2
0

generic.py 142 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502350335043505350635073508350935103511351235133514351535163517351835193520
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. int_or_none,
  21. is_html,
  22. js_to_json,
  23. KNOWN_EXTENSIONS,
  24. merge_dicts,
  25. mimetype2ext,
  26. orderedSet,
  27. parse_duration,
  28. sanitized_Request,
  29. smuggle_url,
  30. unescapeHTML,
  31. unified_timestamp,
  32. unsmuggle_url,
  33. UnsupportedError,
  34. url_or_none,
  35. xpath_attr,
  36. xpath_text,
  37. xpath_with_ns,
  38. )
  39. from .commonprotocols import RtmpIE
  40. from .brightcove import (
  41. BrightcoveLegacyIE,
  42. BrightcoveNewIE,
  43. )
  44. from .nexx import (
  45. NexxIE,
  46. NexxEmbedIE,
  47. )
  48. from .nbc import NBCSportsVPlayerIE
  49. from .ooyala import OoyalaIE
  50. from .rutv import RUTVIE
  51. from .tvc import TVCIE
  52. from .sportbox import SportBoxIE
  53. from .myvi import MyviIE
  54. from .condenast import CondeNastIE
  55. from .udn import UDNEmbedIE
  56. from .senateisvp import SenateISVPIE
  57. from .svt import SVTIE
  58. from .pornhub import PornHubIE
  59. from .xhamster import XHamsterEmbedIE
  60. from .tnaflix import TNAFlixNetworkEmbedIE
  61. from .drtuber import DrTuberIE
  62. from .redtube import RedTubeIE
  63. from .tube8 import Tube8IE
  64. from .mofosex import MofosexEmbedIE
  65. from .spankwire import SpankwireIE
  66. from .youporn import YouPornIE
  67. from .vimeo import VimeoIE
  68. from .dailymotion import DailymotionIE
  69. from .dailymail import DailyMailIE
  70. from .onionstudios import OnionStudiosIE
  71. from .viewlift import ViewLiftEmbedIE
  72. from .mtv import MTVServicesEmbeddedIE
  73. from .pladform import PladformIE
  74. from .videomore import VideomoreIE
  75. from .webcaster import WebcasterFeedIE
  76. from .googledrive import GoogleDriveIE
  77. from .jwplatform import JWPlatformIE
  78. from .digiteka import DigitekaIE
  79. from .arkena import ArkenaIE
  80. from .instagram import InstagramIE
  81. from .liveleak import LiveLeakIE
  82. from .threeqsdn import ThreeQSDNIE
  83. from .theplatform import ThePlatformIE
  84. from .kaltura import KalturaIE
  85. from .eagleplatform import EaglePlatformIE
  86. from .facebook import FacebookIE
  87. from .soundcloud import SoundcloudEmbedIE
  88. from .tunein import TuneInBaseIE
  89. from .vbox7 import Vbox7IE
  90. from .dbtv import DBTVIE
  91. from .piksel import PikselIE
  92. from .videa import VideaIE
  93. from .twentymin import TwentyMinutenIE
  94. from .ustream import UstreamIE
  95. from .arte import ArteTVEmbedIE
  96. from .videopress import VideoPressIE
  97. from .rutube import RutubeIE
  98. from .limelight import LimelightBaseIE
  99. from .anvato import AnvatoIE
  100. from .washingtonpost import WashingtonPostIE
  101. from .wistia import WistiaIE
  102. from .mediaset import MediasetIE
  103. from .joj import JojIE
  104. from .megaphone import MegaphoneIE
  105. from .vzaar import VzaarIE
  106. from .channel9 import Channel9IE
  107. from .vshare import VShareIE
  108. from .mediasite import MediasiteIE
  109. from .springboardplatform import SpringboardPlatformIE
  110. from .yapfiles import YapFilesIE
  111. from .vice import ViceIE
  112. from .xfileshare import XFileShareIE
  113. from .cloudflarestream import CloudflareStreamIE
  114. from .peertube import PeerTubeIE
  115. from .teachable import TeachableIE
  116. from .indavideo import IndavideoEmbedIE
  117. from .apa import APAIE
  118. from .foxnews import FoxNewsIE
  119. from .viqeo import ViqeoIE
  120. from .expressen import ExpressenIE
  121. from .zype import ZypeIE
  122. from .odnoklassniki import OdnoklassnikiIE
