Nevar pievienot vairāk kā 25 tēmas Tēmai ir jāsākas ar burtu vai ciparu, tā var saturēt domu zīmes ('-') un var būt līdz 35 simboliem gara.

3398 rindas
137KB

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. is_html,
  21. js_to_json,
  22. KNOWN_EXTENSIONS,
  23. merge_dicts,
  24. mimetype2ext,
  25. orderedSet,
  26. sanitized_Request,
  27. smuggle_url,
  28. unescapeHTML,
  29. unified_strdate,
  30. unsmuggle_url,
  31. UnsupportedError,
  32. xpath_text,
  33. )
  34. from .commonprotocols import RtmpIE
  35. from .brightcove import (
  36. BrightcoveLegacyIE,
  37. BrightcoveNewIE,
  38. )
  39. from .nexx import (
  40. NexxIE,
  41. NexxEmbedIE,
  42. )
  43. from .nbc import NBCSportsVPlayerIE
  44. from .ooyala import OoyalaIE
  45. from .rutv import RUTVIE
  46. from .tvc import TVCIE
  47. from .sportbox import SportBoxIE
  48. from .smotri import SmotriIE
  49. from .myvi import MyviIE
  50. from .condenast import CondeNastIE
  51. from .udn import UDNEmbedIE
  52. from .senateisvp import SenateISVPIE
  53. from .svt import SVTIE
  54. from .pornhub import PornHubIE
  55. from .xhamster import XHamsterEmbedIE
  56. from .tnaflix import TNAFlixNetworkEmbedIE
  57. from .drtuber import DrTuberIE
  58. from .redtube import RedTubeIE
  59. from .tube8 import Tube8IE
  60. from .vimeo import VimeoIE
  61. from .dailymotion import DailymotionIE
  62. from .dailymail import DailyMailIE
  63. from .onionstudios import OnionStudiosIE
  64. from .viewlift import ViewLiftEmbedIE
  65. from .mtv import MTVServicesEmbeddedIE
  66. from .pladform import PladformIE
  67. from .videomore import VideomoreIE
  68. from .webcaster import WebcasterFeedIE
  69. from .googledrive import GoogleDriveIE
  70. from .jwplatform import JWPlatformIE
  71. from .digiteka import DigitekaIE
  72. from .arkena import ArkenaIE
  73. from .instagram import InstagramIE
  74. from .liveleak import LiveLeakIE
  75. from .threeqsdn import ThreeQSDNIE
  76. from .theplatform import ThePlatformIE
  77. from .vessel import VesselIE
  78. from .kaltura import KalturaIE
  79. from .eagleplatform import EaglePlatformIE
  80. from .facebook import FacebookIE
  81. from .soundcloud import SoundcloudIE
  82. from .tunein import TuneInBaseIE
  83. from .vbox7 import Vbox7IE
  84. from .dbtv import DBTVIE
  85. from .piksel import PikselIE
  86. from .videa import VideaIE
  87. from .twentymin import TwentyMinutenIE
  88. from .ustream import UstreamIE
  89. from .openload import OpenloadIE
  90. from .videopress import VideoPressIE
  91. from .rutube import RutubeIE
  92. from .limelight import LimelightBaseIE
  93. from .anvato import AnvatoIE
  94. from .washingtonpost import WashingtonPostIE
  95. from .wistia import WistiaIE
  96. from .mediaset import MediasetIE
  97. from .joj import JojIE
  98. from .megaphone import MegaphoneIE
  99. from .vzaar import VzaarIE
  100. from .channel9 import Channel9IE
  101. from .vshare import VShareIE
  102. from .mediasite import MediasiteIE
  103. from .springboardplatform import SpringboardPlatformIE
  104. from .yapfiles import YapFilesIE
  105. from .vice import ViceIE
  106. from .xfileshare import XFileShareIE
  107. from .cloudflarestream import CloudflareStreamIE
  108. from .peertube import PeerTubeIE
  109. from .teachable import TeachableIE
  110. from .indavideo import IndavideoEmbedIE
  111. from .apa import APAIE
  112. from .foxnews import FoxNewsIE
  113. from .viqeo import ViqeoIE
  114. from .expressen import ExpressenIE
  115. from .zype import ZypeIE
  116. class GenericIE(InfoExtractor):
  117. IE_DESC = 'Generic downloader that works on some sites'
  118. _VALID_URL = r'.*'
  119. IE_NAME = 'generic'
  120. _TESTS = [
  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. },
  132. # Direct link to media delivered compressed (until Accept-Encoding is *)
  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.'
  144. ],
  145. 'skip': 'URL invalid',
  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': [
  159. r'501.*Not Implemented',
  160. r'400.*Bad Request',
  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. },
  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. },
  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',
  216. 'upload_date': '20130627',
  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. },
  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',
  285. 'thumbnail': r're:^https?://.*\.jpg$',
  286. 'duration': 33,
  287. },
  288. 'params': {
  289. 'skip_download': True,
  290. },
  291. },
  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',
  301. 'upload_date': '20130904',
  302. },
  303. 'params': {
  304. 'format': 'bestvideo',
  305. },
  306. },
  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,
  319. },
  320. 'skip': 'video gone',
  321. },
  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,
  335. },
  336. 'skip': 'video gone',
  337. },
  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',
  346. 'description': r're:^Chris Ziegler takes a look at the\.*',
  347. 'uploader': 'The Verge',
  348. 'title': 'First Firefox OS phones side-by-side',
  349. },
  350. 'params': {
  351. 'skip_download': False,
  352. }
  353. },
  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. },
  370. {
  371. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  372. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  373. 'info_dict': {
  374. 'id': '13601338388002',
  375. 'ext': 'mp4',
  376. 'uploader': 'www.hodiho.fr',
  377. 'title': 'R\u00e9gis plante sa Jeep',
  378. }
  379. },
  380. # bandcamp page with custom domain
  381. {
  382. 'add_ie': ['Bandcamp'],
  383. 'url': 'http://bronyrock.com/track/the-pony-mash',
  384. 'info_dict': {
  385. 'id': '3235767654',
  386. 'ext': 'mp3',
  387. 'title': 'The Pony Mash',
  388. 'uploader': 'M_Pallante',
  389. },
  390. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  391. },
  392. {
  393. # embedded brightcove video
  394. # it also tests brightcove videos that need to set the 'Referer'
  395. # in the http requests
  396. 'add_ie': ['BrightcoveLegacy'],
  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',
  404. },
  405. 'params': {
  406. 'skip_download': True,
  407. },
  408. },
  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. },
  427. {
  428. # https://github.com/ytdl-org/youtube-dl/issues/2253
  429. 'url': 'http://bcove.me/i6nfkrc3',
  430. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  431. 'info_dict': {
  432. 'id': '3101154703001',
  433. 'ext': 'mp4',
  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. },
  438. 'add_ie': ['BrightcoveLegacy'],
  439. 'skip': 'video gone',
  440. },
  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. },
  452. {
  453. # https://github.com/ytdl-org/youtube-dl/issues/3541
  454. 'add_ie': ['BrightcoveLegacy'],
  455. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  456. 'info_dict': {
  457. 'id': '3866516442001',
  458. 'ext': 'mp4',
  459. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  460. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  461. 'uploader': 'SBS Broadcasting',
  462. },
  463. 'skip': 'Restricted to Netherlands',
  464. 'params': {
  465. 'skip_download': True, # m3u8 download
  466. },
  467. },
  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. },
  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. },
  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. # Alternative brightcove <video> attributes
  537. '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/',
  538. 'info_dict': {
  539. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  540. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  541. },
  542. 'playlist': [{
  543. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  544. 'info_dict': {
  545. 'id': '5311302538001',
  546. 'ext': 'mp4',
  547. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  548. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  549. 'timestamp': 1486321708,
  550. 'upload_date': '20170205',
  551. 'uploader_id': '800000640001',
  552. },
  553. 'only_matching': True,
  554. }],
  555. },
  556. {
  557. # Brightcove with UUID in videoPlayer
  558. 'url': 'http://www8.hp.com/cn/zh/home.html',
  559. 'info_dict': {
  560. 'id': '5255815316001',
  561. 'ext': 'mp4',
  562. 'title': 'Sprocket Video - China',
  563. 'description': 'Sprocket Video - China',
  564. 'uploader': 'HP-Video Gallery',
  565. 'timestamp': 1482263210,
  566. 'upload_date': '20161220',
  567. 'uploader_id': '1107601872001',
  568. },
  569. 'params': {
  570. 'skip_download': True, # m3u8 download
  571. },
  572. },
  573. # ooyala video
  574. {
  575. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  576. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  577. 'info_dict': {
  578. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  579. 'ext': 'mp4',
  580. 'title': '2cc213299525360.mov', # that's what we get
  581. 'duration': 238.231,
  582. },
  583. 'add_ie': ['Ooyala'],
  584. },
  585. {
  586. # ooyala video embedded with http://player.ooyala.com/iframe.js
  587. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  588. 'info_dict': {
  589. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  590. 'ext': 'mp4',
  591. 'title': '"Steve Jobs: Man in the Machine" trailer',
  592. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  593. 'duration': 135.427,
  594. },
  595. 'params': {
  596. 'skip_download': True,
  597. },
  598. 'skip': 'movie expired',
  599. },
  600. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  601. {
  602. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  603. 'info_dict': {
  604. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  605. 'ext': 'mp4',
  606. 'title': 'Steampunk Fest Comes to Honesdale',
  607. 'duration': 43.276,
  608. },
  609. 'params': {
  610. 'skip_download': True,
  611. }
  612. },
  613. # embed.ly video
  614. {
  615. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  616. 'info_dict': {
  617. 'id': '9ODmcdjQcHQ',
  618. 'ext': 'mp4',
  619. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  620. 'upload_date': '20140225',
  621. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  622. 'uploader': 'Tested',
  623. 'uploader_id': 'testedcom',
  624. },
  625. # No need to test YoutubeIE here
  626. 'params': {
  627. 'skip_download': True,
  628. },
  629. },
  630. # funnyordie embed
  631. {
  632. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  633. 'info_dict': {
  634. 'id': '18e820ec3f',
  635. 'ext': 'mp4',
  636. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  637. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  638. },
  639. # HEAD requests lead to endless 301, while GET is OK
  640. 'expected_warnings': ['301'],
  641. },
  642. # RUTV embed
  643. {
  644. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  645. 'info_dict': {
  646. 'id': '776940',
  647. 'ext': 'mp4',
  648. 'title': 'Охотское море стало целиком российским',
  649. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  650. },
  651. 'params': {
  652. # m3u8 download
  653. 'skip_download': True,
  654. },
  655. },
  656. # TVC embed
  657. {
  658. '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/',
  659. 'info_dict': {
  660. 'id': '55304',
  661. 'ext': 'mp4',
  662. 'title': 'Дошкольное воспитание',
  663. },
  664. },
  665. # SportBox embed
  666. {
  667. 'url': 'http://www.vestifinance.ru/articles/25753',
  668. 'info_dict': {
  669. 'id': '25753',
  670. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  671. },
  672. 'playlist': [{
  673. 'info_dict': {
  674. 'id': '370908',
  675. 'title': 'Госзаказ. День 3',
  676. 'ext': 'mp4',
  677. }
  678. }, {
  679. 'info_dict': {
  680. 'id': '370905',
  681. 'title': 'Госзаказ. День 2',
  682. 'ext': 'mp4',
  683. }
  684. }, {
  685. 'info_dict': {
  686. 'id': '370902',
  687. 'title': 'Госзаказ. День 1',
  688. 'ext': 'mp4',
  689. }
  690. }],
  691. 'params': {
  692. # m3u8 download
  693. 'skip_download': True,
  694. },
  695. },
  696. # Myvi.ru embed
  697. {
  698. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  699. 'info_dict': {
  700. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  701. 'ext': 'mp4',
  702. 'title': 'Ужастики, русский трейлер (2015)',
