.get('Content-Type', '').lower()
1908 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1909 if m:
1910 format_id = m.group('format_id')
1911 if format_id.endswith('mpegurl'):
1912 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1913 elif format_id == 'f4m':
1914 formats = self._extract_f4m_formats(url, video_id)
1915 else:
1916 formats = [{
1917 'format_id': m.group('format_id'),
1918 'url': url,
1919 'vcodec': 'none' if m.group('type') == 'audio' else None
1920 }]
1921 info_dict['direct'] = True
1922 self._sort_formats(formats)
1923 info_dict['formats'] = formats
1924 return info_dict
1925
1926 if not self._downloader.params.get('test', False) and not is_intentional:
1927 force = self._downloader.params.get('force_generic_extractor', False)
1928 self._downloader.report_warning(
1929 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1930
1931 if not full_response:
1932 request = sanitized_Request(url)
1933 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1934 # making it impossible to download only chunk of the file (yet we need only 512kB to
1935 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1936 # that will always result in downloading the whole file that is not desirable.
1937 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1938 # to accept raw bytes and being able to download only a chunk.
1939 # It may probably better to solve this by checking Content-Type for application/octet-stream
1940 # after HEAD request finishes, but not sure if we can rely on this.
1941 request.add_header('Accept-Encoding', '*')
1942 full_response = self._request_webpage(request, video_id)
1943
1944 first_bytes = full_response.read(512)
1945
1946 # Is it an M3U playlist?
1947 if first_bytes.startswith(b'#EXTM3U'):
1948 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1949 self._sort_formats(info_dict['formats'])
1950 return info_dict
1951
1952 # Maybe it's a direct link to a video?
1953 # Be careful not to download the whole thing!
1954 if not is_html(first_bytes):
1955 self._downloader.report_warning(
1956 'URL could be a direct video link, returning it as such.')
1957 info_dict.update({
1958 'direct': True,
1959 'url': url,
1960 })
1961 return info_dict
1962
1963 webpage = self._webpage_read_content(
1964 full_response, url, video_id, prefix=first_bytes)
1965
1966 self.report_extraction(video_id)
1967
1968 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1969 try:
1970 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1971 if doc.tag == 'rss':
1972 return self._extract_rss(url, video_id, doc)
1973 elif doc.tag == 'SmoothStreamingMedia':
1974 info_dict['formats'] = self._parse_ism_formats(doc, url)
1975 self._sort_formats(info_dict['formats'])
1976 return info_dict
1977 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1978 smil = self._parse_smil(doc, url, video_id)
1979 self._sort_formats(smil['formats'])
1980 return smil
1981 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1982 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1983 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1984 info_dict['formats'] = self._parse_mpd_formats(
1985 doc, video_id,
1986 mpd_base_url=full_response.geturl().rpartition('/')[0],
1987 mpd_url=url)
1988 self._sort_formats(info_dict['formats'])
1989 return info_dict
1990 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1991 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1992 self._sort_formats(info_dict['formats'])
1993 return info_dict
1994 except compat_xml_parse_error:
1995 pass
1996
1997 # Is it a Camtasia project?
1998 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1999 if camtasia_res is not None:
2000 return camtasia_res
2001
2002 # Sometimes embedded video player is hidden behind percent encoding
2003 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2004 # Unescaping the whole page allows to handle those cases in a generic way
2005 webpage = compat_urllib_parse_unquote(webpage)
2006
2007 # it's tempting to parse this further, but you would
2008 # have to take into account all the variations like
2009 # Video Title - Site Name
2010 # Site Name | Video Title
2011 # Video Title - Tagline | Site Name
2012 # and so on and so forth; it's just not practical
2013 video_title = self._og_search_title(
2014 webpage, default=None) or self._html_search_regex(
2015 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2016 default='video')
2017
2018 # Try to detect age limit automatically
2019 age_limit = self._rta_search(webpage)
2020 # And then there are the jokers who advertise that they use RTA,
2021 # but actually don't.
