]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
7d0edf09c6a2e8428b84b3e7ebf787738db1bfaa
[youtubedl] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 is_html,
24 js_to_json,
25 orderedSet,
26 sanitized_Request,
27 smuggle_url,
28 unescapeHTML,
29 unified_strdate,
30 unsmuggle_url,
31 UnsupportedError,
32 xpath_text,
33 )
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
36 BrightcoveLegacyIE,
37 BrightcoveNewIE,
38 )
39 from .nexx import (
40 NexxIE,
41 NexxEmbedIE,
42 )
43 from .nbc import NBCSportsVPlayerIE
44 from .ooyala import OoyalaIE
45 from .rutv import RUTVIE
46 from .tvc import TVCIE
47 from .sportbox import SportBoxEmbedIE
48 from .smotri import SmotriIE
49 from .myvi import MyviIE
50 from .condenast import CondeNastIE
51 from .udn import UDNEmbedIE
52 from .senateisvp import SenateISVPIE
53 from .svt import SVTIE
54 from .pornhub import PornHubIE
55 from .xhamster import XHamsterEmbedIE
56 from .tnaflix import TNAFlixNetworkEmbedIE
57 from .drtuber import DrTuberIE
58 from .redtube import RedTubeIE
59 from .vimeo import VimeoIE
60 from .dailymotion import (
61 DailymotionIE,
62 DailymotionCloudIE,
63 )
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
101 from .vzaar import VzaarIE
102
103
104 class GenericIE(InfoExtractor):
105 IE_DESC = 'Generic downloader that works on some sites'
106 _VALID_URL = r'.*'
107 IE_NAME = 'generic'
108 _TESTS = [
109 # Direct link to a video
110 {
111 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
112 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
113 'info_dict': {
114 'id': 'trailer',
115 'ext': 'mp4',
116 'title': 'trailer',
117 'upload_date': '20100513',
118 }
119 },
120 # Direct link to media delivered compressed (until Accept-Encoding is *)
121 {
122 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
123 'md5': '128c42e68b13950268b648275386fc74',
124 'info_dict': {
125 'id': 'FictionJunction-Parallel_Hearts',
126 'ext': 'flac',
127 'title': 'FictionJunction-Parallel_Hearts',
128 'upload_date': '20140522',
129 },
130 'expected_warnings': [
131 'URL could be a direct video link, returning it as such.'
132 ],
133 'skip': 'URL invalid',
134 },
135 # Direct download with broken HEAD
136 {
137 'url': 'http://ai-radio.org:8000/radio.opus',
138 'info_dict': {
139 'id': 'radio',
140 'ext': 'opus',
141 'title': 'radio',
142 },
143 'params': {
144 'skip_download': True, # infinite live stream
145 },
146 'expected_warnings': [
147 r'501.*Not Implemented',
148 r'400.*Bad Request',
149 ],
150 },
151 # Direct link with incorrect MIME type
152 {
153 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
154 'md5': '4ccbebe5f36706d85221f204d7eb5913',
155 'info_dict': {
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'id': '5_Lennart_Poettering_-_Systemd',
158 'ext': 'webm',
159 'title': '5_Lennart_Poettering_-_Systemd',
160 'upload_date': '20141120',
161 },
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
164 ]
165 },
166 # RSS feed
167 {
168 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
169 'info_dict': {
170 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'title': 'Zero Punctuation',
172 'description': 're:.*groundbreaking video review series.*'
173 },
174 'playlist_mincount': 11,
175 },
176 # RSS feed with enclosure
177 {
178 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
179 'info_dict': {
180 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
181 'ext': 'm4v',
182 'upload_date': '20150228',
183 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
184 }
185 },
186 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
187 {
188 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
189 'info_dict': {
190 'id': 'smil',
191 'ext': 'mp4',
192 'title': 'Automatics, robotics and biocybernetics',
193 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
194 'upload_date': '20130627',
195 'formats': 'mincount:16',
196 'subtitles': 'mincount:1',
197 },
198 'params': {
199 'force_generic_extractor': True,
200 'skip_download': True,
201 },
202 },
203 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
204 {
205 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
206 'info_dict': {
207 'id': 'hds',
208 'ext': 'flv',
209 'title': 'hds',
210 'formats': 'mincount:1',
211 },
212 'params': {
213 'skip_download': True,
214 },
215 },
216 # SMIL from https://www.restudy.dk/video/play/id/1637
217 {
218 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
219 'info_dict': {
220 'id': 'video_1637',
221 'ext': 'flv',
222 'title': 'video_1637',
223 'formats': 'mincount:3',
224 },
225 'params': {
226 'skip_download': True,
227 },
228 },
229 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
230 {
231 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
232 'info_dict': {
233 'id': 'smil-service',
234 'ext': 'flv',
235 'title': 'smil-service',
236 'formats': 'mincount:1',
237 },
238 'params': {
239 'skip_download': True,
240 },
241 },
242 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
243 {
244 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
245 'info_dict': {
246 'id': '4719370',
247 'ext': 'mp4',
248 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
249 'formats': 'mincount:3',
250 },
251 'params': {
252 'skip_download': True,
253 },
254 },
255 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
256 {
257 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
258 'info_dict': {
259 'id': 'mZlp2ctYIUEB',
260 'ext': 'mp4',
261 'title': 'Tikibad ontruimd wegens brand',
262 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
263 'thumbnail': r're:^https?://.*\.jpg$',
264 'duration': 33,
265 },
266 'params': {
267 'skip_download': True,
268 },
269 },
270 # MPD from http://dash-mse-test.appspot.com/media.html
271 {
272 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
273 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
274 'info_dict': {
275 'id': 'car-20120827-manifest',
276 'ext': 'mp4',
277 'title': 'car-20120827-manifest',
278 'formats': 'mincount:9',
279 'upload_date': '20130904',
280 },
281 'params': {
282 'format': 'bestvideo',
283 },
284 },
285 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
286 {
287 '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',
288 'info_dict': {
289 'id': 'content',
290 'ext': 'mp4',
291 'title': 'content',
292 'formats': 'mincount:8',
293 },
294 'params': {
295 # m3u8 downloads
296 'skip_download': True,
297 },
298 'skip': 'video gone',
299 },
300 # m3u8 served with Content-Type: text/plain
301 {
302 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
303 'info_dict': {
304 'id': 'index',
305 'ext': 'mp4',
306 'title': 'index',
307 'upload_date': '20140720',
308 'formats': 'mincount:11',
309 },
310 'params': {
311 # m3u8 downloads
312 'skip_download': True,
313 },
314 'skip': 'video gone',
315 },
316 # google redirect
317 {
318 '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',
319 'info_dict': {
320 'id': 'cmQHVoWB5FY',
321 'ext': 'mp4',
322 'upload_date': '20130224',
323 'uploader_id': 'TheVerge',
324 'description': r're:^Chris Ziegler takes a look at the\.*',
325 'uploader': 'The Verge',
326 'title': 'First Firefox OS phones side-by-side',
327 },
328 'params': {
329 'skip_download': False,
330 }
331 },
332 {
333 # redirect in Refresh HTTP header
334 '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',
335 'info_dict': {
336 'id': 'pO8h3EaFRdo',
337 'ext': 'mp4',
338 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
339 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
340 'upload_date': '20150917',
341 'uploader_id': 'brtvofficial',
342 'uploader': 'Boiler Room',
343 },
344 'params': {
345 'skip_download': False,
346 },
347 },
348 {
349 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
350 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
351 'info_dict': {
352 'id': '13601338388002',
353 'ext': 'mp4',
354 'uploader': 'www.hodiho.fr',
355 'title': 'R\u00e9gis plante sa Jeep',
356 }
357 },
358 # bandcamp page with custom domain
359 {
360 'add_ie': ['Bandcamp'],
361 'url': 'http://bronyrock.com/track/the-pony-mash',
362 'info_dict': {
363 'id': '3235767654',
364 'ext': 'mp3',
365 'title': 'The Pony Mash',
366 'uploader': 'M_Pallante',
367 },
368 'skip': 'There is a limit of 200 free downloads / month for the test song',
369 },
370 {
371 # embedded brightcove video
372 # it also tests brightcove videos that need to set the 'Referer'
373 # in the http requests
374 'add_ie': ['BrightcoveLegacy'],
375 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
376 'info_dict': {
377 'id': '2765128793001',
378 'ext': 'mp4',
379 'title': 'Le cours de bourse : lā€™analyse technique',
380 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
381 'uploader': 'BFM BUSINESS',
382 },
383 'params': {
384 'skip_download': True,
385 },
386 },
387 {
388 # embedded with itemprop embedURL and video id spelled as `idVideo`
389 'add_id': ['BrightcoveLegacy'],
390 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
391 'info_dict': {
392 'id': '5255628253001',
393 'ext': 'mp4',
394 'title': 'md5:37c519b1128915607601e75a87995fc0',
395 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
396 'uploader': 'BFM BUSINESS',
397 'uploader_id': '876450612001',
398 'timestamp': 1482255315,
399 'upload_date': '20161220',
400 },
401 'params': {
402 'skip_download': True,
403 },
404 },
405 {
406 # https://github.com/rg3/youtube-dl/issues/2253
407 'url': 'http://bcove.me/i6nfkrc3',
408 'md5': '0ba9446db037002366bab3b3eb30c88c',
409 'info_dict': {
410 'id': '3101154703001',
411 'ext': 'mp4',
412 'title': 'Still no power',
413 'uploader': 'thestar.com',
414 '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.',
415 },
416 'add_ie': ['BrightcoveLegacy'],
417 'skip': 'video gone',
418 },
419 {
420 'url': 'http://www.championat.com/video/football/v/87/87499.html',
421 'md5': 'fb973ecf6e4a78a67453647444222983',
422 'info_dict': {
423 'id': '3414141473001',
424 'ext': 'mp4',
425 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
426 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
427 'uploader': 'Championat',
428 },
429 },
430 {
431 # https://github.com/rg3/youtube-dl/issues/3541
432 'add_ie': ['BrightcoveLegacy'],
433 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
434 'info_dict': {
435 'id': '3866516442001',
436 'ext': 'mp4',
437 'title': 'Leer mij vrouwen kennen: Aflevering 1',
438 'description': 'Leer mij vrouwen kennen: Aflevering 1',
439 'uploader': 'SBS Broadcasting',
440 },
441 'skip': 'Restricted to Netherlands',
442 'params': {
443 'skip_download': True, # m3u8 download
444 },
445 },
446 {
447 # Brightcove video in <iframe>
448 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
449 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
450 'info_dict': {
451 'id': '5360463607001',
452 'ext': 'mp4',
453 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
454 '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€‚',
455 'uploader': 'United Nations',
456 'uploader_id': '1362235914001',
457 'timestamp': 1489593889,
458 'upload_date': '20170315',
459 },
460 'add_ie': ['BrightcoveLegacy'],
461 },
462 {
463 # Brightcove with alternative playerID key
464 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
465 'info_dict': {
466 'id': 'nmeth.2062_SV1',
467 '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',
468 },
469 'playlist': [{
470 'info_dict': {
471 'id': '2228375078001',
472 'ext': 'mp4',
473 'title': 'nmeth.2062-sv1',
474 'description': 'nmeth.2062-sv1',
475 'timestamp': 1363357591,
476 'upload_date': '20130315',
477 'uploader': 'Nature Publishing Group',
478 'uploader_id': '1964492299001',
479 },
480 }],
481 },
482 {
483 # Brightcove with UUID in videoPlayer
484 'url': 'http://www8.hp.com/cn/zh/home.html',
485 'info_dict': {
486 'id': '5255815316001',
487 'ext': 'mp4',
488 'title': 'Sprocket Video - China',
489 'description': 'Sprocket Video - China',
490 'uploader': 'HP-Video Gallery',
491 'timestamp': 1482263210,
492 'upload_date': '20161220',
493 'uploader_id': '1107601872001',
494 },
495 'params': {
496 'skip_download': True, # m3u8 download
497 },
498 'skip': 'video rotates...weekly?',
499 },
500 {
501 # Brightcove:new type [2].