  703. 'thumbnail': r're:^https?://.*\.jpg$',
  704. 'duration': 153,
  705. }
  706. },
  707. # XHamster embed
  708. {
  709. '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',
  710. 'info_dict': {
  711. 'id': 'showthread',
  712. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  713. },
  714. 'playlist_mincount': 7,
  715. # This forum does not allow <iframe> syntaxes anymore
  716. # Now HTML tags are displayed as-is
  717. 'skip': 'No videos on this page',
  718. },
  719. # Embedded TED video
  720. {
  721. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  722. 'md5': '65fdff94098e4a607385a60c5177c638',
  723. 'info_dict': {
  724. 'id': '1969',
  725. 'ext': 'mp4',
  726. 'title': 'Hidden miracles of the natural world',
  727. 'uploader': 'Louie Schwartzberg',
  728. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  729. }
  730. },
  731. # nowvideo embed hidden behind percent encoding
  732. {
  733. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  734. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  735. 'info_dict': {
  736. 'id': '06e53103ca9aa',
  737. 'ext': 'flv',
  738. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  739. 'description': 'No description',
  740. },
  741. },
  742. # arte embed
  743. {
  744. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  745. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  746. 'info_dict': {
  747. 'id': '048195-004_PLUS7-F',
  748. 'ext': 'flv',
  749. 'title': 'X:enius',
  750. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  751. 'upload_date': '20140320',
  752. },
  753. 'params': {
  754. 'skip_download': 'Requires rtmpdump'
  755. },
  756. 'skip': 'video gone',
  757. },
  758. # francetv embed
  759. {
  760. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  761. 'info_dict': {
  762. 'id': 'EV_30231',
  763. 'ext': 'mp4',
  764. 'title': 'Alcaline, le concert avec Calogero',
  765. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  766. 'upload_date': '20150226',
  767. 'timestamp': 1424989860,
  768. 'duration': 5400,
  769. },
  770. 'params': {
  771. # m3u8 downloads
  772. 'skip_download': True,
  773. },
  774. 'expected_warnings': [
  775. 'Forbidden'
  776. ]
  777. },
  778. # Condé Nast embed
  779. {
  780. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  781. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  782. 'info_dict': {
  783. 'id': '53501be369702d3275860000',
  784. 'ext': 'mp4',
  785. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  786. }
  787. },
  788. # Dailymotion embed
  789. {
  790. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  791. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  792. 'info_dict': {
  793. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  794. 'ext': 'mp4',
  795. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  796. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  797. 'uploader': 'Spi0n',
  798. 'uploader_id': 'xgditw',
  799. 'upload_date': '20140425',
  800. 'timestamp': 1398441542,
  801. },
  802. 'add_ie': ['Dailymotion'],
  803. },
  804. # DailyMail embed
  805. {
  806. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  807. 'info_dict': {
  808. 'id': '1495629',
  809. 'ext': 'mp4',
  810. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  811. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  812. },
  813. 'add_ie': ['DailyMail'],
  814. 'params': {
  815. 'skip_download': True,
  816. },
  817. },
  818. # YouTube embed
  819. {
  820. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  821. 'info_dict': {
  822. 'id': 'FXRb4ykk4S0',
  823. 'ext': 'mp4',
  824. 'title': 'The NBL Auction 2014',
  825. 'uploader': 'BADMINTON England',
  826. 'uploader_id': 'BADMINTONEvents',
  827. 'upload_date': '20140603',
  828. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  829. },
  830. 'add_ie': ['Youtube'],
  831. 'params': {
  832. 'skip_download': True,
  833. }
  834. },
  835. # MTVSercices embed
  836. {
  837. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  838. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  839. 'info_dict': {
  840. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  841. 'ext': 'mp4',
  842. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  843. 'description': 'Two valets share their love for movie star Liam Neesons.',
  844. 'timestamp': 1349922600,
  845. 'upload_date': '20121011',
  846. },
  847. },
  848. # YouTube embed via <data-embed-url="">
  849. {
  850. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  851. 'info_dict': {
  852. 'id': '4vAffPZIT44',
  853. 'ext': 'mp4',
  854. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  855. 'uploader': 'Gameloft',
  856. 'uploader_id': 'gameloft',
  857. 'upload_date': '20140828',
  858. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  859. },
  860. 'params': {
  861. 'skip_download': True,
  862. }
  863. },
  864. # YouTube <object> embed
  865. {
  866. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  867. 'md5': '516718101ec834f74318df76259fb3cc',
  868. 'info_dict': {
  869. 'id': 'msN87y-iEx0',
  870. 'ext': 'webm',
  871. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  872. 'upload_date': '20080526',
  873. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  874. 'uploader': 'Christopher Sykes',
  875. 'uploader_id': 'ChristopherJSykes',
  876. },
  877. 'add_ie': ['Youtube'],
  878. },
  879. # Camtasia studio
  880. {
  881. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  882. 'playlist': [{
  883. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  884. 'info_dict': {
  885. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  886. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  887. 'ext': 'flv',
  888. 'duration': 2235.90,
  889. }
  890. }, {
  891. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  892. 'info_dict': {
  893. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  894. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  895. 'ext': 'flv',
  896. 'duration': 2235.93,
  897. }
  898. }],
  899. 'info_dict': {
  900. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  901. }
  902. },
  903. # Flowplayer
  904. {
  905. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  906. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  907. 'info_dict': {
  908. 'id': '5123ea6d5e5a7',
  909. 'ext': 'mp4',
  910. 'age_limit': 18,
  911. 'uploader': 'www.handjobhub.com',
  912. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  913. }
  914. },
  915. # Multiple brightcove videos
  916. # https://github.com/ytdl-org/youtube-dl/issues/2283
  917. {
  918. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  919. 'info_dict': {
  920. 'id': 'always-never',
  921. 'title': 'Always / Never - The New Yorker',
  922. },
  923. 'playlist_count': 3,
  924. 'params': {
  925. 'extract_flat': False,
  926. 'skip_download': True,
  927. }
  928. },
  929. # MLB embed
  930. {
  931. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  932. 'md5': '96f09a37e44da40dd083e12d9a683327',
  933. 'info_dict': {
  934. 'id': '33322633',
  935. 'ext': 'mp4',
  936. 'title': 'Ump changes call to ball',
  937. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  938. 'duration': 48,
  939. 'timestamp': 1401537900,
  940. 'upload_date': '20140531',
  941. 'thumbnail': r're:^https?://.*\.jpg$',
  942. },
  943. },
  944. # Wistia embed
  945. {
  946. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  947. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  948. 'info_dict': {
  949. 'id': '6e2wtrbdaf',
  950. 'ext': 'mov',
  951. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  952. 'description': 'a Paywall Videos video from Remilon',
  953. 'duration': 644.072,
  954. 'uploader': 'study.com',
  955. 'timestamp': 1459678540,
  956. 'upload_date': '20160403',
  957. 'filesize': 24687186,
  958. },
  959. },
  960. {
  961. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  962. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  963. 'info_dict': {
  964. 'id': 'uxjb0lwrcz',
  965. 'ext': 'mp4',
  966. 'title': 'Conversation about Hexagonal Rails Part 1',
  967. 'description': 'a Martin Fowler video from ThoughtWorks',
  968. 'duration': 1715.0,
  969. 'uploader': 'thoughtworks.wistia.com',
  970. 'timestamp': 1401832161,
  971. 'upload_date': '20140603',
  972. },
  973. },
  974. # Wistia standard embed (async)
  975. {
  976. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  977. 'info_dict': {
  978. 'id': '807fafadvk',
  979. 'ext': 'mp4',
  980. 'title': 'Drip Brennan Dunn Workshop',
  981. 'description': 'a JV Webinars video from getdrip-1',
  982. 'duration': 4986.95,
  983. 'timestamp': 1463607249,
  984. 'upload_date': '20160518',
  985. },
  986. 'params': {
  987. 'skip_download': True,
  988. }
  989. },
  990. # Soundcloud embed
  991. {
  992. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  993. 'info_dict': {
  994. 'id': '174391317',
  995. 'ext': 'mp3',
  996. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  997. 'uploader': 'Sophos Security',
  998. 'title': 'Chet Chat 171 - Oct 29, 2014',
  999. 'upload_date': '20141029',
  1000. }
  1001. },
  1002. # Soundcloud multiple embeds
  1003. {
  1004. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1005. 'info_dict': {
  1006. 'id': '52809',
  1007. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1008. },
  1009. 'playlist_mincount': 7,
  1010. },
  1011. # TuneIn station embed
  1012. {
  1013. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1014. 'info_dict': {
  1015. 'id': '204146',
  1016. 'ext': 'mp3',
  1017. 'title': 'CNRV',
  1018. 'location': 'Paris, France',
  1019. 'is_live': True,
  1020. },
  1021. 'params': {
  1022. # Live stream
  1023. 'skip_download': True,
  1024. },
  1025. },
  1026. # Livestream embed
  1027. {
  1028. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1029. 'info_dict': {
  1030. 'id': '67864563',
  1031. 'ext': 'flv',
  1032. 'upload_date': '20141112',
  1033. 'title': 'Rosetta #CometLanding webcast HL 10',
  1034. }
  1035. },
  1036. # Another Livestream embed, without 'new.' in URL
  1037. {
  1038. 'url': 'https://www.freespeech.org/',
  1039. 'info_dict': {
  1040. 'id': '123537347',
  1041. 'ext': 'mp4',
  1042. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1043. },
  1044. 'params': {
  1045. # Live stream
  1046. 'skip_download': True,
  1047. },
  1048. },
  1049. # LazyYT
  1050. {
  1051. 'url': 'https://skiplagged.com/',
  1052. 'info_dict': {
  1053. 'id': 'skiplagged',
  1054. 'title': 'Skiplagged: The smart way to find cheap flights',
  1055. },
  1056. 'playlist_mincount': 1,
  1057. 'add_ie': ['Youtube'],
  1058. },
  1059. # Cinchcast embed
  1060. {
  1061. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1062. 'info_dict': {
  1063. 'id': '7141703',
  1064. 'ext': 'mp3',
  1065. 'upload_date': '20141126',
  1066. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1067. }
  1068. },
  1069. # Cinerama player
  1070. {
  1071. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1072. 'info_dict': {
  1073. 'id': '730m_DandD_1901_512k',
  1074. 'ext': 'mp4',
  1075. 'uploader': 'www.abc.net.au',
  1076. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1077. }
  1078. },
  1079. # embedded viddler video
  1080. {
  1081. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1082. 'info_dict': {
  1083. 'id': '4d03aad9',
  1084. 'ext': 'mp4',
  1085. 'uploader': 'deadspin',
  1086. 'title': 'WALL-TO-GORTAT',
  1087. 'timestamp': 1422285291,
  1088. 'upload_date': '20150126',
  1089. },
  1090. 'add_ie': ['Viddler'],
  1091. },
  1092. # Libsyn embed
  1093. {
  1094. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1095. 'info_dict': {
  1096. 'id': '3377616',
  1097. 'ext': 'mp3',
  1098. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1099. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1100. 'upload_date': '20150220',
  1101. },
  1102. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1103. },
  1104. # jwplayer YouTube
  1105. {
  1106. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1107. 'info_dict': {
  1108. 'id': 'Mrj4DVp2zeA',
  1109. 'ext': 'mp4',
  1110. 'upload_date': '20150212',
  1111. 'uploader': 'The National Archives UK',