2022 AGE_LIMIT_MARKERS = [
2023 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2024 ]
2025 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2026 age_limit = 18
2027
2028 # video uploader is domain name
2029 video_uploader = self._search_regex(
2030 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2031
2032 video_description = self._og_search_description(webpage, default=None)
2033 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2034
2035 # Look for Brightcove Legacy Studio embeds
2036 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2037 if bc_urls:
2038 entries = [{
2039 '_type': 'url',
2040 'url': smuggle_url(bc_url, {'Referer': url}),
2041 'ie_key': 'BrightcoveLegacy'
2042 } for bc_url in bc_urls]
2043
2044 return {
2045 '_type': 'playlist',
2046 'title': video_title,
2047 'id': video_id,
2048 'entries': entries,
2049 }
2050
2051 # Look for Brightcove New Studio embeds
2052 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2053 if bc_urls:
2054 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2055
2056 # Look for ThePlatform embeds
2057 tp_urls = ThePlatformIE._extract_urls(webpage)
2058 if tp_urls:
2059 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2060
2061 # Look for Vessel embeds
2062 vessel_urls = VesselIE._extract_urls(webpage)
2063 if vessel_urls:
2064 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2065
2066 # Look for embedded rtl.nl player
2067 matches = re.findall(
2068 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2069 webpage)
2070 if matches:
2071 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2072
2073 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2074 if vimeo_urls:
2075 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2076
2077 vid_me_embed_url = self._search_regex(
2078 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2079 webpage, 'vid.me embed', default=None)
2080 if vid_me_embed_url is not None:
2081 return self.url_result(vid_me_embed_url, 'Vidme')
2082
2083 # Look for embedded YouTube player
2084 matches = re.findall(r'''(?x)
2085 (?:
2086 <iframe[^>]+?src=|
2087 data-video-url=|
2088 <embed[^>]+?src=|
2089 embedSWF\(?:\s*|
2090 <object[^>]+data=|
2091 new\s+SWFObject\(
2092 )
2093 (["\'])
2094 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2095 (?:embed|v|p)/.+?)
2096 \1''', webpage)
2097 if matches:
2098 return self.playlist_from_matches(
2099 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2100
2101 # Look for lazyYT YouTube embed
2102 matches = re.findall(
2103 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2104 if matches:
2105 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2106
2107 # Look for Wordpress "YouTube Video Importer" plugin
2108 matches = re.findall(r'''(?x)<div[^>]+
2109 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2110 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2111 if matches:
2112 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2113
2114 matches = DailymotionIE._extract_urls(webpage)
2115 if matches:
2116 return self.playlist_from_matches(matches, video_id, video_title)
2117
2118 # Look for embedded Dailymotion playlist player (#3822)
2119 m = re.search(
2120 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2121 if m:
2122 playlists = re.findall(
2123 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2124 if playlists:
2125 return self.playlist_from_matches(
2126 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2127
2128 # Look for embedded Wistia player
2129 wistia_url = WistiaIE._extract_url(webpage)
2130 if wistia_url:
2131 return {
2132 '_type': 'url_transparent',
2133 'url': self._proto_relative_url(wistia_url),
2134 'ie_key': WistiaIE.ie_key(),
2135 'uploader': video_uploader,
2136 }
2137
2138 # Look for SVT player
2139 svt_url = SVTIE._extract_url(webpage)
2140 if svt_url:
2141 return self.url_result(svt_url, 'SVT')
2142
2143 # Look for Bandcamp pages with custom domain
2144 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2145 if mobj is not None:
2146 burl = unescapeHTML(mobj.group(1))
2147 # Don't set the extractor because it can be a track url or an album
2148 return self.url_result(burl)
2149
2150 # Look for embedded Vevo player
2151 mobj = re.search(
2152 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2153 if mobj is not None:
2154 return self.url_result(mobj.group('url'))
2155
2156 # Look for embedded Viddler player
2157 mobj = re.search(
2158 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2159 webpage)
2160 if mobj is not None:
2161 return self.url_result(mobj.group('url'))
2162
2163 # Look for NYTimes player
2164 mobj = re.search(
2165 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2166 webpage)
2167 if mobj is not None:
2168 return self.url_result(mobj.group('url'))
2169
2170 # Look for Libsyn player
2171 mobj = re.search(
2172 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2173 if mobj is not None:
2174 return self.url_result(mobj.group('url'))
2175
2176 # Look for Ooyala videos
2177 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2178 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2179 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2180 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2181 if mobj is not None:
2182 embed_token = self._search_regex(
2183 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2184 webpage, 'ooyala embed token', default=None)
2185 return OoyalaIE._build_url_result(smuggle_url(
2186 mobj.group('ec'), {
2187 'domain': url,
2188 'embed_token': embed_token,
2189 }))
2190
2191 # Look for multiple Ooyala embeds on SBN network websites
2192 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2193 if mobj is not None:
2194 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2195 if embeds:
2196 return self.playlist_from_matches(
2197 embeds, video_id, video_title,
2198 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2199
2200 # Look for Aparat videos
2201 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2202 if mobj is not None:
2203 return self.url_result(mobj.group(1), 'Aparat')
2204
2205 # Look for MPORA videos
2206 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2207 if mobj is not None:
2208 return self.url_result(mobj.group(1), 'Mpora')
2209
2210 # Look for embedded NovaMov-based player
2211 mobj = re.search(
2212 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2213 (?P<url>http://(?:(?:embed|www)\.)?
