generic.py 106 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656
  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_urllib_parse_unquote,
  11. compat_urlparse,
  12. compat_xml_parse_error,
  13. )
  14. from ..utils import (
  15. determine_ext,
  16. ExtractorError,
  17. float_or_none,
  18. HEADRequest,
  19. is_html,
  20. orderedSet,
  21. sanitized_Request,
  22. smuggle_url,
  23. unescapeHTML,
  24. unified_strdate,
  25. unsmuggle_url,
  26. UnsupportedError,
  27. xpath_text,
  28. )
  29. from .commonprotocols import RtmpIE
  30. from .brightcove import (
  31. BrightcoveLegacyIE,
  32. BrightcoveNewIE,
  33. )
  34. from .nbc import NBCSportsVPlayerIE
  35. from .ooyala import OoyalaIE
  36. from .rutv import RUTVIE
  37. from .tvc import TVCIE
  38. from .sportbox import SportBoxEmbedIE
  39. from .smotri import SmotriIE
  40. from .myvi import MyviIE
  41. from .condenast import CondeNastIE
  42. from .udn import UDNEmbedIE
  43. from .senateisvp import SenateISVPIE
  44. from .svt import SVTIE
  45. from .pornhub import PornHubIE
  46. from .xhamster import XHamsterEmbedIE
  47. from .tnaflix import TNAFlixNetworkEmbedIE
  48. from .drtuber import DrTuberIE
  49. from .redtube import RedTubeIE
  50. from .vimeo import VimeoIE
  51. from .dailymotion import (
  52. DailymotionIE,
  53. DailymotionCloudIE,
  54. )
  55. from .onionstudios import OnionStudiosIE
  56. from .viewlift import ViewLiftEmbedIE
  57. from .mtv import MTVServicesEmbeddedIE
  58. from .pladform import PladformIE
  59. from .videomore import VideomoreIE
  60. from .webcaster import WebcasterFeedIE
  61. from .googledrive import GoogleDriveIE
  62. from .jwplatform import JWPlatformIE
  63. from .digiteka import DigitekaIE
  64. from .arkena import ArkenaIE
  65. from .instagram import InstagramIE
  66. from .liveleak import LiveLeakIE
  67. from .threeqsdn import ThreeQSDNIE
  68. from .theplatform import ThePlatformIE
  69. from .vessel import VesselIE
  70. from .kaltura import KalturaIE
  71. from .eagleplatform import EaglePlatformIE
  72. from .facebook import FacebookIE
  73. from .soundcloud import SoundcloudIE
  74. from .tunein import TuneInBaseIE
  75. from .vbox7 import Vbox7IE
  76. from .dbtv import DBTVIE
  77. from .piksel import PikselIE
  78. from .videa import VideaIE
  79. from .twentymin import TwentyMinutenIE
  80. from .ustream import UstreamIE
  81. from .openload import OpenloadIE
  82. from .videopress import VideoPressIE
  83. class GenericIE(InfoExtractor):
  84. IE_DESC = 'Generic downloader that works on some sites'
  85. _VALID_URL = r'.*'
  86. IE_NAME = 'generic'
  87. _TESTS = [
  88. # Direct link to a video
  89. {
  90. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  91. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  92. 'info_dict': {
  93. 'id': 'trailer',
  94. 'ext': 'mp4',
  95. 'title': 'trailer',
  96. 'upload_date': '20100513',
  97. }
  98. },
  99. # Direct link to media delivered compressed (until Accept-Encoding is *)
  100. {
  101. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  102. 'md5': '128c42e68b13950268b648275386fc74',
  103. 'info_dict': {
  104. 'id': 'FictionJunction-Parallel_Hearts',
  105. 'ext': 'flac',
  106. 'title': 'FictionJunction-Parallel_Hearts',
  107. 'upload_date': '20140522',
  108. },
  109. 'expected_warnings': [
  110. 'URL could be a direct video link, returning it as such.'
  111. ],
  112. 'skip': 'URL invalid',
  113. },
  114. # Direct download with broken HEAD
  115. {
  116. 'url': 'http://ai-radio.org:8000/radio.opus',
  117. 'info_dict': {
  118. 'id': 'radio',
  119. 'ext': 'opus',
  120. 'title': 'radio',
  121. },
  122. 'params': {
  123. 'skip_download': True, # infinite live stream
  124. },
  125. 'expected_warnings': [
  126. r'501.*Not Implemented',
  127. r'400.*Bad Request',
  128. ],
  129. },
  130. # Direct link with incorrect MIME type
  131. {
  132. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  133. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  134. 'info_dict': {
  135. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  136. 'id': '5_Lennart_Poettering_-_Systemd',
  137. 'ext': 'webm',
  138. 'title': '5_Lennart_Poettering_-_Systemd',
  139. 'upload_date': '20141120',
  140. },
  141. 'expected_warnings': [
  142. 'URL could be a direct video link, returning it as such.'
  143. ]
  144. },
  145. # RSS feed
  146. {
  147. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  148. 'info_dict': {
  149. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  150. 'title': 'Zero Punctuation',
  151. 'description': 're:.*groundbreaking video review series.*'
  152. },
  153. 'playlist_mincount': 11,
  154. },
  155. # RSS feed with enclosure
  156. {
  157. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  158. 'info_dict': {
  159. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  160. 'ext': 'm4v',
  161. 'upload_date': '20150228',
  162. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  163. }
  164. },
  165. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  166. {
  167. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  168. 'info_dict': {
  169. 'id': 'smil',
  170. 'ext': 'mp4',
  171. 'title': 'Automatics, robotics and biocybernetics',
  172. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  173. 'upload_date': '20130627',
  174. 'formats': 'mincount:16',
  175. 'subtitles': 'mincount:1',
  176. },
  177. 'params': {
  178. 'force_generic_extractor': True,
  179. 'skip_download': True,
  180. },
  181. },
  182. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  183. {
  184. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  185. 'info_dict': {
  186. 'id': 'hds',
  187. 'ext': 'flv',
  188. 'title': 'hds',
  189. 'formats': 'mincount:1',
  190. },
  191. 'params': {
  192. 'skip_download': True,
  193. },
  194. },
  195. # SMIL from https://www.restudy.dk/video/play/id/1637
  196. {
  197. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  198. 'info_dict': {
  199. 'id': 'video_1637',
  200. 'ext': 'flv',
  201. 'title': 'video_1637',
  202. 'formats': 'mincount:3',
  203. },
  204. 'params': {
  205. 'skip_download': True,
  206. },
  207. },
  208. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  209. {
  210. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  211. 'info_dict': {
  212. 'id': 'smil-service',
  213. 'ext': 'flv',
  214. 'title': 'smil-service',
  215. 'formats': 'mincount:1',
  216. },
  217. 'params': {
  218. 'skip_download': True,
  219. },
  220. },
  221. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  222. {
  223. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  224. 'info_dict': {
  225. 'id': '4719370',
  226. 'ext': 'mp4',
  227. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  228. 'formats': 'mincount:3',
  229. },
  230. 'params': {
  231. 'skip_download': True,
  232. },
  233. },
  234. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  235. {
  236. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  237. 'info_dict': {
  238. 'id': 'mZlp2ctYIUEB',
  239. 'ext': 'mp4',
  240. 'title': 'Tikibad ontruimd wegens brand',
  241. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  242. 'thumbnail': r're:^https?://.*\.jpg$',
  243. 'duration': 33,
  244. },
  245. 'params': {
  246. 'skip_download': True,
  247. },
  248. },
  249. # MPD from http://dash-mse-test.appspot.com/media.html
  250. {
  251. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  252. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  253. 'info_dict': {
  254. 'id': 'car-20120827-manifest',
  255. 'ext': 'mp4',
  256. 'title': 'car-20120827-manifest',
  257. 'formats': 'mincount:9',
  258. 'upload_date': '20130904',
  259. },
  260. 'params': {
  261. 'format': 'bestvideo',
  262. },
  263. },
  264. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  265. {
  266. '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',
  267. 'info_dict': {
  268. 'id': 'content',
  269. 'ext': 'mp4',
  270. 'title': 'content',
  271. 'formats': 'mincount:8',
  272. },
  273. 'params': {
  274. # m3u8 downloads
  275. 'skip_download': True,
  276. },
  277. 'skip': 'video gone',
  278. },
  279. # m3u8 served with Content-Type: text/plain
  280. {
  281. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  282. 'info_dict': {
  283. 'id': 'index',
  284. 'ext': 'mp4',
  285. 'title': 'index',
  286. 'upload_date': '20140720',
  287. 'formats': 'mincount:11',
  288. },
  289. 'params': {
  290. # m3u8 downloads
  291. 'skip_download': True,
  292. },
  293. 'skip': 'video gone',
  294. },
  295. # google redirect
  296. {
  297. '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',
  298. 'info_dict': {
  299. 'id': 'cmQHVoWB5FY',
  300. 'ext': 'mp4',
  301. 'upload_date': '20130224',
  302. 'uploader_id': 'TheVerge',
  303. 'description': r're:^Chris Ziegler takes a look at the\.*',
  304. 'uploader': 'The Verge',
  305. 'title': 'First Firefox OS phones side-by-side',
  306. },
  307. 'params': {
  308. 'skip_download': False,
  309. }
  310. },
  311. {
  312. # redirect in Refresh HTTP header
  313. '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',
  314. 'info_dict': {
  315. 'id': 'pO8h3EaFRdo',
  316. 'ext': 'mp4',
  317. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  318. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  319. 'upload_date': '20150917',
  320. 'uploader_id': 'brtvofficial',
  321. 'uploader': 'Boiler Room',
  322. },
  323. 'params': {
  324. 'skip_download': False,
  325. },
  326. },
  327. {
  328. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  329. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  330. 'info_dict': {
  331. 'id': '13601338388002',
  332. 'ext': 'mp4',
  333. 'uploader': 'www.hodiho.fr',
  334. 'title': 'R\u00e9gis plante sa Jeep',
  335. }
  336. },
  337. # bandcamp page with custom domain
  338. {
  339. 'add_ie': ['Bandcamp'],
  340. 'url': 'http://bronyrock.com/track/the-pony-mash',
  341. 'info_dict': {
  342. 'id': '3235767654',
  343. 'ext': 'mp3',
  344. 'title': 'The Pony Mash',
  345. 'uploader': 'M_Pallante',
  346. },
  347. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  348. },
  349. {
  350. # embedded brightcove video
  351. # it also tests brightcove videos that need to set the 'Referer'
