]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[9c9media] PEP 8
[yt-dlp.git] / youtube_dl / extractor / generic.py
CommitLineData
dcdb292f 1# coding: utf-8
cfe50f04 2
79649588
PH
3from __future__ import unicode_literals
4
9b122384
PH
5import os
6import re
6c91a5a7 7import sys
9b122384
PH
8
9from .common import InfoExtractor
fc9713a1 10from .youtube import YoutubeIE
8c25f81b 11from ..compat import (
f7854627 12 compat_etree_fromstring,
4e363703 13 compat_str,
1ddb9456 14 compat_urllib_parse_unquote,
a5caba1e 15 compat_urlparse,
f7300c5c 16 compat_xml_parse_error,
8c25f81b
PH
17)
18from ..utils import (
b759a0d4 19 determine_ext,
9b122384 20 ExtractorError,
c8e9a235 21 float_or_none,
aa94a6d3 22 HEADRequest,
61ca9a80 23 is_html,
a4a554a7 24 js_to_json,
63d990d2 25 KNOWN_EXTENSIONS,
6cc62232 26 merge_dicts,
63d990d2 27 mimetype2ext,
ed2d6a19 28 orderedSet,
5c2266df 29 sanitized_Request,
9d4660ca
PH
30 smuggle_url,
31 unescapeHTML,
42393ce2 32 unified_strdate,
4d54ef20 33 unsmuggle_url,
416c7fcb 34 UnsupportedError,
76c73715 35 xpath_text,
9b122384 36)
b7a8c1bc 37from .commonprotocols import RtmpIE
ed126900 38from .brightcove import (
4fcaa4f4 39 BrightcoveLegacyIE,
5c17f0a6 40 BrightcoveNewIE,
ed126900 41)
3f59b015
S
42from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45)
a2edf2e7 46from .nbc import NBCSportsVPlayerIE
c0d0b01f 47from .ooyala import OoyalaIE
93d020dd 48from .rutv import RUTVIE
954c1d05 49from .tvc import TVCIE
d40a3b5b 50from .sportbox import SportBoxEmbedIE
cb3ac1c6 51from .smotri import SmotriIE
6dd94d3a 52from .myvi import MyviIE
1419fafd 53from .condenast import CondeNastIE
418c5cc3 54from .udn import UDNEmbedIE
2fe1b5bd 55from .senateisvp import SenateISVPIE
bab19a8e 56from .svt import SVTIE
65d161c4 57from .pornhub import PornHubIE
2bb5b6d0 58from .xhamster import XHamsterEmbedIE
2c9ca782 59from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 60from .drtuber import DrTuberIE
e28ed498 61from .redtube import RedTubeIE
06993715 62from .tube8 import Tube8IE
b407e173 63from .vimeo import VimeoIE
3c4fbfec 64from .dailymotion import DailymotionIE
71a1db89 65from .dailymail import DailyMailIE
1ac1c4c2 66from .onionstudios import OnionStudiosIE
67167920 67from .viewlift import ViewLiftEmbedIE
46fde8a1 68from .mtv import MTVServicesEmbeddedIE
45dad7ba 69from .pladform import PladformIE
ff18735c 70from .videomore import VideomoreIE
83f1481b 71from .webcaster import WebcasterFeedIE
5b251628 72from .googledrive import GoogleDriveIE
7cb09524 73from .jwplatform import JWPlatformIE
aecfcd4e 74from .digiteka import DigitekaIE
1979969f 75from .arkena import ArkenaIE
5a51775a 76from .instagram import InstagramIE
b8f67449 77from .liveleak import LiveLeakIE
5d39176f 78from .threeqsdn import ThreeQSDNIE
4d8819d2 79from .theplatform import ThePlatformIE
48a5eabc 80from .vessel import VesselIE
c287f2bc 81from .kaltura import KalturaIE
06a96da1 82from .eagleplatform import EaglePlatformIE
fd6ca382 83from .facebook import FacebookIE
94aae015 84from .soundcloud import SoundcloudIE
027e2312 85from .tunein import TuneInBaseIE
2a1321a2 86from .vbox7 import Vbox7IE
b0c8f2e9 87from .dbtv import DBTVIE
b1c35797 88from .piksel import PikselIE
e186a9ec 89from .videa import VideaIE
b687c85e 90from .twentymin import TwentyMinutenIE
d77ac737 91from .ustream import UstreamIE
17f8deeb 92from .openload import OpenloadIE
6ef3e65a 93from .videopress import VideoPressIE
eb3079b6 94from .rutube import RutubeIE
e5d39886 95from .limelight import LimelightBaseIE
7986c3ab 96from .anvato import AnvatoIE
55719459 97from .washingtonpost import WashingtonPostIE
58bb4402 98from .wistia import WistiaIE
5d29af3d 99from .mediaset import MediasetIE
73cf76a9 100from .joj import JojIE
24e966e8 101from .megaphone import MegaphoneIE
41918eaa 102from .vzaar import VzaarIE
26bae2d9 103from .channel9 import Channel9IE
0987f2dd 104from .vshare import VShareIE
2ca7ed41 105from .mediasite import MediasiteIE
7d540621 106from .springboardplatform import SpringboardPlatformIE
4c780fbd 107from .yapfiles import YapFilesIE
86c8cfc5 108from .vice import ViceIE
178ee883 109from .xfileshare import XFileShareIE
660a230b 110from .cloudflarestream import CloudflareStreamIE
6bd499e8 111from .peertube import PeerTubeIE
aee36ca8 112from .indavideo import IndavideoEmbedIE
cfd7f2a6 113from .apa import APAIE
9b122384 114
0838239e 115
9b122384 116class GenericIE(InfoExtractor):
79649588 117 IE_DESC = 'Generic downloader that works on some sites'
9b122384 118 _VALID_URL = r'.*'
79649588 119 IE_NAME = 'generic'
cfe50f04 120 _TESTS = [
c5fa81fe
S
121 # Direct link to a video
122 {
123 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
124 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
125 'info_dict': {
126 'id': 'trailer',
127 'ext': 'mp4',
128 'title': 'trailer',
129 'upload_date': '20100513',
130 }
131 },
c5138a7c 132 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
133 {
134 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
135 'md5': '128c42e68b13950268b648275386fc74',
136 'info_dict': {
137 'id': 'FictionJunction-Parallel_Hearts',
138 'ext': 'flac',
139 'title': 'FictionJunction-Parallel_Hearts',
140 'upload_date': '20140522',
141 },
142 'expected_warnings': [
143 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
144 ],
145 'skip': 'URL invalid',
c5fa81fe
S
146 },
147 # Direct download with broken HEAD
148 {
149 'url': 'http://ai-radio.org:8000/radio.opus',
150 'info_dict': {
151 'id': 'radio',
152 'ext': 'opus',
153 'title': 'radio',
154 },
155 'params': {
156 'skip_download': True, # infinite live stream
157 },
158 'expected_warnings': [
ef0e4e7b
YCH
159 r'501.*Not Implemented',
160 r'400.*Bad Request',
c5fa81fe
S
161 ],
162 },
163 # Direct link with incorrect MIME type
164 {
165 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
166 'md5': '4ccbebe5f36706d85221f204d7eb5913',
167 'info_dict': {
168 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
169 'id': '5_Lennart_Poettering_-_Systemd',
170 'ext': 'webm',
171 'title': '5_Lennart_Poettering_-_Systemd',
172 'upload_date': '20141120',
173 },
174 'expected_warnings': [
175 'URL could be a direct video link, returning it as such.'
176 ]
177 },
178 # RSS feed
179 {
180 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
181 'info_dict': {
182 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
183 'title': 'Zero Punctuation',
184 'description': 're:.*groundbreaking video review series.*'
185 },
186 'playlist_mincount': 11,
187 },
188 # RSS feed with enclosure
189 {
190 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
191 'info_dict': {
192 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
193 'ext': 'm4v',
194 'upload_date': '20150228',
195 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
196 }
197 },
01aec848
BG
198 # RSS feed with enclosures and unsupported link URLs
199 {
200 'url': 'http://www.hellointernet.fm/podcast?format=rss',
201 'info_dict': {
202 'id': 'http://www.hellointernet.fm/podcast?format=rss',
203 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
204 'title': 'Hello Internet',
205 },
206 'playlist_mincount': 100,
207 },
8765222d
S
208 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
209 {
210 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
211 'info_dict': {
212 'id': 'smil',
213 'ext': 'mp4',
214 'title': 'Automatics, robotics and biocybernetics',
215 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 216 'upload_date': '20130627',
8765222d
S
217 'formats': 'mincount:16',
218 'subtitles': 'mincount:1',
219 },
220 'params': {
221 'force_generic_extractor': True,
222 'skip_download': True,
223 },
224 },
225 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
226 {
227 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
228 'info_dict': {
229 'id': 'hds',
230 'ext': 'flv',
231 'title': 'hds',
232 'formats': 'mincount:1',
233 },
234 'params': {
235 'skip_download': True,
236 },
237 },
238 # SMIL from https://www.restudy.dk/video/play/id/1637
239 {
240 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
241 'info_dict': {
242 'id': 'video_1637',
243 'ext': 'flv',
244 'title': 'video_1637',
245 'formats': 'mincount:3',
246 },
247 'params': {
248 'skip_download': True,
249 },
250 },
251 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
252 {
253 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
254 'info_dict': {
255 'id': 'smil-service',
256 'ext': 'flv',
257 'title': 'smil-service',
258 'formats': 'mincount:1',
259 },
260 'params': {
261 'skip_download': True,
262 },
263 },
264 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
265 {
266 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
267 'info_dict': {
268 'id': '4719370',
269 'ext': 'mp4',
270 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
271 'formats': 'mincount:3',
272 },
273 'params': {
274 'skip_download': True,
275 },
276 },
1de5cd3b
S
277 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
278 {
279 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
280 'info_dict': {
281 'id': 'mZlp2ctYIUEB',
282 'ext': 'mp4',
283 'title': 'Tikibad ontruimd wegens brand',
284 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 285 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
286 'duration': 33,
287 },
288 'params': {
289 'skip_download': True,
290 },
291 },
9d939cec
S
292 # MPD from http://dash-mse-test.appspot.com/media.html
293 {
294 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
295 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
296 'info_dict': {
297 'id': 'car-20120827-manifest',
298 'ext': 'mp4',
299 'title': 'car-20120827-manifest',
300 'formats': 'mincount:9',
0738187f 301 'upload_date': '20130904',
9d939cec
S
302 },
303 'params': {
304 'format': 'bestvideo',
305 },
306 },
20938f76
S
307 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
308 {
309 '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',
310 'info_dict': {
311 'id': 'content',
312 'ext': 'mp4',
313 'title': 'content',
314 'formats': 'mincount:8',
315 },
316 'params': {
317 # m3u8 downloads
318 'skip_download': True,
39efc6e3
YCH
319 },
320 'skip': 'video gone',
20938f76 321 },
edd9b71c
S
322 # m3u8 served with Content-Type: text/plain
323 {
324 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
325 'info_dict': {
326 'id': 'index',
327 'ext': 'mp4',
328 'title': 'index',
329 'upload_date': '20140720',
330 'formats': 'mincount:11',
331 },
332 'params': {
333 # m3u8 downloads
334 'skip_download': True,
39efc6e3
YCH
335 },
336 'skip': 'video gone',
edd9b71c 337 },
c5fa81fe
S
338 # google redirect
339 {
340 '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',
341 'info_dict': {
342 'id': 'cmQHVoWB5FY',
343 'ext': 'mp4',
344 'upload_date': '20130224',
345 'uploader_id': 'TheVerge',
ec85ded8 346 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
347 'uploader': 'The Verge',
348 'title': 'First Firefox OS phones side-by-side',
349 },
350 'params': {
351 'skip_download': False,
352 }
353 },
6c91a5a7
S
354 {
355 # redirect in Refresh HTTP header
356 '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',
357 'info_dict': {
358 'id': 'pO8h3EaFRdo',
359 'ext': 'mp4',
360 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
361 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
362 'upload_date': '20150917',
363 'uploader_id': 'brtvofficial',
364 'uploader': 'Boiler Room',
365 },
366 'params': {
367 'skip_download': False,
368 },
369 },
cfe50f04 370 {
79649588 371 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 372 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 373 'info_dict': {
d360a146
S
374 'id': '13601338388002',
375 'ext': 'mp4',
79649588
PH
376 'uploader': 'www.hodiho.fr',
377 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
378 }
379 },
c19f7764
JMF
380 # bandcamp page with custom domain
381 {
79649588
PH
382 'add_ie': ['Bandcamp'],
383 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 384 'info_dict': {
fd50bf62
S
385 'id': '3235767654',
386 'ext': 'mp3',
79649588
PH
387 'title': 'The Pony Mash',
388 'uploader': 'M_Pallante',
c19f7764 389 },
79649588 390 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 391 },
eeb165e6 392 {
53a664ed
S
393 # embedded brightcove video
394 # it also tests brightcove videos that need to set the 'Referer'
395 # in the http requests
3b7d9aa4 396 'add_ie': ['BrightcoveLegacy'],
79649588
PH
397 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
398 'info_dict': {
399 'id': '2765128793001',
400 'ext': 'mp4',
401 'title': 'Le cours de bourse : l’analyse technique',
402 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