502 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
503 'md5': '2b35148fcf48da41c9fb4591650784f3',
504 'info_dict': {
505 'id': '5348741021001',
506 'ext': 'mp4',
507 'upload_date': '20170306',
508 'uploader_id': '4191638492001',
509 'timestamp': 1488769918,
510 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
511
512 },
513 },
514 {
515 # Alternative brightcove <video> attributes
516 '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/',
517 'info_dict': {
518 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
519 '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",
520 },
521 'playlist': [{
522 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
523 'info_dict': {
524 'id': '5311302538001',
525 'ext': 'mp4',
526 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
527 '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)",
528 'timestamp': 1486321708,
529 'upload_date': '20170205',
530 'uploader_id': '800000640001',
531 },
532 'only_matching': True,
533 }],
534 },
535 {
536 # Brightcove with UUID in videoPlayer
537 'url': 'http://www8.hp.com/cn/zh/home.html',
538 'info_dict': {
539 'id': '5255815316001',
540 'ext': 'mp4',
541 'title': 'Sprocket Video - China',
542 'description': 'Sprocket Video - China',
543 'uploader': 'HP-Video Gallery',
544 'timestamp': 1482263210,
545 'upload_date': '20161220',
546 'uploader_id': '1107601872001',
547 },
548 'params': {
549 'skip_download': True, # m3u8 download
550 },
551 },
552 # ooyala video
553 {
554 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
555 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
556 'info_dict': {
557 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
558 'ext': 'mp4',
559 'title': '2cc213299525360.mov', # that's what we get
560 'duration': 238.231,
561 },
562 'add_ie': ['Ooyala'],
563 },
564 {
565 # ooyala video embedded with http://player.ooyala.com/iframe.js
566 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
567 'info_dict': {
568 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
569 'ext': 'mp4',
570 'title': '"Steve Jobs: Man in the Machine" trailer',
571 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
572 'duration': 135.427,
573 },
574 'params': {
575 'skip_download': True,
576 },
577 'skip': 'movie expired',
578 },
579 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
580 {
581 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
582 'info_dict': {
583 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
584 'ext': 'mp4',
585 'title': 'Steampunk Fest Comes to Honesdale',
586 'duration': 43.276,
587 },
588 'params': {
589 'skip_download': True,
590 }
591 },
592 # embed.ly video
593 {
594 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
595 'info_dict': {
596 'id': '9ODmcdjQcHQ',
597 'ext': 'mp4',
598 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
599 'upload_date': '20140225',
600 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
601 'uploader': 'Tested',
602 'uploader_id': 'testedcom',
603 },
604 # No need to test YoutubeIE here
605 'params': {
606 'skip_download': True,
607 },
608 },
609 # funnyordie embed
610 {
611 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
612 'info_dict': {
613 'id': '18e820ec3f',
614 'ext': 'mp4',
615 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
616 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
617 },
618 # HEAD requests lead to endless 301, while GET is OK
619 'expected_warnings': ['301'],
620 },
621 # RUTV embed
622 {
623 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
624 'info_dict': {
625 'id': '776940',
626 'ext': 'mp4',
627 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
628 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
629 },
630 'params': {
631 # m3u8 download
632 'skip_download': True,
633 },
634 },
635 # TVC embed
636 {
637 '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/',
638 'info_dict': {
639 'id': '55304',
640 'ext': 'mp4',
641 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
642 },
643 },
644 # SportBox embed
645 {
646 'url': 'http://www.vestifinance.ru/articles/25753',
647 'info_dict': {
648 'id': '25753',
649 '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"',
650 },
651 'playlist': [{
652 'info_dict': {
653 'id': '370908',
654 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
655 'ext': 'mp4',
656 }
657 }, {
658 'info_dict': {
659 'id': '370905',
660 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
661 'ext': 'mp4',
662 }
663 }, {
664 'info_dict': {
665 'id': '370902',
666 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
667 'ext': 'mp4',
668 }
669 }],
670 'params': {
671 # m3u8 download
672 'skip_download': True,
673 },
674 },
675 # Myvi.ru embed
676 {
677 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
678 'info_dict': {
679 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
680 'ext': 'mp4',
681 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
682 'thumbnail': r're:^https?://.*\.jpg$',
683 'duration': 153,
684 }
685 },
686 # XHamster embed
687 {
688 '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',
689 'info_dict': {
690 'id': 'showthread',
691 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
692 },
693 'playlist_mincount': 7,
694 # This forum does not allow <iframe> syntaxes anymore
695 # Now HTML tags are displayed as-is
696 'skip': 'No videos on this page',
697 },
698 # Embedded TED video
699 {
700 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
701 'md5': '65fdff94098e4a607385a60c5177c638',
702 'info_dict': {
703 'id': '1969',
704 'ext': 'mp4',
705 'title': 'Hidden miracles of the natural world',
706 'uploader': 'Louie Schwartzberg',
707 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
708 }
709 },
710 # nowvideo embed hidden behind percent encoding
711 {
712 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
713 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
714 'info_dict': {
715 'id': '06e53103ca9aa',
716 'ext': 'flv',
717 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
718 'description': 'No description',
719 },
720 },
721 # arte embed
722 {
723 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
724 'md5': '7653032cbb25bf6c80d80f217055fa43',
725 'info_dict': {
726 'id': '048195-004_PLUS7-F',
727 'ext': 'flv',
728 'title': 'X:enius',
729 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
730 'upload_date': '20140320',
731 },
732 'params': {
733 'skip_download': 'Requires rtmpdump'
734 },
735 'skip': 'video gone',
736 },
737 # francetv embed
738 {
739 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
740 'info_dict': {
741 'id': 'EV_30231',
742 'ext': 'mp4',
743 'title': 'Alcaline, le concert avec Calogero',
744 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
745 'upload_date': '20150226',
746 'timestamp': 1424989860,
747 'duration': 5400,
748 },
749 'params': {
750 # m3u8 downloads
751 'skip_download': True,
752 },
753 'expected_warnings': [
754 'Forbidden'
755 ]
756 },
757 # CondƩ Nast embed
758 {
759 'url': 'http://www.wired.com/2014/04/honda-asimo/',
760 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
761 'info_dict': {
762 'id': '53501be369702d3275860000',
763 'ext': 'mp4',
764 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
765 }
766 },
767 # Dailymotion embed
768 {
769 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
770 'md5': '441aeeb82eb72c422c7f14ec533999cd',
771 'info_dict': {
772 'id': 'k2mm4bCdJ6CQ2i7c8o2',
773 'ext': 'mp4',
774 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
775 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
776 'uploader': 'Spi0n',
777 'uploader_id': 'xgditw',
778 'upload_date': '20140425',
779 'timestamp': 1398441542,
780 },
781 'add_ie': ['Dailymotion'],
782 },
783 # DailyMail embed
784 {
785 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
786 'info_dict': {
787 'id': '1495629',
788 'ext': 'mp4',
789 'title': 'Care worker punches elderly dementia patient in head 11 times',
790 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
791 },
792 'add_ie': ['DailyMail'],
793 'params': {
794 'skip_download': True,
795 },
796 },
797 # YouTube embed
798 {
799 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
800 'info_dict': {
801 'id': 'FXRb4ykk4S0',
802 'ext': 'mp4',
803 'title': 'The NBL Auction 2014',
804 'uploader': 'BADMINTON England',
805 'uploader_id': 'BADMINTONEvents',
806 'upload_date': '20140603',
807 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
808 },
809 'add_ie': ['Youtube'],
810 'params': {
811 'skip_download': True,
812 }
813 },
814 # MTVSercices embed
815 {
816 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
817 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
818 'info_dict': {
819 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
820 'ext': 'mp4',
821 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
822 'description': 'Two valets share their love for movie star Liam Neesons.',
823 'timestamp': 1349922600,
824 'upload_date': '20121011',
825 },
826 },
827 # YouTube embed via <data-embed-url="">
828 {
829 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
830 'info_dict': {
831 'id': '4vAffPZIT44',
832 'ext': 'mp4',
833 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
834 'uploader': 'Gameloft',
835 'uploader_id': 'gameloft',
836 'upload_date': '20140828',
837 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
838 },
839 'params': {
840 'skip_download': True,
841 }
842 },
843 # YouTube <object> embed
844 {
845 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
846 'md5': '516718101ec834f74318df76259fb3cc',
847 'info_dict': {
848 'id': 'msN87y-iEx0',
849 'ext': 'webm',
850 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
851 'upload_date': '20080526',
852 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
853 'uploader': 'Christopher Sykes',
854 'uploader_id': 'ChristopherJSykes',
855 },
856 'add_ie': ['Youtube'],
857 },