  352. # in the http requests
  353. 'add_ie': ['BrightcoveLegacy'],
  354. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  355. 'info_dict': {
  356. 'id': '2765128793001',
  357. 'ext': 'mp4',
  358. 'title': 'Le cours de bourse : l’analyse technique',
  359. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  360. 'uploader': 'BFM BUSINESS',
  361. },
  362. 'params': {
  363. 'skip_download': True,
  364. },
  365. },
  366. {
  367. # embedded with itemprop embedURL and video id spelled as `idVideo`
  368. 'add_id': ['BrightcoveLegacy'],
  369. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  370. 'info_dict': {
  371. 'id': '5255628253001',
  372. 'ext': 'mp4',
  373. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  374. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  375. 'uploader': 'BFM BUSINESS',
  376. 'uploader_id': '876450612001',
  377. 'timestamp': 1482255315,
  378. 'upload_date': '20161220',
  379. },
  380. 'params': {
  381. 'skip_download': True,
  382. },
  383. },
  384. {
  385. # https://github.com/rg3/youtube-dl/issues/2253
  386. 'url': 'http://bcove.me/i6nfkrc3',
  387. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  388. 'info_dict': {
  389. 'id': '3101154703001',
  390. 'ext': 'mp4',
  391. 'title': 'Still no power',
  392. 'uploader': 'thestar.com',
  393. '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.',
  394. },
  395. 'add_ie': ['BrightcoveLegacy'],
  396. 'skip': 'video gone',
  397. },
  398. {
  399. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  400. 'md5': 'fb973ecf6e4a78a67453647444222983',
  401. 'info_dict': {
  402. 'id': '3414141473001',
  403. 'ext': 'mp4',
  404. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  405. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  406. 'uploader': 'Championat',
  407. },
  408. },
  409. {
  410. # https://github.com/rg3/youtube-dl/issues/3541
  411. 'add_ie': ['BrightcoveLegacy'],
  412. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  413. 'info_dict': {
  414. 'id': '3866516442001',
  415. 'ext': 'mp4',
  416. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  417. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  418. 'uploader': 'SBS Broadcasting',
  419. },
  420. 'skip': 'Restricted to Netherlands',
  421. 'params': {
  422. 'skip_download': True, # m3u8 download
  423. },
  424. },
  425. {
  426. # Brightcove with alternative playerID key
  427. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  428. 'info_dict': {
  429. 'id': 'nmeth.2062_SV1',
  430. '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',
  431. },
  432. 'playlist': [{
  433. 'info_dict': {
  434. 'id': '2228375078001',
  435. 'ext': 'mp4',
  436. 'title': 'nmeth.2062-sv1',
  437. 'description': 'nmeth.2062-sv1',
  438. 'timestamp': 1363357591,
  439. 'upload_date': '20130315',
  440. 'uploader': 'Nature Publishing Group',
  441. 'uploader_id': '1964492299001',
  442. },
  443. }],
  444. },
  445. # ooyala video
  446. {
  447. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  448. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  449. 'info_dict': {
  450. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  451. 'ext': 'mp4',
  452. 'title': '2cc213299525360.mov', # that's what we get
  453. 'duration': 238.231,
  454. },
  455. 'add_ie': ['Ooyala'],
  456. },
  457. {
  458. # ooyala video embedded with http://player.ooyala.com/iframe.js
  459. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  460. 'info_dict': {
  461. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  462. 'ext': 'mp4',
  463. 'title': '"Steve Jobs: Man in the Machine" trailer',
  464. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  465. 'duration': 135.427,
  466. },
  467. 'params': {
  468. 'skip_download': True,
  469. },
  470. 'skip': 'movie expired',
  471. },
  472. # embed.ly video
  473. {
  474. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  475. 'info_dict': {
  476. 'id': '9ODmcdjQcHQ',
  477. 'ext': 'mp4',
  478. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  479. 'upload_date': '20140225',
  480. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  481. 'uploader': 'Tested',
  482. 'uploader_id': 'testedcom',
  483. },
  484. # No need to test YoutubeIE here
  485. 'params': {
  486. 'skip_download': True,
  487. },
  488. },
  489. # funnyordie embed
  490. {
  491. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  492. 'info_dict': {
  493. 'id': '18e820ec3f',
  494. 'ext': 'mp4',
  495. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  496. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  497. },
  498. # HEAD requests lead to endless 301, while GET is OK
  499. 'expected_warnings': ['301'],
  500. },
  501. # RUTV embed
  502. {
  503. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  504. 'info_dict': {
  505. 'id': '776940',
  506. 'ext': 'mp4',
  507. 'title': 'Охотское море стало целиком российским',
  508. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  509. },
  510. 'params': {
  511. # m3u8 download
  512. 'skip_download': True,
  513. },
  514. },
  515. # TVC embed
  516. {
  517. '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/',
  518. 'info_dict': {
  519. 'id': '55304',
  520. 'ext': 'mp4',
  521. 'title': 'Дошкольное воспитание',
  522. },
  523. },
  524. # SportBox embed
  525. {
  526. 'url': 'http://www.vestifinance.ru/articles/25753',
  527. 'info_dict': {
  528. 'id': '25753',
  529. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  530. },
  531. 'playlist': [{
  532. 'info_dict': {
  533. 'id': '370908',
  534. 'title': 'Госзаказ. День 3',
  535. 'ext': 'mp4',
  536. }
  537. }, {
  538. 'info_dict': {
  539. 'id': '370905',
  540. 'title': 'Госзаказ. День 2',
  541. 'ext': 'mp4',
  542. }
  543. }, {
  544. 'info_dict': {
  545. 'id': '370902',
  546. 'title': 'Госзаказ. День 1',
  547. 'ext': 'mp4',
  548. }
  549. }],
  550. 'params': {
  551. # m3u8 download
  552. 'skip_download': True,
  553. },
  554. },
  555. # Myvi.ru embed
  556. {
  557. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  558. 'info_dict': {
  559. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  560. 'ext': 'mp4',
  561. 'title': 'Ужастики, русский трейлер (2015)',
  562. 'thumbnail': r're:^https?://.*\.jpg$',
  563. 'duration': 153,
  564. }
  565. },
  566. # XHamster embed
  567. {
  568. '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',
  569. 'info_dict': {
  570. 'id': 'showthread',
  571. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  572. },
  573. 'playlist_mincount': 7,
  574. # This forum does not allow <iframe> syntaxes anymore
  575. # Now HTML tags are displayed as-is
  576. 'skip': 'No videos on this page',
  577. },
  578. # Embedded TED video
  579. {
  580. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  581. 'md5': '65fdff94098e4a607385a60c5177c638',
  582. 'info_dict': {
  583. 'id': '1969',
  584. 'ext': 'mp4',
  585. 'title': 'Hidden miracles of the natural world',
  586. 'uploader': 'Louie Schwartzberg',
  587. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  588. }
  589. },
  590. # nowvideo embed hidden behind percent encoding
  591. {
  592. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  593. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  594. 'info_dict': {
  595. 'id': '06e53103ca9aa',
  596. 'ext': 'flv',
  597. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  598. 'description': 'No description',
  599. },
  600. },
  601. # arte embed
  602. {
  603. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  604. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  605. 'info_dict': {
  606. 'id': '048195-004_PLUS7-F',
  607. 'ext': 'flv',
  608. 'title': 'X:enius',
  609. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  610. 'upload_date': '20140320',
  611. },
  612. 'params': {
  613. 'skip_download': 'Requires rtmpdump'
  614. },
  615. 'skip': 'video gone',
  616. },
  617. # francetv embed
  618. {
  619. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  620. 'info_dict': {
  621. 'id': 'EV_30231',
  622. 'ext': 'mp4',
  623. 'title': 'Alcaline, le concert avec Calogero',
  624. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  625. 'upload_date': '20150226',
  626. 'timestamp': 1424989860,
  627. 'duration': 5400,
  628. },
  629. 'params': {
  630. # m3u8 downloads
  631. 'skip_download': True,
  632. },
  633. 'expected_warnings': [
  634. 'Forbidden'
  635. ]
  636. },
  637. # Condé Nast embed
  638. {
  639. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  640. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  641. 'info_dict': {
  642. 'id': '53501be369702d3275860000',
  643. 'ext': 'mp4',
  644. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  645. }
  646. },
  647. # Dailymotion embed
  648. {
  649. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  650. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  651. 'info_dict': {
  652. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  653. 'ext': 'mp4',
  654. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  655. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  656. 'uploader': 'Spi0n',
  657. 'uploader_id': 'xgditw',
  658. 'upload_date': '20140425',
  659. 'timestamp': 1398441542,
  660. },
  661. 'add_ie': ['Dailymotion'],
  662. },
  663. # YouTube embed
  664. {
  665. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  666. 'info_dict': {
  667. 'id': 'FXRb4ykk4S0',
  668. 'ext': 'mp4',
  669. 'title': 'The NBL Auction 2014',
  670. 'uploader': 'BADMINTON England',
  671. 'uploader_id': 'BADMINTONEvents',
  672. 'upload_date': '20140603',
  673. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  674. },
  675. 'add_ie': ['Youtube'],
  676. 'params': {
  677. 'skip_download': True,
  678. }
  679. },
  680. # MTVSercices embed
  681. {
  682. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  683. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  684. 'info_dict': {
  685. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  686. 'ext': 'mp4',
  687. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  688. 'description': 'Two valets share their love for movie star Liam Neesons.',
  689. 'timestamp': 1349922600,
  690. 'upload_date': '20121011',