2214 (?:novamov\.com|
2215 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2216 videoweed\.(?:es|com)|
2217 movshare\.(?:net|sx|ag)|
2218 divxstage\.(?:eu|net|ch|co|at|ag))
2219 /embed\.php.+?)\1''', webpage)
2220 if mobj is not None:
2221 return self.url_result(mobj.group('url'))
2222
2223 # Look for embedded Facebook player
2224 facebook_url = FacebookIE._extract_url(webpage)
2225 if facebook_url is not None:
2226 return self.url_result(facebook_url, 'Facebook')
2227
2228 # Look for embedded VK player
2229 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2230 if mobj is not None:
2231 return self.url_result(mobj.group('url'), 'VK')
2232
2233 # Look for embedded Odnoklassniki player
2234 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2235 if mobj is not None:
2236 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2237
2238 # Look for embedded ivi player
2239 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2240 if mobj is not None:
2241 return self.url_result(mobj.group('url'), 'Ivi')
2242
2243 # Look for embedded Huffington Post player
2244 mobj = re.search(
2245 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2246 if mobj is not None:
2247 return self.url_result(mobj.group('url'), 'HuffPost')
2248
2249 # Look for embed.ly
2250 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2251 if mobj is not None:
2252 return self.url_result(mobj.group('url'))
2253 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2254 if mobj is not None:
2255 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2256
2257 # Look for funnyordie embed
2258 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2259 if matches:
2260 return self.playlist_from_matches(
2261 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2262
2263 # Look for BBC iPlayer embed
2264 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2265 if matches:
2266 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2267
2268 # Look for embedded RUTV player
2269 rutv_url = RUTVIE._extract_url(webpage)
2270 if rutv_url:
2271 return self.url_result(rutv_url, 'RUTV')
2272
2273 # Look for embedded TVC player
2274 tvc_url = TVCIE._extract_url(webpage)
2275 if tvc_url:
2276 return self.url_result(tvc_url, 'TVC')
2277
2278 # Look for embedded SportBox player
2279 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2280 if sportbox_urls:
2281 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2282
2283 # Look for embedded XHamster player
2284 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2285 if xhamster_urls:
2286 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2287
2288 # Look for embedded TNAFlixNetwork player
2289 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2290 if tnaflix_urls:
2291 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2292
2293 # Look for embedded PornHub player
2294 pornhub_urls = PornHubIE._extract_urls(webpage)
2295 if pornhub_urls:
2296 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2297
2298 # Look for embedded DrTuber player
2299 drtuber_urls = DrTuberIE._extract_urls(webpage)
2300 if drtuber_urls:
2301 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2302
2303 # Look for embedded RedTube player
2304 redtube_urls = RedTubeIE._extract_urls(webpage)
2305 if redtube_urls:
2306 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2307
2308 # Look for embedded Tvigle player
2309 mobj = re.search(
2310 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2311 if mobj is not None:
2312 return self.url_result(mobj.group('url'), 'Tvigle')
2313
2314 # Look for embedded TED player
2315 mobj = re.search(
2316 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2317 if mobj is not None:
2318 return self.url_result(mobj.group('url'), 'TED')
2319
2320 # Look for embedded Ustream videos
2321 ustream_url = UstreamIE._extract_url(webpage)
2322 if ustream_url:
2323 return self.url_result(ustream_url, UstreamIE.ie_key())
2324
2325 # Look for embedded arte.tv player
2326 mobj = re.search(
2327 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2328 webpage)
2329 if mobj is not None:
2330 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2331
2332 # Look for embedded francetv player
2333 mobj = re.search(