858 # Camtasia studio
859 {
860 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
861 'playlist': [{
862 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
863 'info_dict': {
864 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
865 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
866 'ext': 'flv',
867 'duration': 2235.90,
868 }
869 }, {
870 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
871 'info_dict': {
872 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
873 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
874 'ext': 'flv',
875 'duration': 2235.93,
876 }
877 }],
878 'info_dict': {
879 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
880 }
881 },
882 # Flowplayer
883 {
884 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
885 'md5': '9d65602bf31c6e20014319c7d07fba27',
886 'info_dict': {
887 'id': '5123ea6d5e5a7',
888 'ext': 'mp4',
889 'age_limit': 18,
890 'uploader': 'www.handjobhub.com',
891 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
892 }
893 },
894 # Multiple brightcove videos
895 # https://github.com/rg3/youtube-dl/issues/2283
896 {
897 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
898 'info_dict': {
899 'id': 'always-never',
900 'title': 'Always / Never - The New Yorker',
901 },
902 'playlist_count': 3,
903 'params': {
904 'extract_flat': False,
905 'skip_download': True,
906 }
907 },
908 # MLB embed
909 {
910 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
911 'md5': '96f09a37e44da40dd083e12d9a683327',
912 'info_dict': {
913 'id': '33322633',
914 'ext': 'mp4',
915 'title': 'Ump changes call to ball',
916 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
917 'duration': 48,
918 'timestamp': 1401537900,
919 'upload_date': '20140531',
920 'thumbnail': r're:^https?://.*\.jpg$',
921 },
922 },
923 # Wistia embed
924 {
925 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
926 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
927 'info_dict': {
928 'id': '6e2wtrbdaf',
929 'ext': 'mov',
930 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
931 'description': 'a Paywall Videos video from Remilon',
932 'duration': 644.072,
933 'uploader': 'study.com',
934 'timestamp': 1459678540,
935 'upload_date': '20160403',
936 'filesize': 24687186,
937 },
938 },
939 {
940 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
941 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
942 'info_dict': {
943 'id': 'uxjb0lwrcz',
944 'ext': 'mp4',
945 'title': 'Conversation about Hexagonal Rails Part 1',
946 'description': 'a Martin Fowler video from ThoughtWorks',
947 'duration': 1715.0,
948 'uploader': 'thoughtworks.wistia.com',
949 'timestamp': 1401832161,
950 'upload_date': '20140603',
951 },
952 },
953 # Wistia standard embed (async)
954 {
955 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
956 'info_dict': {
957 'id': '807fafadvk',
958 'ext': 'mp4',
959 'title': 'Drip Brennan Dunn Workshop',
960 'description': 'a JV Webinars video from getdrip-1',
961 'duration': 4986.95,
962 'timestamp': 1463607249,
963 'upload_date': '20160518',
964 },
965 'params': {
966 'skip_download': True,
967 }
968 },
969 # Soundcloud embed
970 {
971 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
972 'info_dict': {
973 'id': '174391317',
974 'ext': 'mp3',
975 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
976 'uploader': 'Sophos Security',
977 'title': 'Chet Chat 171 - Oct 29, 2014',
978 'upload_date': '20141029',
979 }
980 },
981 # Soundcloud multiple embeds
982 {
983 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
984 'info_dict': {
985 'id': '52809',
986 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
987 },
988 'playlist_mincount': 7,
989 },
990 # TuneIn station embed
991 {
992 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
993 'info_dict': {
994 'id': '204146',
995 'ext': 'mp3',
996 'title': 'CNRV',
997 'location': 'Paris, France',
998 'is_live': True,
999 },
1000 'params': {
1001 # Live stream
1002 'skip_download': True,
1003 },
1004 },
1005 # Livestream embed
1006 {
1007 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1008 'info_dict': {
1009 'id': '67864563',
1010 'ext': 'flv',
1011 'upload_date': '20141112',
1012 'title': 'Rosetta #CometLanding webcast HL 10',
1013 }
1014 },
1015 # Another Livestream embed, without 'new.' in URL
1016 {
1017 'url': 'https://www.freespeech.org/',
1018 'info_dict': {
1019 'id': '123537347',
1020 'ext': 'mp4',
1021 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1022 },
1023 'params': {
1024 # Live stream
1025 'skip_download': True,
1026 },
1027 },
1028 # LazyYT
1029 {
1030 'url': 'https://skiplagged.com/',
1031 'info_dict': {
1032 'id': 'skiplagged',
1033 'title': 'Skiplagged: The smart way to find cheap flights',
1034 },
1035 'playlist_mincount': 1,
1036 'add_ie': ['Youtube'],
1037 },
1038 # Cinchcast embed
1039 {
1040 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1041 'info_dict': {
1042 'id': '7141703',
1043 'ext': 'mp3',
1044 'upload_date': '20141126',
1045 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1046 }
1047 },
1048 # Cinerama player
1049 {
1050 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1051 'info_dict': {
1052 'id': '730m_DandD_1901_512k',
1053 'ext': 'mp4',
1054 'uploader': 'www.abc.net.au',
1055 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1056 }
1057 },
1058 # embedded viddler video
1059 {
1060 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1061 'info_dict': {
1062 'id': '4d03aad9',
1063 'ext': 'mp4',
1064 'uploader': 'deadspin',
1065 'title': 'WALL-TO-GORTAT',
1066 'timestamp': 1422285291,
1067 'upload_date': '20150126',
1068 },
1069 'add_ie': ['Viddler'],
1070 },
1071 # Libsyn embed
1072 {
1073 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1074 'info_dict': {
1075 'id': '3377616',
1076 'ext': 'mp3',
1077 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1078 'description': 'md5:601cb790edd05908957dae8aaa866465',
1079 'upload_date': '20150220',
1080 },
1081 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1082 },
1083 # jwplayer YouTube
1084 {
1085 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1086 'info_dict': {
1087 'id': 'Mrj4DVp2zeA',
1088 'ext': 'mp4',
1089 'upload_date': '20150212',
1090 'uploader': 'The National Archives UK',
1091 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1092 'uploader_id': 'NationalArchives08',
1093 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1094 },
1095 },
1096 # jwplayer rtmp
1097 {
1098 'url': 'http://www.suffolk.edu/sjc/',
1099 'info_dict': {
1100 'id': 'sjclive',
1101 'ext': 'flv',
1102 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1103 'uploader': 'www.suffolk.edu',
1104 },
1105 'params': {
1106 'skip_download': True,
1107 }
1108 },
1109 # Complex jwplayer
1110 {
1111 'url': 'http://www.indiedb.com/games/king-machine/videos',
1112 'info_dict': {
1113 'id': 'videos',
1114 'ext': 'mp4',
1115 'title': 'king machine trailer 1',
1116 'thumbnail': r're:^https?://.*\.jpg$',
1117 },
1118 },
1119 {
1120 # JWPlayer config passed as variable
1121 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1122 'info_dict': {
1123 'id': '3326530_hq',
1124 'ext': 'mp4',
1125 'title': 'ARIELE | Tube Cup',
1126 'uploader': 'www.txxx.com',
1127 'age_limit': 18,
1128 },
1129 'params': {
1130 'skip_download': True,
1131 }
1132 },
1133 # rtl.nl embed
1134 {
1135 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1136 'playlist_mincount': 5,
1137 'info_dict': {
1138 'id': 'aanslagen-kopenhagen',
1139 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1140 }
1141 },
1142 # Zapiks embed
1143 {
1144 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1145 'info_dict': {
1146 'id': '118046',
1147 'ext': 'mp4',
1148 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1149 }
1150 },
1151 # Kaltura embed (different embed code)
1152 {
1153 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1154 'info_dict': {
1155 'id': '1_a52wc67y',
1156 'ext': 'flv',
1157 'upload_date': '20150127',
1158 'uploader_id': 'PremierMedia',
1159 'timestamp': int,
1160 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1161 },
1162 },
1163 # Kaltura embed with single quotes
1164 {
1165 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1166 'info_dict': {
1167 'id': '0_izeg5utt',
1168 'ext': 'mp4',
1169 'title': '35871',
1170 'timestamp': 1355743100,
1171 'upload_date': '20121217',
1172 'uploader_id': 'batchUser',
1173 },
1174 'add_ie': ['Kaltura'],
1175 },
1176 {
1177 # Kaltura embedded via quoted entry_id
1178 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1179 'info_dict': {
1180 'id': '0_utuok90b',
1181 'ext': 'mp4',
1182 'title': '06_matthew_brender_raj_dutt',
1183 'timestamp': 1466638791,
1184 'upload_date': '20160622',
1185 },
1186 'add_ie': ['Kaltura'],
1187 'expected_warnings': [
1188 'Could not send HEAD request'
1189 ],
1190 'params': {
1191 'skip_download': True,
1192 }
1193 },
1194 {
1195 # Kaltura embedded, some fileExt broken (#11480)
1196 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1197 'info_dict': {
1198 'id': '1_sgtvehim',
1199 'ext': 'mp4',
1200 'title': 'Our "Standard Models" of particle physics and cosmology',
1201 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1202 'timestamp': 1321158993,
1203 'upload_date': '20111113',
1204 'uploader_id': 'kps1',
1205 },
1206 'add_ie': ['Kaltura'],
1207 },
1208 {
1209 # Kaltura iframe embed
1210 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1211 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1212 'info_dict': {
1213 'id': '0_f2cfbpwy',
1214 'ext': 'mp4',
1215 'title': 'I. M. Pei: A Centennial Celebration',
1216 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1217 'upload_date': '20170403',
1218 'uploader_id': 'batchUser',
1219 'timestamp': 1491232186,
1220 },
1221 'add_ie': ['Kaltura'],
1222 },
1223 # EaglePlatform embed (generic URL)
1224 {