  691. },
  692. },
  693. # YouTube embed via <data-embed-url="">
  694. {
  695. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  696. 'info_dict': {
  697. 'id': '4vAffPZIT44',
  698. 'ext': 'mp4',
  699. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  700. 'uploader': 'Gameloft',
  701. 'uploader_id': 'gameloft',
  702. 'upload_date': '20140828',
  703. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  704. },
  705. 'params': {
  706. 'skip_download': True,
  707. }
  708. },
  709. # Camtasia studio
  710. {
  711. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  712. 'playlist': [{
  713. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  714. 'info_dict': {
  715. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  716. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  717. 'ext': 'flv',
  718. 'duration': 2235.90,
  719. }
  720. }, {
  721. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  722. 'info_dict': {
  723. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  724. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  725. 'ext': 'flv',
  726. 'duration': 2235.93,
  727. }
  728. }],
  729. 'info_dict': {
  730. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  731. }
  732. },
  733. # Flowplayer
  734. {
  735. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  736. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  737. 'info_dict': {
  738. 'id': '5123ea6d5e5a7',
  739. 'ext': 'mp4',
  740. 'age_limit': 18,
  741. 'uploader': 'www.handjobhub.com',
  742. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  743. }
  744. },
  745. # Multiple brightcove videos
  746. # https://github.com/rg3/youtube-dl/issues/2283
  747. {
  748. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  749. 'info_dict': {
  750. 'id': 'always-never',
  751. 'title': 'Always / Never - The New Yorker',
  752. },
  753. 'playlist_count': 3,
  754. 'params': {
  755. 'extract_flat': False,
  756. 'skip_download': True,
  757. }
  758. },
  759. # MLB embed
  760. {
  761. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  762. 'md5': '96f09a37e44da40dd083e12d9a683327',
  763. 'info_dict': {
  764. 'id': '33322633',
  765. 'ext': 'mp4',
  766. 'title': 'Ump changes call to ball',
  767. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  768. 'duration': 48,
  769. 'timestamp': 1401537900,
  770. 'upload_date': '20140531',
  771. 'thumbnail': r're:^https?://.*\.jpg$',
  772. },
  773. },
  774. # Wistia embed
  775. {
  776. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  777. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  778. 'info_dict': {
  779. 'id': '6e2wtrbdaf',
  780. 'ext': 'mov',
  781. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  782. 'description': 'a Paywall Videos video from Remilon',
  783. 'duration': 644.072,
  784. 'uploader': 'study.com',
  785. 'timestamp': 1459678540,
  786. 'upload_date': '20160403',
  787. 'filesize': 24687186,
  788. },
  789. },
  790. {
  791. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  792. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  793. 'info_dict': {
  794. 'id': 'uxjb0lwrcz',
  795. 'ext': 'mp4',
  796. 'title': 'Conversation about Hexagonal Rails Part 1',
  797. 'description': 'a Martin Fowler video from ThoughtWorks',
  798. 'duration': 1715.0,
  799. 'uploader': 'thoughtworks.wistia.com',
  800. 'timestamp': 1401832161,
  801. 'upload_date': '20140603',
  802. },
  803. },
  804. # Wistia standard embed (async)
  805. {
  806. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  807. 'info_dict': {
  808. 'id': '807fafadvk',
  809. 'ext': 'mp4',
  810. 'title': 'Drip Brennan Dunn Workshop',
  811. 'description': 'a JV Webinars video from getdrip-1',
  812. 'duration': 4986.95,
  813. 'timestamp': 1463607249,
  814. 'upload_date': '20160518',
  815. },
  816. 'params': {
  817. 'skip_download': True,
  818. }
  819. },
  820. # Soundcloud embed
  821. {
  822. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  823. 'info_dict': {
  824. 'id': '174391317',
  825. 'ext': 'mp3',
  826. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  827. 'uploader': 'Sophos Security',
  828. 'title': 'Chet Chat 171 - Oct 29, 2014',
  829. 'upload_date': '20141029',
  830. }
  831. },
  832. # Soundcloud multiple embeds
  833. {
  834. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  835. 'info_dict': {
  836. 'id': '52809',
  837. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  838. },
  839. 'playlist_mincount': 7,
  840. },
  841. # TuneIn station embed
  842. {
  843. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  844. 'info_dict': {
  845. 'id': '204146',
  846. 'ext': 'mp3',
  847. 'title': 'CNRV',
  848. 'location': 'Paris, France',
  849. 'is_live': True,
  850. },
  851. 'params': {
  852. # Live stream
  853. 'skip_download': True,
  854. },
  855. },
  856. # Livestream embed
  857. {
  858. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  859. 'info_dict': {
  860. 'id': '67864563',
  861. 'ext': 'flv',
  862. 'upload_date': '20141112',
  863. 'title': 'Rosetta #CometLanding webcast HL 10',
  864. }
  865. },
  866. # Another Livestream embed, without 'new.' in URL
  867. {
  868. 'url': 'https://www.freespeech.org/',
  869. 'info_dict': {
  870. 'id': '123537347',
  871. 'ext': 'mp4',
  872. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  873. },
  874. 'params': {
  875. # Live stream
  876. 'skip_download': True,
  877. },
  878. },
  879. # LazyYT
  880. {
  881. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  882. 'info_dict': {
  883. 'id': '1986',
  884. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  885. },
  886. 'playlist_mincount': 2,
  887. },
  888. # Cinchcast embed
  889. {
  890. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  891. 'info_dict': {
  892. 'id': '7141703',
  893. 'ext': 'mp3',
  894. 'upload_date': '20141126',
  895. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  896. }
  897. },
  898. # Cinerama player
  899. {
  900. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  901. 'info_dict': {
  902. 'id': '730m_DandD_1901_512k',
  903. 'ext': 'mp4',
  904. 'uploader': 'www.abc.net.au',
  905. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  906. }
  907. },
  908. # embedded viddler video
  909. {
  910. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  911. 'info_dict': {
  912. 'id': '4d03aad9',
  913. 'ext': 'mp4',
  914. 'uploader': 'deadspin',
  915. 'title': 'WALL-TO-GORTAT',
  916. 'timestamp': 1422285291,
  917. 'upload_date': '20150126',
  918. },
  919. 'add_ie': ['Viddler'],
  920. },
  921. # Libsyn embed
  922. {
  923. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  924. 'info_dict': {
  925. 'id': '3377616',
  926. 'ext': 'mp3',
  927. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  928. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  929. 'upload_date': '20150220',
  930. },
  931. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  932. },
  933. # jwplayer YouTube
  934. {
  935. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  936. 'info_dict': {
  937. 'id': 'Mrj4DVp2zeA',
  938. 'ext': 'mp4',
  939. 'upload_date': '20150212',
  940. 'uploader': 'The National Archives UK',
  941. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  942. 'uploader_id': 'NationalArchives08',
  943. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  944. },
  945. },
  946. # jwplayer rtmp
  947. {
  948. 'url': 'http://www.suffolk.edu/sjc/',
  949. 'info_dict': {
  950. 'id': 'sjclive',
  951. 'ext': 'flv',
  952. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  953. 'uploader': 'www.suffolk.edu',
  954. },
  955. 'params': {
  956. 'skip_download': True,
  957. }
  958. },
  959. # rtl.nl embed
  960. {
  961. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  962. 'playlist_mincount': 5,
  963. 'info_dict': {
  964. 'id': 'aanslagen-kopenhagen',
  965. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  966. }
  967. },
  968. # Zapiks embed
  969. {
  970. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  971. 'info_dict': {
  972. 'id': '118046',
  973. 'ext': 'mp4',
  974. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  975. }
  976. },
  977. # Kaltura embed (different embed code)
  978. {
  979. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  980. 'info_dict': {
  981. 'id': '1_a52wc67y',
  982. 'ext': 'flv',
  983. 'upload_date': '20150127',
  984. 'uploader_id': 'PremierMedia',
  985. 'timestamp': int,
  986. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  987. },
  988. },
  989. # Kaltura embed with single quotes
  990. {
  991. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  992. 'info_dict': {
  993. 'id': '0_izeg5utt',
  994. 'ext': 'mp4',
  995. 'title': '35871',
  996. 'timestamp': 1355743100,
  997. 'upload_date': '20121217',
  998. 'uploader_id': 'batchUser',
  999. },
  1000. 'add_ie': ['Kaltura'],
  1001. },
  1002. {
  1003. # Kaltura embedded via quoted entry_id
  1004. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1005. 'info_dict': {
  1006. 'id': '0_utuok90b',
  1007. 'ext': 'mp4',
  1008. 'title': '06_matthew_brender_raj_dutt',
  1009. 'timestamp': 1466638791,
  1010. 'upload_date': '20160622',
  1011. },
  1012. 'add_ie': ['Kaltura'],
  1013. 'expected_warnings': [
  1014. 'Could not send HEAD request'
  1015. ],
  1016. 'params': {
  1017. 'skip_download': True,
  1018. }
  1019. },
  1020. {
  1021. # Kaltura embedded, some fileExt broken (#11480)
  1022. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1023. 'info_dict': {
  1024. 'id': '1_sgtvehim',
  1025. 'ext': 'mp4',
  1026. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1027. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1028. 'timestamp': 1321158993,
  1029. 'upload_date': '20111113',
  1030. 'uploader_id': 'kps1',
  1031. },
  1032. 'add_ie': ['Kaltura'],
  1033. },
  1034. # Eagle.Platform embed (generic URL)
  1035. {
  1036. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  1037. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1038. 'info_dict': {
  1039. 'id': '227304',
  1040. 'ext': 'mp4',
  1041. 'title': 'Навальный вышел на свободу',
  1042. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  1043. 'thumbnail': r're:^https?://.*\.jpg$',