2334 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2335 webpage)
2336 if mobj is not None:
2337 return self.url_result(mobj.group('url'))
2338
2339 # Look for embedded smotri.com player
2340 smotri_url = SmotriIE._extract_url(webpage)
2341 if smotri_url:
2342 return self.url_result(smotri_url, 'Smotri')
2343
2344 # Look for embedded Myvi.ru player
2345 myvi_url = MyviIE._extract_url(webpage)
2346 if myvi_url:
2347 return self.url_result(myvi_url)
2348
2349 # Look for embedded soundcloud player
2350 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2351 if soundcloud_urls:
2352 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2353
2354 # Look for tunein player
2355 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2356 if tunein_urls:
2357 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2358
2359 # Look for embedded mtvservices player
2360 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2361 if mtvservices_url:
2362 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2363
2364 # Look for embedded yahoo player
2365 mobj = re.search(
2366 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2367 webpage)
2368 if mobj is not None:
2369 return self.url_result(mobj.group('url'), 'Yahoo')
2370
2371 # Look for embedded sbs.com.au player
2372 mobj = re.search(
2373 r'''(?x)
2374 (?:
2375 <meta\s+property="og:video"\s+content=|
2376 <iframe[^>]+?src=
2377 )
2378 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2379 webpage)
2380 if mobj is not None:
2381 return self.url_result(mobj.group('url'), 'SBS')
2382
2383 # Look for embedded Cinchcast player
2384 mobj = re.search(
2385 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2386 webpage)
2387 if mobj is not None:
2388 return self.url_result(mobj.group('url'), 'Cinchcast')
2389
2390 mobj = re.search(
2391 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2392 webpage)
2393 if not mobj:
2394 mobj = re.search(
2395 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2396 webpage)
2397 if mobj is not None:
2398 return self.url_result(mobj.group('url'), 'MLB')
2399
2400 mobj = re.search(
2401 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2402 webpage)
2403 if mobj is not None:
2404 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2405
2406 mobj = re.search(
2407 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2408 webpage)
2409 if mobj is not None:
2410 return self.url_result(mobj.group('url'), 'Livestream')
2411
2412 # Look for Zapiks embed
2413 mobj = re.search(
2414 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2415 if mobj is not None:
2416 return self.url_result(mobj.group('url'), 'Zapiks')
2417
2418 # Look for Kaltura embeds
2419 kaltura_url = KalturaIE._extract_url(webpage)
2420 if kaltura_url:
2421 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2422
2423 # Look for Eagle.Platform embeds
2424 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2425 if eagleplatform_url:
2426 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2427
2428 # Look for ClipYou (uses Eagle.Platform) embeds
2429 mobj = re.search(
2430 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2431 if mobj is not None:
2432 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2433
2434 # Look for Pladform embeds
2435 pladform_url = PladformIE._extract_url(webpage)
2436 if pladform_url:
2437 return self.url_result(pladform_url)
2438
2439 # Look for Videomore embeds
2440 videomore_url = VideomoreIE._extract_url(webpage)
2441 if videomore_url:
2442 return self.url_result(videomore_url)
2443
2444 # Look for Webcaster embeds
2445 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2446 if webcaster_url:
2447 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2448
2449 # Look for Playwire embeds
2450 mobj = re.search(
2451 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2452 if mobj is not None:
2453 return self.url_result(mobj.group('url'))
2454
2455 # Look for 5min embeds
2456 mobj = re.search(
2457 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2458 if mobj is not None:
2459 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2460
2461 # Look for Crooks and Liars embeds
2462 mobj = re.search(
2463 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2464 if mobj is not None:
2465 return self.url_result(mobj.group('url'))
2466
2467 # Look for NBC Sports VPlayer embeds
2468 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2469 if nbc_sports_url:
2470 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2471
2472 # Look for NBC News embeds
2473 nbc_news_embed_url = re.search(
2474 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2475 if nbc_news_embed_url:
2476 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2477
2478 # Look for Google Drive embeds
2479 google_drive_url = GoogleDriveIE._extract_url(webpage)
2480 if google_drive_url:
2481 return self.url_result(google_drive_url, 'GoogleDrive')
2482
2483 # Look for UDN embeds
2484 mobj = re.search(
2485 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2486 if mobj is not None:
2487 return self.url_result(
2488 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2489
2490 # Look for Senate ISVP iframe
2491 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2492 if senate_isvp_url:
2493 return self.url_result(senate_isvp_url, 'SenateISVP')
2494
2495 # Look for Dailymotion Cloud videos
2496 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2497 if dmcloud_url:
2498 return self.url_result(dmcloud_url, 'DailymotionCloud')
2499
2500 # Look for OnionStudios embeds
2501 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2502 if onionstudios_url:
2503 return self.url_result(onionstudios_url)
2504
2505 # Look for ViewLift embeds
2506 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2507 if viewlift_url:
2508 return self.url_result(viewlift_url)
2509
2510 # Look for JWPlatform embeds
2511 jwplatform_url = JWPlatformIE._extract_url(webpage)
2512 if jwplatform_url:
2513 return self.url_result(jwplatform_url, 'JWPlatform')
2514
2515 # Look for Digiteka embeds
2516 digiteka_url = DigitekaIE._extract_url(webpage)
2517 if digiteka_url:
2518 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2519
2520 # Look for Arkena embeds
2521 arkena_url = ArkenaIE._extract_url(webpage)
2522 if arkena_url:
2523 return self.url_result(arkena_url, ArkenaIE.ie_key())
2524
2525 # Look for Piksel embeds
2526 piksel_url = PikselIE._extract_url(webpage)
2527 if piksel_url:
2528 return self.url_result(piksel_url, PikselIE.ie_key())
2529
2530 # Look for Limelight embeds
2531 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2532 if limelight_urls:
2533 return self.playlist_result(
2534 limelight_urls, video_id, video_title, video_description)
2535
2536 # Look for Anvato embeds
2537 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2538 if anvato_urls:
2539 return self.playlist_result(
2540 anvato_urls, video_id, video_title, video_description)
2541
2542 # Look for AdobeTVVideo embeds
2543 mobj = re.search(
2544 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2545 webpage)
2546 if mobj is not None:
2547 return self.url_result(
2548 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2549 'AdobeTVVideo')
2550
2551 # Look for Vine embeds
2552 mobj = re.search(
2553 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2554 webpage)
2555 if mobj is not None:
2556 return self.url_result(
2557 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2558
2559 # Look for VODPlatform embeds
2560 mobj = re.search(
2561 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2562 webpage)
2563 if mobj is not None:
2564 return self.url_result(
2565 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2566
2567 # Look for Mangomolo embeds
2568 mobj = re.search(
2569 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2570 (?:
2571 video\?.*?\bid=(?P<video_id>\d+)|
2572 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2573 ).+?)\1''', webpage)
2574 if mobj is not None:
2575 info = {
2576 '_type': 'url_transparent',
2577 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2578 'title': video_title,
2579 'description': video_description,
2580 'thumbnail': video_thumbnail,
2581 'uploader': video_uploader,
2582 }
2583 video_id = mobj.group('video_id')
2584 if video_id:
2585 info.update({
2586 'ie_key': 'MangomoloVideo',
2587 'id': video_id,
2588 })
2589 else:
2590 info.update({
2591 'ie_key': 'MangomoloLive',
2592 'id': mobj.group('channel_id'),
2593 })
2594 return info
2595
2596 # Look for Instagram embeds