1225 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1226 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1227 'info_dict': {
1228 'id': '227304',
1229 'ext': 'mp4',
1230 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1231 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1232 'thumbnail': r're:^https?://.*\.jpg$',
1233 'duration': 87,
1234 'view_count': int,
1235 'age_limit': 0,
1236 },
1237 'params': {
1238 'skip_download': True,
1239 },
1240 },
1241 # referrer protected EaglePlatform embed
1242 {
1243 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1244 'info_dict': {
1245 'id': '582306',
1246 'ext': 'mp4',
1247 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1248 'thumbnail': r're:^https?://.*\.jpg$',
1249 'duration': 3382,
1250 'view_count': int,
1251 },
1252 'params': {
1253 'skip_download': True,
1254 },
1255 },
1256 # ClipYou (EaglePlatform) embed (custom URL)
1257 {
1258 'url': 'http://muz-tv.ru/play/7129/',
1259 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1260 'info_dict': {
1261 'id': '12820',
1262 'ext': 'mp4',
1263 'title': "'O Sole Mio",
1264 'thumbnail': r're:^https?://.*\.jpg$',
1265 'duration': 216,
1266 'view_count': int,
1267 },
1268 'params': {
1269 'skip_download': True,
1270 },
1271 },
1272 # Pladform embed
1273 {
1274 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1275 'info_dict': {
1276 'id': '100183293',
1277 'ext': 'mp4',
1278 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1279 '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°',
1280 'thumbnail': r're:^https?://.*\.jpg$',
1281 'duration': 694,
1282 'age_limit': 0,
1283 },
1284 },
1285 # Playwire embed
1286 {
1287 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1288 'info_dict': {
1289 'id': '3519514',
1290 'ext': 'mp4',
1291 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1292 'thumbnail': r're:^https?://.*\.png$',
1293 'duration': 45.115,
1294 },
1295 },
1296 # 5min embed
1297 {
1298 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1299 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1300 'info_dict': {
1301 'id': '518726732',
1302 'ext': 'mp4',
1303 'title': 'Facebook Creates "On This Day" | Crunch Report',
1304 },
1305 },
1306 # SVT embed
1307 {
1308 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1309 'info_dict': {
1310 'id': '2900353',
1311 'ext': 'flv',
1312 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1313 'duration': 27,
1314 'age_limit': 0,
1315 },
1316 },
1317 # Crooks and Liars embed
1318 {
1319 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1320 'info_dict': {
1321 'id': '8RUoRhRi',
1322 'ext': 'mp4',
1323 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1324 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1325 'timestamp': 1428207000,
1326 'upload_date': '20150405',
1327 'uploader': 'Heather',
1328 },
1329 },
1330 # Crooks and Liars external embed
1331 {
1332 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1333 'info_dict': {
1334 'id': 'MTE3MjUtMzQ2MzA',
1335 'ext': 'mp4',
1336 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1337 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1338 'timestamp': 1265032391,
1339 'upload_date': '20100201',
1340 'uploader': 'Heather',
1341 },
1342 },
1343 # NBC Sports vplayer embed
1344 {
1345 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1346 'info_dict': {
1347 'id': 'ln7x1qSThw4k',
1348 'ext': 'flv',
1349 'title': "PFT Live: New leader in the 'new-look' defense",
1350 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1351 'uploader': 'NBCU-SPORTS',
1352 'upload_date': '20140107',
1353 'timestamp': 1389118457,
1354 },
1355 },
1356 # NBC News embed
1357 {
1358 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1359 'md5': '1aa589c675898ae6d37a17913cf68d66',
1360 'info_dict': {
1361 'id': '701714499682',
1362 'ext': 'mp4',
1363 'title': 'PREVIEW: On Assignment: David Letterman',
1364 '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.',
1365 },
1366 },
1367 # UDN embed
1368 {
1369 'url': 'https://video.udn.com/news/300346',
1370 'md5': 'fd2060e988c326991037b9aff9df21a6',
1371 'info_dict': {
1372 'id': '300346',
1373 'ext': 'mp4',
1374 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1375 'thumbnail': r're:^https?://.*\.jpg$',
1376 },
1377 'params': {
1378 # m3u8 download
1379 'skip_download': True,
1380 },
1381 },
1382 # Ooyala embed
1383 {
1384 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1385 'info_dict': {
1386 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1387 'ext': 'mp4',
1388 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1389 'title': 'This is what separates the Excel masters from the wannabes',
1390 'duration': 191.933,
1391 },
1392 'params': {
1393 # m3u8 downloads
1394 'skip_download': True,
1395 }
1396 },
1397 # Brightcove URL in single quotes
1398 {
1399 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1400 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1401 'info_dict': {
1402 'id': '4255764656001',
1403 'ext': 'mp4',
1404 'title': 'SN Presents: Russell Martin, World Citizen',
1405 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1406 'uploader': 'Rogers Sportsnet',
1407 'uploader_id': '1704050871',
1408 'upload_date': '20150525',
1409 'timestamp': 1432570283,
1410 },
1411 },
1412 # Dailymotion Cloud video
1413 {
1414 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1415 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1416 'info_dict': {
1417 'id': 'x2uy8t3',
1418 'ext': 'mp4',
1419 'title': 'Sauvons les abeilles ! - Le dƩbat',
1420 'description': 'md5:d9082128b1c5277987825d684939ca26',
1421 'thumbnail': r're:^https?://.*\.jpe?g$',
1422 'timestamp': 1434970506,
1423 'upload_date': '20150622',
1424 'uploader': 'Public SĆ©nat',
1425 'uploader_id': 'xa9gza',
1426 }
1427 },
1428 # OnionStudios embed
1429 {
1430 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1431 'info_dict': {
1432 'id': '2855',
1433 'ext': 'mp4',
1434 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1435 'thumbnail': r're:^https?://.*\.jpe?g$',
1436 'uploader': 'ClickHole',
1437 'uploader_id': 'clickhole',
1438 }
1439 },
1440 # SnagFilms embed
1441 {
1442 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1443 'info_dict': {
1444 'id': '74849a00-85a9-11e1-9660-123139220831',
1445 'ext': 'mp4',
1446 'title': '#whilewewatch',
1447 }
1448 },
1449 # AdobeTVVideo embed
1450 {
1451 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1452 'md5': '43662b577c018ad707a63766462b1e87',
1453 'info_dict': {
1454 'id': '2456',
1455 'ext': 'mp4',
1456 'title': 'New experience with Acrobat DC',
1457 'description': 'New experience with Acrobat DC',
1458 'duration': 248.667,
1459 },
1460 },
1461 # BrightcoveInPageEmbed embed
1462 {
1463 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1464 'info_dict': {
1465 'id': '4238694884001',
1466 'ext': 'flv',
1467 'title': 'Tabletop: Dread, Last Thoughts',
1468 'description': 'Tabletop: Dread, Last Thoughts',
1469 'duration': 51690,
1470 },
1471 },
1472 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1473 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1474 {
1475 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1476 'info_dict': {
1477 'id': '4785848093001',
1478 'ext': 'mp4',
1479 'title': 'The Cardinal Pell Interview',
1480 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1481 'uploader': 'GlobeCast Australia - GlobeStream',
1482 'uploader_id': '2733773828001',
1483 'upload_date': '20160304',
1484 'timestamp': 1457083087,
1485 },
1486 'params': {
1487 # m3u8 downloads
1488 'skip_download': True,
1489 },
1490 },
1491 {
1492 # Brightcove embed with whitespace around attribute names
1493 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1494 'info_dict': {
1495 'id': '3167554373001',
1496 'ext': 'mp4',
1497 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1498 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1499 'uploader_id': '1079349493',
1500 'upload_date': '20140207',
1501 'timestamp': 1391810548,
1502 },
1503 'params': {
1504 'skip_download': True,
1505 },
1506 },
1507 # Another form of arte.tv embed
1508 {
1509 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1510 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1511 'info_dict': {
1512 'id': '030273-562_PLUS7-F',
1513 'ext': 'mp4',
1514 'title': 'ARTE Reportage - Nulle part, en France',
1515 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1516 'upload_date': '20160409',
1517 },
1518 },
1519 # LiveLeak embed
1520 {
1521 'url': 'http://www.wykop.pl/link/3088787/',
1522 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1523 'info_dict': {
1524 'id': '874_1459135191',
1525 'ext': 'mp4',
1526 'title': 'Man shows poor quality of new apartment building',
1527 'description': 'The wall is like a sand pile.',
1528 'uploader': 'Lake8737',
1529 },
1530 'add_ie': [LiveLeakIE.ie_key()],
1531 },
1532 # Another LiveLeak embed pattern (#13336)
1533 {
1534 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1535 'info_dict': {
1536 'id': '2eb_1496309988',
1537 'ext': 'mp4',
1538 'title': 'Thief robs place where everyone was armed',
1539 'description': 'md5:694d73ee79e535953cf2488562288eee',
1540 'uploader': 'brazilwtf',
1541 },
1542 'add_ie': [LiveLeakIE.ie_key()],
1543 },
1544 # Duplicated embedded video URLs
1545 {
1546 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1547 'info_dict': {
1548 'id': '149298443_480_16c25b74_2',
1549 'ext': 'mp4',
1550 'title': 'vs. Blue Orange Spring Game',
1551 'uploader': 'www.hudl.com',
1552 },
1553 },
1554 # twitter:player:stream embed
1555 {
1556 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1557 'info_dict': {
1558 'id': 'master',
1559 'ext': 'mp4',
1560 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1561 'uploader': 'www.rtl.be',
1562 },
1563 'params': {
1564 # m3u8 downloads
1565 'skip_download': True,
1566 },
1567 },
1568 # twitter:player embed
1569 {