403 'uploader': 'BFM BUSINESS',
eeb165e6 404 },
79649588
PH
405 'params': {
406 'skip_download': True,
eeb165e6
JMF
407 },
408 },
53a664ed
S
409 {
410 # embedded with itemprop embedURL and video id spelled as `idVideo`
411 'add_id': ['BrightcoveLegacy'],
412 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
413 'info_dict': {
414 'id': '5255628253001',
415 'ext': 'mp4',
416 'title': 'md5:37c519b1128915607601e75a87995fc0',
417 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
418 'uploader': 'BFM BUSINESS',
419 'uploader_id': '876450612001',
420 'timestamp': 1482255315,
421 'upload_date': '20161220',
422 },
423 'params': {
424 'skip_download': True,
425 },
426 },
17ab4d3b
PH
427 {
428 # https://github.com/rg3/youtube-dl/issues/2253
429 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
430 'md5': '0ba9446db037002366bab3b3eb30c88c',
431 'info_dict': {
fd50bf62
S
432 'id': '3101154703001',
433 'ext': 'mp4',
17ab4d3b
PH
434 'title': 'Still no power',
435 'uploader': 'thestar.com',
436 '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.',
437 },
3b7d9aa4 438 'add_ie': ['BrightcoveLegacy'],
39efc6e3 439 'skip': 'video gone',
17ab4d3b 440 },
0479c625
S
441 {
442 'url': 'http://www.championat.com/video/football/v/87/87499.html',
443 'md5': 'fb973ecf6e4a78a67453647444222983',
444 'info_dict': {
445 'id': '3414141473001',
446 'ext': 'mp4',
447 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
448 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
449 'uploader': 'Championat',
450 },
451 },
bdf97017 452 {
37aab278 453 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 454 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
455 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
456 'info_dict': {
457 'id': '3866516442001',
37aab278 458 'ext': 'mp4',
bdf97017
NJ
459 'title': 'Leer mij vrouwen kennen: Aflevering 1',
460 'description': 'Leer mij vrouwen kennen: Aflevering 1',
461 'uploader': 'SBS Broadcasting',
462 },
37aab278 463 'skip': 'Restricted to Netherlands',
bdf97017 464 'params': {
37aab278 465 'skip_download': True, # m3u8 download
bdf97017
NJ
466 },
467 },
06d0ad9a
YCH
468 {
469 # Brightcove video in <iframe>
470 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
471 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
472 'info_dict': {
473 'id': '5360463607001',
474 'ext': 'mp4',
475 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
476 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
477 'uploader': 'United Nations',
478 'uploader_id': '1362235914001',
479 'timestamp': 1489593889,
480 'upload_date': '20170315',
481 },
482 'add_ie': ['BrightcoveLegacy'],
483 },
16e2c8f7
YCH
484 {
485 # Brightcove with alternative playerID key
486 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
487 'info_dict': {
488 'id': 'nmeth.2062_SV1',
489 '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',
490 },
491 'playlist': [{
492 'info_dict': {
493 'id': '2228375078001',
494 'ext': 'mp4',
495 'title': 'nmeth.2062-sv1',
496 'description': 'nmeth.2062-sv1',
497 'timestamp': 1363357591,
498 'upload_date': '20130315',
499 'uploader': 'Nature Publishing Group',
500 'uploader_id': '1964492299001',
501 },
502 }],
503 },
40158f55
JH
504 {
505 # Brightcove with UUID in videoPlayer
506 'url': 'http://www8.hp.com/cn/zh/home.html',
507 'info_dict': {
508 'id': '5255815316001',
509 'ext': 'mp4',
510 'title': 'Sprocket Video - China',
511 'description': 'Sprocket Video - China',
512 'uploader': 'HP-Video Gallery',
513 'timestamp': 1482263210,
514 'upload_date': '20161220',
515 'uploader_id': '1107601872001',
516 },
517 'params': {
518 'skip_download': True, # m3u8 download
519 },
520 'skip': 'video rotates...weekly?',
521 },
522 {
523 # Brightcove:new type [2].
524 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
525 'md5': '2b35148fcf48da41c9fb4591650784f3',
526 'info_dict': {
527 'id': '5348741021001',
528 'ext': 'mp4',
529 'upload_date': '20170306',
530 'uploader_id': '4191638492001',
531 'timestamp': 1488769918,
532 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
533
534 },
535 },
536 {
537 # Alternative brightcove <video> attributes
538 '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/',
539 'info_dict': {
540 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
541 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
542 },
543 'playlist': [{
544 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
545 'info_dict': {
546 'id': '5311302538001',
547 'ext': 'mp4',
548 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
549 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
550 'timestamp': 1486321708,
551 'upload_date': '20170205',
552 'uploader_id': '800000640001',
553 },
554 'only_matching': True,
555 }],
556 },
b68a812e
S
557 {
558 # Brightcove with UUID in videoPlayer
559 'url': 'http://www8.hp.com/cn/zh/home.html',
560 'info_dict': {
561 'id': '5255815316001',
562 'ext': 'mp4',
563 'title': 'Sprocket Video - China',
564 'description': 'Sprocket Video - China',
565 'uploader': 'HP-Video Gallery',
566 'timestamp': 1482263210,
567 'upload_date': '20161220',
568 'uploader_id': '1107601872001',
569 },
570 'params': {
571 'skip_download': True, # m3u8 download
572 },
573 },
c0d0b01f
JMF
574 # ooyala video
575 {
79649588 576 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 577 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
578 'info_dict': {
579 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
580 'ext': 'mp4',
3486df38 581 'title': '2cc213299525360.mov', # that's what we get
53e06b25 582 'duration': 238.231,
c0d0b01f 583 },
87830900 584 'add_ie': ['Ooyala'],
c0d0b01f 585 },
bf94d763
S
586 {
587 # ooyala video embedded with http://player.ooyala.com/iframe.js
588 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
589 'info_dict': {
590 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
591 'ext': 'mp4',
592 'title': '"Steve Jobs: Man in the Machine" trailer',
593 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 594 'duration': 135.427,
bf94d763
S
595 },
596 'params': {
597 'skip_download': True,
598 },
39efc6e3 599 'skip': 'movie expired',
bf94d763 600 },
198d4cb4
GR
601 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
602 {
603 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
604 'info_dict': {
605 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
606 'ext': 'mp4',
607 'title': 'Steampunk Fest Comes to Honesdale',
608 'duration': 43.276,
609 },
610 'params': {
611 'skip_download': True,
612 }
613 },
1b86cc41 614 # embed.ly video
615 {
616 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
617 'info_dict': {
618 'id': '9ODmcdjQcHQ',
619 'ext': 'mp4',
0a5bce56
PH
620 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
621 'upload_date': '20140225',
622 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
623 'uploader': 'Tested',
624 'uploader_id': 'testedcom',
1b86cc41 625 },
626 # No need to test YoutubeIE here
627 'params': {
628 'skip_download': True,
629 },
630 },
60cc4dc4
PH
631 # funnyordie embed
632 {
633 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
634 'info_dict': {
635 'id': '18e820ec3f',
636 'ext': 'mp4',
637 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
638 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 639 },
39efc6e3
YCH
640 # HEAD requests lead to endless 301, while GET is OK
641 'expected_warnings': ['301'],
60cc4dc4 642 },
93d020dd
S
643 # RUTV embed
644 {
645 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
646 'info_dict': {
647 'id': '776940',
648 'ext': 'mp4',
649 'title': 'Охотское море стало целиком российским',
650 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
651 },
652 'params': {
653 # m3u8 download
654 'skip_download': True,
655 },
aab74fa1 656 },
f37bdbe5
S
657 # TVC embed
658 {
659 '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/',
660 'info_dict': {
661 'id': '55304',
662 'ext': 'mp4',
663 'title': 'Дошкольное воспитание',
664 },
665 },
b827a601
S
666 # SportBox embed
667 {
668 'url': 'http://www.vestifinance.ru/articles/25753',
669 'info_dict': {
670 'id': '25753',
05d1e7aa 671 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
672 },
673 'playlist': [{
674 'info_dict': {
675 'id': '370908',
676 'title': 'Госзаказ. День 3',
677 'ext': 'mp4',
678 }
679 }, {
680 'info_dict': {
681 'id': '370905',
682 'title': 'Госзаказ. День 2',
683 'ext': 'mp4',
684 }
685 }, {
686 'info_dict': {
687 'id': '370902',
688 'title': 'Госзаказ. День 1',
689 'ext': 'mp4',
690 }
691 }],
692 'params': {
693 # m3u8 download
694 'skip_download': True,
695 },
696 },
bf20b9c5
S
697 # Myvi.ru embed
698 {
699 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
700 'info_dict': {
701 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
702 'ext': 'mp4',
703 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 704 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
705 'duration': 153,
706 }
707 },
c76799c5
S
708 # XHamster embed
709 {
710 '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',
711 'info_dict': {
712 'id': 'showthread',
713 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
714 },
715 'playlist_mincount': 7,
39efc6e3
YCH
716 # This forum does not allow <iframe> syntaxes anymore
717 # Now HTML tags are displayed as-is
718 'skip': 'No videos on this page',
c76799c5 719 },
aab74fa1
PH
720 # Embedded TED video
721 {
722 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 723 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 724 'info_dict': {
a8eb5a8e 725 'id': '1969',
aab74fa1 726 'ext': 'mp4',
a8eb5a8e
PH
727 'title': 'Hidden miracles of the natural world',
728 'uploader': 'Louie Schwartzberg',
729 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 730 }
60cc4dc4 731 },
d95e35d6
S
732 # nowvideo embed hidden behind percent encoding
733 {
734 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
735 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
736 'info_dict': {
737 'id': '06e53103ca9aa',
738 'ext': 'flv',
739 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
740 'description': 'No description',
741 },
0f2a2ba1 742 },
893f8832
PH
743 # arte embed
744 {
745 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
746 'md5': '7653032cbb25bf6c80d80f217055fa43',
747 'info_dict': {
748 'id': '048195-004_PLUS7-F',
749 'ext': 'flv',
750 'title': 'X:enius',
751 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
752 'upload_date': '20140320',
753 },
754 'params': {
755 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
756 },
757 'skip': 'video gone',
893f8832 758 },
cbd55ade
S
759 # francetv embed
760 {
761 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
762 'info_dict': {
763 'id': 'EV_30231',
764 'ext': 'mp4',
765 'title': 'Alcaline, le concert avec Calogero',
766 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
767 'upload_date': '20150226',
768 'timestamp': 1424989860,
769 'duration': 5400,
770 },
771 'params': {
772 # m3u8 downloads
773 'skip_download': True,
774 },
775 'expected_warnings': [
776 'Forbidden'
777 ]
778 },
fa35cdad
PH
779 # Condé Nast embed
780 {
781 'url': 'http://www.wired.com/2014/04/honda-asimo/',
782 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
783 'info_dict': {
784 'id': '53501be369702d3275860000',
785 'ext': 'mp4',
786 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
787 }
ebd3c7b3
PH
788 },
789 # Dailymotion embed
790 {
791 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
792 'md5': '441aeeb82eb72c422c7f14ec533999cd',
793 'info_dict': {
794 'id': 'k2mm4bCdJ6CQ2i7c8o2',
795 'ext': 'mp4',
796 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 797 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 798 'uploader': 'Spi0n',
0738187f
YCH
799 'uploader_id': 'xgditw',
800 'upload_date': '20140425',
801 'timestamp': 1398441542,
ebd3c7b3
PH
802 },
803 'add_ie': ['Dailymotion'],
2b88feed 804 },
71a1db89
S
805 # DailyMail embed
806 {
807 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
808 'info_dict': {
809 'id': '1495629',
810 'ext': 'mp4',
811 'title': 'Care worker punches elderly dementia patient in head 11 times',
812 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
813 },
814 'add_ie': ['DailyMail'],
815 'params': {
816 'skip_download': True,
817 },
818 },
2b88feed
PH
819 # YouTube embed
820 {
821 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
822 'info_dict': {
823 'id': 'FXRb4ykk4S0',
824 'ext': 'mp4',
825 'title': 'The NBL Auction 2014',
826 'uploader': 'BADMINTON England',
827 'uploader_id': 'BADMINTONEvents',
828 'upload_date': '20140603',
829 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
830 },