  1112. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1113. 'uploader_id': 'NationalArchives08',
  1114. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1115. },
  1116. },
  1117. # jwplayer rtmp
  1118. {
  1119. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1120. 'info_dict': {
  1121. 'id': 'live',
  1122. 'ext': 'flv',
  1123. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1124. 'uploader': 'www.suffolk.edu',
  1125. },
  1126. 'params': {
  1127. 'skip_download': True,
  1128. },
  1129. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1130. },
  1131. # Complex jwplayer
  1132. {
  1133. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1134. 'info_dict': {
  1135. 'id': 'videos',
  1136. 'ext': 'mp4',
  1137. 'title': 'king machine trailer 1',
  1138. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1139. 'thumbnail': r're:^https?://.*\.jpg$',
  1140. },
  1141. },
  1142. {
  1143. # JWPlayer config passed as variable
  1144. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1145. 'info_dict': {
  1146. 'id': '3326530_hq',
  1147. 'ext': 'mp4',
  1148. 'title': 'ARIELE | Tube Cup',
  1149. 'uploader': 'www.txxx.com',
  1150. 'age_limit': 18,
  1151. },
  1152. 'params': {
  1153. 'skip_download': True,
  1154. }
  1155. },
  1156. {
  1157. # JWPlatform iframe
  1158. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1159. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1160. 'info_dict': {
  1161. 'id': 'O0c5JcKT',
  1162. 'ext': 'mp4',
  1163. 'upload_date': '20171122',
  1164. 'timestamp': 1511366290,
  1165. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1166. },
  1167. 'add_ie': [JWPlatformIE.ie_key()],
  1168. },
  1169. {
  1170. # Video.js embed, multiple formats
  1171. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1172. 'info_dict': {
  1173. 'id': 'yygqldloqIk',
  1174. 'ext': 'mp4',
  1175. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1176. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1177. 'upload_date': '20130314',
  1178. 'uploader': 'PROстое3D',
  1179. 'uploader_id': 'PROstoe3D',
  1180. },
  1181. 'params': {
  1182. 'skip_download': True,
  1183. },
  1184. },
  1185. {
  1186. # Video.js embed, single format
  1187. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1188. 'info_dict': {
  1189. 'id': 'watch',
  1190. 'ext': 'mp4',
  1191. 'title': 'Step 1 - Good Foundation',
  1192. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1193. },
  1194. 'params': {
  1195. 'skip_download': True,
  1196. },
  1197. },
  1198. # rtl.nl embed
  1199. {
  1200. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1201. 'playlist_mincount': 5,
  1202. 'info_dict': {
  1203. 'id': 'aanslagen-kopenhagen',
  1204. 'title': 'Aanslagen Kopenhagen',
  1205. }
  1206. },
  1207. # Zapiks embed
  1208. {
  1209. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1210. 'info_dict': {
  1211. 'id': '118046',
  1212. 'ext': 'mp4',
  1213. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1214. }
  1215. },
  1216. # Kaltura embed (different embed code)
  1217. {
  1218. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1219. 'info_dict': {
  1220. 'id': '1_a52wc67y',
  1221. 'ext': 'flv',
  1222. 'upload_date': '20150127',
  1223. 'uploader_id': 'PremierMedia',
  1224. 'timestamp': int,
  1225. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1226. },
  1227. },
  1228. # Kaltura embed with single quotes
  1229. {
  1230. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1231. 'info_dict': {
  1232. 'id': '0_izeg5utt',
  1233. 'ext': 'mp4',
  1234. 'title': '35871',
  1235. 'timestamp': 1355743100,
  1236. 'upload_date': '20121217',
  1237. 'uploader_id': 'cplapp@learn360.com',
  1238. },
  1239. 'add_ie': ['Kaltura'],
  1240. },
  1241. {
  1242. # Kaltura embedded via quoted entry_id
  1243. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1244. 'info_dict': {
  1245. 'id': '0_utuok90b',
  1246. 'ext': 'mp4',
  1247. 'title': '06_matthew_brender_raj_dutt',
  1248. 'timestamp': 1466638791,
  1249. 'upload_date': '20160622',
  1250. },
  1251. 'add_ie': ['Kaltura'],
  1252. 'expected_warnings': [
  1253. 'Could not send HEAD request'
  1254. ],
  1255. 'params': {
  1256. 'skip_download': True,
  1257. }
  1258. },
  1259. {
  1260. # Kaltura embedded, some fileExt broken (#11480)
  1261. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1262. 'info_dict': {
  1263. 'id': '1_sgtvehim',
  1264. 'ext': 'mp4',
  1265. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1266. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1267. 'timestamp': 1321158993,
  1268. 'upload_date': '20111113',
  1269. 'uploader_id': 'kps1',
  1270. },
  1271. 'add_ie': ['Kaltura'],
  1272. },
  1273. {
  1274. # Kaltura iframe embed
  1275. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1276. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1277. 'info_dict': {
  1278. 'id': '0_f2cfbpwy',
  1279. 'ext': 'mp4',
  1280. 'title': 'I. M. Pei: A Centennial Celebration',
  1281. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1282. 'upload_date': '20170403',
  1283. 'uploader_id': 'batchUser',
  1284. 'timestamp': 1491232186,
  1285. },
  1286. 'add_ie': ['Kaltura'],
  1287. },
  1288. {
  1289. # Kaltura iframe embed, more sophisticated
  1290. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1291. 'info_dict': {
  1292. 'id': '1_9gzouybz',
  1293. 'ext': 'mp4',
  1294. 'title': 'lecture-05sep2017',
  1295. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1296. 'upload_date': '20170913',
  1297. 'uploader_id': 'eps2',
  1298. 'timestamp': 1505340777,
  1299. },
  1300. 'params': {
  1301. 'skip_download': True,
  1302. },
  1303. 'add_ie': ['Kaltura'],
  1304. },
  1305. {
  1306. # meta twitter:player
  1307. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1308. 'info_dict': {
  1309. 'id': '0_01b42zps',
  1310. 'ext': 'mp4',
  1311. 'title': 'Main Twerk (Video)',
  1312. 'upload_date': '20171208',
  1313. 'uploader_id': 'sebastian.salinas@thechive.com',
  1314. 'timestamp': 1512713057,
  1315. },
  1316. 'params': {
  1317. 'skip_download': True,
  1318. },
  1319. 'add_ie': ['Kaltura'],
  1320. },
  1321. # referrer protected EaglePlatform embed
  1322. {
  1323. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1324. 'info_dict': {
  1325. 'id': '582306',
  1326. 'ext': 'mp4',
  1327. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1328. 'thumbnail': r're:^https?://.*\.jpg$',
  1329. 'duration': 3382,
  1330. 'view_count': int,
  1331. },
  1332. 'params': {
  1333. 'skip_download': True,
  1334. },
  1335. },
  1336. # ClipYou (EaglePlatform) embed (custom URL)
  1337. {
  1338. 'url': 'http://muz-tv.ru/play/7129/',
  1339. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1340. 'info_dict': {
  1341. 'id': '12820',
  1342. 'ext': 'mp4',
  1343. 'title': "'O Sole Mio",
  1344. 'thumbnail': r're:^https?://.*\.jpg$',
  1345. 'duration': 216,
  1346. 'view_count': int,
  1347. },
  1348. 'params': {
  1349. 'skip_download': True,
  1350. },
  1351. 'skip': 'This video is unavailable.',
  1352. },
  1353. # Pladform embed
  1354. {
  1355. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1356. 'info_dict': {
  1357. 'id': '100183293',
  1358. 'ext': 'mp4',
  1359. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1360. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1361. 'thumbnail': r're:^https?://.*\.jpg$',
  1362. 'duration': 694,
  1363. 'age_limit': 0,
  1364. },
  1365. 'skip': 'HTTP Error 404: Not Found',
  1366. },
  1367. # Playwire embed
  1368. {
  1369. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1370. 'info_dict': {
  1371. 'id': '3519514',
  1372. 'ext': 'mp4',
  1373. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1374. 'thumbnail': r're:^https?://.*\.png$',
  1375. 'duration': 45.115,
  1376. },
  1377. },
  1378. # 5min embed
  1379. {
  1380. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1381. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1382. 'info_dict': {
  1383. 'id': '518726732',
  1384. 'ext': 'mp4',
  1385. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1386. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1387. 'timestamp': 1427237531,
  1388. 'uploader': 'Crunch Report',
  1389. 'upload_date': '20150324',
  1390. },
  1391. 'params': {
  1392. # m3u8 download
  1393. 'skip_download': True,
  1394. },
  1395. },
  1396. # Crooks and Liars embed
  1397. {
  1398. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1399. 'info_dict': {
  1400. 'id': '8RUoRhRi',
  1401. 'ext': 'mp4',
  1402. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1403. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1404. 'timestamp': 1428207000,
  1405. 'upload_date': '20150405',
  1406. 'uploader': 'Heather',
  1407. },
  1408. },
  1409. # Crooks and Liars external embed
  1410. {
  1411. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1412. 'info_dict': {
  1413. 'id': 'MTE3MjUtMzQ2MzA',
  1414. 'ext': 'mp4',
  1415. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1416. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1417. 'timestamp': 1265032391,
  1418. 'upload_date': '20100201',
  1419. 'uploader': 'Heather',
  1420. },
  1421. },
  1422. # NBC Sports vplayer embed
  1423. {
  1424. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1425. 'info_dict': {
  1426. 'id': 'ln7x1qSThw4k',
  1427. 'ext': 'flv',
  1428. 'title': "PFT Live: New leader in the 'new-look' defense",
  1429. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1430. 'uploader': 'NBCU-SPORTS',
  1431. 'upload_date': '20140107',
  1432. 'timestamp': 1389118457,
  1433. },
  1434. 'skip': 'Invalid Page URL',
  1435. },
  1436. # NBC News embed
  1437. {
  1438. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1439. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1440. 'info_dict': {
  1441. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1442. 'ext': 'mp4',
  1443. 'title': 'David Letterman: A Preview',
  1444. '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.',
  1445. 'upload_date': '20160609',
  1446. 'timestamp': 1465431544,
  1447. 'uploader': 'NBCU-NEWS',
  1448. },
  1449. },
  1450. # UDN embed
  1451. {
  1452. 'url': 'https://video.udn.com/news/300346',
  1453. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1454. 'info_dict': {
  1455. 'id': '300346',
  1456. 'ext': 'mp4',
  1457. 'title': '中一中男師變性 全校師生力挺',
  1458. 'thumbnail': r're:^https?://.*\.jpg$',
  1459. },
  1460. 'params': {
  1461. # m3u8 download
  1462. 'skip_download': True,
  1463. },
  1464. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1465. },
  1466. # Brightcove URL in single quotes
  1467. {
  1468. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1469. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1470. 'info_dict': {
  1471. 'id': '4255764656001',
  1472. 'ext': 'mp4',
  1473. 'title': 'SN Presents: Russell Martin, World Citizen',
  1474. '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.',
  1475. 'uploader': 'Rogers Sportsnet',
  1476. 'uploader_id': '1704050871',
  1477. 'upload_date': '20150525',
  1478. 'timestamp': 1432570283,
  1479. },
  1480. },
  1481. # OnionStudios embed
  1482. {
  1483. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1484. 'info_dict': {
  1485. 'id': '2855',
  1486. 'ext': 'mp4',
  1487. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1488. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1489. 'uploader': 'ClickHole',
  1490. 'uploader_id': 'clickhole',
  1491. }
  1492. },
  1493. # SnagFilms embed
  1494. {
  1495. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1496. 'info_dict': {
  1497. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1498. 'ext': 'mp4',
  1499. 'title': '#whilewewatch',
  1500. }
  1501. },
  1502. # AdobeTVVideo embed
  1503. {
  1504. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1505. 'md5': '43662b577c018ad707a63766462b1e87',
  1506. 'info_dict': {
  1507. 'id': '2456',
  1508. 'ext': 'mp4',
  1509. 'title': 'New experience with Acrobat DC',
  1510. 'description': 'New experience with Acrobat DC',
  1511. 'duration': 248.667,
  1512. },
  1513. },
  1514. # BrightcoveInPageEmbed embed
  1515. {
  1516. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1517. 'info_dict': {
  1518. 'id': '4238694884001',
  1519. 'ext': 'flv',
  1520. 'title': 'Tabletop: Dread, Last Thoughts',