  1044. 'duration': 87,
  1045. 'view_count': int,
  1046. 'age_limit': 0,
  1047. },
  1048. },
  1049. # ClipYou (Eagle.Platform) embed (custom URL)
  1050. {
  1051. 'url': 'http://muz-tv.ru/play/7129/',
  1052. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1053. 'info_dict': {
  1054. 'id': '12820',
  1055. 'ext': 'mp4',
  1056. 'title': "'O Sole Mio",
  1057. 'thumbnail': r're:^https?://.*\.jpg$',
  1058. 'duration': 216,
  1059. 'view_count': int,
  1060. },
  1061. },
  1062. # Pladform embed
  1063. {
  1064. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1065. 'info_dict': {
  1066. 'id': '100183293',
  1067. 'ext': 'mp4',
  1068. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1069. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1070. 'thumbnail': r're:^https?://.*\.jpg$',
  1071. 'duration': 694,
  1072. 'age_limit': 0,
  1073. },
  1074. },
  1075. # Playwire embed
  1076. {
  1077. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1078. 'info_dict': {
  1079. 'id': '3519514',
  1080. 'ext': 'mp4',
  1081. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1082. 'thumbnail': r're:^https?://.*\.png$',
  1083. 'duration': 45.115,
  1084. },
  1085. },
  1086. # 5min embed
  1087. {
  1088. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1089. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1090. 'info_dict': {
  1091. 'id': '518726732',
  1092. 'ext': 'mp4',
  1093. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1094. },
  1095. },
  1096. # SVT embed
  1097. {
  1098. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  1099. 'info_dict': {
  1100. 'id': '2900353',
  1101. 'ext': 'flv',
  1102. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  1103. 'duration': 27,
  1104. 'age_limit': 0,
  1105. },
  1106. },
  1107. # Crooks and Liars embed
  1108. {
  1109. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1110. 'info_dict': {
  1111. 'id': '8RUoRhRi',
  1112. 'ext': 'mp4',
  1113. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1114. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1115. 'timestamp': 1428207000,
  1116. 'upload_date': '20150405',
  1117. 'uploader': 'Heather',
  1118. },
  1119. },
  1120. # Crooks and Liars external embed
  1121. {
  1122. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1123. 'info_dict': {
  1124. 'id': 'MTE3MjUtMzQ2MzA',
  1125. 'ext': 'mp4',
  1126. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1127. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1128. 'timestamp': 1265032391,
  1129. 'upload_date': '20100201',
  1130. 'uploader': 'Heather',
  1131. },
  1132. },
  1133. # NBC Sports vplayer embed
  1134. {
  1135. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1136. 'info_dict': {
  1137. 'id': 'ln7x1qSThw4k',
  1138. 'ext': 'flv',
  1139. 'title': "PFT Live: New leader in the 'new-look' defense",
  1140. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1141. 'uploader': 'NBCU-SPORTS',
  1142. 'upload_date': '20140107',
  1143. 'timestamp': 1389118457,
  1144. },
  1145. },
  1146. # NBC News embed
  1147. {
  1148. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1149. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1150. 'info_dict': {
  1151. 'id': '701714499682',
  1152. 'ext': 'mp4',
  1153. 'title': 'PREVIEW: On Assignment: David Letterman',
  1154. '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.',
  1155. },
  1156. },
  1157. # UDN embed
  1158. {
  1159. 'url': 'https://video.udn.com/news/300346',
  1160. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1161. 'info_dict': {
  1162. 'id': '300346',
  1163. 'ext': 'mp4',
  1164. 'title': '中一中男師變性 全校師生力挺',
  1165. 'thumbnail': r're:^https?://.*\.jpg$',
  1166. },
  1167. 'params': {
  1168. # m3u8 download
  1169. 'skip_download': True,
  1170. },
  1171. },
  1172. # Ooyala embed
  1173. {
  1174. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1175. 'info_dict': {
  1176. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1177. 'ext': 'mp4',
  1178. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  1179. 'title': 'This is what separates the Excel masters from the wannabes',
  1180. 'duration': 191.933,
  1181. },
  1182. 'params': {
  1183. # m3u8 downloads
  1184. 'skip_download': True,
  1185. }
  1186. },
  1187. # Brightcove URL in single quotes
  1188. {
  1189. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1190. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1191. 'info_dict': {
  1192. 'id': '4255764656001',
  1193. 'ext': 'mp4',
  1194. 'title': 'SN Presents: Russell Martin, World Citizen',
  1195. 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
  1196. 'uploader': 'Rogers Sportsnet',
  1197. 'uploader_id': '1704050871',
  1198. 'upload_date': '20150525',
  1199. 'timestamp': 1432570283,
  1200. },
  1201. },
  1202. # Dailymotion Cloud video
  1203. {
  1204. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1205. 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
  1206. 'info_dict': {
  1207. 'id': 'x2uy8t3',
  1208. 'ext': 'mp4',
  1209. 'title': 'Sauvons les abeilles ! - Le débat',
  1210. 'description': 'md5:d9082128b1c5277987825d684939ca26',
  1211. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1212. 'timestamp': 1434970506,
  1213. 'upload_date': '20150622',
  1214. 'uploader': 'Public Sénat',
  1215. 'uploader_id': 'xa9gza',
  1216. }
  1217. },
  1218. # OnionStudios embed
  1219. {
  1220. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1221. 'info_dict': {
  1222. 'id': '2855',
  1223. 'ext': 'mp4',
  1224. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1225. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1226. 'uploader': 'ClickHole',
  1227. 'uploader_id': 'clickhole',
  1228. }
  1229. },
  1230. # SnagFilms embed
  1231. {
  1232. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1233. 'info_dict': {
  1234. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1235. 'ext': 'mp4',
  1236. 'title': '#whilewewatch',
  1237. }
  1238. },
  1239. # AdobeTVVideo embed
  1240. {
  1241. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1242. 'md5': '43662b577c018ad707a63766462b1e87',
  1243. 'info_dict': {
  1244. 'id': '2456',
  1245. 'ext': 'mp4',
  1246. 'title': 'New experience with Acrobat DC',
  1247. 'description': 'New experience with Acrobat DC',
  1248. 'duration': 248.667,
  1249. },
  1250. },
  1251. # BrightcoveInPageEmbed embed
  1252. {
  1253. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1254. 'info_dict': {
  1255. 'id': '4238694884001',
  1256. 'ext': 'flv',
  1257. 'title': 'Tabletop: Dread, Last Thoughts',
  1258. 'description': 'Tabletop: Dread, Last Thoughts',
  1259. 'duration': 51690,
  1260. },
  1261. },
  1262. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1263. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1264. {
  1265. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1266. 'info_dict': {
  1267. 'id': '4785848093001',
  1268. 'ext': 'mp4',
  1269. 'title': 'The Cardinal Pell Interview',
  1270. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1271. 'uploader': 'GlobeCast Australia - GlobeStream',
  1272. 'uploader_id': '2733773828001',
  1273. 'upload_date': '20160304',
  1274. 'timestamp': 1457083087,
  1275. },
  1276. 'params': {
  1277. # m3u8 downloads
  1278. 'skip_download': True,
  1279. },
  1280. },
  1281. # Another form of arte.tv embed
  1282. {
  1283. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1284. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1285. 'info_dict': {
  1286. 'id': '030273-562_PLUS7-F',
  1287. 'ext': 'mp4',
  1288. 'title': 'ARTE Reportage - Nulle part, en France',
  1289. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1290. 'upload_date': '20160409',
  1291. },
  1292. },
  1293. # LiveLeak embed
  1294. {
  1295. 'url': 'http://www.wykop.pl/link/3088787/',
  1296. 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
  1297. 'info_dict': {
  1298. 'id': '874_1459135191',
  1299. 'ext': 'mp4',
  1300. 'title': 'Man shows poor quality of new apartment building',
  1301. 'description': 'The wall is like a sand pile.',
  1302. 'uploader': 'Lake8737',
  1303. }
  1304. },
  1305. # Duplicated embedded video URLs
  1306. {
  1307. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1308. 'info_dict': {
  1309. 'id': '149298443_480_16c25b74_2',
  1310. 'ext': 'mp4',
  1311. 'title': 'vs. Blue Orange Spring Game',
  1312. 'uploader': 'www.hudl.com',
  1313. },
  1314. },
  1315. # twitter:player:stream embed
  1316. {
  1317. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1318. 'info_dict': {
  1319. 'id': 'master',
  1320. 'ext': 'mp4',
  1321. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1322. 'uploader': 'www.rtl.be',
  1323. },
  1324. 'params': {
  1325. # m3u8 downloads
  1326. 'skip_download': True,
  1327. },
  1328. },
  1329. # twitter:player embed
  1330. {
  1331. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1332. 'md5': 'a3e0df96369831de324f0778e126653c',
  1333. 'info_dict': {
  1334. 'id': '4909620399001',
  1335. 'ext': 'mp4',
  1336. 'title': 'What Do Black Holes Sound Like?',
  1337. 'description': 'what do black holes sound like',
  1338. 'upload_date': '20160524',
  1339. 'uploader_id': '29913724001',
  1340. 'timestamp': 1464107587,
  1341. 'uploader': 'TheAtlantic',
  1342. },
  1343. 'add_ie': ['BrightcoveLegacy'],
  1344. },
  1345. # Facebook <iframe> embed
  1346. {
  1347. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1348. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1349. 'info_dict': {
  1350. 'id': '599637780109885',
  1351. 'ext': 'mp4',
  1352. 'title': 'Facebook video #599637780109885',
  1353. },
  1354. },
  1355. # Facebook API embed
  1356. {
  1357. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1358. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1359. 'info_dict': {
  1360. 'id': '10153467542406923',
  1361. 'ext': 'mp4',
  1362. 'title': 'Facebook video #10153467542406923',
  1363. },
  1364. },
  1365. # Wordpress "YouTube Video Importer" plugin
  1366. {
  1367. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1368. 'md5': 'd16797741b560b485194eddda8121b48',
  1369. 'info_dict': {
  1370. 'id': 'HNTXWDXV9Is',
  1371. 'ext': 'mp4',
  1372. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1373. 'upload_date': '20160627',