831 'add_ie': ['Youtube'],
832 'params': {
833 'skip_download': True,
834 }
835 },
c5cd249e
JMF
836 # MTVSercices embed
837 {
1fa309da
YCH
838 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
839 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 840 'info_dict': {
1fa309da 841 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 842 'ext': 'mp4',
1fa309da
YCH
843 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
844 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
845 'timestamp': 1349922600,
846 'upload_date': '20121011',
c5cd249e
JMF
847 },
848 },
61013473 849 # YouTube embed via <data-embed-url="">
850 {
851 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 852 'info_dict': {
a8eb5a8e 853 'id': '4vAffPZIT44',
61013473 854 'ext': 'mp4',
a8eb5a8e 855 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
856 'uploader': 'Gameloft',
857 'uploader_id': 'gameloft',
a8eb5a8e
PH
858 'upload_date': '20140828',
859 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
860 },
861 'params': {
862 'skip_download': True,
61013473 863 }
c8e9a235 864 },
61568e50
JH
865 # YouTube <object> embed
866 {
867 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
868 'md5': '516718101ec834f74318df76259fb3cc',
869 'info_dict': {
870 'id': 'msN87y-iEx0',
871 'ext': 'webm',
872 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
873 'upload_date': '20080526',
874 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
875 'uploader': 'Christopher Sykes',
876 'uploader_id': 'ChristopherJSykes',
877 },
878 'add_ie': ['Youtube'],
879 },
c8e9a235
PH
880 # Camtasia studio
881 {
882 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
883 'playlist': [{
884 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
885 'info_dict': {
886 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
887 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
888 'ext': 'flv',
889 'duration': 2235.90,
890 }
891 }, {
892 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
893 'info_dict': {
894 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
895 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
896 'ext': 'flv',
897 'duration': 2235.93,
898 }
899 }],
900 'info_dict': {
901 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
902 }
4d805e06
PH
903 },
904 # Flowplayer
905 {
906 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
907 'md5': '9d65602bf31c6e20014319c7d07fba27',
908 'info_dict': {
909 'id': '5123ea6d5e5a7',
910 'ext': 'mp4',
911 'age_limit': 18,
912 'uploader': 'www.handjobhub.com',
d6d9186f 913 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 914 }
0990305d 915 },
22a6f150
PH
916 # Multiple brightcove videos
917 # https://github.com/rg3/youtube-dl/issues/2283
918 {
919 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
920 'info_dict': {
921 'id': 'always-never',
922 'title': 'Always / Never - The New Yorker',
923 },
924 'playlist_count': 3,
925 'params': {
926 'extract_flat': False,
927 'skip_download': True,
928 }
1a94ff68
S
929 },
930 # MLB embed
931 {
932 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
933 'md5': '96f09a37e44da40dd083e12d9a683327',
934 'info_dict': {
935 'id': '33322633',
936 'ext': 'mp4',
937 'title': 'Ump changes call to ball',
938 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
939 'duration': 48,
940 'timestamp': 1401537900,
941 'upload_date': '20140531',
ec85ded8 942 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
943 },
944 },
746c67d7
NJ
945 # Wistia embed
946 {
6c114b12
S
947 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
948 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 949 'info_dict': {
6c114b12 950 'id': '6e2wtrbdaf',
746c67d7 951 'ext': 'mov',
6c114b12
S
952 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
953 'description': 'a Paywall Videos video from Remilon',
954 'duration': 644.072,
955 'uploader': 'study.com',
956 'timestamp': 1459678540,
957 'upload_date': '20160403',
958 'filesize': 24687186,
746c67d7
NJ
959 },
960 },
52cffcb1 961 {
962 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
963 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
964 'info_dict': {
965 'id': 'uxjb0lwrcz',
966 'ext': 'mp4',
6c114b12 967 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 968 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 969 'duration': 1715.0,
85d7b765 970 'uploader': 'thoughtworks.wistia.com',
0738187f 971 'timestamp': 1401832161,
6c114b12 972 'upload_date': '20140603',
70b7e3fb 973 },
52cffcb1 974 },
7ded6545
S
975 # Wistia standard embed (async)
976 {
977 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
978 'info_dict': {
979 'id': '807fafadvk',
980 'ext': 'mp4',
981 'title': 'Drip Brennan Dunn Workshop',
982 'description': 'a JV Webinars video from getdrip-1',
983 'duration': 4986.95,
7ded6545 984 'timestamp': 1463607249,
6c114b12 985 'upload_date': '20160518',
7ded6545
S
986 },
987 'params': {
988 'skip_download': True,
989 }
990 },
ac645ac7
PH
991 # Soundcloud embed
992 {
993 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
994 'info_dict': {
995 'id': '174391317',
996 'ext': 'mp3',
997 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
998 'uploader': 'Sophos Security',
999 'title': 'Chet Chat 171 - Oct 29, 2014',
1000 'upload_date': '20141029',
1001 }
af63fed7 1002 },
db19df6c
S
1003 # Soundcloud multiple embeds
1004 {
1005 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1006 'info_dict': {
1007 'id': '52809',
1008 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1009 },
1010 'playlist_mincount': 7,
1011 },
027e2312
S
1012 # TuneIn station embed
1013 {
1014 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1015 'info_dict': {
1016 'id': '204146',
1017 'ext': 'mp3',
1018 'title': 'CNRV',
1019 'location': 'Paris, France',
1020 'is_live': True,
1021 },
1022 'params': {
1023 # Live stream
1024 'skip_download': True,
1025 },
1026 },
af63fed7
PH
1027 # Livestream embed
1028 {
1029 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1030 'info_dict': {
1031 'id': '67864563',
1032 'ext': 'flv',
1033 'upload_date': '20141112',
1034 'title': 'Rosetta #CometLanding webcast HL 10',
1035 }
1036 },
78d3b3e2
YCH
1037 # Another Livestream embed, without 'new.' in URL
1038 {
1039 'url': 'https://www.freespeech.org/',
1040 'info_dict': {
1041 'id': '123537347',
1042 'ext': 'mp4',
1043 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1044 },
1045 'params': {
1046 # Live stream
1047 'skip_download': True,
1048 },
1049 },
65f3a228
PH
1050 # LazyYT
1051 {
e8e4cc5a 1052 'url': 'https://skiplagged.com/',
65f3a228 1053 'info_dict': {
e8e4cc5a
JH
1054 'id': 'skiplagged',
1055 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1056 },
e8e4cc5a
JH
1057 'playlist_mincount': 1,
1058 'add_ie': ['Youtube'],
4e262a88 1059 },
42bdd9d0
PH
1060 # Cinchcast embed
1061 {
1062 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1063 'info_dict': {
1064 'id': '7141703',
1065 'ext': 'mp3',
1066 'upload_date': '20141126',
1067 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1068 }
1069 },
501f13fb
PH
1070 # Cinerama player
1071 {
1072 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1073 'info_dict': {
1074 'id': '730m_DandD_1901_512k',
1075 'ext': 'mp4',
1076 'uploader': 'www.abc.net.au',
1077 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1078 }
796df3c6
S
1079 },
1080 # embedded viddler video
1081 {
1082 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1083 'info_dict': {
1084 'id': '4d03aad9',
1085 'ext': 'mp4',
1086 'uploader': 'deadspin',
1087 'title': 'WALL-TO-GORTAT',
1088 'timestamp': 1422285291,
1089 'upload_date': '20150126',
1090 },
1091 'add_ie': ['Viddler'],
a0f71985 1092 },
2051acde
S
1093 # Libsyn embed
1094 {
1095 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1096 'info_dict': {
1097 'id': '3377616',
1098 'ext': 'mp3',
1099 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1100 'description': 'md5:601cb790edd05908957dae8aaa866465',
1101 'upload_date': '20150220',
1102 },
326fa4e6 1103 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1104 },
a0f71985
PH
1105 # jwplayer YouTube
1106 {
1107 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1108 'info_dict': {
1109 'id': 'Mrj4DVp2zeA',
1110 'ext': 'mp4',
f37e3f99 1111 'upload_date': '20150212',
a0f71985 1112 'uploader': 'The National Archives UK',
2637fadc 1113 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1114 'uploader_id': 'NationalArchives08',
1115 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1116 },
59b8ab58 1117 },
5620f840
S
1118 # jwplayer rtmp
1119 {
6899b1d9 1120 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1121 'info_dict': {
6899b1d9 1122 'id': 'live',
5620f840
S
1123 'ext': 'flv',
1124 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1125 'uploader': 'www.suffolk.edu',
1126 },
1127 'params': {
1128 'skip_download': True,
2637fadc 1129 },
6899b1d9 1130 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1131 },
a4a554a7
YCH
1132 # Complex jwplayer
1133 {
1134 'url': 'http://www.indiedb.com/games/king-machine/videos',
1135 'info_dict': {
1136 'id': 'videos',
1137 'ext': 'mp4',
1138 'title': 'king machine trailer 1',
2637fadc 1139 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1140 'thumbnail': r're:^https?://.*\.jpg$',
1141 },
1142 },
03486dbb
RU
1143 {
1144 # JWPlayer config passed as variable
1145 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1146 'info_dict': {
1147 'id': '3326530_hq',
1148 'ext': 'mp4',
1149 'title': 'ARIELE | Tube Cup',
1150 'uploader': 'www.txxx.com',
1151 'age_limit': 18,
1152 },
1153 'params': {
1154 'skip_download': True,
1155 }
1156 },
939be9ad
JH
1157 {
1158 # JWPlatform iframe
1159 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1160 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1161 'info_dict': {
1162 'id': 'O0c5JcKT',
1163 'ext': 'mp4',
1164 'upload_date': '20171122',
1165 'timestamp': 1511366290,
1166 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1167 },
805f5bf7 1168 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1169 },
63d990d2 1170 {
c5b7014a 1171 # Video.js embed, multiple formats
63d990d2
S
1172 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1173 'info_dict': {
1174 'id': 'yygqldloqIk',
1175 'ext': 'mp4',
1176 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1177 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1178 'upload_date': '20130314',
1179 'uploader': 'PROстое3D',
1180 'uploader_id': 'PROstoe3D',
1181 },
1182 'params': {
1183 'skip_download': True,
1184 },
1185 },
c5b7014a
S
1186 {
1187 # Video.js embed, single format
1188 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1189 'info_dict': {
1190 'id': 'watch',
1191 'ext': 'mp4',
1192 'title': 'Step 1 - Good Foundation',
1193 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1194 },
1195 'params': {
1196 'skip_download': True,
1197 },
1198 },
59b8ab58
PH
1199 # rtl.nl embed
1200 {
1201 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1202 'playlist_mincount': 5,
1203 'info_dict': {
1204 'id': 'aanslagen-kopenhagen',
2637fadc 1205 'title': 'Aanslagen Kopenhagen',
59b8ab58 1206 }
255fca5e
S
1207 },
1208 # Zapiks embed
1209 {
1210 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1211 'info_dict': {
1212 'id': '118046',
1213 'ext': 'mp4',
1214 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1215 }
1216 },
66e568de
S
1217 # Kaltura embed (different embed code)
1218 {
1219 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1220 'info_dict': {
1221 'id': '1_a52wc67y',
1222 'ext': 'flv',
1223 'upload_date': '20150127',
1224 'uploader_id': 'PremierMedia',
1225 'timestamp': int,
1226 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1227 },
1228 },
87703231
YCH
1229 # Kaltura embed with single quotes
1230 {
1231 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1232 'info_dict': {
1233 'id': '0_izeg5utt',
1234 'ext': 'mp4',
1235 'title': '35871',
1236 'timestamp': 1355743100,
1237 'upload_date': '20121217',
e30991f9 1238 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1239 },
1240 'add_ie': ['Kaltura'],
1241 },
427cd050
S
1242 {
1243 # Kaltura embedded via quoted entry_id
1244 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1245 'info_dict': {
1246 'id': '0_utuok90b',
1247 'ext': 'mp4',
1248 'title': '06_matthew_brender_raj_dutt',
1249 'timestamp': 1466638791,
1250 'upload_date': '20160622',
1251 },
1252 'add_ie': ['Kaltura'],
1253 'expected_warnings': [
1254 'Could not send HEAD request'
1255 ],
1256 'params': {
1257 'skip_download': True,
1258 }
1259 },
8ab7e6c4
YCH
1260 {
1261 # Kaltura embedded, some fileExt broken (#11480)