  1521. 'description': 'Tabletop: Dread, Last Thoughts',
  1522. 'duration': 51690,
  1523. },
  1524. },
  1525. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1526. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1527. {
  1528. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1529. 'info_dict': {
  1530. 'id': '4785848093001',
  1531. 'ext': 'mp4',
  1532. 'title': 'The Cardinal Pell Interview',
  1533. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1534. 'uploader': 'GlobeCast Australia - GlobeStream',
  1535. 'uploader_id': '2733773828001',
  1536. 'upload_date': '20160304',
  1537. 'timestamp': 1457083087,
  1538. },
  1539. 'params': {
  1540. # m3u8 downloads
  1541. 'skip_download': True,
  1542. },
  1543. },
  1544. {
  1545. # Brightcove embed with whitespace around attribute names
  1546. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1547. 'info_dict': {
  1548. 'id': '3167554373001',
  1549. 'ext': 'mp4',
  1550. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1551. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1552. 'uploader_id': '1079349493',
  1553. 'upload_date': '20140207',
  1554. 'timestamp': 1391810548,
  1555. },
  1556. 'params': {
  1557. 'skip_download': True,
  1558. },
  1559. },
  1560. # Another form of arte.tv embed
  1561. {
  1562. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1563. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1564. 'info_dict': {
  1565. 'id': '030273-562_PLUS7-F',
  1566. 'ext': 'mp4',
  1567. 'title': 'ARTE Reportage - Nulle part, en France',
  1568. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1569. 'upload_date': '20160409',
  1570. },
  1571. },
  1572. # LiveLeak embed
  1573. {
  1574. 'url': 'http://www.wykop.pl/link/3088787/',
  1575. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1576. 'info_dict': {
  1577. 'id': '874_1459135191',
  1578. 'ext': 'mp4',
  1579. 'title': 'Man shows poor quality of new apartment building',
  1580. 'description': 'The wall is like a sand pile.',
  1581. 'uploader': 'Lake8737',
  1582. },
  1583. 'add_ie': [LiveLeakIE.ie_key()],
  1584. },
  1585. # Another LiveLeak embed pattern (#13336)
  1586. {
  1587. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1588. 'info_dict': {
  1589. 'id': '2eb_1496309988',
  1590. 'ext': 'mp4',
  1591. 'title': 'Thief robs place where everyone was armed',
  1592. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1593. 'uploader': 'brazilwtf',
  1594. },
  1595. 'add_ie': [LiveLeakIE.ie_key()],
  1596. },
  1597. # Duplicated embedded video URLs
  1598. {
  1599. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1600. 'info_dict': {
  1601. 'id': '149298443_480_16c25b74_2',
  1602. 'ext': 'mp4',
  1603. 'title': 'vs. Blue Orange Spring Game',
  1604. 'uploader': 'www.hudl.com',
  1605. },
  1606. },
  1607. # twitter:player:stream embed
  1608. {
  1609. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1610. 'info_dict': {
  1611. 'id': 'master',
  1612. 'ext': 'mp4',
  1613. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1614. 'uploader': 'www.rtl.be',
  1615. },
  1616. 'params': {
  1617. # m3u8 downloads
  1618. 'skip_download': True,
  1619. },
  1620. },
  1621. # twitter:player embed
  1622. {
  1623. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1624. 'md5': 'a3e0df96369831de324f0778e126653c',
  1625. 'info_dict': {
  1626. 'id': '4909620399001',
  1627. 'ext': 'mp4',
  1628. 'title': 'What Do Black Holes Sound Like?',
  1629. 'description': 'what do black holes sound like',
  1630. 'upload_date': '20160524',
  1631. 'uploader_id': '29913724001',
  1632. 'timestamp': 1464107587,
  1633. 'uploader': 'TheAtlantic',
  1634. },
  1635. 'add_ie': ['BrightcoveLegacy'],
  1636. },
  1637. # Facebook <iframe> embed
  1638. {
  1639. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1640. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1641. 'info_dict': {
  1642. 'id': '599637780109885',
  1643. 'ext': 'mp4',
  1644. 'title': 'Facebook video #599637780109885',
  1645. },
  1646. },
  1647. # Facebook <iframe> embed, plugin video
  1648. {
  1649. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1650. 'info_dict': {
  1651. 'id': '1754168231264132',
  1652. 'ext': 'mp4',
  1653. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1654. 'uploader': 'Tariq Ramadan (official)',
  1655. 'timestamp': 1496758379,
  1656. 'upload_date': '20170606',
  1657. },
  1658. 'params': {
  1659. 'skip_download': True,
  1660. },
  1661. },
  1662. # Facebook API embed
  1663. {
  1664. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1665. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1666. 'info_dict': {
  1667. 'id': '10153467542406923',
  1668. 'ext': 'mp4',
  1669. 'title': 'Facebook video #10153467542406923',
  1670. },
  1671. },
  1672. # Wordpress "YouTube Video Importer" plugin
  1673. {
  1674. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1675. 'md5': 'd16797741b560b485194eddda8121b48',
  1676. 'info_dict': {
  1677. 'id': 'HNTXWDXV9Is',
  1678. 'ext': 'mp4',
  1679. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1680. 'upload_date': '20160627',
  1681. 'uploader_id': 'GENOCIDE8GENERAL10',
  1682. 'uploader': 'cylus cyrus',
  1683. },
  1684. },
  1685. {
  1686. # video stored on custom kaltura server
  1687. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1688. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1689. 'info_dict': {
  1690. 'id': '0_1iotm5bh',
  1691. 'ext': 'mp4',
  1692. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1693. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1694. 'uploader_id': 'videos.expansion@el-mundo.net',
  1695. 'upload_date': '20150429',
  1696. 'timestamp': 1430303472,
  1697. },
  1698. 'add_ie': ['Kaltura'],
  1699. },
  1700. {
  1701. # Non-standard Vimeo embed
  1702. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1703. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1704. 'info_dict': {
  1705. 'id': '148867247',
  1706. 'ext': 'mp4',
  1707. 'title': 'Understanding the web - Teaser',
  1708. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1709. 'upload_date': '20151214',
  1710. 'uploader': 'OpenClassrooms',
  1711. 'uploader_id': 'openclassrooms',
  1712. },
  1713. 'add_ie': ['Vimeo'],
  1714. },
  1715. {
  1716. # generic vimeo embed that requires original URL passed as Referer
  1717. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1718. 'only_matching': True,
  1719. },
  1720. {
  1721. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1722. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1723. 'info_dict': {
  1724. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1725. 'ext': 'mp4',
  1726. 'title': 'Big Buck Bunny',
  1727. 'description': 'Royalty free test video',
  1728. 'timestamp': 1432816365,
  1729. 'upload_date': '20150528',
  1730. 'is_live': False,
  1731. },
  1732. 'params': {
  1733. 'skip_download': True,
  1734. },
  1735. 'add_ie': [ArkenaIE.ie_key()],
  1736. },
  1737. {
  1738. '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/',
  1739. 'info_dict': {
  1740. 'id': '1c7141f46c',
  1741. 'ext': 'mp4',
  1742. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1743. },
  1744. 'params': {
  1745. 'skip_download': True,
  1746. },
  1747. 'add_ie': [Vbox7IE.ie_key()],
  1748. },
  1749. {
  1750. # DBTV embeds
  1751. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1752. 'info_dict': {
  1753. 'id': '43254897',
  1754. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1755. },
  1756. 'playlist_mincount': 3,
  1757. },
  1758. {
  1759. # Videa embeds
  1760. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1761. 'info_dict': {
  1762. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1763. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1764. },
  1765. 'playlist_mincount': 2,
  1766. },
  1767. {
  1768. # 20 minuten embed
  1769. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1770. 'info_dict': {
  1771. 'id': '523629',
  1772. 'ext': 'mp4',
  1773. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1774. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1775. },
  1776. 'params': {
  1777. 'skip_download': True,
  1778. },
  1779. 'add_ie': [TwentyMinutenIE.ie_key()],
  1780. },
  1781. {
  1782. # VideoPress embed
  1783. 'url': 'https://en.support.wordpress.com/videopress/',
  1784. 'info_dict': {
  1785. 'id': 'OcobLTqC',
  1786. 'ext': 'm4v',
  1787. 'title': 'IMG_5786',
  1788. 'timestamp': 1435711927,
  1789. 'upload_date': '20150701',
  1790. },
  1791. 'params': {
  1792. 'skip_download': True,
  1793. },
  1794. 'add_ie': [VideoPressIE.ie_key()],
  1795. },
  1796. {
  1797. # Rutube embed
  1798. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1799. 'info_dict': {
  1800. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1801. 'ext': 'flv',
  1802. 'title': 'Магаззино: Казань 2',
  1803. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1804. 'uploader': 'Магаззино',
  1805. 'upload_date': '20170228',
  1806. 'uploader_id': '996642',
  1807. },
  1808. 'params': {
  1809. 'skip_download': True,
  1810. },
  1811. 'add_ie': [RutubeIE.ie_key()],
  1812. },
  1813. {
  1814. # ThePlatform embedded with whitespaces in URLs
  1815. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1816. 'only_matching': True,
  1817. },
  1818. {
  1819. # Senate ISVP iframe https
  1820. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1821. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1822. 'info_dict': {
  1823. 'id': 'govtaff020316',
  1824. 'ext': 'mp4',
  1825. 'title': 'Integrated Senate Video Player',
  1826. },
  1827. 'add_ie': [SenateISVPIE.ie_key()],
  1828. },
  1829. {
  1830. # Limelight embeds (1 channel embed + 4 media embeds)
  1831. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1832. 'info_dict': {
  1833. 'id': 'FacilitatorTraining2017',
  1834. 'title': 'Facilitator Training 2017',
  1835. },
  1836. 'playlist_mincount': 5,
  1837. },
  1838. {
  1839. # Limelight embed (LimelightPlayerUtil.embed)
  1840. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1841. 'info_dict': {
  1842. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1843. 'ext': 'mp4',
  1844. 'title': '07448641',
  1845. 'timestamp': 1499890639,
  1846. 'upload_date': '20170712',
  1847. },
  1848. 'params': {
  1849. 'skip_download': True,
  1850. },
  1851. 'add_ie': ['LimelightMedia'],
  1852. },
  1853. {
  1854. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1855. 'info_dict': {
  1856. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1857. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1858. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1859. },
  1860. 'playlist_mincount': 4,
  1861. },
  1862. {
  1863. # WashingtonPost embed
  1864. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1865. 'info_dict': {
  1866. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1867. 'ext': 'mp4',
  1868. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1869. '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.',
  1870. 'timestamp': 1455216756,
  1871. 'uploader': 'The Washington Post',
  1872. 'upload_date': '20160211',
  1873. },
  1874. 'add_ie': [WashingtonPostIE.ie_key()],
  1875. },
  1876. {
  1877. # Mediaset embed
  1878. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1879. 'info_dict': {
  1880. 'id': '720642',
  1881. 'ext': 'mp4',
  1882. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1883. },
  1884. 'params': {
  1885. 'skip_download': True,
  1886. },
  1887. 'add_ie': [MediasetIE.ie_key()],
  1888. },
  1889. {
  1890. # JOJ.sk embeds
  1891. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1892. 'info_dict': {
  1893. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1894. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1895. },
  1896. 'playlist_mincount': 5,
  1897. 'add_ie': [JojIE.ie_key()],
  1898. },
  1899. {
  1900. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1901. 'url': 'https://tvrain.ru/amp/418921/',
  1902. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1903. 'info_dict': {
  1904. 'id': '418921',
  1905. 'ext': 'mp4',
  1906. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1907. },
  1908. },
  1909. {
  1910. # vzaar embed
  1911. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1912. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1913. 'info_dict': {