  1374. 'uploader_id': 'GENOCIDE8GENERAL10',
  1375. 'uploader': 'cylus cyrus',
  1376. },
  1377. },
  1378. {
  1379. # video stored on custom kaltura server
  1380. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1381. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1382. 'info_dict': {
  1383. 'id': '0_1iotm5bh',
  1384. 'ext': 'mp4',
  1385. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1386. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1387. 'uploader_id': 'videos.expansion@el-mundo.net',
  1388. 'upload_date': '20150429',
  1389. 'timestamp': 1430303472,
  1390. },
  1391. 'add_ie': ['Kaltura'],
  1392. },
  1393. {
  1394. # Non-standard Vimeo embed
  1395. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1396. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1397. 'info_dict': {
  1398. 'id': '148867247',
  1399. 'ext': 'mp4',
  1400. 'title': 'Understanding the web - Teaser',
  1401. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1402. 'upload_date': '20151214',
  1403. 'uploader': 'OpenClassrooms',
  1404. 'uploader_id': 'openclassrooms',
  1405. },
  1406. 'add_ie': ['Vimeo'],
  1407. },
  1408. {
  1409. # generic vimeo embed that requires original URL passed as Referer
  1410. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1411. 'only_matching': True,
  1412. },
  1413. {
  1414. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1415. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1416. 'info_dict': {
  1417. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1418. 'ext': 'mp4',
  1419. 'title': 'Big Buck Bunny',
  1420. 'description': 'Royalty free test video',
  1421. 'timestamp': 1432816365,
  1422. 'upload_date': '20150528',
  1423. 'is_live': False,
  1424. },
  1425. 'params': {
  1426. 'skip_download': True,
  1427. },
  1428. 'add_ie': [ArkenaIE.ie_key()],
  1429. },
  1430. {
  1431. '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/',
  1432. 'info_dict': {
  1433. 'id': '1c7141f46c',
  1434. 'ext': 'mp4',
  1435. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1436. },
  1437. 'params': {
  1438. 'skip_download': True,
  1439. },
  1440. 'add_ie': [Vbox7IE.ie_key()],
  1441. },
  1442. {
  1443. # DBTV embeds
  1444. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1445. 'info_dict': {
  1446. 'id': '43254897',
  1447. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1448. },
  1449. 'playlist_mincount': 3,
  1450. },
  1451. {
  1452. # Videa embeds
  1453. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1454. 'info_dict': {
  1455. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1456. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1457. },
  1458. 'playlist_mincount': 2,
  1459. },
  1460. {
  1461. # 20 minuten embed
  1462. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1463. 'info_dict': {
  1464. 'id': '523629',
  1465. 'ext': 'mp4',
  1466. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1467. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1468. },
  1469. 'params': {
  1470. 'skip_download': True,
  1471. },
  1472. 'add_ie': [TwentyMinutenIE.ie_key()],
  1473. },
  1474. {
  1475. # VideoPress embed
  1476. 'url': 'https://en.support.wordpress.com/videopress/',
  1477. 'info_dict': {
  1478. 'id': 'OcobLTqC',
  1479. 'ext': 'm4v',
  1480. 'title': 'IMG_5786',
  1481. 'timestamp': 1435711927,
  1482. 'upload_date': '20150701',
  1483. },
  1484. 'params': {
  1485. 'skip_download': True,
  1486. },
  1487. 'add_ie': [VideoPressIE.ie_key()],
  1488. }
  1489. # {
  1490. # # TODO: find another test
  1491. # # http://schema.org/VideoObject
  1492. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  1493. # 'md5': '888dcf08b7ea671381f00fab74692755',
  1494. # 'info_dict': {
  1495. # 'id': 'nyvTSJMKId',
  1496. # 'ext': 'mp4',
  1497. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  1498. # 'description': '#love for cats.',
  1499. # 'timestamp': 1461244995,
  1500. # 'upload_date': '20160421',
  1501. # },
  1502. # 'params': {
  1503. # 'force_generic_extractor': True,
  1504. # },
  1505. # }
  1506. ]
  1507. def report_following_redirect(self, new_url):
  1508. """Report information extraction."""
  1509. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1510. def _extract_rss(self, url, video_id, doc):
  1511. playlist_title = doc.find('./channel/title').text
  1512. playlist_desc_el = doc.find('./channel/description')
  1513. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1514. entries = []
  1515. for it in doc.findall('./channel/item'):
  1516. next_url = xpath_text(it, 'link', fatal=False)
  1517. if not next_url:
  1518. enclosure_nodes = it.findall('./enclosure')
  1519. for e in enclosure_nodes:
  1520. next_url = e.attrib.get('url')
  1521. if next_url:
  1522. break
  1523. if not next_url:
  1524. continue
  1525. entries.append({
  1526. '_type': 'url',
  1527. 'url': next_url,
  1528. 'title': it.find('title').text,
  1529. })
  1530. return {
  1531. '_type': 'playlist',
  1532. 'id': url,
  1533. 'title': playlist_title,
  1534. 'description': playlist_desc,
  1535. 'entries': entries,
  1536. }
  1537. def _extract_camtasia(self, url, video_id, webpage):
  1538. """ Returns None if no camtasia video can be found. """
  1539. camtasia_cfg = self._search_regex(
  1540. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1541. webpage, 'camtasia configuration file', default=None)
  1542. if camtasia_cfg is None:
  1543. return None
  1544. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1545. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1546. camtasia_cfg = self._download_xml(
  1547. camtasia_url, video_id,
  1548. note='Downloading camtasia configuration',
  1549. errnote='Failed to download camtasia configuration')
  1550. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1551. entries = []
  1552. for n in fileset_node.getchildren():
  1553. url_n = n.find('./uri')
  1554. if url_n is None:
  1555. continue
  1556. entries.append({
  1557. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1558. 'title': '%s - %s' % (title, n.tag),
  1559. 'url': compat_urlparse.urljoin(url, url_n.text),
  1560. 'duration': float_or_none(n.find('./duration').text),
  1561. })
  1562. return {
  1563. '_type': 'playlist',
  1564. 'entries': entries,
  1565. 'title': title,
  1566. }
  1567. def _real_extract(self, url):
  1568. if url.startswith('//'):
  1569. return {
  1570. '_type': 'url',
  1571. 'url': self.http_scheme() + url,
  1572. }
  1573. parsed_url = compat_urlparse.urlparse(url)
  1574. if not parsed_url.scheme:
  1575. default_search = self._downloader.params.get('default_search')
  1576. if default_search is None:
  1577. default_search = 'fixup_error'
  1578. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1579. if '/' in url:
  1580. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1581. return self.url_result('http://' + url)
  1582. elif default_search != 'fixup_error':
  1583. if default_search == 'auto_warning':
  1584. if re.match(r'^(?:url|URL)$', url):
  1585. raise ExtractorError(
  1586. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1587. expected=True)
  1588. else:
  1589. self._downloader.report_warning(
  1590. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1591. return self.url_result('ytsearch:' + url)
  1592. if default_search in ('error', 'fixup_error'):
  1593. raise ExtractorError(
  1594. '%r is not a valid URL. '
  1595. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1596. % (url, url), expected=True)
  1597. else:
  1598. if ':' not in default_search:
  1599. default_search += ':'
  1600. return self.url_result(default_search + url)
  1601. url, smuggled_data = unsmuggle_url(url)
  1602. force_videoid = None
  1603. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1604. if smuggled_data and 'force_videoid' in smuggled_data:
  1605. force_videoid = smuggled_data['force_videoid']
  1606. video_id = force_videoid
  1607. else:
  1608. video_id = self._generic_id(url)
  1609. self.to_screen('%s: Requesting header' % video_id)
  1610. head_req = HEADRequest(url)
  1611. head_response = self._request_webpage(
  1612. head_req, video_id,
  1613. note=False, errnote='Could not send HEAD request to %s' % url,
  1614. fatal=False)
  1615. if head_response is not False:
  1616. # Check for redirect
  1617. new_url = head_response.geturl()
  1618. if url != new_url:
  1619. self.report_following_redirect(new_url)
  1620. if force_videoid:
  1621. new_url = smuggle_url(
  1622. new_url, {'force_videoid': force_videoid})
  1623. return self.url_result(new_url)
  1624. full_response = None
  1625. if head_response is False:
  1626. request = sanitized_Request(url)
  1627. request.add_header('Accept-Encoding', '*')
  1628. full_response = self._request_webpage(request, video_id)
  1629. head_response = full_response
  1630. info_dict = {
  1631. 'id': video_id,
  1632. 'title': self._generic_title(url),
  1633. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  1634. }
  1635. # Check for direct link to a video
  1636. content_type = head_response.headers.get('Content-Type', '').lower()
  1637. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  1638. if m:
  1639. format_id = m.group('format_id')
  1640. if format_id.endswith('mpegurl'):
  1641. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1642. elif format_id == 'f4m':
  1643. formats = self._extract_f4m_formats(url, video_id)
  1644. else:
  1645. formats = [{
  1646. 'format_id': m.group('format_id'),
  1647. 'url': url,
  1648. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1649. }]
  1650. info_dict['direct'] = True
  1651. self._sort_formats(formats)
  1652. info_dict['formats'] = formats
  1653. return info_dict
  1654. if not self._downloader.params.get('test', False) and not is_intentional:
  1655. force = self._downloader.params.get('force_generic_extractor', False)
  1656. self._downloader.report_warning(
  1657. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1658. if not full_response:
  1659. request = sanitized_Request(url)
  1660. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1661. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1662. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1663. # that will always result in downloading the whole file that is not desirable.