1570 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1571 'md5': 'a3e0df96369831de324f0778e126653c',
1572 'info_dict': {
1573 'id': '4909620399001',
1574 'ext': 'mp4',
1575 'title': 'What Do Black Holes Sound Like?',
1576 'description': 'what do black holes sound like',
1577 'upload_date': '20160524',
1578 'uploader_id': '29913724001',
1579 'timestamp': 1464107587,
1580 'uploader': 'TheAtlantic',
1581 },
1582 'add_ie': ['BrightcoveLegacy'],
1583 },
1584 # Nexx embed
1585 {
1586 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1587 'info_dict': {
1588 'id': '247746',
1589 'ext': 'mp4',
1590 'title': "Yesterday's Jam (OV)",
1591 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1592 'timestamp': 1492594816,
1593 'upload_date': '20170419',
1594 },
1595 'params': {
1596 'format': 'bestvideo',
1597 'skip_download': True,
1598 },
1599 },
1600 # Facebook <iframe> embed
1601 {
1602 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1603 'md5': 'fbcde74f534176ecb015849146dd3aee',
1604 'info_dict': {
1605 'id': '599637780109885',
1606 'ext': 'mp4',
1607 'title': 'Facebook video #599637780109885',
1608 },
1609 },
1610 # Facebook <iframe> embed, plugin video
1611 {
1612 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1613 'info_dict': {
1614 'id': '1754168231264132',
1615 'ext': 'mp4',
1616 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1617 'uploader': 'Tariq Ramadan (official)',
1618 'timestamp': 1496758379,
1619 'upload_date': '20170606',
1620 },
1621 'params': {
1622 'skip_download': True,
1623 },
1624 },
1625 # Facebook API embed
1626 {
1627 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1628 'md5': 'a47372ee61b39a7b90287094d447d94e',
1629 'info_dict': {
1630 'id': '10153467542406923',
1631 'ext': 'mp4',
1632 'title': 'Facebook video #10153467542406923',
1633 },
1634 },
1635 # Wordpress "YouTube Video Importer" plugin
1636 {
1637 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1638 'md5': 'd16797741b560b485194eddda8121b48',
1639 'info_dict': {
1640 'id': 'HNTXWDXV9Is',
1641 'ext': 'mp4',
1642 'title': 'Blue Devils Drumline Stanford lot 2016',
1643 'upload_date': '20160627',
1644 'uploader_id': 'GENOCIDE8GENERAL10',
1645 'uploader': 'cylus cyrus',
1646 },
1647 },
1648 {
1649 # video stored on custom kaltura server
1650 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1651 'md5': '537617d06e64dfed891fa1593c4b30cc',
1652 'info_dict': {
1653 'id': '0_1iotm5bh',
1654 'ext': 'mp4',
1655 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1656 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1657 'uploader_id': 'videos.expansion@el-mundo.net',
1658 'upload_date': '20150429',
1659 'timestamp': 1430303472,
1660 },
1661 'add_ie': ['Kaltura'],
1662 },
1663 {
1664 # Non-standard Vimeo embed
1665 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1666 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1667 'info_dict': {
1668 'id': '148867247',
1669 'ext': 'mp4',
1670 'title': 'Understanding the web - Teaser',
1671 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1672 'upload_date': '20151214',
1673 'uploader': 'OpenClassrooms',
1674 'uploader_id': 'openclassrooms',
1675 },
1676 'add_ie': ['Vimeo'],
1677 },
1678 {
1679 # generic vimeo embed that requires original URL passed as Referer
1680 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1681 'only_matching': True,
1682 },
1683 {
1684 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1685 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1686 'info_dict': {
1687 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1688 'ext': 'mp4',
1689 'title': 'Big Buck Bunny',
1690 'description': 'Royalty free test video',
1691 'timestamp': 1432816365,
1692 'upload_date': '20150528',
1693 'is_live': False,
1694 },
1695 'params': {
1696 'skip_download': True,
1697 },
1698 'add_ie': [ArkenaIE.ie_key()],
1699 },
1700 {
1701 '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/',
1702 'info_dict': {
1703 'id': '1c7141f46c',
1704 'ext': 'mp4',
1705 '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',
1706 },
1707 'params': {
1708 'skip_download': True,
1709 },
1710 'add_ie': [Vbox7IE.ie_key()],
1711 },
1712 {
1713 # DBTV embeds
1714 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1715 'info_dict': {
1716 'id': '43254897',
1717 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1718 },
1719 'playlist_mincount': 3,
1720 },
1721 {
1722 # Videa embeds
1723 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1724 'info_dict': {
1725 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1726 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1727 },
1728 'playlist_mincount': 2,
1729 },
1730 {
1731 # 20 minuten embed
1732 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1733 'info_dict': {
1734 'id': '523629',
1735 'ext': 'mp4',
1736 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1737 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1738 },
1739 'params': {
1740 'skip_download': True,
1741 },
1742 'add_ie': [TwentyMinutenIE.ie_key()],
1743 },
1744 {
1745 # VideoPress embed
1746 'url': 'https://en.support.wordpress.com/videopress/',
1747 'info_dict': {
1748 'id': 'OcobLTqC',
1749 'ext': 'm4v',
1750 'title': 'IMG_5786',
1751 'timestamp': 1435711927,
1752 'upload_date': '20150701',
1753 },
1754 'params': {
1755 'skip_download': True,
1756 },
1757 'add_ie': [VideoPressIE.ie_key()],
1758 },
1759 {
1760 # Rutube embed
1761 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1762 'info_dict': {
1763 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1764 'ext': 'flv',
1765 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1766 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1767 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1768 'upload_date': '20170228',
1769 'uploader_id': '996642',
1770 },
1771 'params': {
1772 'skip_download': True,
1773 },
1774 'add_ie': [RutubeIE.ie_key()],
1775 },
1776 {
1777 # ThePlatform embedded with whitespaces in URLs
1778 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1779 'only_matching': True,
1780 },
1781 {
1782 # Senate ISVP iframe https
1783 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1784 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1785 'info_dict': {
1786 'id': 'govtaff020316',
1787 'ext': 'mp4',
1788 'title': 'Integrated Senate Video Player',
1789 },
1790 'add_ie': [SenateISVPIE.ie_key()],
1791 },
1792 {
1793 # Limelight embeds (1 channel embed + 4 media embeds)
1794 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1795 'info_dict': {
1796 'id': 'FacilitatorTraining2017',
1797 'title': 'Facilitator Training 2017',
1798 },
1799 'playlist_mincount': 5,
1800 },
1801 {
1802 # Limelight embed (LimelightPlayerUtil.embed)
1803 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1804 'info_dict': {
1805 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1806 'ext': 'mp4',
1807 'title': '07448641',
1808 'timestamp': 1499890639,
1809 'upload_date': '20170712',
1810 },
1811 'params': {
1812 'skip_download': True,
1813 },
1814 'add_ie': ['LimelightMedia'],
1815 },
1816 {
1817 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1818 'info_dict': {
1819 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1820 'title': 'Standoff with Walnut Creek murder suspect ends',
1821 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1822 },
1823 'playlist_mincount': 4,
1824 },
1825 {
1826 # WashingtonPost embed
1827 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1828 'info_dict': {
1829 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1830 'ext': 'mp4',
1831 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1832 '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.',
1833 'timestamp': 1455216756,
1834 'uploader': 'The Washington Post',
1835 'upload_date': '20160211',
1836 },
1837 'add_ie': [WashingtonPostIE.ie_key()],
1838 },
1839 {
1840 # Mediaset embed
1841 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1842 'info_dict': {
1843 'id': '720642',
1844 'ext': 'mp4',
1845 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1846 },
1847 'params': {
1848 'skip_download': True,
1849 },
1850 'add_ie': [MediasetIE.ie_key()],
1851 },
1852 {
1853 # JOJ.sk embeds
1854 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1855 'info_dict': {
1856 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1857 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1858 },
1859 'playlist_mincount': 5,
1860 'add_ie': [JojIE.ie_key()],
1861 },
1862 {
1863 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1864 'url': 'https://tvrain.ru/amp/418921/',
1865 'md5': 'cc00413936695987e8de148b67d14f1d',
1866 'info_dict': {
1867 'id': '418921',
1868 'ext': 'mp4',
1869 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1870 },
1871 },
1872 {
1873 # vzaar embed
1874 'url': 'http://help.vzaar.com/article/165-embedding-video',
1875 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1876 'info_dict': {
1877 'id': '8707641',
1878 'ext': 'mp4',
1879 'title': 'Building A Business Online: Principal Chairs Q & A',
1880 },
1881 },
1882 {
1883 # multiple HTML5 videos on one page
1884 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1885 'info_dict': {
1886 'id': 'keyscenarios',
1887 'title': 'Rescue Kit 14 Free Edition - Getting started',
1888 },
1889 'playlist_count': 4,
1890 }
1891 # {
1892 # # TODO: find another test
1893 # # http://schema.org/VideoObject
1894 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1895 # 'md5': '888dcf08b7ea671381f00fab74692755',
1896 # 'info_dict': {
1897 # 'id': 'nyvTSJMKId',
1898 # 'ext': 'mp4',
1899 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1900 # 'description': '#love for cats.',
1901 # 'timestamp': 1461244995,
1902 # 'upload_date': '20160421',
1903 # },
1904 # 'params': {
1905 # 'force_generic_extractor': True,
1906 # },
1907 # }
1908 ]
1909
1910 def report_following_redirect(self, new_url):
1911 """Report information extraction."""