  1914. 'id': '8707641',
  1915. 'ext': 'mp4',
  1916. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1917. },
  1918. },
  1919. {
  1920. # multiple HTML5 videos on one page
  1921. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1922. 'info_dict': {
  1923. 'id': 'keyscenarios',
  1924. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1925. },
  1926. 'playlist_count': 4,
  1927. },
  1928. {
  1929. # vshare embed
  1930. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1931. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1932. 'info_dict': {
  1933. 'id': '0f64ce6',
  1934. 'title': 'vl14062007715967',
  1935. 'ext': 'mp4',
  1936. }
  1937. },
  1938. {
  1939. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1940. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1941. 'info_dict': {
  1942. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1943. 'ext': 'mp4',
  1944. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1945. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1946. 'timestamp': 1474354800,
  1947. 'upload_date': '20160920',
  1948. }
  1949. },
  1950. {
  1951. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1952. 'info_dict': {
  1953. 'id': '1731611',
  1954. 'ext': 'mp4',
  1955. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1956. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1957. 'timestamp': 1516100691,
  1958. 'upload_date': '20180116',
  1959. },
  1960. 'params': {
  1961. 'skip_download': True,
  1962. },
  1963. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1964. },
  1965. {
  1966. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1967. 'info_dict': {
  1968. 'id': 'uPDB5I9wfp8',
  1969. 'ext': 'webm',
  1970. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1971. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  1972. 'upload_date': '20160219',
  1973. 'uploader': 'Pocoyo - Português (BR)',
  1974. 'uploader_id': 'PocoyoBrazil',
  1975. },
  1976. 'add_ie': [YoutubeIE.ie_key()],
  1977. 'params': {
  1978. 'skip_download': True,
  1979. },
  1980. },
  1981. {
  1982. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  1983. 'info_dict': {
  1984. 'id': 'vMDE4NzI1Mjgt690b',
  1985. 'ext': 'mp4',
  1986. 'title': 'Котята',
  1987. },
  1988. 'add_ie': [YapFilesIE.ie_key()],
  1989. 'params': {
  1990. 'skip_download': True,
  1991. },
  1992. },
  1993. {
  1994. # CloudflareStream embed
  1995. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  1996. 'info_dict': {
  1997. 'id': '31c9291ab41fac05471db4e73aa11717',
  1998. 'ext': 'mp4',
  1999. 'title': '31c9291ab41fac05471db4e73aa11717',
  2000. },
  2001. 'add_ie': [CloudflareStreamIE.ie_key()],
  2002. 'params': {
  2003. 'skip_download': True,
  2004. },
  2005. },
  2006. {
  2007. # PeerTube embed
  2008. 'url': 'https://joinpeertube.org/fr/home/',
  2009. 'info_dict': {
  2010. 'id': 'home',
  2011. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2012. },
  2013. 'playlist_count': 2,
  2014. },
  2015. {
  2016. # Indavideo embed
  2017. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2018. 'info_dict': {
  2019. 'id': '1693903',
  2020. 'ext': 'mp4',
  2021. 'title': 'Így kell otthon hamburgert sütni',
  2022. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2023. 'timestamp': 1426330212,
  2024. 'upload_date': '20150314',
  2025. 'uploader': 'StreetKitchen',
  2026. 'uploader_id': '546363',
  2027. },
  2028. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2029. 'params': {
  2030. 'skip_download': True,
  2031. },
  2032. },
  2033. {
  2034. # APA embed via JWPlatform embed
  2035. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2036. 'info_dict': {
  2037. 'id': 'jjv85FdZ',
  2038. 'ext': 'mp4',
  2039. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2040. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2041. 'thumbnail': r're:^https?://.*\.jpg$',
  2042. 'duration': 254,
  2043. 'timestamp': 1519211149,
  2044. 'upload_date': '20180221',
  2045. },
  2046. 'params': {
  2047. 'skip_download': True,
  2048. },
  2049. },
  2050. {
  2051. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2052. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2053. 'info_dict': {
  2054. 'id': '83645793',
  2055. 'title': 'Lock up and get excited',
  2056. 'ext': 'mp4'
  2057. },
  2058. 'skip': 'TODO: fix nested playlists processing in tests',
  2059. },
  2060. {
  2061. # Viqeo embeds
  2062. 'url': 'https://viqeo.tv/',
  2063. 'info_dict': {
  2064. 'id': 'viqeo',
  2065. 'title': 'All-new video platform',
  2066. },
  2067. 'playlist_count': 6,
  2068. },
  2069. {
  2070. # Zype embed
  2071. 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2072. 'info_dict': {
  2073. 'id': '5b400b834b32992a310622b9',
  2074. 'ext': 'mp4',
  2075. 'title': 'Smoky Barbecue Favorites',
  2076. 'thumbnail': r're:^https?://.*\.jpe?g',
  2077. },
  2078. 'add_ie': [ZypeIE.ie_key()],
  2079. 'params': {
  2080. 'skip_download': True,
  2081. },
  2082. },
  2083. {
  2084. # videojs embed
  2085. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2086. 'info_dict': {
  2087. 'id': 'shell',
  2088. 'ext': 'mp4',
  2089. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2090. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2091. 'thumbnail': r're:^https?://.*\.jpg$',
  2092. },
  2093. 'params': {
  2094. 'skip_download': True,
  2095. },
  2096. 'expected_warnings': ['Failed to download MPD manifest'],
  2097. },
  2098. # {
  2099. # # TODO: find another test
  2100. # # http://schema.org/VideoObject
  2101. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2102. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2103. # 'info_dict': {
  2104. # 'id': 'nyvTSJMKId',
  2105. # 'ext': 'mp4',
  2106. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2107. # 'description': '#love for cats.',
  2108. # 'timestamp': 1461244995,
  2109. # 'upload_date': '20160421',
  2110. # },
  2111. # 'params': {
  2112. # 'force_generic_extractor': True,
  2113. # },
  2114. # }
  2115. ]
  2116. def report_following_redirect(self, new_url):
  2117. """Report information extraction."""
  2118. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2119. def _extract_rss(self, url, video_id, doc):
  2120. playlist_title = doc.find('./channel/title').text
  2121. playlist_desc_el = doc.find('./channel/description')
  2122. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2123. entries = []
  2124. for it in doc.findall('./channel/item'):
  2125. next_url = None
  2126. enclosure_nodes = it.findall('./enclosure')
  2127. for e in enclosure_nodes:
  2128. next_url = e.attrib.get('url')
  2129. if next_url:
  2130. break
  2131. if not next_url:
  2132. next_url = xpath_text(it, 'link', fatal=False)
  2133. if not next_url:
  2134. continue
  2135. entries.append({
  2136. '_type': 'url_transparent',
  2137. 'url': next_url,
  2138. 'title': it.find('title').text,
  2139. })
  2140. return {
  2141. '_type': 'playlist',
  2142. 'id': url,
  2143. 'title': playlist_title,
  2144. 'description': playlist_desc,
  2145. 'entries': entries,
  2146. }
  2147. def _extract_camtasia(self, url, video_id, webpage):
  2148. """ Returns None if no camtasia video can be found. """
  2149. camtasia_cfg = self._search_regex(
  2150. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2151. webpage, 'camtasia configuration file', default=None)
  2152. if camtasia_cfg is None:
  2153. return None
  2154. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2155. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2156. camtasia_cfg = self._download_xml(
  2157. camtasia_url, video_id,
  2158. note='Downloading camtasia configuration',
  2159. errnote='Failed to download camtasia configuration')
  2160. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2161. entries = []
  2162. for n in fileset_node.getchildren():
  2163. url_n = n.find('./uri')
  2164. if url_n is None:
  2165. continue
  2166. entries.append({
  2167. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2168. 'title': '%s - %s' % (title, n.tag),
  2169. 'url': compat_urlparse.urljoin(url, url_n.text),
  2170. 'duration': float_or_none(n.find('./duration').text),
  2171. })
  2172. return {
  2173. '_type': 'playlist',
  2174. 'entries': entries,
  2175. 'title': title,
  2176. }
  2177. def _real_extract(self, url):
  2178. if url.startswith('//'):
  2179. return self.url_result(self.http_scheme() + url)
  2180. parsed_url = compat_urlparse.urlparse(url)
  2181. if not parsed_url.scheme:
  2182. default_search = self._downloader.params.get('default_search')
  2183. if default_search is None:
  2184. default_search = 'fixup_error'
  2185. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2186. if '/' in url:
  2187. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2188. return self.url_result('http://' + url)
  2189. elif default_search != 'fixup_error':
  2190. if default_search == 'auto_warning':
  2191. if re.match(r'^(?:url|URL)$', url):
  2192. raise ExtractorError(
  2193. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2194. expected=True)
  2195. else:
  2196. self._downloader.report_warning(
  2197. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2198. return self.url_result('ytsearch:' + url)
  2199. if default_search in ('error', 'fixup_error'):
  2200. raise ExtractorError(
  2201. '%r is not a valid URL. '
  2202. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2203. % (url, url), expected=True)
  2204. else:
  2205. if ':' not in default_search:
  2206. default_search += ':'
  2207. return self.url_result(default_search + url)
  2208. url, smuggled_data = unsmuggle_url(url)
  2209. force_videoid = None
  2210. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2211. if smuggled_data and 'force_videoid' in smuggled_data:
  2212. force_videoid = smuggled_data['force_videoid']
  2213. video_id = force_videoid
  2214. else:
  2215. video_id = self._generic_id(url)
  2216. self.to_screen('%s: Requesting header' % video_id)
  2217. head_req = HEADRequest(url)
  2218. head_response = self._request_webpage(
  2219. head_req, video_id,
  2220. note=False, errnote='Could not send HEAD request to %s' % url,
  2221. fatal=False)
  2222. if head_response is not False:
  2223. # Check for redirect
  2224. new_url = compat_str(head_response.geturl())
  2225. if url != new_url:
  2226. self.report_following_redirect(new_url)
  2227. if force_videoid:
  2228. new_url = smuggle_url(
  2229. new_url, {'force_videoid': force_videoid})
  2230. return self.url_result(new_url)
  2231. full_response = None
  2232. if head_response is False:
  2233. request = sanitized_Request(url)
  2234. request.add_header('Accept-Encoding', '*')
  2235. full_response = self._request_webpage(request, video_id)
  2236. head_response = full_response
  2237. info_dict = {
  2238. 'id': video_id,
  2239. 'title': self._generic_title(url),
  2240. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2241. }
  2242. # Check for direct link to a video
  2243. content_type = head_response.headers.get('Content-Type', '').lower()
  2244. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2245. if m:
  2246. format_id = compat_str(m.group('format_id'))
  2247. if format_id.endswith('mpegurl'):
  2248. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2249. elif format_id == 'f4m':
  2250. formats = self._extract_f4m_formats(url, video_id)
  2251. else:
  2252. formats = [{
  2253. 'format_id': format_id,
  2254. 'url': url,
  2255. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2256. }]
  2257. info_dict['direct'] = True
  2258. self._sort_formats(formats)
  2259. info_dict['formats'] = formats
  2260. return info_dict
  2261. if not self._downloader.params.get('test', False) and not is_intentional:
  2262. force = self._downloader.params.get('force_generic_extractor', False)
  2263. self._downloader.report_warning(
  2264. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2265. if not full_response:
  2266. request = sanitized_Request(url)
  2267. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2268. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2269. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2270. # that will always result in downloading the whole file that is not desirable.