  1664. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1665. # to accept raw bytes and being able to download only a chunk.
  1666. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1667. # after HEAD request finishes, but not sure if we can rely on this.
  1668. request.add_header('Accept-Encoding', '*')
  1669. full_response = self._request_webpage(request, video_id)
  1670. first_bytes = full_response.read(512)
  1671. # Is it an M3U playlist?
  1672. if first_bytes.startswith(b'#EXTM3U'):
  1673. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  1674. self._sort_formats(info_dict['formats'])
  1675. return info_dict
  1676. # Maybe it's a direct link to a video?
  1677. # Be careful not to download the whole thing!
  1678. if not is_html(first_bytes):
  1679. self._downloader.report_warning(
  1680. 'URL could be a direct video link, returning it as such.')
  1681. info_dict.update({
  1682. 'direct': True,
  1683. 'url': url,
  1684. })
  1685. return info_dict
  1686. webpage = self._webpage_read_content(
  1687. full_response, url, video_id, prefix=first_bytes)
  1688. self.report_extraction(video_id)
  1689. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1690. try:
  1691. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1692. if doc.tag == 'rss':
  1693. return self._extract_rss(url, video_id, doc)
  1694. elif doc.tag == 'SmoothStreamingMedia':
  1695. info_dict['formats'] = self._parse_ism_formats(doc, url)
  1696. self._sort_formats(info_dict['formats'])
  1697. return info_dict
  1698. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1699. smil = self._parse_smil(doc, url, video_id)
  1700. self._sort_formats(smil['formats'])
  1701. return smil
  1702. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1703. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1704. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1705. info_dict['formats'] = self._parse_mpd_formats(
  1706. doc, video_id,
  1707. mpd_base_url=full_response.geturl().rpartition('/')[0],
  1708. mpd_url=url)
  1709. self._sort_formats(info_dict['formats'])
  1710. return info_dict
  1711. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  1712. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  1713. self._sort_formats(info_dict['formats'])
  1714. return info_dict
  1715. except compat_xml_parse_error:
  1716. pass
  1717. # Is it a Camtasia project?
  1718. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1719. if camtasia_res is not None:
  1720. return camtasia_res
  1721. # Sometimes embedded video player is hidden behind percent encoding
  1722. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1723. # Unescaping the whole page allows to handle those cases in a generic way
  1724. webpage = compat_urllib_parse_unquote(webpage)
  1725. # it's tempting to parse this further, but you would
  1726. # have to take into account all the variations like
  1727. # Video Title - Site Name
  1728. # Site Name | Video Title
  1729. # Video Title - Tagline | Site Name
  1730. # and so on and so forth; it's just not practical
  1731. video_title = self._og_search_title(
  1732. webpage, default=None) or self._html_search_regex(
  1733. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1734. default='video')
  1735. # Try to detect age limit automatically
  1736. age_limit = self._rta_search(webpage)
  1737. # And then there are the jokers who advertise that they use RTA,
  1738. # but actually don't.
  1739. AGE_LIMIT_MARKERS = [
  1740. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1741. ]
  1742. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1743. age_limit = 18
  1744. # video uploader is domain name
  1745. video_uploader = self._search_regex(
  1746. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1747. video_description = self._og_search_description(webpage, default=None)
  1748. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  1749. # Helper method
  1750. def _playlist_from_matches(matches, getter=None, ie=None):
  1751. urlrs = orderedSet(
  1752. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1753. for m in matches)
  1754. return self.playlist_result(
  1755. urlrs, playlist_id=video_id, playlist_title=video_title)
  1756. # Look for Brightcove Legacy Studio embeds
  1757. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1758. if bc_urls:
  1759. self.to_screen('Brightcove video detected.')
  1760. entries = [{
  1761. '_type': 'url',
  1762. 'url': smuggle_url(bc_url, {'Referer': url}),
  1763. 'ie_key': 'BrightcoveLegacy'
  1764. } for bc_url in bc_urls]
  1765. return {
  1766. '_type': 'playlist',
  1767. 'title': video_title,
  1768. 'id': video_id,
  1769. 'entries': entries,
  1770. }
  1771. # Look for Brightcove New Studio embeds
  1772. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1773. if bc_urls:
  1774. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1775. # Look for ThePlatform embeds
  1776. tp_urls = ThePlatformIE._extract_urls(webpage)
  1777. if tp_urls:
  1778. return _playlist_from_matches(tp_urls, ie='ThePlatform')
  1779. # Look for Vessel embeds
  1780. vessel_urls = VesselIE._extract_urls(webpage)
  1781. if vessel_urls:
  1782. return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
  1783. # Look for embedded rtl.nl player
  1784. matches = re.findall(
  1785. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1786. webpage)
  1787. if matches:
  1788. return _playlist_from_matches(matches, ie='RtlNl')
  1789. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  1790. if vimeo_urls:
  1791. return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
  1792. vid_me_embed_url = self._search_regex(
  1793. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1794. webpage, 'vid.me embed', default=None)
  1795. if vid_me_embed_url is not None:
  1796. return self.url_result(vid_me_embed_url, 'Vidme')
  1797. # Look for embedded YouTube player
  1798. matches = re.findall(r'''(?x)
  1799. (?:
  1800. <iframe[^>]+?src=|
  1801. data-video-url=|
  1802. <embed[^>]+?src=|
  1803. embedSWF\(?:\s*|
  1804. new\s+SWFObject\(
  1805. )
  1806. (["\'])
  1807. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1808. (?:embed|v|p)/.+?)
  1809. \1''', webpage)
  1810. if matches:
  1811. return _playlist_from_matches(
  1812. matches, lambda m: unescapeHTML(m[1]))
  1813. # Look for lazyYT YouTube embed
  1814. matches = re.findall(
  1815. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1816. if matches:
  1817. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1818. # Look for Wordpress "YouTube Video Importer" plugin
  1819. matches = re.findall(r'''(?x)<div[^>]+
  1820. class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
  1821. data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
  1822. if matches:
  1823. return _playlist_from_matches(matches, lambda m: m[-1])
  1824. matches = DailymotionIE._extract_urls(webpage)
  1825. if matches:
  1826. return _playlist_from_matches(matches)
  1827. # Look for embedded Dailymotion playlist player (#3822)
  1828. m = re.search(
  1829. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1830. if m:
  1831. playlists = re.findall(
  1832. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1833. if playlists:
  1834. return _playlist_from_matches(
  1835. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1836. # Look for embedded Wistia player
  1837. match = re.search(
  1838. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1839. if match:
  1840. embed_url = self._proto_relative_url(
  1841. unescapeHTML(match.group('url')))
  1842. return {
  1843. '_type': 'url_transparent',
  1844. 'url': embed_url,
  1845. 'ie_key': 'Wistia',
  1846. 'uploader': video_uploader,
  1847. }
  1848. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1849. if match:
  1850. return {
  1851. '_type': 'url_transparent',
  1852. 'url': 'wistia:%s' % match.group('id'),
  1853. 'ie_key': 'Wistia',
  1854. 'uploader': video_uploader,
  1855. }
  1856. match = re.search(
  1857. r'''(?sx)
  1858. <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
  1859. <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
  1860. ''', webpage)
  1861. if match:
  1862. return self.url_result(self._proto_relative_url(
  1863. 'wistia:%s' % match.group('id')), 'Wistia')
  1864. # Look for SVT player
  1865. svt_url = SVTIE._extract_url(webpage)
  1866. if svt_url:
  1867. return self.url_result(svt_url, 'SVT')
  1868. # Look for embedded condenast player
  1869. matches = re.findall(
  1870. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1871. webpage)
  1872. if matches:
  1873. return {
  1874. '_type': 'playlist',
  1875. 'entries': [{
  1876. '_type': 'url',
  1877. 'ie_key': 'CondeNast',
  1878. 'url': ma,
  1879. } for ma in matches],
  1880. 'title': video_title,
  1881. 'id': video_id,
  1882. }
  1883. # Look for Bandcamp pages with custom domain
  1884. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1885. if mobj is not None:
  1886. burl = unescapeHTML(mobj.group(1))
  1887. # Don't set the extractor because it can be a track url or an album
  1888. return self.url_result(burl)
  1889. # Look for embedded Vevo player
  1890. mobj = re.search(
  1891. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1892. if mobj is not None:
  1893. return self.url_result(mobj.group('url'))
  1894. # Look for embedded Viddler player
  1895. mobj = re.search(
  1896. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1897. webpage)
  1898. if mobj is not None:
  1899. return self.url_result(mobj.group('url'))
  1900. # Look for NYTimes player
  1901. mobj = re.search(
  1902. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1903. webpage)
  1904. if mobj is not None:
  1905. return self.url_result(mobj.group('url'))
  1906. # Look for Libsyn player
  1907. mobj = re.search(
  1908. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1909. if mobj is not None:
  1910. return self.url_result(mobj.group('url'))
  1911. # Look for Ooyala videos
  1912. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1913. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1914. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1915. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1916. if mobj is not None:
  1917. embed_token = self._search_regex(
  1918. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  1919. webpage, 'ooyala embed token', default=None)
  1920. return OoyalaIE._build_url_result(smuggle_url(
  1921. mobj.group('ec'), {
  1922. 'domain': url,
  1923. 'embed_token': embed_token,
  1924. }))
  1925. # Look for multiple Ooyala embeds on SBN network websites
  1926. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1927. if mobj is not None:
  1928. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1929. if embeds:
  1930. return _playlist_from_matches(
  1931. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1932. # Look for Aparat videos
  1933. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1934. if mobj is not None:
  1935. return self.url_result(mobj.group(1), 'Aparat')
  1936. # Look for MPORA videos
  1937. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1938. if mobj is not None:
  1939. return self.url_result(mobj.group(1), 'Mpora')
  1940. # Look for embedded NovaMov-based player
  1941. mobj = re.search(
  1942. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1943. (?P<url>http://(?:(?:embed|www)\.)?