2597 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2598 if instagram_embed_url is not None:
2599 return self.url_result(
2600 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2601
2602 # Look for LiveLeak embeds
2603 liveleak_url = LiveLeakIE._extract_url(webpage)
2604 if liveleak_url:
2605 return self.url_result(liveleak_url, 'LiveLeak')
2606
2607 # Look for 3Q SDN embeds
2608 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2609 if threeqsdn_url:
2610 return {
2611 '_type': 'url_transparent',
2612 'ie_key': ThreeQSDNIE.ie_key(),
2613 'url': self._proto_relative_url(threeqsdn_url),
2614 'title': video_title,
2615 'description': video_description,
2616 'thumbnail': video_thumbnail,
2617 'uploader': video_uploader,
2618 }
2619
2620 # Look for VBOX7 embeds
2621 vbox7_url = Vbox7IE._extract_url(webpage)
2622 if vbox7_url:
2623 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2624
2625 # Look for DBTV embeds
2626 dbtv_urls = DBTVIE._extract_urls(webpage)
2627 if dbtv_urls:
2628 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2629
2630 # Look for Videa embeds
2631 videa_urls = VideaIE._extract_urls(webpage)
2632 if videa_urls:
2633 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2634
2635 # Look for 20 minuten embeds
2636 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2637 if twentymin_urls:
2638 return self.playlist_from_matches(
2639 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2640
2641 # Look for Openload embeds
2642 openload_urls = OpenloadIE._extract_urls(webpage)
2643 if openload_urls:
2644 return self.playlist_from_matches(
2645 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2646
2647 # Look for VideoPress embeds
2648 videopress_urls = VideoPressIE._extract_urls(webpage)
2649 if videopress_urls:
2650 return self.playlist_from_matches(
2651 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2652
2653 # Look for Rutube embeds
2654 rutube_urls = RutubeIE._extract_urls(webpage)
2655 if rutube_urls:
2656 return self.playlist_from_matches(
2657 rutube_urls, ie=RutubeIE.ie_key())
2658
2659 # Look for WashingtonPost embeds
2660 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2661 if wapo_urls:
2662 return self.playlist_from_matches(
2663 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2664
2665 # Look for Mediaset embeds
2666 mediaset_urls = MediasetIE._extract_urls(webpage)
2667 if mediaset_urls:
2668 return self.playlist_from_matches(
2669 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2670
2671 # Looking for http://schema.org/VideoObject
2672 json_ld = self._search_json_ld(
2673 webpage, video_id, default={}, expected_type='VideoObject')
2674 if json_ld.get('url'):
2675 info_dict.update({
2676 'title': video_title or info_dict['title'],
2677 'description': video_description,
2678 'thumbnail': video_thumbnail,
2679 'age_limit': age_limit
2680 })
2681 info_dict.update(json_ld)
2682 return info_dict
2683
2684 # Look for HTML5 media
2685 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2686 if entries:
2687 for entry in entries:
2688 entry.update({
2689 'id': video_id,
2690 'title': video_title,
2691 })
2692 self._sort_formats(entry['formats'])
2693 return self.playlist_result(entries)
2694
2695 jwplayer_data = self._find_jwplayer_data(
2696 webpage, video_id, transform_source=js_to_json)
2697 if jwplayer_data:
2698 info = self._parse_jwplayer_data(
2699 jwplayer_data, video_id, require_title=False, base_url=url)
2700 if not info.get('title'):
2701 info['title'] = video_title
2702 return info
2703
2704 def check_video(vurl):
2705 if YoutubeIE.suitable(vurl):
2706 return True
2707 if RtmpIE.suitable(vurl):
2708 return True
2709 vpath = compat_urlparse.urlparse(vurl).path
2710 vext = determine_ext(vpath)
2711 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2712
2713 def filter_video(urls):
2714 return list(filter(check_video, urls))
2715
2716 # Start with something easy: JW Player in SWFObject
2717 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2718 if not found:
2719 # Look for gorilla-vid style embedding
2720 found = filter_video(re.findall(r'''(?sx)
2721 (?:
2722 jw_plugins|
2723 JWPlayerOptions|
2724 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2725 )
2726 .*?