  2271. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2272. # to accept raw bytes and being able to download only a chunk.
  2273. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2274. # after HEAD request finishes, but not sure if we can rely on this.
  2275. request.add_header('Accept-Encoding', '*')
  2276. full_response = self._request_webpage(request, video_id)
  2277. first_bytes = full_response.read(512)
  2278. # Is it an M3U playlist?
  2279. if first_bytes.startswith(b'#EXTM3U'):
  2280. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2281. self._sort_formats(info_dict['formats'])
  2282. return info_dict
  2283. # Maybe it's a direct link to a video?
  2284. # Be careful not to download the whole thing!
  2285. if not is_html(first_bytes):
  2286. self._downloader.report_warning(
  2287. 'URL could be a direct video link, returning it as such.')
  2288. info_dict.update({
  2289. 'direct': True,
  2290. 'url': url,
  2291. })
  2292. return info_dict
  2293. webpage = self._webpage_read_content(
  2294. full_response, url, video_id, prefix=first_bytes)
  2295. self.report_extraction(video_id)
  2296. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2297. try:
  2298. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2299. if doc.tag == 'rss':
  2300. return self._extract_rss(url, video_id, doc)
  2301. elif doc.tag == 'SmoothStreamingMedia':
  2302. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2303. self._sort_formats(info_dict['formats'])
  2304. return info_dict
  2305. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2306. smil = self._parse_smil(doc, url, video_id)
  2307. self._sort_formats(smil['formats'])
  2308. return smil
  2309. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2310. return self.playlist_result(
  2311. self._parse_xspf(
  2312. doc, video_id, xspf_url=url,
  2313. xspf_base_url=compat_str(full_response.geturl())),
  2314. video_id)
  2315. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2316. info_dict['formats'] = self._parse_mpd_formats(
  2317. doc,
  2318. mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
  2319. mpd_url=url)
  2320. self._sort_formats(info_dict['formats'])
  2321. return info_dict
  2322. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2323. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2324. self._sort_formats(info_dict['formats'])
  2325. return info_dict
  2326. except compat_xml_parse_error:
  2327. pass
  2328. # Is it a Camtasia project?
  2329. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2330. if camtasia_res is not None:
  2331. return camtasia_res
  2332. # Sometimes embedded video player is hidden behind percent encoding
  2333. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2334. # Unescaping the whole page allows to handle those cases in a generic way
  2335. webpage = compat_urllib_parse_unquote(webpage)
  2336. # it's tempting to parse this further, but you would
  2337. # have to take into account all the variations like
  2338. # Video Title - Site Name
  2339. # Site Name | Video Title
  2340. # Video Title - Tagline | Site Name
  2341. # and so on and so forth; it's just not practical
  2342. video_title = self._og_search_title(
  2343. webpage, default=None) or self._html_search_regex(
  2344. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2345. default='video')
  2346. # Try to detect age limit automatically
  2347. age_limit = self._rta_search(webpage)
  2348. # And then there are the jokers who advertise that they use RTA,
  2349. # but actually don't.
  2350. AGE_LIMIT_MARKERS = [
  2351. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2352. ]
  2353. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2354. age_limit = 18
  2355. # video uploader is domain name
  2356. video_uploader = self._search_regex(
  2357. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2358. video_description = self._og_search_description(webpage, default=None)
  2359. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2360. info_dict.update({
  2361. 'title': video_title,
  2362. 'description': video_description,
  2363. 'thumbnail': video_thumbnail,
  2364. 'age_limit': age_limit,
  2365. })
  2366. # Look for Brightcove Legacy Studio embeds
  2367. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2368. if bc_urls:
  2369. entries = [{
  2370. '_type': 'url',
  2371. 'url': smuggle_url(bc_url, {'Referer': url}),
  2372. 'ie_key': 'BrightcoveLegacy'
  2373. } for bc_url in bc_urls]
  2374. return {
  2375. '_type': 'playlist',
  2376. 'title': video_title,
  2377. 'id': video_id,
  2378. 'entries': entries,
  2379. }
  2380. # Look for Brightcove New Studio embeds
  2381. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2382. if bc_urls:
  2383. return self.playlist_from_matches(
  2384. bc_urls, video_id, video_title,
  2385. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2386. ie='BrightcoveNew')
  2387. # Look for Nexx embeds
  2388. nexx_urls = NexxIE._extract_urls(webpage)
  2389. if nexx_urls:
  2390. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2391. # Look for Nexx iFrame embeds
  2392. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2393. if nexx_embed_urls:
  2394. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2395. # Look for ThePlatform embeds
  2396. tp_urls = ThePlatformIE._extract_urls(webpage)
  2397. if tp_urls:
  2398. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2399. # Look for Vessel embeds
  2400. vessel_urls = VesselIE._extract_urls(webpage)
  2401. if vessel_urls:
  2402. return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
  2403. # Look for embedded rtl.nl player
  2404. matches = re.findall(
  2405. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2406. webpage)
  2407. if matches:
  2408. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2409. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2410. if vimeo_urls:
  2411. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2412. vid_me_embed_url = self._search_regex(
  2413. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2414. webpage, 'vid.me embed', default=None)
  2415. if vid_me_embed_url is not None:
  2416. return self.url_result(vid_me_embed_url, 'Vidme')
  2417. # Look for YouTube embeds
  2418. youtube_urls = YoutubeIE._extract_urls(webpage)
  2419. if youtube_urls:
  2420. return self.playlist_from_matches(
  2421. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2422. matches = DailymotionIE._extract_urls(webpage)
  2423. if matches:
  2424. return self.playlist_from_matches(matches, video_id, video_title)
  2425. # Look for embedded Dailymotion playlist player (#3822)
  2426. m = re.search(
  2427. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2428. if m:
  2429. playlists = re.findall(
  2430. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2431. if playlists:
  2432. return self.playlist_from_matches(
  2433. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2434. # Look for DailyMail embeds
  2435. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2436. if dailymail_urls:
  2437. return self.playlist_from_matches(
  2438. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2439. # Look for embedded Wistia player
  2440. wistia_url = WistiaIE._extract_url(webpage)
  2441. if wistia_url:
  2442. return {
  2443. '_type': 'url_transparent',
  2444. 'url': self._proto_relative_url(wistia_url),
  2445. 'ie_key': WistiaIE.ie_key(),
  2446. 'uploader': video_uploader,
  2447. }
  2448. # Look for SVT player
  2449. svt_url = SVTIE._extract_url(webpage)
  2450. if svt_url:
  2451. return self.url_result(svt_url, 'SVT')
  2452. # Look for Bandcamp pages with custom domain
  2453. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2454. if mobj is not None:
  2455. burl = unescapeHTML(mobj.group(1))
  2456. # Don't set the extractor because it can be a track url or an album
  2457. return self.url_result(burl)
  2458. # Look for embedded Vevo player
  2459. mobj = re.search(
  2460. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2461. if mobj is not None:
  2462. return self.url_result(mobj.group('url'))
  2463. # Look for embedded Viddler player
  2464. mobj = re.search(
  2465. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2466. webpage)
  2467. if mobj is not None:
  2468. return self.url_result(mobj.group('url'))
  2469. # Look for NYTimes player
  2470. mobj = re.search(
  2471. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2472. webpage)
  2473. if mobj is not None:
  2474. return self.url_result(mobj.group('url'))
  2475. # Look for Libsyn player
  2476. mobj = re.search(
  2477. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2478. if mobj is not None:
  2479. return self.url_result(mobj.group('url'))
  2480. # Look for Ooyala videos
  2481. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  2482. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2483. re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2484. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  2485. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2486. if mobj is not None:
  2487. embed_token = self._search_regex(
  2488. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2489. webpage, 'ooyala embed token', default=None)
  2490. return OoyalaIE._build_url_result(smuggle_url(
  2491. mobj.group('ec'), {
  2492. 'domain': url,
  2493. 'embed_token': embed_token,
  2494. }))
  2495. # Look for multiple Ooyala embeds on SBN network websites
  2496. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2497. if mobj is not None:
  2498. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2499. if embeds:
  2500. return self.playlist_from_matches(
  2501. embeds, video_id, video_title,
  2502. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2503. # Look for Aparat videos
  2504. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2505. if mobj is not None:
  2506. return self.url_result(mobj.group(1), 'Aparat')
  2507. # Look for MPORA videos
  2508. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2509. if mobj is not None:
  2510. return self.url_result(mobj.group(1), 'Mpora')
  2511. # Look for embedded NovaMov-based player
  2512. mobj = re.search(
  2513. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  2514. (?P<url>http://(?:(?:embed|www)\.)?