1262 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1263 'info_dict': {
1264 'id': '1_sgtvehim',
1265 'ext': 'mp4',
1266 'title': 'Our "Standard Models" of particle physics and cosmology',
1267 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1268 'timestamp': 1321158993,
1269 'upload_date': '20111113',
1270 'uploader_id': 'kps1',
1271 },
1272 'add_ie': ['Kaltura'],
1273 },
a01825a5
JH
1274 {
1275 # Kaltura iframe embed
1276 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1277 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1278 'info_dict': {
1279 'id': '0_f2cfbpwy',
1280 'ext': 'mp4',
1281 'title': 'I. M. Pei: A Centennial Celebration',
1282 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1283 'upload_date': '20170403',
1284 'uploader_id': 'batchUser',
1285 'timestamp': 1491232186,
1286 },
1287 'add_ie': ['Kaltura'],
1288 },
c21692fa
S
1289 {
1290 # Kaltura iframe embed, more sophisticated
1291 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1292 'info_dict': {
1293 'id': '1_9gzouybz',
1294 'ext': 'mp4',
1295 'title': 'lecture-05sep2017',
1296 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1297 'upload_date': '20170913',
1298 'uploader_id': 'eps2',
1299 'timestamp': 1505340777,
1300 },
1301 'params': {
1302 'skip_download': True,
1303 },
1304 'add_ie': ['Kaltura'],
1305 },
e30991f9
S
1306 {
1307 # meta twitter:player
1308 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1309 'info_dict': {
1310 'id': '0_01b42zps',
1311 'ext': 'mp4',
1312 'title': 'Main Twerk (Video)',
1313 'upload_date': '20171208',
1314 'uploader_id': 'sebastian.salinas@thechive.com',
1315 'timestamp': 1512713057,
1316 },
1317 'params': {
1318 'skip_download': True,
1319 },
1320 'add_ie': ['Kaltura'],
1321 },
250b042c
S
1322 # referrer protected EaglePlatform embed
1323 {
1324 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1325 'info_dict': {
1326 'id': '582306',
1327 'ext': 'mp4',
1328 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1329 'thumbnail': r're:^https?://.*\.jpg$',
1330 'duration': 3382,
1331 'view_count': int,
1332 },
1333 'params': {
1334 'skip_download': True,
1335 },
135c9c42 1336 },
665e9452 1337 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1338 {
1339 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1340 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1341 'info_dict': {
1342 'id': '12820',
1343 'ext': 'mp4',
1344 'title': "'O Sole Mio",
ec85ded8 1345 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1346 'duration': 216,
1347 'view_count': int,
1348 },
250b042c
S
1349 'params': {
1350 'skip_download': True,
1351 },
2637fadc 1352 'skip': 'This video is unavailable.',
d47ae7f6 1353 },
f8388757
S
1354 # Pladform embed
1355 {
1356 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1357 'info_dict': {
1358 'id': '100183293',
1359 'ext': 'mp4',
62259846 1360 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1361 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1362 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1363 'duration': 694,
1364 'age_limit': 0,
1365 },
2637fadc 1366 'skip': 'HTTP Error 404: Not Found',
f8388757 1367 },
c798f15b
S
1368 # Playwire embed
1369 {
1370 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1371 'info_dict': {
1372 'id': '3519514',
1373 'ext': 'mp4',
1374 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1375 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1376 'duration': 45.115,
1377 },
1378 },
ad320e9b
NJ
1379 # 5min embed
1380 {
1381 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1382 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1383 'info_dict': {
1384 'id': '518726732',
1385 'ext': 'mp4',
1386 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1387 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1388 'timestamp': 1427237531,
1389 'uploader': 'Crunch Report',
1390 'upload_date': '20150324',
1391 },
1392 'params': {
1393 # m3u8 download
1394 'skip_download': True,
ad320e9b
NJ
1395 },
1396 },
dc455a5f
S
1397 # SVT embed
1398 {
1399 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1400 'info_dict': {
1401 'id': '2900353',
1402 'ext': 'flv',
1403 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1404 'duration': 27,
1405 'age_limit': 0,
1406 },
1407 },
a4257017
S
1408 # Crooks and Liars embed
1409 {
1410 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1411 'info_dict': {
1412 'id': '8RUoRhRi',
1413 'ext': 'mp4',
1414 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1415 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1416 'timestamp': 1428207000,
1417 'upload_date': '20150405',
1418 'uploader': 'Heather',
1419 },
1420 },
1421 # Crooks and Liars external embed
1422 {
1423 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1424 'info_dict': {
1425 'id': 'MTE3MjUtMzQ2MzA',
1426 'ext': 'mp4',
1427 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1428 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1429 'timestamp': 1265032391,
1430 'upload_date': '20100201',
1431 'uploader': 'Heather',
1432 },
1433 },
facecb84 1434 # NBC Sports vplayer embed
a2edf2e7 1435 {
facecb84 1436 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1437 'info_dict': {
facecb84
S
1438 'id': 'ln7x1qSThw4k',
1439 'ext': 'flv',
1440 'title': "PFT Live: New leader in the 'new-look' defense",
1441 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1442 'uploader': 'NBCU-SPORTS',
1443 'upload_date': '20140107',
1444 'timestamp': 1389118457,
a2edf2e7 1445 },
2637fadc 1446 'skip': 'Invalid Page URL',
418c5cc3 1447 },
de3eb07e
YCH
1448 # NBC News embed
1449 {
1450 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1451 'md5': '1aa589c675898ae6d37a17913cf68d66',
1452 'info_dict': {
2637fadc 1453 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1454 'ext': 'mp4',
2637fadc 1455 'title': 'David Letterman: A Preview',
de3eb07e 1456 '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.',
2637fadc
RA
1457 'upload_date': '20160609',
1458 'timestamp': 1465431544,
1459 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1460 },
1461 },
418c5cc3
YCH
1462 # UDN embed
1463 {
811586eb 1464 'url': 'https://video.udn.com/news/300346',
01c58f84 1465 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1466 'info_dict': {
01c58f84 1467 'id': '300346',
418c5cc3 1468 'ext': 'mp4',
01c58f84 1469 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1470 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1471 },
1472 'params': {
1473 # m3u8 download
1474 'skip_download': True,
1475 },
2637fadc 1476 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1477 },
b26733ba
YCH
1478 # Brightcove URL in single quotes
1479 {
1480 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1481 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1482 'info_dict': {
1483 'id': '4255764656001',
1484 'ext': 'mp4',
1485 'title': 'SN Presents: Russell Martin, World Citizen',
1486 'description': 'To understand why he was the Toronto Blue Jays’ 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.',
1487 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1488 'uploader_id': '1704050871',
1489 'upload_date': '20150525',
1490 'timestamp': 1432570283,
b26733ba 1491 },
756f574e 1492 },
8084be78
S
1493 # OnionStudios embed
1494 {
1495 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1496 'info_dict': {
1497 'id': '2855',
1498 'ext': 'mp4',
1499 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1500 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1501 'uploader': 'ClickHole',
1502 'uploader_id': 'clickhole',
1503 }
1504 },
b8c1cc1a
S
1505 # SnagFilms embed
1506 {
1507 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1508 'info_dict': {
1509 'id': '74849a00-85a9-11e1-9660-123139220831',
1510 'ext': 'mp4',
1511 'title': '#whilewewatch',
1512 }
1513 },
a5158f38
YCH
1514 # AdobeTVVideo embed
1515 {
1516 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1517 'md5': '43662b577c018ad707a63766462b1e87',
1518 'info_dict': {
1519 'id': '2456',
1520 'ext': 'mp4',
1521 'title': 'New experience with Acrobat DC',
1522 'description': 'New experience with Acrobat DC',
1523 'duration': 248.667,
1524 },
1f812580 1525 },
ed126900 1526 # BrightcoveInPageEmbed embed
1527 {
1528 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1529 'info_dict': {
1530 'id': '4238694884001',
1531 'ext': 'flv',
1532 'title': 'Tabletop: Dread, Last Thoughts',
1533 'description': 'Tabletop: Dread, Last Thoughts',
1534 'duration': 51690,
1535 },
750b9ff0 1536 },
d10fe835
YCH
1537 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1538 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1539 {
1540 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1541 'info_dict': {
1542 'id': '4785848093001',
1543 'ext': 'mp4',
1544 'title': 'The Cardinal Pell Interview',
1545 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1546 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1547 'uploader_id': '2733773828001',
1548 'upload_date': '20160304',
1549 'timestamp': 1457083087,
d10fe835
YCH
1550 },
1551 'params': {
1552 # m3u8 downloads
1553 'skip_download': True,
1554 },
1555 },
9edf47df
S
1556 {
1557 # Brightcove embed with whitespace around attribute names
1558 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1559 'info_dict': {
1560 'id': '3167554373001',
1561 'ext': 'mp4',
1562 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1563 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1564 'uploader_id': '1079349493',
1565 'upload_date': '20140207',
1566 'timestamp': 1391810548,
1567 },
1568 'params': {
1569 'skip_download': True,
1570 },
1571 },
134c207e
YCH
1572 # Another form of arte.tv embed
1573 {
1574 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1575 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1576 'info_dict': {
1577 'id': '030273-562_PLUS7-F',
1578 'ext': 'mp4',
1579 'title': 'ARTE Reportage - Nulle part, en France',
1580 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1581 'upload_date': '20160409',
1582 },
1583 },
b8f67449
KM
1584 # LiveLeak embed
1585 {
1586 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1587 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1588 'info_dict': {
1589 'id': '874_1459135191',
1590 'ext': 'mp4',
1591 'title': 'Man shows poor quality of new apartment building',
1592 'description': 'The wall is like a sand pile.',
1593 'uploader': 'Lake8737',
09747ba7
YCH
1594 },
1595 'add_ie': [LiveLeakIE.ie_key()],
1596 },
1597 # Another LiveLeak embed pattern (#13336)
1598 {
1599 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1600 'info_dict': {
1601 'id': '2eb_1496309988',
1602 'ext': 'mp4',
1603 'title': 'Thief robs place where everyone was armed',
1604 'description': 'md5:694d73ee79e535953cf2488562288eee',
1605 'uploader': 'brazilwtf',
1606 },
1607 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1608 },
4a120778
YCH
1609 # Duplicated embedded video URLs
1610 {
1611 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1612 'info_dict': {
1613 'id': '149298443_480_16c25b74_2',
1614 'ext': 'mp4',
1615 'title': 'vs. Blue Orange Spring Game',
1616 'uploader': 'www.hudl.com',
1617 },
1618 },
371ddb14
S
1619 # twitter:player:stream embed
1620 {
1621 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1622 'info_dict': {
1623 'id': 'master',
1624 'ext': 'mp4',
1625 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1626 'uploader': 'www.rtl.be',
1627 },
1628 'params': {
1629 # m3u8 downloads
1630 'skip_download': True,
1631 },
1632 },
32917907
RA
1633 # twitter:player embed
1634 {
1635 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1636 'md5': 'a3e0df96369831de324f0778e126653c',
1637 'info_dict': {
1638 'id': '4909620399001',
1639 'ext': 'mp4',
1640 'title': 'What Do Black Holes Sound Like?',
1641 'description': 'what do black holes sound like',
1642 'upload_date': '20160524',
1643 'uploader_id': '29913724001',
1644 'timestamp': 1464107587,
1645 'uploader': 'TheAtlantic',
1646 },
1647 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1648 },
1649 # Facebook <iframe> embed
1650 {
1651 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1652 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1653 'info_dict': {
1654 'id': '599637780109885',
1655 'ext': 'mp4',
1656 'title': 'Facebook video #599637780109885',
1657 },
1658 },
fd1c5fba
S
1659 # Facebook <iframe> embed, plugin video
1660 {
1661 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1662 'info_dict': {
1663 'id': '1754168231264132',
1664 'ext': 'mp4',
1665 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1666 'uploader': 'Tariq Ramadan (official)',
1667 'timestamp': 1496758379,