1912 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1913
1914 def _extract_rss(self, url, video_id, doc):
1915 playlist_title = doc.find('./channel/title').text
1916 playlist_desc_el = doc.find('./channel/description')
1917 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1918
1919 entries = []
1920 for it in doc.findall('./channel/item'):
1921 next_url = xpath_text(it, 'link', fatal=False)
1922 if not next_url:
1923 enclosure_nodes = it.findall('./enclosure')
1924 for e in enclosure_nodes:
1925 next_url = e.attrib.get('url')
1926 if next_url:
1927 break
1928
1929 if not next_url:
1930 continue
1931
1932 entries.append({
1933 '_type': 'url_transparent',
1934 'url': next_url,
1935 'title': it.find('title').text,
1936 })
1937
1938 return {
1939 '_type': 'playlist',
1940 'id': url,
1941 'title': playlist_title,
1942 'description': playlist_desc,
1943 'entries': entries,
1944 }
1945
1946 def _extract_camtasia(self, url, video_id, webpage):
1947 """ Returns None if no camtasia video can be found. """
1948
1949 camtasia_cfg = self._search_regex(
1950 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1951 webpage, 'camtasia configuration file', default=None)
1952 if camtasia_cfg is None:
1953 return None
1954
1955 title = self._html_search_meta('DC.title', webpage, fatal=True)
1956
1957 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1958 camtasia_cfg = self._download_xml(
1959 camtasia_url, video_id,
1960 note='Downloading camtasia configuration',
1961 errnote='Failed to download camtasia configuration')
1962 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1963
1964 entries = []
1965 for n in fileset_node.getchildren():
1966 url_n = n.find('./uri')
1967 if url_n is None:
1968 continue
1969
1970 entries.append({
1971 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1972 'title': '%s - %s' % (title, n.tag),
1973 'url': compat_urlparse.urljoin(url, url_n.text),
1974 'duration': float_or_none(n.find('./duration').text),
1975 })
1976
1977 return {
1978 '_type': 'playlist',
1979 'entries': entries,
1980 'title': title,
1981 }
1982
1983 def _real_extract(self, url):
1984 if url.startswith('//'):
1985 return {
1986 '_type': 'url',
1987 'url': self.http_scheme() + url,
1988 }
1989
1990 parsed_url = compat_urlparse.urlparse(url)
1991 if not parsed_url.scheme:
1992 default_search = self._downloader.params.get('default_search')
1993 if default_search is None:
1994 default_search = 'fixup_error'
1995
1996 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1997 if '/' in url:
1998 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1999 return self.url_result('http://' + url)
2000 elif default_search != 'fixup_error':
2001 if default_search == 'auto_warning':
2002 if re.match(r'^(?:url|URL)$', url):
2003 raise ExtractorError(
2004 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2005 expected=True)
2006 else:
2007 self._downloader.report_warning(
2008 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2009 return self.url_result('ytsearch:' + url)
2010
2011 if default_search in ('error', 'fixup_error'):
2012 raise ExtractorError(
2013 '%r is not a valid URL. '
2014 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2015 % (url, url), expected=True)
2016 else:
2017 if ':' not in default_search:
2018 default_search += ':'
2019 return self.url_result(default_search + url)
2020
2021 url, smuggled_data = unsmuggle_url(url)
2022 force_videoid = None
2023 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2024 if smuggled_data and 'force_videoid' in smuggled_data:
2025 force_videoid = smuggled_data['force_videoid']
2026 video_id = force_videoid
2027 else:
2028 video_id = self._generic_id(url)
2029
2030 self.to_screen('%s: Requesting header' % video_id)
2031
2032 head_req = HEADRequest(url)
2033 head_response = self._request_webpage(
2034 head_req, video_id,
2035 note=False, errnote='Could not send HEAD request to %s' % url,
2036 fatal=False)
2037
2038 if head_response is not False:
2039 # Check for redirect
2040 new_url = compat_str(head_response.geturl())
2041 if url != new_url:
2042 self.report_following_redirect(new_url)
2043 if force_videoid:
2044 new_url = smuggle_url(
2045 new_url, {'force_videoid': force_videoid})
2046 return self.url_result(new_url)
2047
2048 full_response = None
2049 if head_response is False:
2050 request = sanitized_Request(url)
2051 request.add_header('Accept-Encoding', '*')
2052 full_response = self._request_webpage(request, video_id)
2053 head_response = full_response
2054
2055 info_dict = {
2056 'id': video_id,
2057 'title': self._generic_title(url),
2058 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2059 }
2060
2061 # Check for direct link to a video
2062 content_type = head_response.headers.get('Content-Type', '').lower()
2063 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2064 if m:
2065 format_id = compat_str(m.group('format_id'))
2066 if format_id.endswith('mpegurl'):
2067 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2068 elif format_id == 'f4m':
2069 formats = self._extract_f4m_formats(url, video_id)
2070 else:
2071 formats = [{
2072 'format_id': format_id,
2073 'url': url,
2074 'vcodec': 'none' if m.group('type') == 'audio' else None
2075 }]
2076 info_dict['direct'] = True
2077 self._sort_formats(formats)
2078 info_dict['formats'] = formats
2079 return info_dict
2080
2081 if not self._downloader.params.get('test', False) and not is_intentional:
2082 force = self._downloader.params.get('force_generic_extractor', False)
2083 self._downloader.report_warning(
2084 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2085
2086 if not full_response:
2087 request = sanitized_Request(url)
2088 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2089 # making it impossible to download only chunk of the file (yet we need only 512kB to
2090 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2091 # that will always result in downloading the whole file that is not desirable.
2092 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2093 # to accept raw bytes and being able to download only a chunk.
2094 # It may probably better to solve this by checking Content-Type for application/octet-stream
2095 # after HEAD request finishes, but not sure if we can rely on this.
2096 request.add_header('Accept-Encoding', '*')
2097 full_response = self._request_webpage(request, video_id)
2098
2099 first_bytes = full_response.read(512)
2100
2101 # Is it an M3U playlist?
2102 if first_bytes.startswith(b'#EXTM3U'):
2103 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2104 self._sort_formats(info_dict['formats'])
2105 return info_dict
2106
2107 # Maybe it's a direct link to a video?
2108 # Be careful not to download the whole thing!
2109 if not is_html(first_bytes):
2110 self._downloader.report_warning(
2111 'URL could be a direct video link, returning it as such.')
2112 info_dict.update({
2113 'direct': True,
2114 'url': url,
2115 })
2116 return info_dict
2117
2118 webpage = self._webpage_read_content(
2119 full_response, url, video_id, prefix=first_bytes)
2120
2121 self.report_extraction(video_id)
2122
2123 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2124 try:
2125 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2126 if doc.tag == 'rss':
2127 return self._extract_rss(url, video_id, doc)
2128 elif doc.tag == 'SmoothStreamingMedia':
2129 info_dict['formats'] = self._parse_ism_formats(doc, url)
2130 self._sort_formats(info_dict['formats'])
2131 return info_dict
2132 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2133 smil = self._parse_smil(doc, url, video_id)
2134 self._sort_formats(smil['formats'])
2135 return smil
2136 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2137 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2138 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2139 info_dict['formats'] = self._parse_mpd_formats(
2140 doc, video_id,
2141 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2142 mpd_url=url)
2143 self._sort_formats(info_dict['formats'])
2144 return info_dict
2145 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2146 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2147 self._sort_formats(info_dict['formats'])
2148 return info_dict
2149 except compat_xml_parse_error:
2150 pass
2151
2152 # Is it a Camtasia project?
2153 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2154 if camtasia_res is not None:
2155 return camtasia_res
2156
2157 # Sometimes embedded video player is hidden behind percent encoding
2158 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2159 # Unescaping the whole page allows to handle those cases in a generic way
2160 webpage = compat_urllib_parse_unquote(webpage)
2161
2162 # it's tempting to parse this further, but you would
2163 # have to take into account all the variations like
2164 # Video Title - Site Name
2165 # Site Name | Video Title
2166 # Video Title - Tagline | Site Name
2167 # and so on and so forth; it's just not practical
2168 video_title = self._og_search_title(
2169 webpage, default=None) or self._html_search_regex(
2170 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2171 default='video')
2172
2173 # Try to detect age limit automatically
2174 age_limit = self._rta_search(webpage)
2175 # And then there are the jokers who advertise that they use RTA,
2176 # but actually don't.
2177 AGE_LIMIT_MARKERS = [
2178 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2179 ]
2180 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2181 age_limit = 18
2182
2183 # video uploader is domain name
2184 video_uploader = self._search_regex(
2185 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2186
2187 video_description = self._og_search_description(webpage, default=None)
2188 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2189
2190 info_dict.update({
2191 'title': video_title,
2192 'description': video_description,
2193 'thumbnail': video_thumbnail,
2194 'age_limit': age_limit,
2195 })
2196
2197 # Look for Brightcove Legacy Studio embeds
2198 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2199 if bc_urls:
2200 entries = [{
2201 '_type': 'url',
2202 'url': smuggle_url(bc_url, {'Referer': url}),
2203 'ie_key': 'BrightcoveLegacy'
2204 } for bc_url in bc_urls]
2205
2206 return {
2207 '_type': 'playlist',
2208 'title': video_title,
2209 'id': video_id,
2210 'entries': entries,
2211 }
2212
2213 # Look for Brightcove New Studio embeds
2214 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2215 if bc_urls:
2216 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2217
2218 # Look for Nexx embeds
2219 nexx_urls = NexxIE._extract_urls(webpage)
2220 if nexx_urls:
2221 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2222
2223 # Look for Nexx iFrame embeds
2224 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2225 if nexx_embed_urls:
2226 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2227
2228 # Look for ThePlatform embeds
2229 tp_urls = ThePlatformIE._extract_urls(webpage)
2230 if tp_urls:
2231 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2232
2233 # Look for Vessel embeds
2234 vessel_urls = VesselIE._extract_urls(webpage)
2235 if vessel_urls:
2236 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2237
2238 # Look for embedded rtl.nl player
2239 matches = re.findall(
2240 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2241 webpage)
2242 if matches:
2243 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2244
2245 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2246 if vimeo_urls:
2247 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2248
2249 vid_me_embed_url = self._search_regex(
2250 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2251 webpage, 'vid.me embed', default=None)
2252 if vid_me_embed_url is not None:
2253 return self.url_result(vid_me_embed_url, 'Vidme')
2254
2255 # Look for YouTube embeds
2256 youtube_urls = YoutubeIE._extract_urls(webpage)
2257 if youtube_urls:
2258 return self.playlist_from_matches(
2259 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2260
2261 matches = DailymotionIE._extract_urls(webpage)
2262 if matches:
2263 return self.playlist_from_matches(matches, video_id, video_title)
2264
2265 # Look for embedded Dailymotion playlist player (#3822)
2266 m = re.search(
2267 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2268 if m:
2269 playlists = re.findall(
2270 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2271 if playlists:
2272 return self.playlist_from_matches(
2273 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2274
2275 # Look for DailyMail embeds
2276 dailymail_urls = DailyMailIE._extract_urls(webpage)
2277 if dailymail_urls:
2278 return self.playlist_from_matches(
2279 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2280
2281 # Look for embedded Wistia player
2282 wistia_url = WistiaIE._extract_url(webpage)
2283 if wistia_url:
2284 return {
2285 '_type': 'url_transparent',
2286 'url': self._proto_relative_url(wistia_url),
2287 'ie_key': WistiaIE.ie_key(),
2288 'uploader': video_uploader,
2289 }
2290
2291 # Look for SVT player
2292 svt_url = SVTIE._extract_url(webpage)
2293 if svt_url:
2294 return self.url_result(svt_url, 'SVT')
2295
2296 # Look for Bandcamp pages with custom domain
2297 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2298 if mobj is not None:
2299 burl = unescapeHTML(mobj.group(1))
2300 # Don't set the extractor because it can be a track url or an album
2301 return self.url_result(burl)
2302
2303 # Look for embedded Vevo player
2304 mobj = re.search(
2305 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2306 if mobj is not None:
2307 return self.url_result(mobj.group('url'))
2308
2309 # Look for embedded Viddler player
2310 mobj = re.search(
2311 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2312 webpage)
2313 if mobj is not None:
2314 return self.url_result(mobj.group('url'))
2315
2316 # Look for NYTimes player
2317 mobj = re.search(
2318 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2319 webpage)
2320 if mobj is not None:
2321 return self.url_result(mobj.group('url'))
2322
2323 # Look for Libsyn player
2324 mobj = re.search(
2325 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2326 if mobj is not None:
2327 return self.url_result(mobj.group('url'))
2328
2329 # Look for Ooyala videos
2330 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2331 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2332 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2333 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2334 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2335 if mobj is not None:
2336 embed_token = self._search_regex(
2337 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2338 webpage, 'ooyala embed token', default=None)
2339 return OoyalaIE._build_url_result(smuggle_url(
2340 mobj.group('ec'), {
2341 'domain': url,
2342 'embed_token': embed_token,
2343 }))
2344
2345 # Look for multiple Ooyala embeds on SBN network websites
2346 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2347 if mobj is not None:
2348 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2349 if embeds:
2350 return self.playlist_from_matches(
2351 embeds, video_id, video_title,
2352 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2353
2354 # Look for Aparat videos
2355 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2356 if mobj is not None:
2357 return self.url_result(mobj.group(1), 'Aparat')
2358
2359 # Look for MPORA videos
2360 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2361 if mobj is not None:
2362 return self.url_result(mobj.group(1), 'Mpora')
2363
2364 # Look for embedded NovaMov-based player
2365 mobj = re.search(
2366 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2367 (?P<url>http://(?:(?:embed|www)\.)?