  2515. (?:novamov\.com|
  2516. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  2517. videoweed\.(?:es|com)|
  2518. movshare\.(?:net|sx|ag)|
  2519. divxstage\.(?:eu|net|ch|co|at|ag))
  2520. /embed\.php.+?)\1''', webpage)
  2521. if mobj is not None:
  2522. return self.url_result(mobj.group('url'))
  2523. # Look for embedded Facebook player
  2524. facebook_urls = FacebookIE._extract_urls(webpage)
  2525. if facebook_urls:
  2526. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2527. # Look for embedded VK player
  2528. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2529. if mobj is not None:
  2530. return self.url_result(mobj.group('url'), 'VK')
  2531. # Look for embedded Odnoklassniki player
  2532. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  2533. if mobj is not None:
  2534. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  2535. # Look for embedded ivi player
  2536. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2537. if mobj is not None:
  2538. return self.url_result(mobj.group('url'), 'Ivi')
  2539. # Look for embedded Huffington Post player
  2540. mobj = re.search(
  2541. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2542. if mobj is not None:
  2543. return self.url_result(mobj.group('url'), 'HuffPost')
  2544. # Look for embed.ly
  2545. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2546. if mobj is not None:
  2547. return self.url_result(mobj.group('url'))
  2548. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2549. if mobj is not None:
  2550. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2551. # Look for funnyordie embed
  2552. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2553. if matches:
  2554. return self.playlist_from_matches(
  2555. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2556. # Look for BBC iPlayer embed
  2557. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2558. if matches:
  2559. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2560. # Look for embedded RUTV player
  2561. rutv_url = RUTVIE._extract_url(webpage)
  2562. if rutv_url:
  2563. return self.url_result(rutv_url, 'RUTV')
  2564. # Look for embedded TVC player
  2565. tvc_url = TVCIE._extract_url(webpage)
  2566. if tvc_url:
  2567. return self.url_result(tvc_url, 'TVC')
  2568. # Look for embedded SportBox player
  2569. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2570. if sportbox_urls:
  2571. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2572. # Look for embedded XHamster player
  2573. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2574. if xhamster_urls:
  2575. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2576. # Look for embedded TNAFlixNetwork player
  2577. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2578. if tnaflix_urls:
  2579. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2580. # Look for embedded PornHub player
  2581. pornhub_urls = PornHubIE._extract_urls(webpage)
  2582. if pornhub_urls:
  2583. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2584. # Look for embedded DrTuber player
  2585. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2586. if drtuber_urls:
  2587. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2588. # Look for embedded RedTube player
  2589. redtube_urls = RedTubeIE._extract_urls(webpage)
  2590. if redtube_urls:
  2591. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2592. # Look for embedded Tube8 player
  2593. tube8_urls = Tube8IE._extract_urls(webpage)
  2594. if tube8_urls:
  2595. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2596. # Look for embedded Tvigle player
  2597. mobj = re.search(
  2598. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2599. if mobj is not None:
  2600. return self.url_result(mobj.group('url'), 'Tvigle')
  2601. # Look for embedded TED player
  2602. mobj = re.search(
  2603. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2604. if mobj is not None:
  2605. return self.url_result(mobj.group('url'), 'TED')
  2606. # Look for embedded Ustream videos
  2607. ustream_url = UstreamIE._extract_url(webpage)
  2608. if ustream_url:
  2609. return self.url_result(ustream_url, UstreamIE.ie_key())
  2610. # Look for embedded arte.tv player
  2611. mobj = re.search(
  2612. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2613. webpage)
  2614. if mobj is not None:
  2615. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2616. # Look for embedded francetv player
  2617. mobj = re.search(
  2618. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2619. webpage)
  2620. if mobj is not None:
  2621. return self.url_result(mobj.group('url'))
  2622. # Look for embedded smotri.com player
  2623. smotri_url = SmotriIE._extract_url(webpage)
  2624. if smotri_url:
  2625. return self.url_result(smotri_url, 'Smotri')
  2626. # Look for embedded Myvi.ru player
  2627. myvi_url = MyviIE._extract_url(webpage)
  2628. if myvi_url:
  2629. return self.url_result(myvi_url)
  2630. # Look for embedded soundcloud player
  2631. soundcloud_urls = SoundcloudIE._extract_urls(webpage)
  2632. if soundcloud_urls:
  2633. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
  2634. # Look for tunein player
  2635. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2636. if tunein_urls:
  2637. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2638. # Look for embedded mtvservices player
  2639. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2640. if mtvservices_url:
  2641. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2642. # Look for embedded yahoo player
  2643. mobj = re.search(
  2644. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2645. webpage)
  2646. if mobj is not None:
  2647. return self.url_result(mobj.group('url'), 'Yahoo')
  2648. # Look for embedded sbs.com.au player
  2649. mobj = re.search(
  2650. r'''(?x)
  2651. (?:
  2652. <meta\s+property="og:video"\s+content=|
  2653. <iframe[^>]+?src=
  2654. )
  2655. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2656. webpage)
  2657. if mobj is not None:
  2658. return self.url_result(mobj.group('url'), 'SBS')
  2659. # Look for embedded Cinchcast player
  2660. mobj = re.search(
  2661. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2662. webpage)
  2663. if mobj is not None:
  2664. return self.url_result(mobj.group('url'), 'Cinchcast')
  2665. mobj = re.search(
  2666. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2667. webpage)
  2668. if not mobj:
  2669. mobj = re.search(
  2670. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2671. webpage)
  2672. if mobj is not None:
  2673. return self.url_result(mobj.group('url'), 'MLB')
  2674. mobj = re.search(
  2675. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2676. webpage)
  2677. if mobj is not None:
  2678. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2679. mobj = re.search(
  2680. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2681. webpage)
  2682. if mobj is not None:
  2683. return self.url_result(mobj.group('url'), 'Livestream')
  2684. # Look for Zapiks embed
  2685. mobj = re.search(
  2686. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2687. if mobj is not None:
  2688. return self.url_result(mobj.group('url'), 'Zapiks')
  2689. # Look for Kaltura embeds
  2690. kaltura_url = KalturaIE._extract_url(webpage)
  2691. if kaltura_url:
  2692. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2693. # Look for EaglePlatform embeds
  2694. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2695. if eagleplatform_url:
  2696. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2697. # Look for ClipYou (uses EaglePlatform) embeds
  2698. mobj = re.search(
  2699. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2700. if mobj is not None:
  2701. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2702. # Look for Pladform embeds
  2703. pladform_url = PladformIE._extract_url(webpage)
  2704. if pladform_url:
  2705. return self.url_result(pladform_url)
  2706. # Look for Videomore embeds
  2707. videomore_url = VideomoreIE._extract_url(webpage)
  2708. if videomore_url:
  2709. return self.url_result(videomore_url)
  2710. # Look for Webcaster embeds
  2711. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2712. if webcaster_url:
  2713. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2714. # Look for Playwire embeds
  2715. mobj = re.search(
  2716. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2717. if mobj is not None:
  2718. return self.url_result(mobj.group('url'))
  2719. # Look for 5min embeds
  2720. mobj = re.search(
  2721. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2722. if mobj is not None:
  2723. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2724. # Look for Crooks and Liars embeds
  2725. mobj = re.search(
  2726. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2727. if mobj is not None:
  2728. return self.url_result(mobj.group('url'))
  2729. # Look for NBC Sports VPlayer embeds
  2730. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2731. if nbc_sports_url:
  2732. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2733. # Look for NBC News embeds
  2734. nbc_news_embed_url = re.search(
  2735. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2736. if nbc_news_embed_url:
  2737. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2738. # Look for Google Drive embeds
  2739. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2740. if google_drive_url:
  2741. return self.url_result(google_drive_url, 'GoogleDrive')
  2742. # Look for UDN embeds
  2743. mobj = re.search(
  2744. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2745. if mobj is not None:
  2746. return self.url_result(
  2747. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2748. # Look for Senate ISVP iframe
  2749. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2750. if senate_isvp_url:
  2751. return self.url_result(senate_isvp_url, 'SenateISVP')
  2752. # Look for OnionStudios embeds
  2753. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2754. if onionstudios_url:
  2755. return self.url_result(onionstudios_url)
  2756. # Look for ViewLift embeds
  2757. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2758. if viewlift_url:
  2759. return self.url_result(viewlift_url)
  2760. # Look for JWPlatform embeds
  2761. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2762. if jwplatform_urls:
  2763. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2764. # Look for Digiteka embeds
  2765. digiteka_url = DigitekaIE._extract_url(webpage)
  2766. if digiteka_url:
  2767. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2768. # Look for Arkena embeds
  2769. arkena_url = ArkenaIE._extract_url(webpage)
  2770. if arkena_url:
  2771. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2772. # Look for Piksel embeds
  2773. piksel_url = PikselIE._extract_url(webpage)
  2774. if piksel_url:
  2775. return self.url_result(piksel_url, PikselIE.ie_key())
  2776. # Look for Limelight embeds
  2777. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2778. if limelight_urls:
  2779. return self.playlist_result(
  2780. limelight_urls, video_id, video_title, video_description)
  2781. # Look for Anvato embeds
  2782. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2783. if anvato_urls:
  2784. return self.playlist_result(
  2785. anvato_urls, video_id, video_title, video_description)
  2786. # Look for AdobeTVVideo embeds
  2787. mobj = re.search(
  2788. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2789. webpage)
  2790. if mobj is not None:
  2791. return self.url_result(
  2792. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2793. 'AdobeTVVideo')
  2794. # Look for Vine embeds
  2795. mobj = re.search(
  2796. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2797. webpage)
  2798. if mobj is not None:
  2799. return self.url_result(
  2800. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2801. # Look for VODPlatform embeds
  2802. mobj = re.search(
  2803. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2804. webpage)
  2805. if mobj is not None:
  2806. return self.url_result(
  2807. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2808. # Look for Mangomolo embeds
  2809. mobj = re.search(
  2810. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
  2811. (?:
  2812. video\?.*?\bid=(?P<video_id>\d+)|
  2813. index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2814. ).+?)\1''', webpage)
  2815. if mobj is not None:
  2816. info = {
  2817. '_type': 'url_transparent',
  2818. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2819. 'title': video_title,
  2820. 'description': video_description,
  2821. 'thumbnail': video_thumbnail,
  2822. 'uploader': video_uploader,
  2823. }
  2824. video_id = mobj.group('video_id')
  2825. if video_id:
  2826. info.update({
  2827. 'ie_key': 'MangomoloVideo',
  2828. 'id': video_id,
  2829. })
  2830. else:
  2831. info.update({
  2832. 'ie_key': 'MangomoloLive',
  2833. 'id': mobj.group('channel_id'),
  2834. })
  2835. return info
  2836. # Look for Instagram embeds
  2837. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2838. if instagram_embed_url is not None:
  2839. return self.url_result(
  2840. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2841. # Look for LiveLeak embeds
  2842. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2843. if liveleak_urls:
  2844. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2845. # Look for 3Q SDN embeds
  2846. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2847. if threeqsdn_url:
  2848. return {
  2849. '_type': 'url_transparent',
  2850. 'ie_key': ThreeQSDNIE.ie_key(),
  2851. 'url': self._proto_relative_url(threeqsdn_url),
  2852. 'title': video_title,
  2853. 'description': video_description,
  2854. 'thumbnail': video_thumbnail,
  2855. 'uploader': video_uploader,
  2856. }
  2857. # Look for VBOX7 embeds
  2858. vbox7_url = Vbox7IE._extract_url(webpage)
  2859. if vbox7_url:
  2860. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2861. # Look for DBTV embeds
  2862. dbtv_urls = DBTVIE._extract_urls(webpage)
  2863. if dbtv_urls:
  2864. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2865. # Look for Videa embeds
  2866. videa_urls = VideaIE._extract_urls(webpage)
  2867. if videa_urls:
  2868. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2869. # Look for 20 minuten embeds