1668 'upload_date': '20170606',
1669 },
1670 'params': {
1671 'skip_download': True,
1672 },
1673 },
fd6ca382
YCH
1674 # Facebook API embed
1675 {
1676 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1677 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1678 'info_dict': {
1679 'id': '10153467542406923',
1680 'ext': 'mp4',
1681 'title': 'Facebook video #10153467542406923',
1682 },
7deef1ba
YCH
1683 },
1684 # Wordpress "YouTube Video Importer" plugin
1685 {
1686 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1687 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1688 'info_dict': {
1689 'id': 'HNTXWDXV9Is',
1690 'ext': 'mp4',
1691 'title': 'Blue Devils Drumline Stanford lot 2016',
1692 'upload_date': '20160627',
1693 'uploader_id': 'GENOCIDE8GENERAL10',
1694 'uploader': 'cylus cyrus',
1695 },
1696 },
81953d1a
RA
1697 {
1698 # video stored on custom kaltura server
1699 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1700 'md5': '537617d06e64dfed891fa1593c4b30cc',
1701 'info_dict': {
1702 'id': '0_1iotm5bh',
1703 'ext': 'mp4',
1704 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1705 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1706 'uploader_id': 'videos.expansion@el-mundo.net',
1707 'upload_date': '20150429',
1708 'timestamp': 1430303472,
1709 },
1710 'add_ie': ['Kaltura'],
1711 },
c03adf90
YCH
1712 {
1713 # Non-standard Vimeo embed
1714 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1715 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1716 'info_dict': {
1717 'id': '148867247',
1718 'ext': 'mp4',
1719 'title': 'Understanding the web - Teaser',
1720 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1721 'upload_date': '20151214',
1722 'uploader': 'OpenClassrooms',
1723 'uploader_id': 'openclassrooms',
1724 },
1725 'add_ie': ['Vimeo'],
1726 },
a5ff05df
S
1727 {
1728 # generic vimeo embed that requires original URL passed as Referer
1729 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1730 'only_matching': True,
1731 },
1979969f
S
1732 {
1733 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1734 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1735 'info_dict': {
1736 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1737 'ext': 'mp4',
1738 'title': 'Big Buck Bunny',
1739 'description': 'Royalty free test video',
1740 'timestamp': 1432816365,
1741 'upload_date': '20150528',
1742 'is_live': False,
1743 },
1744 'params': {
1745 'skip_download': True,
1746 },
1747 'add_ie': [ArkenaIE.ie_key()],
1748 },
2a1321a2
S
1749 {
1750 '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/',
1751 'info_dict': {
1752 'id': '1c7141f46c',
1753 'ext': 'mp4',
1754 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1755 },
1756 'params': {
1757 'skip_download': True,
1758 },
1759 'add_ie': [Vbox7IE.ie_key()],
1760 },
b0c8f2e9
DR
1761 {
1762 # DBTV embeds
1763 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1764 'info_dict': {
1765 'id': '43254897',
1766 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1767 },
b0c8f2e9
DR
1768 'playlist_mincount': 3,
1769 },
e186a9ec
S
1770 {
1771 # Videa embeds
1772 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1773 'info_dict': {
1774 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1775 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1776 },
1777 'playlist_mincount': 2,
1778 },
b687c85e
S
1779 {
1780 # 20 minuten embed
1781 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1782 'info_dict': {
1783 'id': '523629',
1784 'ext': 'mp4',
1785 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1786 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1787 },
1788 'params': {
1789 'skip_download': True,
1790 },
1791 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1792 },
1793 {
1794 # VideoPress embed
1795 'url': 'https://en.support.wordpress.com/videopress/',
1796 'info_dict': {
1797 'id': 'OcobLTqC',
1798 'ext': 'm4v',
1799 'title': 'IMG_5786',
1800 'timestamp': 1435711927,
1801 'upload_date': '20150701',
1802 },
1803 'params': {
1804 'skip_download': True,
1805 },
1806 'add_ie': [VideoPressIE.ie_key()],
fef51645 1807 },
eb3079b6
S
1808 {
1809 # Rutube embed
1810 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1811 'info_dict': {
1812 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1813 'ext': 'flv',
1814 'title': 'Магаззино: Казань 2',
1815 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1816 'uploader': 'Магаззино',
1817 'upload_date': '20170228',
1818 'uploader_id': '996642',
1819 },
1820 'params': {
1821 'skip_download': True,
1822 },
1823 'add_ie': [RutubeIE.ie_key()],
1824 },
fef51645
YCH
1825 {
1826 # ThePlatform embedded with whitespaces in URLs
1827 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1828 'only_matching': True,
1829 },
97952bdb
JH
1830 {
1831 # Senate ISVP iframe https
1832 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1833 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1834 'info_dict': {
1835 'id': 'govtaff020316',
1836 'ext': 'mp4',
1837 'title': 'Integrated Senate Video Player',
1838 },
1839 'add_ie': [SenateISVPIE.ie_key()],
1840 },
ab87c260
S
1841 {
1842 # Limelight embeds (1 channel embed + 4 media embeds)
1843 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1844 'info_dict': {
1845 'id': 'FacilitatorTraining2017',
1846 'title': 'Facilitator Training 2017',
1847 },
1848 'playlist_mincount': 5,
1849 },
eb02940c
S
1850 {
1851 # Limelight embed (LimelightPlayerUtil.embed)
1852 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1853 'info_dict': {
1854 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1855 'ext': 'mp4',
1856 'title': '07448641',
1857 'timestamp': 1499890639,
1858 'upload_date': '20170712',
1859 },
1860 'params': {
1861 'skip_download': True,
1862 },
1863 'add_ie': ['LimelightMedia'],
1864 },
7986c3ab
S
1865 {
1866 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1867 'info_dict': {
1868 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1869 'title': 'Standoff with Walnut Creek murder suspect ends',
1870 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1871 },
1872 'playlist_mincount': 4,
1873 },
55719459
JH
1874 {
1875 # WashingtonPost embed
1876 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1877 'info_dict': {
1878 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1879 'ext': 'mp4',
1880 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1881 '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 — and enlisted actors.',
1882 'timestamp': 1455216756,
1883 'uploader': 'The Washington Post',
1884 'upload_date': '20160211',
1885 },
1886 'add_ie': [WashingtonPostIE.ie_key()],
1887 },
2b8e6a68
S
1888 {
1889 # Mediaset embed
1890 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1891 'info_dict': {
1892 'id': '720642',
1893 'ext': 'mp4',
1894 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1895 },
1896 'params': {
1897 'skip_download': True,
1898 },
1899 'add_ie': [MediasetIE.ie_key()],
1900 },
73cf76a9
S
1901 {
1902 # JOJ.sk embeds
1903 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1904 'info_dict': {
1905 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1906 'title': 'Slovenskom sa prehnala vlna silných búrok',
1907 },
1908 'playlist_mincount': 5,
1909 'add_ie': [JojIE.ie_key()],
1910 },
4328ddf8
S
1911 {
1912 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1913 'url': 'https://tvrain.ru/amp/418921/',
1914 'md5': 'cc00413936695987e8de148b67d14f1d',
1915 'info_dict': {
1916 'id': '418921',
1917 'ext': 'mp4',
1918 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1919 },
1920 },
41918eaa 1921 {
1922 # vzaar embed
1663bd6e
S
1923 'url': 'http://help.vzaar.com/article/165-embedding-video',
1924 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1925 'info_dict': {
1663bd6e 1926 'id': '8707641',
41918eaa 1927 'ext': 'mp4',
1663bd6e 1928 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1929 },
1930 },
9ce1ac40 1931 {
1932 # multiple HTML5 videos on one page
1933 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1934 'info_dict': {
1935 'id': 'keyscenarios',
1936 'title': 'Rescue Kit 14 Free Edition - Getting started',
1937 },
1938 'playlist_count': 4,
0987f2dd
T
1939 },
1940 {
1941 # vshare embed
1942 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1943 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1944 'info_dict': {
1945 'id': '0f64ce6',
1946 'title': 'vl14062007715967',
1947 'ext': 'mp4',
1948 }
2ca7ed41
S
1949 },
1950 {
1951 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1952 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1953 'info_dict': {
1954 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1955 'ext': 'mp4',
1956 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1957 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1958 'timestamp': 1474354800,
1959 'upload_date': '20160920',
1960 }
7d540621
S
1961 },
1962 {
1963 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1964 'info_dict': {
1965 'id': '1731611',
1966 'ext': 'mp4',
1967 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1968 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1969 'timestamp': 1516100691,
1970 'upload_date': '20180116',
1971 },
1972 'params': {
1973 'skip_download': True,
1974 },
1975 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1976 },
1977 {
1978 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1979 'info_dict': {
1980 'id': 'uPDB5I9wfp8',
1981 'ext': 'webm',
1982 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1983 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1984 'upload_date': '20160219',
1985 'uploader': 'Pocoyo - Português (BR)',
1986 'uploader_id': 'PocoyoBrazil',
1987 },
1988 'add_ie': [YoutubeIE.ie_key()],
1989 'params': {
1990 'skip_download': True,
1991 },
4c780fbd
S
1992 },
1993 {
1994 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1995 'info_dict': {
1996 'id': 'vMDE4NzI1Mjgt690b',
1997 'ext': 'mp4',
1998 'title': 'Котята',
1999 },
2000 'add_ie': [YapFilesIE.ie_key()],
2001 'params': {
2002 'skip_download': True,
2003 },
1fc37ca3 2004 },
660a230b
S
2005 {
2006 # CloudflareStream embed
2007 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2008 'info_dict': {
2009 'id': '31c9291ab41fac05471db4e73aa11717',
2010 'ext': 'mp4',
2011 'title': '31c9291ab41fac05471db4e73aa11717',
2012 },
2013 'add_ie': [CloudflareStreamIE.ie_key()],
2014 'params': {
2015 'skip_download': True,
2016 },
2017 },
6bd499e8
S
2018 {
2019 # PeerTube embed
2020 'url': 'https://joinpeertube.org/fr/home/',
2021 'info_dict': {
2022 'id': 'home',
2023 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2024 },
2025 'playlist_count': 2,
2026 },
aee36ca8
S
2027 {
2028 # Indavideo embed
2029 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2030 'info_dict': {
2031 'id': '1693903',
2032 'ext': 'mp4',
2033 'title': 'Így kell otthon hamburgert sütni',
2034 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2035 'timestamp': 1426330212,
2036 'upload_date': '20150314',
2037 'uploader': 'StreetKitchen',
2038 'uploader_id': '546363',
2039 },
2040 'add_ie': [IndavideoEmbedIE.ie_key()],
2041 'params': {
2042 'skip_download': True,
2043 },
2044 },
cfd7f2a6
S
2045 {
2046 # APA embed via JWPlatform embed
2047 'url': 'http://www.vol.at/blue-man-group/5593454',
2048 'info_dict': {
2049 'id': 'jjv85FdZ',
2050 'ext': 'mp4',
2051 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2052 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2053 'thumbnail': r're:^https?://.*\.jpg$',
2054 'duration': 254,
2055 'timestamp': 1519211149,
2056 'upload_date': '20180221',
2057 },
2058 'params': {
2059 'skip_download': True,
2060 },
2061 },
1fc37ca3
SO
2062 {
2063 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2064 'md5': 'b68d276de422ab07ee1d49388103f457',
2065 'info_dict': {
2066 'id': '83645793',
2067 'title': 'Lock up and get excited',
1fc37ca3 2068 'ext': 'mp4'
d3431dcb
S
2069 },
2070 'skip': 'TODO: fix nested playlists processing in tests',
2071 },
6e6b70d6
S
2072 # {
2073 # # TODO: find another test
2074 # # http://schema.org/VideoObject
2075 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2076 # 'md5': '888dcf08b7ea671381f00fab74692755',
2077 # 'info_dict': {
2078 # 'id': 'nyvTSJMKId',
2079 # 'ext': 'mp4',
2080 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2081 # 'description': '#love for cats.',
2082 # 'timestamp': 1461244995,
2083 # 'upload_date': '20160421',
2084 # },
2085 # 'params': {
2086 # 'force_generic_extractor': True,
2087 # },
2088 # }
cfe50f04 2089 ]
9b122384 2090
9b122384
PH
2091 def report_following_redirect(self, new_url):
2092 """Report information extraction."""