  1944. (?:novamov\.com|
  1945. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1946. videoweed\.(?:es|com)|
  1947. movshare\.(?:net|sx|ag)|
  1948. divxstage\.(?:eu|net|ch|co|at|ag))
  1949. /embed\.php.+?)\1''', webpage)
  1950. if mobj is not None:
  1951. return self.url_result(mobj.group('url'))
  1952. # Look for embedded Facebook player
  1953. facebook_url = FacebookIE._extract_url(webpage)
  1954. if facebook_url is not None:
  1955. return self.url_result(facebook_url, 'Facebook')
  1956. # Look for embedded VK player
  1957. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1958. if mobj is not None:
  1959. return self.url_result(mobj.group('url'), 'VK')
  1960. # Look for embedded Odnoklassniki player
  1961. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  1962. if mobj is not None:
  1963. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  1964. # Look for embedded ivi player
  1965. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1966. if mobj is not None:
  1967. return self.url_result(mobj.group('url'), 'Ivi')
  1968. # Look for embedded Huffington Post player
  1969. mobj = re.search(
  1970. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1971. if mobj is not None:
  1972. return self.url_result(mobj.group('url'), 'HuffPost')
  1973. # Look for embed.ly
  1974. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1975. if mobj is not None:
  1976. return self.url_result(mobj.group('url'))
  1977. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1978. if mobj is not None:
  1979. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1980. # Look for funnyordie embed
  1981. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1982. if matches:
  1983. return _playlist_from_matches(
  1984. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1985. # Look for BBC iPlayer embed
  1986. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1987. if matches:
  1988. return _playlist_from_matches(matches, ie='BBCCoUk')
  1989. # Look for embedded RUTV player
  1990. rutv_url = RUTVIE._extract_url(webpage)
  1991. if rutv_url:
  1992. return self.url_result(rutv_url, 'RUTV')
  1993. # Look for embedded TVC player
  1994. tvc_url = TVCIE._extract_url(webpage)
  1995. if tvc_url:
  1996. return self.url_result(tvc_url, 'TVC')
  1997. # Look for embedded SportBox player
  1998. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1999. if sportbox_urls:
  2000. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  2001. # Look for embedded XHamster player
  2002. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2003. if xhamster_urls:
  2004. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  2005. # Look for embedded TNAFlixNetwork player
  2006. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2007. if tnaflix_urls:
  2008. return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
  2009. # Look for embedded PornHub player
  2010. pornhub_urls = PornHubIE._extract_urls(webpage)
  2011. if pornhub_urls:
  2012. return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
  2013. # Look for embedded DrTuber player
  2014. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2015. if drtuber_urls:
  2016. return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
  2017. # Look for embedded RedTube player
  2018. redtube_urls = RedTubeIE._extract_urls(webpage)
  2019. if redtube_urls:
  2020. return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
  2021. # Look for embedded Tvigle player
  2022. mobj = re.search(
  2023. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2024. if mobj is not None:
  2025. return self.url_result(mobj.group('url'), 'Tvigle')
  2026. # Look for embedded TED player
  2027. mobj = re.search(
  2028. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2029. if mobj is not None:
  2030. return self.url_result(mobj.group('url'), 'TED')
  2031. # Look for embedded Ustream videos
  2032. ustream_url = UstreamIE._extract_url(webpage)
  2033. if ustream_url:
  2034. return self.url_result(ustream_url, UstreamIE.ie_key())
  2035. # Look for embedded arte.tv player
  2036. mobj = re.search(
  2037. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2038. webpage)
  2039. if mobj is not None:
  2040. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2041. # Look for embedded francetv player
  2042. mobj = re.search(
  2043. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2044. webpage)
  2045. if mobj is not None:
  2046. return self.url_result(mobj.group('url'))
  2047. # Look for embedded smotri.com player
  2048. smotri_url = SmotriIE._extract_url(webpage)
  2049. if smotri_url:
  2050. return self.url_result(smotri_url, 'Smotri')
  2051. # Look for embedded Myvi.ru player
  2052. myvi_url = MyviIE._extract_url(webpage)
  2053. if myvi_url:
  2054. return self.url_result(myvi_url)
  2055. # Look for embedded soundcloud player
  2056. soundcloud_urls = SoundcloudIE._extract_urls(webpage)
  2057. if soundcloud_urls:
  2058. return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
  2059. # Look for tunein player
  2060. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2061. if tunein_urls:
  2062. return _playlist_from_matches(tunein_urls)
  2063. # Look for embedded mtvservices player
  2064. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2065. if mtvservices_url:
  2066. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2067. # Look for embedded yahoo player
  2068. mobj = re.search(
  2069. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2070. webpage)
  2071. if mobj is not None:
  2072. return self.url_result(mobj.group('url'), 'Yahoo')
  2073. # Look for embedded sbs.com.au player
  2074. mobj = re.search(
  2075. r'''(?x)
  2076. (?:
  2077. <meta\s+property="og:video"\s+content=|
  2078. <iframe[^>]+?src=
  2079. )
  2080. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2081. webpage)
  2082. if mobj is not None:
  2083. return self.url_result(mobj.group('url'), 'SBS')
  2084. # Look for embedded Cinchcast player
  2085. mobj = re.search(
  2086. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2087. webpage)
  2088. if mobj is not None:
  2089. return self.url_result(mobj.group('url'), 'Cinchcast')
  2090. mobj = re.search(
  2091. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2092. webpage)
  2093. if not mobj:
  2094. mobj = re.search(
  2095. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2096. webpage)
  2097. if mobj is not None:
  2098. return self.url_result(mobj.group('url'), 'MLB')
  2099. mobj = re.search(
  2100. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2101. webpage)
  2102. if mobj is not None:
  2103. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2104. mobj = re.search(
  2105. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2106. webpage)
  2107. if mobj is not None:
  2108. return self.url_result(mobj.group('url'), 'Livestream')
  2109. # Look for Zapiks embed
  2110. mobj = re.search(
  2111. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2112. if mobj is not None:
  2113. return self.url_result(mobj.group('url'), 'Zapiks')
  2114. # Look for Kaltura embeds
  2115. kaltura_url = KalturaIE._extract_url(webpage)
  2116. if kaltura_url:
  2117. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2118. # Look for Eagle.Platform embeds
  2119. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2120. if eagleplatform_url:
  2121. return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
  2122. # Look for ClipYou (uses Eagle.Platform) embeds
  2123. mobj = re.search(
  2124. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2125. if mobj is not None:
  2126. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2127. # Look for Pladform embeds
  2128. pladform_url = PladformIE._extract_url(webpage)
  2129. if pladform_url:
  2130. return self.url_result(pladform_url)
  2131. # Look for Videomore embeds
  2132. videomore_url = VideomoreIE._extract_url(webpage)
  2133. if videomore_url:
  2134. return self.url_result(videomore_url)
  2135. # Look for Webcaster embeds
  2136. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2137. if webcaster_url:
  2138. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2139. # Look for Playwire embeds
  2140. mobj = re.search(
  2141. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2142. if mobj is not None:
  2143. return self.url_result(mobj.group('url'))
  2144. # Look for 5min embeds
  2145. mobj = re.search(
  2146. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2147. if mobj is not None:
  2148. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2149. # Look for Crooks and Liars embeds
  2150. mobj = re.search(
  2151. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2152. if mobj is not None:
  2153. return self.url_result(mobj.group('url'))
  2154. # Look for NBC Sports VPlayer embeds
  2155. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2156. if nbc_sports_url:
  2157. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2158. # Look for NBC News embeds
  2159. nbc_news_embed_url = re.search(
  2160. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2161. if nbc_news_embed_url:
  2162. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2163. # Look for Google Drive embeds
  2164. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2165. if google_drive_url:
  2166. return self.url_result(google_drive_url, 'GoogleDrive')
  2167. # Look for UDN embeds
  2168. mobj = re.search(
  2169. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2170. if mobj is not None:
  2171. return self.url_result(
  2172. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2173. # Look for Senate ISVP iframe
  2174. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2175. if senate_isvp_url:
  2176. return self.url_result(senate_isvp_url, 'SenateISVP')
  2177. # Look for Dailymotion Cloud videos
  2178. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  2179. if dmcloud_url:
  2180. return self.url_result(dmcloud_url, 'DailymotionCloud')
  2181. # Look for OnionStudios embeds
  2182. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2183. if onionstudios_url:
  2184. return self.url_result(onionstudios_url)
  2185. # Look for ViewLift embeds
  2186. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2187. if viewlift_url:
  2188. return self.url_result(viewlift_url)
  2189. # Look for JWPlatform embeds
  2190. jwplatform_url = JWPlatformIE._extract_url(webpage)
  2191. if jwplatform_url:
  2192. return self.url_result(jwplatform_url, 'JWPlatform')
  2193. # Look for Digiteka embeds
  2194. digiteka_url = DigitekaIE._extract_url(webpage)
  2195. if digiteka_url:
  2196. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2197. # Look for Arkena embeds
  2198. arkena_url = ArkenaIE._extract_url(webpage)
  2199. if arkena_url:
  2200. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2201. # Look for Piksel embeds
  2202. piksel_url = PikselIE._extract_url(webpage)
  2203. if piksel_url:
  2204. return self.url_result(piksel_url, PikselIE.ie_key())
  2205. # Look for Limelight embeds
  2206. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  2207. if mobj:
  2208. lm = {
  2209. 'Media': 'media',
  2210. 'Channel': 'channel',
  2211. 'ChannelList': 'channel_list',