2727 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2728 if not found:
2729 # Broaden the search a little bit
2730 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2731 if not found:
2732 # Broaden the findall a little bit: JWPlayer JS loader
2733 found = filter_video(re.findall(
2734 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2735 if not found:
2736 # Flow player
2737 found = filter_video(re.findall(r'''(?xs)
2738 flowplayer\("[^"]+",\s*
2739 \{[^}]+?\}\s*,
2740 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2741 ["']?url["']?\s*:\s*["']([^"']+)["']
2742 ''', webpage))
2743 if not found:
2744 # Cinerama player
2745 found = re.findall(
2746 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2747 if not found:
2748 # Try to find twitter cards info
2749 # twitter:player:stream should be checked before twitter:player since
2750 # it is expected to contain a raw stream (see
2751 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2752 found = filter_video(re.findall(
2753 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2754 if not found:
2755 # We look for Open Graph info:
2756 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2757 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2758 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2759 if m_video_type is not None:
2760 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2761 if not found:
2762 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2763 found = re.search(
2764 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2765 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2766 webpage)
2767 if not found:
2768 # Look also in Refresh HTTP header
2769 refresh_header = head_response.headers.get('Refresh')
2770 if refresh_header:
2771 # In python 2 response HTTP headers are bytestrings
2772 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2773 refresh_header = refresh_header.decode('iso-8859-1')
2774 found = re.search(REDIRECT_REGEX, refresh_header)
2775 if found:
2776 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2777 if new_url != url:
2778 self.report_following_redirect(new_url)
2779 return {
2780 '_type': 'url',
2781 'url': new_url,
2782 }
2783 else:
2784 found = None
2785
2786 if not found:
2787 # twitter:player is a https URL to iframe player that may or may not
2788 # be supported by youtube-dl thus this is checked the very last (see
2789 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2790 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2791 if embed_url:
2792 return self.url_result(embed_url)
2793
2794 if not found:
2795 raise UnsupportedError(url)
2796
2797 entries = []
2798 for video_url in orderedSet(found):
2799 video_url = unescapeHTML(video_url)
2800 video_url = video_url.replace('\\/', '/')
2801 video_url = compat_urlparse.urljoin(url, video_url)
2802 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2803
2804 # Sometimes, jwplayer extraction will result in a YouTube URL
2805 if YoutubeIE.suitable(video_url):
2806 entries.append(self.url_result(video_url, 'Youtube'))
2807 continue
2808
2809 # here's a fun little line of code for you:
2810 video_id = os.path.splitext(video_id)[0]
2811
2812 entry_info_dict = {
2813 'id': video_id,
2814 'uploader': video_uploader,
2815 'title': video_title,
2816 'age_limit': age_limit,
2817 }
2818
2819 if RtmpIE.suitable(video_url):
2820 entry_info_dict.update({
2821 '_type': 'url_transparent',
2822 'ie_key': RtmpIE.ie_key(),
2823 'url': video_url,
2824 })
2825 entries.append(entry_info_dict)
2826 continue
2827
2828 ext = determine_ext(video_url)
2829 if ext == 'smil':
2830 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2831 elif ext == 'xspf':
2832 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2833 elif ext == 'm3u8':
2834 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2835 elif ext == 'mpd':
2836 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2837 elif ext == 'f4m':
2838 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2839 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2840 # Just matching .ism/manifest is not enough to be reliably sure
2841 # whether it's actually an ISM manifest or some other streaming
2842 # manifest since there are various streaming URL formats
2843 # possible (see [1]) as well as some other shenanigans like
2844 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2845 # so on.
2846 # Thus the most reasonable way to solve this is to delegate
2847 # to generic extractor in order to look into the contents of
2848 # the manifest itself.
2849 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2850 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2851 entry_info_dict = self.url_result(
2852 smuggle_url(video_url, {'to_generic': True}),
2853 GenericIE.ie_key())
2854 else:
2855 entry_info_dict['url'] = video_url
2856
2857 if entry_info_dict.get('formats'):
2858 self._sort_formats(entry_info_dict['formats'])
2859
2860 entries.append(entry_info_dict)
2861
2862 if len(entries) == 1:
2863 return entries[0]
2864 else:
2865 for num, e in enumerate(entries, start=1):
2866 # 'url' results don't have a title
2867 if e.get('title') is not None:
2868 e['title'] = '%s (%d)' % (e['title'], num)
2869 return {
2870 '_type': 'playlist',
2871 'entries': entries,
2872 }