79649588 2093 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2094
4fc946b5
PH
2095 def _extract_rss(self, url, video_id, doc):
2096 playlist_title = doc.find('./channel/title').text
2097 playlist_desc_el = doc.find('./channel/description')
2098 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2099
76c73715
PH
2100 entries = []
2101 for it in doc.findall('./channel/item'):
01aec848
BG
2102 next_url = None
2103 enclosure_nodes = it.findall('./enclosure')
2104 for e in enclosure_nodes:
2105 next_url = e.attrib.get('url')
2106 if next_url:
2107 break
2108
76c73715 2109 if not next_url:
01aec848 2110 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2111
2112 if not next_url:
2113 continue
2114
2115 entries.append({
413c1f8e 2116 '_type': 'url_transparent',
76c73715
PH
2117 'url': next_url,
2118 'title': it.find('title').text,
2119 })
4fc946b5
PH
2120
2121 return {
2122 '_type': 'playlist',
2123 'id': url,
2124 'title': playlist_title,
2125 'description': playlist_desc,
2126 'entries': entries,
2127 }
2128
c8e9a235
PH
2129 def _extract_camtasia(self, url, video_id, webpage):
2130 """ Returns None if no camtasia video can be found. """
2131
2132 camtasia_cfg = self._search_regex(
2133 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2134 webpage, 'camtasia configuration file', default=None)
2135 if camtasia_cfg is None:
2136 return None
2137
2138 title = self._html_search_meta('DC.title', webpage, fatal=True)
2139
2140 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2141 camtasia_cfg = self._download_xml(
2142 camtasia_url, video_id,
2143 note='Downloading camtasia configuration',
2144 errnote='Failed to download camtasia configuration')
2145 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2146
2147 entries = []
2148 for n in fileset_node.getchildren():
2149 url_n = n.find('./uri')
2150 if url_n is None:
2151 continue
2152
2153 entries.append({
2154 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2155 'title': '%s - %s' % (title, n.tag),
2156 'url': compat_urlparse.urljoin(url, url_n.text),
2157 'duration': float_or_none(n.find('./duration').text),
2158 })
2159
2160 return {
2161 '_type': 'playlist',
2162 'entries': entries,
2163 'title': title,
2164 }
2165
9b122384 2166 def _real_extract(self, url):
ebd3c7b3
PH
2167 if url.startswith('//'):
2168 return {
2169 '_type': 'url',
20991253 2170 'url': self.http_scheme() + url,
ebd3c7b3
PH
2171 }
2172
a7130543
JMF
2173 parsed_url = compat_urlparse.urlparse(url)
2174 if not parsed_url.scheme:
04b4d394
PH
2175 default_search = self._downloader.params.get('default_search')
2176 if default_search is None:
1f7ccb90 2177 default_search = 'fixup_error'
04b4d394 2178
1f7ccb90 2179 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2180 if '/' in url:
2181 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2182 return self.url_result('http://' + url)
1f7ccb90 2183 elif default_search != 'fixup_error':
9c1fc022 2184 if default_search == 'auto_warning':
0e67ab0d
PH
2185 if re.match(r'^(?:url|URL)$', url):
2186 raise ExtractorError(
2187 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2188 expected=True)
2189 else:
2190 self._downloader.report_warning(
7571c02c 2191 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2192 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2193
2194 if default_search in ('error', 'fixup_error'):
7571c02c 2195 raise ExtractorError(
b74e86f4
PH
2196 '%r is not a valid URL. '
2197 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2198 % (url, url), expected=True)
04b4d394 2199 else:
f2f2c0c2
PH
2200 if ':' not in default_search:
2201 default_search += ':'
04b4d394 2202 return self.url_result(default_search + url)
4d54ef20
PH
2203
2204 url, smuggled_data = unsmuggle_url(url)
2205 force_videoid = None
d6e6a422 2206 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2207 if smuggled_data and 'force_videoid' in smuggled_data:
2208 force_videoid = smuggled_data['force_videoid']
2209 video_id = force_videoid
2210 else:
9dcd6fd3 2211 video_id = self._generic_id(url)
3d83a1ae 2212
79649588 2213 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2214
ebab4520 2215 head_req = HEADRequest(url)
23be51d8 2216 head_response = self._request_webpage(
ebab4520
PH
2217 head_req, video_id,
2218 note=False, errnote='Could not send HEAD request to %s' % url,
2219 fatal=False)
42393ce2 2220
23be51d8 2221 if head_response is not False:
42393ce2 2222 # Check for redirect
5551d771 2223 new_url = compat_str(head_response.geturl())
42393ce2
PH
2224 if url != new_url:
2225 self.report_following_redirect(new_url)
4d54ef20
PH
2226 if force_videoid:
2227 new_url = smuggle_url(
2228 new_url, {'force_videoid': force_videoid})
cecaaf3f 2229 return self.url_result(new_url)
42393ce2 2230
23be51d8
PH
2231 full_response = None
2232 if head_response is False:
5c2266df 2233 request = sanitized_Request(url)
58bde34a
S
2234 request.add_header('Accept-Encoding', '*')
2235 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2236 head_response = full_response
2237
f930e0c7
S
2238 info_dict = {
2239 'id': video_id,
9dcd6fd3 2240 'title': self._generic_title(url),
303dcdb9 2241 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2242 }
2243
23be51d8 2244 # Check for direct link to a video
955737b2 2245 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2246 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2247 if m:
4e363703 2248 format_id = compat_str(m.group('format_id'))
f930e0c7 2249 if format_id.endswith('mpegurl'):
eadc3ccd 2250 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2251 elif format_id == 'f4m':
2252 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2253 else:
2254 formats = [{
4e363703 2255 'format_id': format_id,
eadc3ccd 2256 'url': url,
2257 'vcodec': 'none' if m.group('type') == 'audio' else None
2258 }]
de6c51e8 2259 info_dict['direct'] = True
19dbaeec 2260 self._sort_formats(formats)
de6c51e8 2261 info_dict['formats'] = formats
f930e0c7 2262 return info_dict
42393ce2 2263
d6e6a422 2264 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2265 force = self._downloader.params.get('force_generic_extractor', False)
2266 self._downloader.report_warning(
2267 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2268
4e262a88 2269 if not full_response:
5c2266df 2270 request = sanitized_Request(url)
58bde34a
S
2271 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2272 # making it impossible to download only chunk of the file (yet we need only 512kB to
2273 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2274 # that will always result in downloading the whole file that is not desirable.
2275 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2276 # to accept raw bytes and being able to download only a chunk.
2277 # It may probably better to solve this by checking Content-Type for application/octet-stream
2278 # after HEAD request finishes, but not sure if we can rely on this.
2279 request.add_header('Accept-Encoding', '*')
2280 full_response = self._request_webpage(request, video_id)
4e262a88 2281
5940862d
S
2282 first_bytes = full_response.read(512)
2283
2284 # Is it an M3U playlist?
0d769bcb 2285 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2286 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2287 self._sort_formats(info_dict['formats'])
5940862d
S
2288 return info_dict
2289
4e262a88
PH
2290 # Maybe it's a direct link to a video?
2291 # Be careful not to download the whole thing!
61ca9a80 2292 if not is_html(first_bytes):
4e262a88
PH
2293 self._downloader.report_warning(
2294 'URL could be a direct video link, returning it as such.')
f930e0c7 2295 info_dict.update({
4e262a88
PH
2296 'direct': True,
2297 'url': url,
f930e0c7
S
2298 })
2299 return info_dict
4e262a88
PH
2300
2301 webpage = self._webpage_read_content(
2302 full_response, url, video_id, prefix=first_bytes)
2303
9b122384 2304 self.report_extraction(video_id)
887c6acd 2305
1b840245 2306 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2307 try:
f7854627 2308 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2309 if doc.tag == 'rss':
2310 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2311 elif doc.tag == 'SmoothStreamingMedia':
2312 info_dict['formats'] = self._parse_ism_formats(doc, url)
2313 self._sort_formats(info_dict['formats'])
2314 return info_dict
e5e8d20a 2315 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2316 smil = self._parse_smil(doc, url, video_id)
2317 self._sort_formats(smil['formats'])
2318 return smil
729accb4 2319 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2320 return self.playlist_result(
47a5cb77
S
2321 self._parse_xspf(
2322 doc, video_id, xspf_url=url,
2323 xspf_base_url=compat_str(full_response.geturl())),
96b8b9ab 2324 video_id)
1b840245 2325 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2326 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2327 doc,
5551d771 2328 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2329 mpd_url=url)
19dbaeec 2330 self._sort_formats(info_dict['formats'])
f930e0c7
S
2331 return info_dict
2332 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2333 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2334 self._sort_formats(info_dict['formats'])
f930e0c7 2335 return info_dict
f7300c5c 2336 except compat_xml_parse_error:
4fc946b5
PH
2337 pass
2338
c8e9a235
PH
2339 # Is it a Camtasia project?
2340 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2341 if camtasia_res is not None:
2342 return camtasia_res
2343
14390730
S
2344 # Sometimes embedded video player is hidden behind percent encoding
2345 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2346 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2347 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2348
887c6acd
PH
2349 # it's tempting to parse this further, but you would
2350 # have to take into account all the variations like
2351 # Video Title - Site Name
2352 # Site Name | Video Title
2353 # Video Title - Tagline | Site Name
2354 # and so on and so forth; it's just not practical
6f41b2bc
S
2355 video_title = self._og_search_title(
2356 webpage, default=None) or self._html_search_regex(
79649588
PH
2357 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2358 default='video')
ef4fd848 2359
4d805e06
PH
2360 # Try to detect age limit automatically
2361 age_limit = self._rta_search(webpage)
2362 # And then there are the jokers who advertise that they use RTA,
2363 # but actually don't.
2364 AGE_LIMIT_MARKERS = [
197224b7 2365 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2366 ]
2367 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2368 age_limit = 18
2369
ef4fd848
PH
2370 # video uploader is domain name
2371 video_uploader = self._search_regex(
79649588 2372 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2373
6f41b2bc
S
2374 video_description = self._og_search_description(webpage, default=None)
2375 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2376
b311b0ea
S
2377 info_dict.update({
2378 'title': video_title,
2379 'description': video_description,
2380 'thumbnail': video_thumbnail,
2381 'age_limit': age_limit,
2382 })
2383
1f4b722b 2384 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2385 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2386 if bc_urls:
99877772
PH
2387 entries = [{
2388 '_type': 'url',
2389 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2390 'ie_key': 'BrightcoveLegacy'
99877772
PH
2391 } for bc_url in bc_urls]
2392
2393 return {
2394 '_type': 'playlist',
2395 'title': video_title,
2396 'id': video_id,
2397 'entries': entries,
2398 }
cfe50f04 2399
f6519f89 2400 # Look for Brightcove New Studio embeds
0254f93b 2401 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2402 if bc_urls:
5399ab3f
S
2403 return self.playlist_from_matches(
2404 bc_urls, video_id, video_title,
2405 getter=lambda x: smuggle_url(x, {'referrer': url}),
2406 ie='BrightcoveNew')
ed126900 2407
4e826cd9
S
2408 # Look for Nexx embeds
2409 nexx_urls = NexxIE._extract_urls(webpage)
2410 if nexx_urls:
2411 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2412
3f59b015
S
2413 # Look for Nexx iFrame embeds
2414 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2415 if nexx_embed_urls:
2416 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2417
4d8819d2
S
2418 # Look for ThePlatform embeds
2419 tp_urls = ThePlatformIE._extract_urls(webpage)
2420 if tp_urls:
46b18f23 2421 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2422
48a5eabc
S
2423 # Look for Vessel embeds
2424 vessel_urls = VesselIE._extract_urls(webpage)
2425 if vessel_urls:
46b18f23 2426 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2427
59b8ab58
PH
2428 # Look for embedded rtl.nl player
2429 matches = re.findall(
2637fadc 2430 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2431 webpage)
2432 if matches:
46b18f23 2433 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2434
09b9c45e
S
2435 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2436 if vimeo_urls:
46b18f23 2437 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2438
a1b85269
YCH
2439 vid_me_embed_url = self._search_regex(
2440 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2441 webpage, 'vid.me embed', default=None)
2442 if vid_me_embed_url is not None:
2443 return self.url_result(vid_me_embed_url, 'Vidme')
2444
66c9fa36
S
2445 # Look for YouTube embeds
2446 youtube_urls = YoutubeIE._extract_urls(webpage)
2447 if youtube_urls:
46b18f23 2448 return self.playlist_from_matches(
66c9fa36 2449 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2450
ad213a1d 2451 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2452 if matches:
46b18f23 2453 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2454
8489578d
NJ
2455 # Look for embedded Dailymotion playlist player (#3822)
2456 m = re.search(
2457 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2458 if m:
2459 playlists = re.findall(
2460 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2461 if playlists:
46b18f23
JH
2462 return self.playlist_from_matches(
2463 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2464
71a1db89
S
2465 # Look for DailyMail embeds
2466 dailymail_urls = DailyMailIE._extract_urls(webpage)
2467 if dailymail_urls:
2468 return self.playlist_from_matches(
2469 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2470
ef4fd848 2471 # Look for embedded Wistia player
58bb4402
S
2472 wistia_url = WistiaIE._extract_url(webpage)
2473 if wistia_url:
ef4fd848
PH
2474 return {
2475 '_type': 'url_transparent',
58bb4402
S
2476 'url': self._proto_relative_url(wistia_url),
2477 'ie_key': WistiaIE.ie_key(),
ef4fd848 2478 'uploader': video_uploader,
ef4fd848 2479 }
5f6a1245 2480
bab19a8e
S
2481 # Look for SVT player
2482 svt_url = SVTIE._extract_url(webpage)
2483 if svt_url:
2484 return self.url_result(svt_url, 'SVT')
2485
c19f7764
JMF
2486 # Look for Bandcamp pages with custom domain
2487 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2488 if mobj is not None:
2489 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2490 # Don't set the extractor because it can be a track url or an album
2491 return self.url_result(burl)
c19f7764 2492
f25571ff
PH
2493 # Look for embedded Vevo player
2494 mobj = re.search(
2495 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2496 if mobj is not None:
2497 return self.url_result(mobj.group('url'))
796df3c6
S
2498
2499 # Look for embedded Viddler player
cb454b33
S
2500 mobj = re.search(
2501 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2502 webpage)
796df3c6
S
2503 if mobj is not None:
2504 return self.url_result(mobj.group('url'))
f25571ff 2505
3378d67a
S
2506 # Look for NYTimes player
2507 mobj = re.search(
2508 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2509 webpage)
2510 if mobj is not None:
2511 return self.url_result(mobj.group('url'))
2512
cefdf970
S
2513 # Look for Libsyn player
2514 mobj = re.search(
2515 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2516 if mobj is not None:
2517 return self.url_result(mobj.group('url'))
2518
c0d0b01f 2519 # Look for Ooyala videos
8a37aa15 2520 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2521 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2522 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2523 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2524 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2525 if mobj is not None:
9837cb75
RA
2526 embed_token = self._search_regex(
2527 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2528 webpage, 'ooyala embed token', default=None)
2529 return OoyalaIE._build_url_result(smuggle_url(
2530 mobj.group('ec'), {
2531 'domain': url,
2532 'embed_token': embed_token,
2533 }))
c0d0b01f 2534
f076b638 2535 # Look for multiple Ooyala embeds on SBN network websites
2536 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2537 if mobj is not None:
2538 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2539 if embeds:
46b18f23
JH
2540 return self.playlist_from_matches(
2541 embeds, video_id, video_title,
2542 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2543
aa94a6d3 2544 # Look for Aparat videos
48099643 2545 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2546 if mobj is not None:
2547 return self.url_result(mobj.group(1), 'Aparat')
2548
c93c2ab1 2549 # Look for MPORA videos
c3f51436 2550 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2551 if mobj is not None:
2552 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2553
15c0e8e7 2554 # Look for embedded NovaMov-based player
8f89e687 2555 mobj = re.search(
8dfa187b 2556 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2557 (?P<url>http://(?:(?:embed|www)\.)?