  123. from .kinja import KinjaEmbedIE
  124. class GenericIE(InfoExtractor):
  125. IE_DESC = 'Generic downloader that works on some sites'
  126. _VALID_URL = r'.*'
  127. IE_NAME = 'generic'
  128. _TESTS = [
  129. # Direct link to a video
  130. {
  131. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  132. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  133. 'info_dict': {
  134. 'id': 'trailer',
  135. 'ext': 'mp4',
  136. 'title': 'trailer',
  137. 'upload_date': '20100513',
  138. }
  139. },
  140. # Direct link to media delivered compressed (until Accept-Encoding is *)
  141. {
  142. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  143. 'md5': '128c42e68b13950268b648275386fc74',
  144. 'info_dict': {
  145. 'id': 'FictionJunction-Parallel_Hearts',
  146. 'ext': 'flac',
  147. 'title': 'FictionJunction-Parallel_Hearts',
  148. 'upload_date': '20140522',
  149. },
  150. 'expected_warnings': [
  151. 'URL could be a direct video link, returning it as such.'
  152. ],
  153. 'skip': 'URL invalid',
  154. },
  155. # Direct download with broken HEAD
  156. {
  157. 'url': 'http://ai-radio.org:8000/radio.opus',
  158. 'info_dict': {
  159. 'id': 'radio',
  160. 'ext': 'opus',
  161. 'title': 'radio',
  162. },
  163. 'params': {
  164. 'skip_download': True, # infinite live stream
  165. },
  166. 'expected_warnings': [
  167. r'501.*Not Implemented',
  168. r'400.*Bad Request',
  169. ],
  170. },
  171. # Direct link with incorrect MIME type
  172. {
  173. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  174. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  175. 'info_dict': {
  176. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  177. 'id': '5_Lennart_Poettering_-_Systemd',
  178. 'ext': 'webm',
  179. 'title': '5_Lennart_Poettering_-_Systemd',
  180. 'upload_date': '20141120',
  181. },
  182. 'expected_warnings': [
  183. 'URL could be a direct video link, returning it as such.'
  184. ]
  185. },
  186. # RSS feed
  187. {
  188. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  189. 'info_dict': {
  190. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  191. 'title': 'Zero Punctuation',
  192. 'description': 're:.*groundbreaking video review series.*'
  193. },
  194. 'playlist_mincount': 11,
  195. },
  196. # RSS feed with enclosure
  197. {
  198. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  199. 'info_dict': {
  200. 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  201. 'title': 'MSNBC Rachel Maddow (video)',
  202. 'description': 're:.*her unique approach to storytelling.*',
  203. },
  204. 'playlist': [{
  205. 'info_dict': {
  206. 'ext': 'mov',
  207. 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
  208. 'title': 're:MSNBC Rachel Maddow',
  209. 'description': 're:.*her unique approach to storytelling.*',
  210. 'timestamp': int,
  211. 'upload_date': compat_str,
  212. 'duration': float,
  213. },
  214. }],
  215. },
  216. # RSS feed with item with description and thumbnails
  217. {
  218. 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
  219. 'info_dict': {
  220. 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
  221. 'title': 're:.*100% Hydrogen.*',
  222. 'description': 're:.*In this episode.*',
  223. },
  224. 'playlist': [{
  225. 'info_dict': {
  226. 'ext': 'm4a',
  227. 'id': 'c1c879525ce2cb640b344507e682c36d',
  228. 'title': 're:Hydrogen!',
  229. 'description': 're:.*In this episode we are going.*',
  230. 'timestamp': int,
  231. 'upload_date': '20190908',
  232. 'duration': int,
  233. 'thumbnail': r're:^https?://.*\.jpg$',
  234. },
  235. }],
  236. 'params': {
  237. 'skip_download': True,
  238. },
  239. },