2368 (?:novamov\.com|
2369 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2370 videoweed\.(?:es|com)|
2371 movshare\.(?:net|sx|ag)|
2372 divxstage\.(?:eu|net|ch|co|at|ag))
2373 /embed\.php.+?)\1''', webpage)
2374 if mobj is not None:
2375 return self.url_result(mobj.group('url'))
2376
2377 # Look for embedded Facebook player
2378 facebook_urls = FacebookIE._extract_urls(webpage)
2379 if facebook_urls:
2380 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2381
2382 # Look for embedded VK player
2383 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2384 if mobj is not None:
2385 return self.url_result(mobj.group('url'), 'VK')
2386
2387 # Look for embedded Odnoklassniki player
2388 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2389 if mobj is not None:
2390 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2391
2392 # Look for embedded ivi player
2393 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2394 if mobj is not None:
2395 return self.url_result(mobj.group('url'), 'Ivi')
2396
2397 # Look for embedded Huffington Post player
2398 mobj = re.search(
2399 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2400 if mobj is not None:
2401 return self.url_result(mobj.group('url'), 'HuffPost')
2402
2403 # Look for embed.ly
2404 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2405 if mobj is not None:
2406 return self.url_result(mobj.group('url'))
2407 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2408 if mobj is not None:
2409 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2410
2411 # Look for funnyordie embed
2412 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2413 if matches:
2414 return self.playlist_from_matches(
2415 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2416
2417 # Look for BBC iPlayer embed
2418 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2419 if matches:
2420 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2421
2422 # Look for embedded RUTV player
2423 rutv_url = RUTVIE._extract_url(webpage)
2424 if rutv_url:
2425 return self.url_result(rutv_url, 'RUTV')
2426
2427 # Look for embedded TVC player
2428 tvc_url = TVCIE._extract_url(webpage)
2429 if tvc_url:
2430 return self.url_result(tvc_url, 'TVC')
2431
2432 # Look for embedded SportBox player
2433 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2434 if sportbox_urls:
2435 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2436
2437 # Look for embedded XHamster player
2438 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2439 if xhamster_urls:
2440 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2441
2442 # Look for embedded TNAFlixNetwork player
2443 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2444 if tnaflix_urls:
2445 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2446
2447 # Look for embedded PornHub player
2448 pornhub_urls = PornHubIE._extract_urls(webpage)
2449 if pornhub_urls:
2450 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2451
2452 # Look for embedded DrTuber player
2453 drtuber_urls = DrTuberIE._extract_urls(webpage)
2454 if drtuber_urls:
2455 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2456
2457 # Look for embedded RedTube player
2458 redtube_urls = RedTubeIE._extract_urls(webpage)
2459 if redtube_urls:
2460 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2461
2462 # Look for embedded Tvigle player
2463 mobj = re.search(
2464 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2465 if mobj is not None:
2466 return self.url_result(mobj.group('url'), 'Tvigle')
2467
2468 # Look for embedded TED player
2469 mobj = re.search(
2470 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2471 if mobj is not None:
2472 return self.url_result(mobj.group('url'), 'TED')
2473
2474 # Look for embedded Ustream videos
2475 ustream_url = UstreamIE._extract_url(webpage)
2476 if ustream_url:
2477 return self.url_result(ustream_url, UstreamIE.ie_key())
2478
2479 # Look for embedded arte.tv player
2480 mobj = re.search(
2481 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2482 webpage)
2483 if mobj is not None:
2484 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2485
2486 # Look for embedded francetv player
2487 mobj = re.search(
2488 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2489 webpage)
2490 if mobj is not None:
2491 return self.url_result(mobj.group('url'))
2492
2493 # Look for embedded smotri.com player
2494 smotri_url = SmotriIE._extract_url(webpage)
2495 if smotri_url:
2496 return self.url_result(smotri_url, 'Smotri')
2497
2498 # Look for embedded Myvi.ru player
2499 myvi_url = MyviIE._extract_url(webpage)
2500 if myvi_url:
2501 return self.url_result(myvi_url)
2502
2503 # Look for embedded soundcloud player
2504 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2505 if soundcloud_urls:
2506 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2507
2508 # Look for tunein player
2509 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2510 if tunein_urls:
2511 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2512
2513 # Look for embedded mtvservices player
2514 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2515 if mtvservices_url:
2516 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2517
2518 # Look for embedded yahoo player
2519 mobj = re.search(
2520 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2521 webpage)
2522 if mobj is not None:
2523 return self.url_result(mobj.group('url'), 'Yahoo')
2524
2525 # Look for embedded sbs.com.au player
2526 mobj = re.search(
2527 r'''(?x)
2528 (?:
2529 <meta\s+property="og:video"\s+content=|
2530 <iframe[^>]+?src=
2531 )
2532 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2533 webpage)
2534 if mobj is not None:
2535 return self.url_result(mobj.group('url'), 'SBS')
2536
2537 # Look for embedded Cinchcast player
2538 mobj = re.search(
2539 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2540 webpage)
2541 if mobj is not None:
2542 return self.url_result(mobj.group('url'), 'Cinchcast')
2543
2544 mobj = re.search(
2545 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2546 webpage)
2547 if not mobj:
2548 mobj = re.search(
2549 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2550 webpage)
2551 if mobj is not None:
2552 return self.url_result(mobj.group('url'), 'MLB')
2553
2554 mobj = re.search(
2555 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2556 webpage)
2557 if mobj is not None:
2558 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2559
2560 mobj = re.search(
2561 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2562 webpage)
2563 if mobj is not None:
2564 return self.url_result(mobj.group('url'), 'Livestream')
2565
2566 # Look for Zapiks embed
2567 mobj = re.search(
2568 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2569 if mobj is not None:
2570 return self.url_result(mobj.group('url'), 'Zapiks')
2571
2572 # Look for Kaltura embeds
2573 kaltura_url = KalturaIE._extract_url(webpage)
2574 if kaltura_url:
2575 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2576
2577 # Look for EaglePlatform embeds
2578 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2579 if eagleplatform_url:
2580 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2581
2582 # Look for ClipYou (uses EaglePlatform) embeds
2583 mobj = re.search(
2584 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2585 if mobj is not None:
2586 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2587
2588 # Look for Pladform embeds
2589 pladform_url = PladformIE._extract_url(webpage)
2590 if pladform_url:
2591 return self.url_result(pladform_url)
2592
2593 # Look for Videomore embeds
2594 videomore_url = VideomoreIE._extract_url(webpage)
2595 if videomore_url:
2596 return self.url_result(videomore_url)
2597
2598 # Look for Webcaster embeds
2599 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2600 if webcaster_url:
2601 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2602
2603 # Look for Playwire embeds
2604 mobj = re.search(
2605 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2606 if mobj is not None:
2607 return self.url_result(mobj.group('url'))
2608
2609 # Look for 5min embeds
2610 mobj = re.search(
2611 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2612 if mobj is not None:
2613 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2614
2615 # Look for Crooks and Liars embeds
2616 mobj = re.search(
2617 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2618 if mobj is not None:
2619 return self.url_result(mobj.group('url'))
2620
2621 # Look for NBC Sports VPlayer embeds
2622 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2623 if nbc_sports_url:
2624 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2625
2626 # Look for NBC News embeds
2627 nbc_news_embed_url = re.search(
2628 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2629 if nbc_news_embed_url:
2630 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2631
2632 # Look for Google Drive embeds
2633 google_drive_url = GoogleDriveIE._extract_url(webpage)
2634 if google_drive_url:
2635 return self.url_result(google_drive_url, 'GoogleDrive')
2636
2637 # Look for UDN embeds
2638 mobj = re.search(
2639 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2640 if mobj is not None:
2641 return self.url_result(
2642 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2643
2644 # Look for Senate ISVP iframe
2645 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2646 if senate_isvp_url:
2647 return self.url_result(senate_isvp_url, 'SenateISVP')
2648
2649 # Look for Dailymotion Cloud videos
2650 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2651 if dmcloud_url:
2652 return self.url_result(dmcloud_url, 'DailymotionCloud')
2653
2654 # Look for OnionStudios embeds
2655 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2656 if onionstudios_url:
2657 return self.url_result(onionstudios_url)
2658
2659 # Look for ViewLift embeds
2660 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2661 if viewlift_url:
2662 return self.url_result(viewlift_url)
2663
2664 # Look for JWPlatform embeds
2665 jwplatform_url = JWPlatformIE._extract_url(webpage)
2666 if jwplatform_url:
2667 return self.url_result(jwplatform_url, 'JWPlatform')
2668
2669 # Look for Digiteka embeds
2670 digiteka_url = DigitekaIE._extract_url(webpage)
2671 if digiteka_url:
2672 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2673
2674 # Look for Arkena embeds
2675 arkena_url = ArkenaIE._extract_url(webpage)
2676 if arkena_url:
2677 return self.url_result(arkena_url, ArkenaIE.ie_key())
2678
2679 # Look for Piksel embeds
2680 piksel_url = PikselIE._extract_url(webpage)
2681 if piksel_url:
2682 return self.url_result(piksel_url, PikselIE.ie_key())
2683
2684 # Look for Limelight embeds
2685 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2686 if limelight_urls:
2687 return self.playlist_result(
2688 limelight_urls, video_id, video_title, video_description)
2689
2690 # Look for Anvato embeds
2691 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2692 if anvato_urls:
2693 return self.playlist_result(
2694 anvato_urls, video_id, video_title, video_description)
2695
2696 # Look for AdobeTVVideo embeds
2697 mobj = re.search(
2698 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2699 webpage)
2700 if mobj is not None:
2701 return self.url_result(
2702 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2703 'AdobeTVVideo')
2704
2705 # Look for Vine embeds
2706 mobj = re.search(
2707 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2708 webpage)
2709 if mobj is not None:
2710 return self.url_result(
2711 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2712