2558 (?:novamov\.com|
2559 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2560 videoweed\.(?:es|com)|
2561 movshare\.(?:net|sx|ag)|
2562 divxstage\.(?:eu|net|ch|co|at|ag))
2563 /embed\.php.+?)\1''', webpage)
8f89e687 2564 if mobj is not None:
15c0e8e7 2565 return self.url_result(mobj.group('url'))
50f56607 2566
9834872b 2567 # Look for embedded Facebook player
0646e34c
S
2568 facebook_urls = FacebookIE._extract_urls(webpage)
2569 if facebook_urls:
2570 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2571
ca97a56e
S
2572 # Look for embedded VK player
2573 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2574 if mobj is not None:
2575 return self.url_result(mobj.group('url'), 'VK')
2576
33d4fdab
S
2577 # Look for embedded Odnoklassniki player
2578 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2579 if mobj is not None:
2580 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2581
0364fa8b
S
2582 # Look for embedded ivi player
2583 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2584 if mobj is not None:
2585 return self.url_result(mobj.group('url'), 'Ivi')
2586
db1f3888
PH
2587 # Look for embedded Huffington Post player
2588 mobj = re.search(
c3f51436 2589 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2590 if mobj is not None:
2591 return self.url_result(mobj.group('url'), 'HuffPost')
2592
1b86cc41 2593 # Look for embed.ly
2594 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2595 if mobj is not None:
2596 return self.url_result(mobj.group('url'))
2597 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2598 if mobj is not None:
f7e6f7fa 2599 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2600
60cc4dc4
PH
2601 # Look for funnyordie embed
2602 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2603 if matches:
46b18f23
JH
2604 return self.playlist_from_matches(
2605 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2606
db546cf8
S
2607 # Look for BBC iPlayer embed
2608 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2609 if matches:
46b18f23 2610 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2611
93d020dd
S
2612 # Look for embedded RUTV player
2613 rutv_url = RUTVIE._extract_url(webpage)
2614 if rutv_url:
2615 return self.url_result(rutv_url, 'RUTV')
2616
494f20cb 2617 # Look for embedded TVC player
b8599718
S
2618 tvc_url = TVCIE._extract_url(webpage)
2619 if tvc_url:
2620 return self.url_result(tvc_url, 'TVC')
494f20cb 2621
d40a3b5b
S
2622 # Look for embedded SportBox player
2623 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2624 if sportbox_urls:
46b18f23 2625 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2626
2bb5b6d0
S
2627 # Look for embedded XHamster player
2628 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2629 if xhamster_urls:
46b18f23 2630 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2631
2c9ca782
S
2632 # Look for embedded TNAFlixNetwork player
2633 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2634 if tnaflix_urls:
46b18f23 2635 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2636
b52c9ef1
S
2637 # Look for embedded PornHub player
2638 pornhub_urls = PornHubIE._extract_urls(webpage)
2639 if pornhub_urls:
46b18f23 2640 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2641
37e7a71c
S
2642 # Look for embedded DrTuber player
2643 drtuber_urls = DrTuberIE._extract_urls(webpage)
2644 if drtuber_urls:
46b18f23 2645 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2646
e28ed498
S
2647 # Look for embedded RedTube player
2648 redtube_urls = RedTubeIE._extract_urls(webpage)
2649 if redtube_urls:
46b18f23 2650 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2651
06993715
S
2652 # Look for embedded Tube8 player
2653 tube8_urls = Tube8IE._extract_urls(webpage)
2654 if tube8_urls:
2655 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2656
9872d311
S
2657 # Look for embedded Tvigle player
2658 mobj = re.search(
2659 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2660 if mobj is not None:
2661 return self.url_result(mobj.group('url'), 'Tvigle')
2662
7e2ede98
JMF
2663 # Look for embedded TED player
2664 mobj = re.search(
d7cc31b6 2665 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2666 if mobj is not None:
2667 return self.url_result(mobj.group('url'), 'TED')
2668
5c386252 2669 # Look for embedded Ustream videos
d77ac737
YCH
2670 ustream_url = UstreamIE._extract_url(webpage)
2671 if ustream_url:
2672 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2673
893f8832
PH
2674 # Look for embedded arte.tv player
2675 mobj = re.search(
134c207e 2676 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2677 webpage)
2678 if mobj is not None:
2679 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2680
cbd55ade
S
2681 # Look for embedded francetv player
2682 mobj = re.search(
2683 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2684 webpage)
2685 if mobj is not None:
2686 return self.url_result(mobj.group('url'))
2687
cb3ac1c6
S
2688 # Look for embedded smotri.com player
2689 smotri_url = SmotriIE._extract_url(webpage)
2690 if smotri_url:
2691 return self.url_result(smotri_url, 'Smotri')
2692
e6c2d9ad 2693 # Look for embedded Myvi.ru player
6dd94d3a 2694 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2695 if myvi_url:
2696 return self.url_result(myvi_url)
2697
dfb1b146 2698 # Look for embedded soundcloud player
94aae015
S
2699 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2700 if soundcloud_urls:
46b18f23 2701 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2702
027e2312
S
2703 # Look for tunein player
2704 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2705 if tunein_urls:
46b18f23 2706 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2707
c5cd249e 2708 # Look for embedded mtvservices player
46fde8a1
S
2709 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2710 if mtvservices_url:
2711 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2712
49807b4a
S
2713 # Look for embedded yahoo player
2714 mobj = re.search(
2715 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2716 webpage)
2717 if mobj is not None:
2718 return self.url_result(mobj.group('url'), 'Yahoo')
2719
2ef6fcb5
PH
2720 # Look for embedded sbs.com.au player
2721 mobj = re.search(
e98b8e79
PH
2722 r'''(?x)
2723 (?:
2724 <meta\s+property="og:video"\s+content=|
2725 <iframe[^>]+?src=
2726 )
2727 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2728 webpage)
2729 if mobj is not None:
2730 return self.url_result(mobj.group('url'), 'SBS')
2731
42bdd9d0
PH
2732 # Look for embedded Cinchcast player
2733 mobj = re.search(
2734 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2735 webpage)
2736 if mobj is not None:
2737 return self.url_result(mobj.group('url'), 'Cinchcast')
2738
1a94ff68 2739 mobj = re.search(
5263cdfc 2740 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2741 webpage)
8001607e
YCH
2742 if not mobj:
2743 mobj = re.search(
2744 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2745 webpage)
1a94ff68
S
2746 if mobj is not None:
2747 return self.url_result(mobj.group('url'), 'MLB')
2748
1419fafd 2749 mobj = re.search(
dd467d33 2750 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2751 webpage)
2752 if mobj is not None:
2753 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2754
af63fed7 2755 mobj = re.search(
78d3b3e2 2756 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2757 webpage)
2758 if mobj is not None:
2759 return self.url_result(mobj.group('url'), 'Livestream')
2760
255fca5e
S
2761 # Look for Zapiks embed
2762 mobj = re.search(
2763 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2764 if mobj is not None:
2765 return self.url_result(mobj.group('url'), 'Zapiks')
2766
e3216b82 2767 # Look for Kaltura embeds
c287f2bc
S
2768 kaltura_url = KalturaIE._extract_url(webpage)
2769 if kaltura_url:
2770 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2771
665e9452 2772 # Look for EaglePlatform embeds
06a96da1
S
2773 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2774 if eagleplatform_url:
665e9452 2775 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2776
665e9452 2777 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2778 mobj = re.search(
2779 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2780 if mobj is not None:
2781 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2782
f8388757 2783 # Look for Pladform embeds
45dad7ba
S
2784 pladform_url = PladformIE._extract_url(webpage)
2785 if pladform_url:
2786 return self.url_result(pladform_url)
f8388757 2787
ff18735c
S
2788 # Look for Videomore embeds
2789 videomore_url = VideomoreIE._extract_url(webpage)
2790 if videomore_url:
2791 return self.url_result(videomore_url)
2792
83f1481b
S
2793 # Look for Webcaster embeds
2794 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2795 if webcaster_url:
2796 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2797
2dcc114f
S
2798 # Look for Playwire embeds
2799 mobj = re.search(
2800 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2801 if mobj is not None:
2802 return self.url_result(mobj.group('url'))
2803
ad320e9b
NJ
2804 # Look for 5min embeds
2805 mobj = re.search(
2806 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2807 if mobj is not None:
2808 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2809
18153f1b
S
2810 # Look for Crooks and Liars embeds
2811 mobj = re.search(
2812 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2813 if mobj is not None:
2814 return self.url_result(mobj.group('url'))
2815
a2edf2e7
YCH
2816 # Look for NBC Sports VPlayer embeds
2817 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2818 if nbc_sports_url:
2819 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2820
de3eb07e
YCH
2821 # Look for NBC News embeds
2822 nbc_news_embed_url = re.search(
2823 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2824 if nbc_news_embed_url:
2825 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2826
653789af 2827 # Look for Google Drive embeds
5b251628 2828 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2829 if google_drive_url:
2830 return self.url_result(google_drive_url, 'GoogleDrive')
2831
418c5cc3
YCH
2832 # Look for UDN embeds
2833 mobj = re.search(
2637fadc 2834 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2835 if mobj is not None:
2836 return self.url_result(
0a160363 2837 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2838
2fe1b5bd
YCH
2839 # Look for Senate ISVP iframe
2840 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2841 if senate_isvp_url:
25c3a734 2842 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2843
1ac1c4c2
S
2844 # Look for OnionStudios embeds
2845 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2846 if onionstudios_url:
2847 return self.url_result(onionstudios_url)
2848
67167920 2849 # Look for ViewLift embeds
2850 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2851 if viewlift_url:
2852 return self.url_result(viewlift_url)
eedd20ef 2853
7cb09524 2854 # Look for JWPlatform embeds
b0ead0e0
S
2855 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2856 if jwplatform_urls:
2857 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2858
aecfcd4e
S
2859 # Look for Digiteka embeds
2860 digiteka_url = DigitekaIE._extract_url(webpage)
2861 if digiteka_url:
2862 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2863
1979969f
S
2864 # Look for Arkena embeds
2865 arkena_url = ArkenaIE._extract_url(webpage)
2866 if arkena_url:
2867 return self.url_result(arkena_url, ArkenaIE.ie_key())
2868
b1c35797
RA
2869 # Look for Piksel embeds
2870 piksel_url = PikselIE._extract_url(webpage)
2871 if piksel_url:
2872 return self.url_result(piksel_url, PikselIE.ie_key())
2873
1bf996fa 2874 # Look for Limelight embeds
e5d39886
S
2875 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2876 if limelight_urls:
2877 return self.playlist_result(
2878 limelight_urls, video_id, video_title, video_description)
2879
7986c3ab
S
2880 # Look for Anvato embeds
2881 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2882 if anvato_urls:
2883 return self.playlist_result(
2884 anvato_urls, video_id, video_title, video_description)
2885
a5158f38
YCH
2886 # Look for AdobeTVVideo embeds
2887 mobj = re.search(
2888 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2889 webpage)
2890 if mobj is not None:
2891 return self.url_result(
2892 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2893 'AdobeTVVideo')
2894
088e1aac
YCH
2895 # Look for Vine embeds
2896 mobj = re.search(
2897 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2898 webpage)
2899 if mobj is not None:
2900 return self.url_result(
2901 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2902
217d5ae0
RA
2903 # Look for VODPlatform embeds
2904 mobj = re.search(
93b84045 2905 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2906 webpage)
2907 if mobj is not None:
2908 return self.url_result(
93b84045 2909 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2910
7d273a38
RA
2911 # Look for Mangomolo embeds
2912 mobj = re.search(
d05ef09d 2913 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2914 (?:
2915 video\?.*?\bid=(?P<video_id>\d+)|
2916 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2917 ).+?)\1''', webpage)
2918 if mobj is not None:
2919 info = {
2920 '_type': 'url_transparent',
2921 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2922 'title': video_title,
2923 'description': video_description,
2924 'thumbnail': video_thumbnail,
2925 'uploader': video_uploader,
2926 }
2927 video_id = mobj.group('video_id')
2928 if video_id:
2929 info.update({
2930 'ie_key': 'MangomoloVideo',
2931 'id': video_id,
2932 })
2933 else:
2934 info.update({
2935 'ie_key': 'MangomoloLive',
2936 'id': mobj.group('channel_id'),
2937 })
2938 return info
2939
5a51775a
YCH
2940 # Look for Instagram embeds
2941 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2942 if instagram_embed_url is not None:
11e60fca
S
2943 return self.url_result(
2944 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2945
b8f67449 2946 # Look for LiveLeak embeds
09747ba7
YCH
2947 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2948 if liveleak_urls:
2949 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2950
5d39176f
S
2951 # Look for 3Q SDN embeds
2952 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2953 if threeqsdn_url:
6f41b2bc
S
2954 return {
2955 '_type': 'url_transparent',
2956 'ie_key': ThreeQSDNIE.ie_key(),
2957 'url': self._proto_relative_url(threeqsdn_url),
2958 'title': video_title,