  2212. }
  2213. return self.url_result(smuggle_url('limelight:%s:%s' % (
  2214. lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
  2215. 'Limelight%s' % mobj.group(1), mobj.group(2))
  2216. mobj = re.search(
  2217. r'''(?sx)
  2218. <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
  2219. <param[^>]+
  2220. name=(["\'])flashVars\2[^>]+
  2221. value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
  2222. ''', webpage)
  2223. if mobj:
  2224. return self.url_result(smuggle_url(
  2225. 'limelight:media:%s' % mobj.group('id'),
  2226. {'source_url': url}), 'LimelightMedia', mobj.group('id'))
  2227. # Look for AdobeTVVideo embeds
  2228. mobj = re.search(
  2229. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2230. webpage)
  2231. if mobj is not None:
  2232. return self.url_result(
  2233. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2234. 'AdobeTVVideo')
  2235. # Look for Vine embeds
  2236. mobj = re.search(
  2237. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2238. webpage)
  2239. if mobj is not None:
  2240. return self.url_result(
  2241. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2242. # Look for VODPlatform embeds
  2243. mobj = re.search(
  2244. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2245. webpage)
  2246. if mobj is not None:
  2247. return self.url_result(
  2248. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2249. # Look for Mangomolo embeds
  2250. mobj = re.search(
  2251. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
  2252. (?:
  2253. video\?.*?\bid=(?P<video_id>\d+)|
  2254. index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2255. ).+?)\1''', webpage)
  2256. if mobj is not None:
  2257. info = {
  2258. '_type': 'url_transparent',
  2259. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2260. 'title': video_title,
  2261. 'description': video_description,
  2262. 'thumbnail': video_thumbnail,
  2263. 'uploader': video_uploader,
  2264. }
  2265. video_id = mobj.group('video_id')
  2266. if video_id:
  2267. info.update({
  2268. 'ie_key': 'MangomoloVideo',
  2269. 'id': video_id,
  2270. })
  2271. else:
  2272. info.update({
  2273. 'ie_key': 'MangomoloLive',
  2274. 'id': mobj.group('channel_id'),
  2275. })
  2276. return info
  2277. # Look for Instagram embeds
  2278. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2279. if instagram_embed_url is not None:
  2280. return self.url_result(
  2281. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2282. # Look for LiveLeak embeds
  2283. liveleak_url = LiveLeakIE._extract_url(webpage)
  2284. if liveleak_url:
  2285. return self.url_result(liveleak_url, 'LiveLeak')
  2286. # Look for 3Q SDN embeds
  2287. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2288. if threeqsdn_url:
  2289. return {
  2290. '_type': 'url_transparent',
  2291. 'ie_key': ThreeQSDNIE.ie_key(),
  2292. 'url': self._proto_relative_url(threeqsdn_url),
  2293. 'title': video_title,
  2294. 'description': video_description,
  2295. 'thumbnail': video_thumbnail,
  2296. 'uploader': video_uploader,
  2297. }
  2298. # Look for VBOX7 embeds
  2299. vbox7_url = Vbox7IE._extract_url(webpage)
  2300. if vbox7_url:
  2301. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2302. # Look for DBTV embeds
  2303. dbtv_urls = DBTVIE._extract_urls(webpage)
  2304. if dbtv_urls:
  2305. return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
  2306. # Look for Videa embeds
  2307. videa_urls = VideaIE._extract_urls(webpage)
  2308. if videa_urls:
  2309. return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
  2310. # Look for 20 minuten embeds
  2311. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2312. if twentymin_urls:
  2313. return _playlist_from_matches(
  2314. twentymin_urls, ie=TwentyMinutenIE.ie_key())
  2315. # Look for Openload embeds
  2316. openload_urls = OpenloadIE._extract_urls(webpage)
  2317. if openload_urls:
  2318. return _playlist_from_matches(
  2319. openload_urls, ie=OpenloadIE.ie_key())
  2320. # Look for VideoPress embeds
  2321. videopress_urls = VideoPressIE._extract_urls(webpage)
  2322. if videopress_urls:
  2323. return _playlist_from_matches(
  2324. videopress_urls, ie=VideoPressIE.ie_key())
  2325. # Looking for http://schema.org/VideoObject
  2326. json_ld = self._search_json_ld(
  2327. webpage, video_id, default={}, expected_type='VideoObject')
  2328. if json_ld.get('url'):
  2329. info_dict.update({
  2330. 'title': video_title or info_dict['title'],
  2331. 'description': video_description,
  2332. 'thumbnail': video_thumbnail,
  2333. 'age_limit': age_limit
  2334. })
  2335. info_dict.update(json_ld)
  2336. return info_dict
  2337. # Look for HTML5 media
  2338. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  2339. if entries:
  2340. for entry in entries:
  2341. entry.update({
  2342. 'id': video_id,
  2343. 'title': video_title,
  2344. })
  2345. self._sort_formats(entry['formats'])
  2346. return self.playlist_result(entries)
  2347. def check_video(vurl):
  2348. if YoutubeIE.suitable(vurl):
  2349. return True
  2350. if RtmpIE.suitable(vurl):
  2351. return True
  2352. vpath = compat_urlparse.urlparse(vurl).path
  2353. vext = determine_ext(vpath)
  2354. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
  2355. def filter_video(urls):
  2356. return list(filter(check_video, urls))
  2357. # Start with something easy: JW Player in SWFObject
  2358. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  2359. if not found:
  2360. # Look for gorilla-vid style embedding
  2361. found = filter_video(re.findall(r'''(?sx)
  2362. (?:
  2363. jw_plugins|
  2364. JWPlayerOptions|
  2365. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  2366. )
  2367. .*?
  2368. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  2369. if not found:
  2370. # Broaden the search a little bit
  2371. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  2372. if not found:
  2373. # Broaden the findall a little bit: JWPlayer JS loader
  2374. found = filter_video(re.findall(
  2375. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  2376. if not found:
  2377. # Flow player
  2378. found = filter_video(re.findall(r'''(?xs)
  2379. flowplayer\("[^"]+",\s*
  2380. \{[^}]+?\}\s*,
  2381. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  2382. ["']?url["']?\s*:\s*["']([^"']+)["']
  2383. ''', webpage))
  2384. if not found:
  2385. # Cinerama player
  2386. found = re.findall(
  2387. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  2388. if not found:
  2389. # Try to find twitter cards info
  2390. # twitter:player:stream should be checked before twitter:player since
  2391. # it is expected to contain a raw stream (see
  2392. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2393. found = filter_video(re.findall(
  2394. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  2395. if not found:
  2396. # We look for Open Graph info:
  2397. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  2398. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  2399. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  2400. if m_video_type is not None:
  2401. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  2402. if not found:
  2403. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  2404. found = re.search(
  2405. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  2406. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  2407. webpage)
  2408. if not found:
  2409. # Look also in Refresh HTTP header
  2410. refresh_header = head_response.headers.get('Refresh')
  2411. if refresh_header:
  2412. # In python 2 response HTTP headers are bytestrings
  2413. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  2414. refresh_header = refresh_header.decode('iso-8859-1')
  2415. found = re.search(REDIRECT_REGEX, refresh_header)
  2416. if found:
  2417. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  2418. self.report_following_redirect(new_url)
  2419. return {
  2420. '_type': 'url',
  2421. 'url': new_url,
  2422. }
  2423. if not found:
  2424. # twitter:player is a https URL to iframe player that may or may not
  2425. # be supported by youtube-dl thus this is checked the very last (see
  2426. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2427. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  2428. if embed_url:
  2429. return self.url_result(embed_url)
  2430. if not found:
  2431. raise UnsupportedError(url)
  2432. entries = []
  2433. for video_url in orderedSet(found):
  2434. video_url = unescapeHTML(video_url)
  2435. video_url = video_url.replace('\\/', '/')
  2436. video_url = compat_urlparse.urljoin(url, video_url)
  2437. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  2438. # Sometimes, jwplayer extraction will result in a YouTube URL
  2439. if YoutubeIE.suitable(video_url):
  2440. entries.append(self.url_result(video_url, 'Youtube'))
  2441. continue
  2442. # here's a fun little line of code for you:
  2443. video_id = os.path.splitext(video_id)[0]
  2444. entry_info_dict = {
  2445. 'id': video_id,
  2446. 'uploader': video_uploader,
  2447. 'title': video_title,
  2448. 'age_limit': age_limit,
  2449. }
  2450. if RtmpIE.suitable(video_url):
  2451. entry_info_dict.update({
  2452. '_type': 'url_transparent',
  2453. 'ie_key': RtmpIE.ie_key(),
  2454. 'url': video_url,
  2455. })
  2456. entries.append(entry_info_dict)
  2457. continue
  2458. ext = determine_ext(video_url)
  2459. if ext == 'smil':
  2460. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  2461. elif ext == 'xspf':
  2462. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  2463. elif ext == 'm3u8':
  2464. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  2465. elif ext == 'mpd':
  2466. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  2467. elif ext == 'f4m':
  2468. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  2469. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  2470. # Just matching .ism/manifest is not enough to be reliably sure
  2471. # whether it's actually an ISM manifest or some other streaming
  2472. # manifest since there are various streaming URL formats
  2473. # possible (see [1]) as well as some other shenanigans like
  2474. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  2475. # so on.
  2476. # Thus the most reasonable way to solve this is to delegate
  2477. # to generic extractor in order to look into the contents of
  2478. # the manifest itself.
  2479. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  2480. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  2481. entry_info_dict = self.url_result(
  2482. smuggle_url(video_url, {'to_generic': True}),
  2483. GenericIE.ie_key())
  2484. else:
  2485. entry_info_dict['url'] = video_url
  2486. if entry_info_dict.get('formats'):
  2487. self._sort_formats(entry_info_dict['formats'])
  2488. entries.append(entry_info_dict)
  2489. if len(entries) == 1:
  2490. return entries[0]
  2491. else:
  2492. for num, e in enumerate(entries, start=1):
  2493. # 'url' results don't have a title
  2494. if e.get('title') is not None:
  2495. e['title'] = '%s (%d)' % (e['title'], num)
  2496. return {
  2497. '_type': 'playlist',
  2498. 'entries': entries,
  2499. }