2713 # Look for VODPlatform embeds
2714 mobj = re.search(
2715 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2716 webpage)
2717 if mobj is not None:
2718 return self.url_result(
2719 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2720
2721 # Look for Mangomolo embeds
2722 mobj = re.search(
2723 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2724 (?:
2725 video\?.*?\bid=(?P<video_id>\d+)|
2726 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2727 ).+?)\1''', webpage)
2728 if mobj is not None:
2729 info = {
2730 '_type': 'url_transparent',
2731 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2732 'title': video_title,
2733 'description': video_description,
2734 'thumbnail': video_thumbnail,
2735 'uploader': video_uploader,
2736 }
2737 video_id = mobj.group('video_id')
2738 if video_id:
2739 info.update({
2740 'ie_key': 'MangomoloVideo',
2741 'id': video_id,
2742 })
2743 else:
2744 info.update({
2745 'ie_key': 'MangomoloLive',
2746 'id': mobj.group('channel_id'),
2747 })
2748 return info
2749
2750 # Look for Instagram embeds
2751 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2752 if instagram_embed_url is not None:
2753 return self.url_result(
2754 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2755
2756 # Look for LiveLeak embeds
2757 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2758 if liveleak_urls:
2759 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2760
2761 # Look for 3Q SDN embeds
2762 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2763 if threeqsdn_url:
2764 return {
2765 '_type': 'url_transparent',
2766 'ie_key': ThreeQSDNIE.ie_key(),
2767 'url': self._proto_relative_url(threeqsdn_url),
2768 'title': video_title,
2769 'description': video_description,
2770 'thumbnail': video_thumbnail,
2771 'uploader': video_uploader,
2772 }
2773
2774 # Look for VBOX7 embeds
2775 vbox7_url = Vbox7IE._extract_url(webpage)
2776 if vbox7_url:
2777 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2778
2779 # Look for DBTV embeds
2780 dbtv_urls = DBTVIE._extract_urls(webpage)
2781 if dbtv_urls:
2782 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2783
2784 # Look for Videa embeds
2785 videa_urls = VideaIE._extract_urls(webpage)
2786 if videa_urls:
2787 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2788
2789 # Look for 20 minuten embeds
2790 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2791 if twentymin_urls:
2792 return self.playlist_from_matches(
2793 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2794
2795 # Look for Openload embeds
2796 openload_urls = OpenloadIE._extract_urls(webpage)
2797 if openload_urls:
2798 return self.playlist_from_matches(
2799 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2800
2801 # Look for VideoPress embeds
2802 videopress_urls = VideoPressIE._extract_urls(webpage)
2803 if videopress_urls:
2804 return self.playlist_from_matches(
2805 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2806
2807 # Look for Rutube embeds
2808 rutube_urls = RutubeIE._extract_urls(webpage)
2809 if rutube_urls:
2810 return self.playlist_from_matches(
2811 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2812
2813 # Look for WashingtonPost embeds
2814 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2815 if wapo_urls:
2816 return self.playlist_from_matches(
2817 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2818
2819 # Look for Mediaset embeds
2820 mediaset_urls = MediasetIE._extract_urls(webpage)
2821 if mediaset_urls:
2822 return self.playlist_from_matches(
2823 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2824
2825 # Look for JOJ.sk embeds
2826 joj_urls = JojIE._extract_urls(webpage)
2827 if joj_urls:
2828 return self.playlist_from_matches(
2829 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2830
2831 # Look for megaphone.fm embeds
2832 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2833 if mpfn_urls:
2834 return self.playlist_from_matches(
2835 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2836
2837 # Look for vzaar embeds
2838 vzaar_urls = VzaarIE._extract_urls(webpage)
2839 if vzaar_urls:
2840 return self.playlist_from_matches(
2841 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2842
2843 def merge_dicts(dict1, dict2):
2844 merged = {}
2845 for k, v in dict1.items():
2846 if v is not None:
2847 merged[k] = v
2848 for k, v in dict2.items():
2849 if v is None:
2850 continue
2851 if (k not in merged or
2852 (isinstance(v, compat_str) and v and
2853 isinstance(merged[k], compat_str) and
2854 not merged[k])):
2855 merged[k] = v
2856 return merged
2857
2858 # Look for HTML5 media
2859 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2860 if entries:
2861 if len(entries) == 1:
2862 entries[0].update({
2863 'id': video_id,
2864 'title': video_title,
2865 })
2866 else:
2867 for num, entry in enumerate(entries, start=1):
2868 entry.update({
2869 'id': '%s-%s' % (video_id, num),
2870 'title': '%s (%d)' % (video_title, num),
2871 })
2872 for entry in entries:
2873 self._sort_formats(entry['formats'])
2874 return self.playlist_result(entries, video_id, video_title)
2875
2876 jwplayer_data = self._find_jwplayer_data(
2877 webpage, video_id, transform_source=js_to_json)
2878 if jwplayer_data:
2879 info = self._parse_jwplayer_data(
2880 jwplayer_data, video_id, require_title=False, base_url=url)
2881 return merge_dicts(info, info_dict)
2882
2883 # Looking for http://schema.org/VideoObject
2884 json_ld = self._search_json_ld(
2885 webpage, video_id, default={}, expected_type='VideoObject')
2886 if json_ld.get('url'):
2887 return merge_dicts(json_ld, info_dict)
2888
2889 def check_video(vurl):
2890 if YoutubeIE.suitable(vurl):
2891 return True
2892 if RtmpIE.suitable(vurl):
2893 return True
2894 vpath = compat_urlparse.urlparse(vurl).path
2895 vext = determine_ext(vpath)
2896 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2897
2898 def filter_video(urls):
2899 return list(filter(check_video, urls))
2900
2901 # Start with something easy: JW Player in SWFObject
2902 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2903 if not found:
2904 # Look for gorilla-vid style embedding
2905 found = filter_video(re.findall(r'''(?sx)
2906 (?:
2907 jw_plugins|
2908 JWPlayerOptions|
2909 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2910 )
2911 .*?
2912 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2913 if not found:
2914 # Broaden the search a little bit
2915 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2916 if not found:
2917 # Broaden the findall a little bit: JWPlayer JS loader
2918 found = filter_video(re.findall(
2919 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2920 if not found:
2921 # Flow player
2922 found = filter_video(re.findall(r'''(?xs)
2923 flowplayer\("[^"]+",\s*
2924 \{[^}]+?\}\s*,
2925 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2926 ["']?url["']?\s*:\s*["']([^"']+)["']
2927 ''', webpage))
2928 if not found:
2929 # Cinerama player
2930 found = re.findall(
2931 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2932 if not found:
2933 # Try to find twitter cards info
2934 # twitter:player:stream should be checked before twitter:player since
2935 # it is expected to contain a raw stream (see
2936 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2937 found = filter_video(re.findall(
2938 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2939 if not found:
2940 # We look for Open Graph info:
2941 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2942 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2943 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2944 if m_video_type is not None:
2945 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2946 if not found:
2947 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2948 found = re.search(
2949 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2950 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2951 webpage)
2952 if not found:
2953 # Look also in Refresh HTTP header
2954 refresh_header = head_response.headers.get('Refresh')
2955 if refresh_header:
2956 # In python 2 response HTTP headers are bytestrings
2957 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2958 refresh_header = refresh_header.decode('iso-8859-1')
2959 found = re.search(REDIRECT_REGEX, refresh_header)
2960 if found:
2961 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2962 if new_url != url:
2963 self.report_following_redirect(new_url)
2964 return {
2965 '_type': 'url',
2966 'url': new_url,
2967 }
2968 else:
2969 found = None
2970
2971 if not found:
2972 # twitter:player is a https URL to iframe player that may or may not
2973 # be supported by youtube-dl thus this is checked the very last (see
2974 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2975 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2976 if embed_url:
2977 return self.url_result(embed_url)
2978
2979 if not found:
2980 raise UnsupportedError(url)
2981
2982 entries = []
2983 for video_url in orderedSet(found):
2984 video_url = unescapeHTML(video_url)
2985 video_url = video_url.replace('\\/', '/')
2986 video_url = compat_urlparse.urljoin(url, video_url)
2987 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2988
2989 # Sometimes, jwplayer extraction will result in a YouTube URL
2990 if YoutubeIE.suitable(video_url):
2991 entries.append(self.url_result(video_url, 'Youtube'))
2992 continue
2993
2994 # here's a fun little line of code for you:
2995 video_id = os.path.splitext(video_id)[0]
2996
2997 entry_info_dict = {
2998 'id': video_id,
2999 'uploader': video_uploader,
3000 'title': video_title,
3001 'age_limit': age_limit,
3002 }
3003
3004 if RtmpIE.suitable(video_url):
3005 entry_info_dict.update({
3006 '_type': 'url_transparent',
3007 'ie_key': RtmpIE.ie_key(),
3008 'url': video_url,
3009 })
3010 entries.append(entry_info_dict)
3011 continue
3012
3013 ext = determine_ext(video_url)
3014 if ext == 'smil':
3015 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3016 elif ext == 'xspf':
3017 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3018 elif ext == 'm3u8':
3019 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3020 elif ext == 'mpd':
3021 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3022 elif ext == 'f4m':
3023 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3024 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3025 # Just matching .ism/manifest is not enough to be reliably sure
3026 # whether it's actually an ISM manifest or some other streaming
3027 # manifest since there are various streaming URL formats
3028 # possible (see [1]) as well as some other shenanigans like
3029 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3030 # so on.
3031 # Thus the most reasonable way to solve this is to delegate
3032 # to generic extractor in order to look into the contents of
3033 # the manifest itself.
3034 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3035 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3036 entry_info_dict = self.url_result(
3037 smuggle_url(video_url, {'to_generic': True}),
3038 GenericIE.ie_key())
3039 else:
3040 entry_info_dict['url'] = video_url
3041
3042 if entry_info_dict.get('formats'):
3043 self._sort_formats(entry_info_dict['formats'])
3044
3045 entries.append(entry_info_dict)
3046
3047 if len(entries) == 1:
3048 return entries[0]
3049 else:
3050 for num, e in enumerate(entries, start=1):
3051 # 'url' results don't have a title
3052 if e.get('title') is not None:
3053 e['title'] = '%s (%d)' % (e['title'], num)
3054 return {
3055 '_type': 'playlist',
3056 'entries': entries,
3057 }