2959 'description': video_description,
2960 'thumbnail': video_thumbnail,
2961 'uploader': video_uploader,
2962 }
5d39176f 2963
2a1321a2
S
2964 # Look for VBOX7 embeds
2965 vbox7_url = Vbox7IE._extract_url(webpage)
2966 if vbox7_url:
2967 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2968
b0c8f2e9
DR
2969 # Look for DBTV embeds
2970 dbtv_urls = DBTVIE._extract_urls(webpage)
2971 if dbtv_urls:
46b18f23 2972 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2973
e186a9ec
S
2974 # Look for Videa embeds
2975 videa_urls = VideaIE._extract_urls(webpage)
2976 if videa_urls:
46b18f23 2977 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2978
b687c85e
S
2979 # Look for 20 minuten embeds
2980 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2981 if twentymin_urls:
46b18f23
JH
2982 return self.playlist_from_matches(
2983 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2984
17f8deeb
S
2985 # Look for Openload embeds
2986 openload_urls = OpenloadIE._extract_urls(webpage)
2987 if openload_urls:
46b18f23
JH
2988 return self.playlist_from_matches(
2989 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2990
6ef3e65a
S
2991 # Look for VideoPress embeds
2992 videopress_urls = VideoPressIE._extract_urls(webpage)
2993 if videopress_urls:
46b18f23
JH
2994 return self.playlist_from_matches(
2995 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2996
eb3079b6
S
2997 # Look for Rutube embeds
2998 rutube_urls = RutubeIE._extract_urls(webpage)
2999 if rutube_urls:
46b18f23 3000 return self.playlist_from_matches(
2583c0b5 3001 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3002
55719459
JH
3003 # Look for WashingtonPost embeds
3004 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3005 if wapo_urls:
3006 return self.playlist_from_matches(
3007 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3008
5d29af3d
S
3009 # Look for Mediaset embeds
3010 mediaset_urls = MediasetIE._extract_urls(webpage)
3011 if mediaset_urls:
3012 return self.playlist_from_matches(
3013 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3014
73cf76a9
S
3015 # Look for JOJ.sk embeds
3016 joj_urls = JojIE._extract_urls(webpage)
3017 if joj_urls:
3018 return self.playlist_from_matches(
3019 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3020
24e966e8
PH
3021 # Look for megaphone.fm embeds
3022 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3023 if mpfn_urls:
3024 return self.playlist_from_matches(
3025 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3026
1663bd6e
S
3027 # Look for vzaar embeds
3028 vzaar_urls = VzaarIE._extract_urls(webpage)
3029 if vzaar_urls:
3030 return self.playlist_from_matches(
3031 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3032
26bae2d9
S
3033 channel9_urls = Channel9IE._extract_urls(webpage)
3034 if channel9_urls:
3035 return self.playlist_from_matches(
3036 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3037
0987f2dd
T
3038 vshare_urls = VShareIE._extract_urls(webpage)
3039 if vshare_urls:
3040 return self.playlist_from_matches(
3041 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3042
8056c854 3043 # Look for Mediasite embeds
2ca7ed41
S
3044 mediasite_urls = MediasiteIE._extract_urls(webpage)
3045 if mediasite_urls:
3046 entries = [
3047 self.url_result(smuggle_url(
3048 compat_urlparse.urljoin(url, mediasite_url),
3049 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3050 for mediasite_url in mediasite_urls]
3051 return self.playlist_result(entries, video_id, video_title)
8056c854 3052
7d540621
S
3053 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3054 if springboardplatform_urls:
3055 return self.playlist_from_matches(
3056 springboardplatform_urls, video_id, video_title,
3057 ie=SpringboardPlatformIE.ie_key())
3058
4c780fbd
S
3059 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3060 if yapfiles_urls:
3061 return self.playlist_from_matches(
3062 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3063
86c8cfc5
S
3064 vice_urls = ViceIE._extract_urls(webpage)
3065 if vice_urls:
3066 return self.playlist_from_matches(
3067 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3068
178ee883
S
3069 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3070 if xfileshare_urls:
3071 return self.playlist_from_matches(
3072 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3073
660a230b
S
3074 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3075 if cloudflarestream_urls:
3076 return self.playlist_from_matches(
3077 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3078
6bd499e8
S
3079 peertube_urls = PeerTubeIE._extract_urls(webpage)
3080 if peertube_urls:
3081 return self.playlist_from_matches(
3082 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3083
aee36ca8
S
3084 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3085 if indavideo_urls:
3086 return self.playlist_from_matches(
3087 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3088
cfd7f2a6
S
3089 apa_urls = APAIE._extract_urls(webpage)
3090 if apa_urls:
3091 return self.playlist_from_matches(
3092 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3093
d3431dcb
S
3094 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3095 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3096 webpage)]
3097 if sharevideos_urls:
3098 return self.playlist_from_matches(
3099 sharevideos_urls, video_id, video_title)
3100
bd264412
YCH
3101 # Look for HTML5 media
3102 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3103 if entries:
9ce1ac40 3104 if len(entries) == 1:
3105 entries[0].update({
bd264412
YCH
3106 'id': video_id,
3107 'title': video_title,
3108 })
9ce1ac40 3109 else:
3110 for num, entry in enumerate(entries, start=1):
3111 entry.update({
3112 'id': '%s-%s' % (video_id, num),
3113 'title': '%s (%d)' % (video_title, num),
3114 })
3115 for entry in entries:
bd264412 3116 self._sort_formats(entry['formats'])
9ce1ac40 3117 return self.playlist_result(entries, video_id, video_title)
bd264412 3118
c73e330e
RU
3119 jwplayer_data = self._find_jwplayer_data(
3120 webpage, video_id, transform_source=js_to_json)
3121 if jwplayer_data:
4f06c1c9 3122 info = self._parse_jwplayer_data(
3e943cfe 3123 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 3124 return merge_dicts(info, info_dict)
a4a554a7 3125
63d990d2
S
3126 # Video.js embed
3127 mobj = re.search(
c5b7014a 3128 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3129 webpage)
3130 if mobj is not None:
3131 sources = self._parse_json(
3132 mobj.group(1), video_id, transform_source=js_to_json,
3133 fatal=False) or []
c5b7014a
S
3134 if not isinstance(sources, list):
3135 sources = [sources]
63d990d2
S
3136 formats = []
3137 for source in sources:
3138 src = source.get('src')
3139 if not src or not isinstance(src, compat_str):
3140 continue
3141 src = compat_urlparse.urljoin(url, src)
3142 src_type = source.get('type')
3143 if isinstance(src_type, compat_str):
3144 src_type = src_type.lower()
3145 ext = determine_ext(src).lower()
3146 if src_type == 'video/youtube':
3147 return self.url_result(src, YoutubeIE.ie_key())
3148 if src_type == 'application/dash+xml' or ext == 'mpd':
3149 formats.extend(self._extract_mpd_formats(
3150 src, video_id, mpd_id='dash', fatal=False))
3151 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3152 formats.extend(self._extract_m3u8_formats(
3153 src, video_id, 'mp4', entry_protocol='m3u8_native',
3154 m3u8_id='hls', fatal=False))
3155 else:
3156 formats.append({
3157 'url': src,
3158 'ext': (mimetype2ext(src_type) or
3159 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3160 })
3161 if formats:
3162 self._sort_formats(formats)
3163 info_dict['formats'] = formats
3164 return info_dict
3165
ff17be3a
S
3166 # Looking for http://schema.org/VideoObject
3167 json_ld = self._search_json_ld(
3168 webpage, video_id, default={}, expected_type='VideoObject')
3169 if json_ld.get('url'):
3170 return merge_dicts(json_ld, info_dict)
3171
ced659bb 3172 def check_video(vurl):
a0f71985
PH
3173 if YoutubeIE.suitable(vurl):
3174 return True
b7a8c1bc
S
3175 if RtmpIE.suitable(vurl):
3176 return True
ced659bb
S
3177 vpath = compat_urlparse.urlparse(vurl).path
3178 vext = determine_ext(vpath)
0ee79a37 3179 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3180
3181 def filter_video(urls):
3182 return list(filter(check_video, urls))
3183
9b122384 3184 # Start with something easy: JW Player in SWFObject
ced659bb 3185 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3186 if not found:
d981cef6 3187 # Look for gorilla-vid style embedding
ced659bb 3188 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3189 (?:
3190 jw_plugins|
3191 JWPlayerOptions|
3192 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3193 )
a0f71985
PH
3194 .*?
3195 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3196 if not found:
9b122384 3197 # Broaden the search a little bit
ced659bb 3198 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3199 if not found:
3200 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3201 found = filter_video(re.findall(
54a9328b 3202 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3203 if not found:
3204 # Flow player
ced659bb 3205 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3206 flowplayer\("[^"]+",\s*
3207 \{[^}]+?\}\s*,
52585fd6 3208 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3209 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3210 ''', webpage))
501f13fb
PH
3211 if not found:
3212 # Cinerama player
3213 found = re.findall(
3214 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3215 if not found:
9b122384 3216 # Try to find twitter cards info
371ddb14
S
3217 # twitter:player:stream should be checked before twitter:player since
3218 # it is expected to contain a raw stream (see
3219 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3220 found = filter_video(re.findall(
3221 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3222 if not found:
9b122384
PH
3223 # We look for Open Graph info:
3224 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3225 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3226 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3227 if m_video_type is not None:
ced659bb 3228 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3229 if not found:
ed9a25dd 3230 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3231 found = re.search(
89ef304b 3232 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3233 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3234 webpage)
84f81016
S
3235 if not found:
3236 # Look also in Refresh HTTP header
3237 refresh_header = head_response.headers.get('Refresh')
3238 if refresh_header:
6c91a5a7
S
3239 # In python 2 response HTTP headers are bytestrings
3240 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3241 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3242 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3243 if found:
b37317d8 3244 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3245 if new_url != url:
3246 self.report_following_redirect(new_url)
3247 return {
3248 '_type': 'url',
3249 'url': new_url,
3250 }
3251 else:
3252 found = None
371ddb14
S
3253
3254 if not found:
3255 # twitter:player is a https URL to iframe player that may or may not
3256 # be supported by youtube-dl thus this is checked the very last (see
3257 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3258 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3259 if embed_url and embed_url != url:
371ddb14
S
3260 return self.url_result(embed_url)
3261
b30b8698 3262 if not found:
416c7fcb 3263 raise UnsupportedError(url)
9b122384 3264
b30b8698 3265 entries = []
4a120778 3266 for video_url in orderedSet(found):
949b6497 3267 video_url = unescapeHTML(video_url)
6cc37c69 3268 video_url = video_url.replace('\\/', '/')
b30b8698 3269 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3270 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3271
b30b8698
PH
3272 # Sometimes, jwplayer extraction will result in a YouTube URL
3273 if YoutubeIE.suitable(video_url):
3274 entries.append(self.url_result(video_url, 'Youtube'))
3275 continue
9b122384 3276
b30b8698
PH
3277 # here's a fun little line of code for you:
3278 video_id = os.path.splitext(video_id)[0]
fc9713a1 3279
28602e74
YCH
3280 entry_info_dict = {
3281 'id': video_id,
3282 'uploader': video_uploader,
3283 'title': video_title,
3284 'age_limit': age_limit,
3285 }
3286
5620f840
S
3287 if RtmpIE.suitable(video_url):
3288 entry_info_dict.update({
3289 '_type': 'url_transparent',
3290 'ie_key': RtmpIE.ie_key(),
3291 'url': video_url,
3292 })
3293 entries.append(entry_info_dict)
3294 continue
3295
729accb4
S
3296 ext = determine_ext(video_url)
3297 if ext == 'smil':
28602e74 3298 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3299 elif ext == 'xspf':
3300 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3301 elif ext == 'm3u8':
3302 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3303 elif ext == 'mpd':
3304 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3305 elif ext == 'f4m':
3306 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3307 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3308 # Just matching .ism/manifest is not enough to be reliably sure
3309 # whether it's actually an ISM manifest or some other streaming
3310 # manifest since there are various streaming URL formats
3311 # possible (see [1]) as well as some other shenanigans like
3312 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3313 # so on.
3314 # Thus the most reasonable way to solve this is to delegate
3315 # to generic extractor in order to look into the contents of
3316 # the manifest itself.
3317 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3318 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3319 entry_info_dict = self.url_result(
3320 smuggle_url(video_url, {'to_generic': True}),
3321 GenericIE.ie_key())
d6fd958c 3322 else:
28602e74
YCH
3323 entry_info_dict['url'] = video_url
3324
19dbaeec
S
3325 if entry_info_dict.get('formats'):
3326 self._sort_formats(entry_info_dict['formats'])
3327
28602e74 3328 entries.append(entry_info_dict)
b30b8698
PH
3329
3330 if len(entries) == 1:
669f0e7c 3331 return entries[0]
b30b8698
PH
3332 else:
3333 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3334 # 'url' results don't have a title
3335 if e.get('title') is not None:
3336 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3337 return {
3338 '_type': 'playlist',
3339 'entries': entries,
3340 }