  2870. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2871. if twentymin_urls:
  2872. return self.playlist_from_matches(
  2873. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2874. # Look for Openload embeds
  2875. openload_urls = OpenloadIE._extract_urls(webpage)
  2876. if openload_urls:
  2877. return self.playlist_from_matches(
  2878. openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
  2879. # Look for VideoPress embeds
  2880. videopress_urls = VideoPressIE._extract_urls(webpage)
  2881. if videopress_urls:
  2882. return self.playlist_from_matches(
  2883. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2884. # Look for Rutube embeds
  2885. rutube_urls = RutubeIE._extract_urls(webpage)
  2886. if rutube_urls:
  2887. return self.playlist_from_matches(
  2888. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2889. # Look for WashingtonPost embeds
  2890. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2891. if wapo_urls:
  2892. return self.playlist_from_matches(
  2893. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2894. # Look for Mediaset embeds
  2895. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  2896. if mediaset_urls:
  2897. return self.playlist_from_matches(
  2898. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2899. # Look for JOJ.sk embeds
  2900. joj_urls = JojIE._extract_urls(webpage)
  2901. if joj_urls:
  2902. return self.playlist_from_matches(
  2903. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  2904. # Look for megaphone.fm embeds
  2905. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  2906. if mpfn_urls:
  2907. return self.playlist_from_matches(
  2908. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  2909. # Look for vzaar embeds
  2910. vzaar_urls = VzaarIE._extract_urls(webpage)
  2911. if vzaar_urls:
  2912. return self.playlist_from_matches(
  2913. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  2914. channel9_urls = Channel9IE._extract_urls(webpage)
  2915. if channel9_urls:
  2916. return self.playlist_from_matches(
  2917. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  2918. vshare_urls = VShareIE._extract_urls(webpage)
  2919. if vshare_urls:
  2920. return self.playlist_from_matches(
  2921. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  2922. # Look for Mediasite embeds
  2923. mediasite_urls = MediasiteIE._extract_urls(webpage)
  2924. if mediasite_urls:
  2925. entries = [
  2926. self.url_result(smuggle_url(
  2927. compat_urlparse.urljoin(url, mediasite_url),
  2928. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  2929. for mediasite_url in mediasite_urls]
  2930. return self.playlist_result(entries, video_id, video_title)
  2931. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  2932. if springboardplatform_urls:
  2933. return self.playlist_from_matches(
  2934. springboardplatform_urls, video_id, video_title,
  2935. ie=SpringboardPlatformIE.ie_key())
  2936. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  2937. if yapfiles_urls:
  2938. return self.playlist_from_matches(
  2939. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  2940. vice_urls = ViceIE._extract_urls(webpage)
  2941. if vice_urls:
  2942. return self.playlist_from_matches(
  2943. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  2944. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  2945. if xfileshare_urls:
  2946. return self.playlist_from_matches(
  2947. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  2948. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  2949. if cloudflarestream_urls:
  2950. return self.playlist_from_matches(
  2951. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  2952. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  2953. if peertube_urls:
  2954. return self.playlist_from_matches(
  2955. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  2956. teachable_url = TeachableIE._extract_url(webpage, url)
  2957. if teachable_url:
  2958. return self.url_result(teachable_url)
  2959. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  2960. if indavideo_urls:
  2961. return self.playlist_from_matches(
  2962. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  2963. apa_urls = APAIE._extract_urls(webpage)
  2964. if apa_urls:
  2965. return self.playlist_from_matches(
  2966. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  2967. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  2968. if foxnews_urls:
  2969. return self.playlist_from_matches(
  2970. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  2971. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  2972. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  2973. webpage)]
  2974. if sharevideos_urls:
  2975. return self.playlist_from_matches(
  2976. sharevideos_urls, video_id, video_title)
  2977. viqeo_urls = ViqeoIE._extract_urls(webpage)
  2978. if viqeo_urls:
  2979. return self.playlist_from_matches(
  2980. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  2981. expressen_urls = ExpressenIE._extract_urls(webpage)
  2982. if expressen_urls:
  2983. return self.playlist_from_matches(
  2984. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  2985. zype_urls = ZypeIE._extract_urls(webpage)
  2986. if zype_urls:
  2987. return self.playlist_from_matches(
  2988. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  2989. # Look for HTML5 media
  2990. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  2991. if entries:
  2992. if len(entries) == 1:
  2993. entries[0].update({
  2994. 'id': video_id,
  2995. 'title': video_title,
  2996. })
  2997. else:
  2998. for num, entry in enumerate(entries, start=1):
  2999. entry.update({
  3000. 'id': '%s-%s' % (video_id, num),
  3001. 'title': '%s (%d)' % (video_title, num),
  3002. })
  3003. for entry in entries:
  3004. self._sort_formats(entry['formats'])
  3005. return self.playlist_result(entries, video_id, video_title)
  3006. jwplayer_data = self._find_jwplayer_data(
  3007. webpage, video_id, transform_source=js_to_json)
  3008. if jwplayer_data:
  3009. try:
  3010. info = self._parse_jwplayer_data(
  3011. jwplayer_data, video_id, require_title=False, base_url=url)
  3012. return merge_dicts(info, info_dict)
  3013. except ExtractorError:
  3014. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3015. pass
  3016. # Video.js embed
  3017. mobj = re.search(
  3018. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3019. webpage)
  3020. if mobj is not None:
  3021. sources = self._parse_json(
  3022. mobj.group(1), video_id, transform_source=js_to_json,
  3023. fatal=False) or []
  3024. if not isinstance(sources, list):
  3025. sources = [sources]
  3026. formats = []
  3027. for source in sources:
  3028. src = source.get('src')
  3029. if not src or not isinstance(src, compat_str):
  3030. continue
  3031. src = compat_urlparse.urljoin(url, src)
  3032. src_type = source.get('type')
  3033. if isinstance(src_type, compat_str):
  3034. src_type = src_type.lower()
  3035. ext = determine_ext(src).lower()
  3036. if src_type == 'video/youtube':
  3037. return self.url_result(src, YoutubeIE.ie_key())
  3038. if src_type == 'application/dash+xml' or ext == 'mpd':
  3039. formats.extend(self._extract_mpd_formats(
  3040. src, video_id, mpd_id='dash', fatal=False))
  3041. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3042. formats.extend(self._extract_m3u8_formats(
  3043. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3044. m3u8_id='hls', fatal=False))
  3045. else:
  3046. formats.append({
  3047. 'url': src,
  3048. 'ext': (mimetype2ext(src_type) or
  3049. ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3050. })
  3051. if formats:
  3052. self._sort_formats(formats)
  3053. info_dict['formats'] = formats
  3054. return info_dict
  3055. # Looking for http://schema.org/VideoObject
  3056. json_ld = self._search_json_ld(
  3057. webpage, video_id, default={}, expected_type='VideoObject')
  3058. if json_ld.get('url'):
  3059. return merge_dicts(json_ld, info_dict)
  3060. def check_video(vurl):
  3061. if YoutubeIE.suitable(vurl):
  3062. return True
  3063. if RtmpIE.suitable(vurl):
  3064. return True
  3065. vpath = compat_urlparse.urlparse(vurl).path
  3066. vext = determine_ext(vpath)
  3067. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3068. def filter_video(urls):
  3069. return list(filter(check_video, urls))
  3070. # Start with something easy: JW Player in SWFObject
  3071. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3072. if not found:
  3073. # Look for gorilla-vid style embedding
  3074. found = filter_video(re.findall(r'''(?sx)
  3075. (?:
  3076. jw_plugins|
  3077. JWPlayerOptions|
  3078. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3079. )
  3080. .*?
  3081. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3082. if not found:
  3083. # Broaden the search a little bit
  3084. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3085. if not found:
  3086. # Broaden the findall a little bit: JWPlayer JS loader
  3087. found = filter_video(re.findall(
  3088. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3089. if not found:
  3090. # Flow player
  3091. found = filter_video(re.findall(r'''(?xs)
  3092. flowplayer\("[^"]+",\s*
  3093. \{[^}]+?\}\s*,
  3094. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3095. ["']?url["']?\s*:\s*["']([^"']+)["']
  3096. ''', webpage))
  3097. if not found:
  3098. # Cinerama player
  3099. found = re.findall(
  3100. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3101. if not found:
  3102. # Try to find twitter cards info
  3103. # twitter:player:stream should be checked before twitter:player since
  3104. # it is expected to contain a raw stream (see
  3105. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3106. found = filter_video(re.findall(
  3107. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3108. if not found:
  3109. # We look for Open Graph info:
  3110. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3111. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3112. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3113. if m_video_type is not None:
  3114. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3115. if not found:
  3116. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3117. found = re.search(
  3118. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3119. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3120. webpage)
  3121. if not found:
  3122. # Look also in Refresh HTTP header
  3123. refresh_header = head_response.headers.get('Refresh')
  3124. if refresh_header:
  3125. # In python 2 response HTTP headers are bytestrings
  3126. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3127. refresh_header = refresh_header.decode('iso-8859-1')
  3128. found = re.search(REDIRECT_REGEX, refresh_header)
  3129. if found:
  3130. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3131. if new_url != url:
  3132. self.report_following_redirect(new_url)
  3133. return {
  3134. '_type': 'url',
  3135. 'url': new_url,
  3136. }
  3137. else:
  3138. found = None
  3139. if not found:
  3140. # twitter:player is a https URL to iframe player that may or may not
  3141. # be supported by youtube-dl thus this is checked the very last (see
  3142. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3143. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3144. if embed_url and embed_url != url:
  3145. return self.url_result(embed_url)
  3146. if not found:
  3147. raise UnsupportedError(url)
  3148. entries = []
  3149. for video_url in orderedSet(found):
  3150. video_url = unescapeHTML(video_url)
  3151. video_url = video_url.replace('\\/', '/')
  3152. video_url = compat_urlparse.urljoin(url, video_url)
  3153. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3154. # Sometimes, jwplayer extraction will result in a YouTube URL
  3155. if YoutubeIE.suitable(video_url):
  3156. entries.append(self.url_result(video_url, 'Youtube'))
  3157. continue
  3158. # here's a fun little line of code for you:
  3159. video_id = os.path.splitext(video_id)[0]
  3160. entry_info_dict = {
  3161. 'id': video_id,
  3162. 'uploader': video_uploader,
  3163. 'title': video_title,
  3164. 'age_limit': age_limit,
  3165. }
  3166. if RtmpIE.suitable(video_url):
  3167. entry_info_dict.update({
  3168. '_type': 'url_transparent',
  3169. 'ie_key': RtmpIE.ie_key(),
  3170. 'url': video_url,
  3171. })
  3172. entries.append(entry_info_dict)
  3173. continue
  3174. ext = determine_ext(video_url)
  3175. if ext == 'smil':
  3176. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3177. elif ext == 'xspf':
  3178. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3179. elif ext == 'm3u8':
  3180. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3181. elif ext == 'mpd':
  3182. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3183. elif ext == 'f4m':
  3184. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3185. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3186. # Just matching .ism/manifest is not enough to be reliably sure
  3187. # whether it's actually an ISM manifest or some other streaming
  3188. # manifest since there are various streaming URL formats
  3189. # possible (see [1]) as well as some other shenanigans like
  3190. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3191. # so on.
  3192. # Thus the most reasonable way to solve this is to delegate
  3193. # to generic extractor in order to look into the contents of
  3194. # the manifest itself.
  3195. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3196. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3197. entry_info_dict = self.url_result(
  3198. smuggle_url(video_url, {'to_generic': True}),
  3199. GenericIE.ie_key())
  3200. else:
  3201. entry_info_dict['url'] = video_url
  3202. if entry_info_dict.get('formats'):
  3203. self._sort_formats(entry_info_dict['formats'])
  3204. entries.append(entry_info_dict)
  3205. if len(entries) == 1:
  3206. return entries[0]
  3207. else:
  3208. for num, e in enumerate(entries, start=1):
  3209. # 'url' results don't have a title
  3210. if e.get('title') is not None:
  3211. e['title'] = '%s (%d)' % (e['title'], num)
  3212. return {
  3213. '_type': 'playlist',
  3214. 'entries': entries,
  3215. }