  240. # RSS feed with enclosures and unsupported link URLs
  241. {
  242. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  243. 'info_dict': {
  244. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  245. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  246. 'title': 'Hello Internet',
  247. },
  248. 'playlist_mincount': 100,
  249. },
  250. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  251. {
  252. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  253. 'info_dict': {
  254. 'id': 'smil',
  255. 'ext': 'mp4',
  256. 'title': 'Automatics, robotics and biocybernetics',
  257. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  258. 'upload_date': '20130627',
  259. 'formats': 'mincount:16',
  260. 'subtitles': 'mincount:1',
  261. },
  262. 'params': {
  263. 'force_generic_extractor': True,
  264. 'skip_download': True,
  265. },
  266. },
  267. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  268. {
  269. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  270. 'info_dict': {
  271. 'id': 'hds',
  272. 'ext': 'flv',
  273. 'title': 'hds',
  274. 'formats': 'mincount:1',
  275. },
  276. 'params': {
  277. 'skip_download': True,
  278. },
  279. },
  280. # SMIL from https://www.restudy.dk/video/play/id/1637
  281. {
  282. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  283. 'info_dict': {
  284. 'id': 'video_1637',
  285. 'ext': 'flv',
  286. 'title': 'video_1637',
  287. 'formats': 'mincount:3',
  288. },
  289. 'params': {
  290. 'skip_download': True,
  291. },
  292. },
  293. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  294. {
  295. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  296. 'info_dict': {
  297. 'id': 'smil-service',
  298. 'ext': 'flv',
  299. 'title': 'smil-service',
  300. 'formats': 'mincount:1',
  301. },
  302. 'params': {
  303. 'skip_download': True,
  304. },
  305. },
  306. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  307. {
  308. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  309. 'info_dict': {
  310. 'id': '4719370',
  311. 'ext': 'mp4',
  312. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  313. 'formats': 'mincount:3',
  314. },
  315. 'params': {
  316. 'skip_download': True,
  317. },
  318. },
  319. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  320. {
  321. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  322. 'info_dict': {
  323. 'id': 'mZlp2ctYIUEB',
  324. 'ext': 'mp4',
  325. 'title': 'Tikibad ontruimd wegens brand',
  326. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  327. 'thumbnail': r're:^https?://.*\.jpg$',
  328. 'duration': 33,
  329. },
  330. 'params': {
  331. 'skip_download': True,
  332. },
  333. },
  334. # MPD from http://dash-mse-test.appspot.com/media.html
  335. {
  336. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  337. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  338. 'info_dict': {
  339. 'id': 'car-20120827-manifest',
  340. 'ext': 'mp4',
  341. 'title': 'car-20120827-manifest',
  342. 'formats': 'mincount:9',
  343. 'upload_date': '20130904',
  344. },
  345. 'params': {
  346. 'format': 'bestvideo',
  347. },
  348. },
  349. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  350. {
  351. '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',
  352. 'info_dict': {
  353. 'id': 'content',
  354. 'ext': 'mp4',
  355. 'title': 'content',
  356. 'formats': 'mincount:8',
  357. },
  358. 'params': {
  359. # m3u8 downloads
  360. 'skip_download': True,
  361. },
  362. 'skip': 'video gone',
  363. },
  364. # m3u8 served with Content-Type: text/plain
  365. {
  366. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  367. 'info_dict': {
  368. 'id': 'index',
  369. 'ext': 'mp4',
  370. 'title': 'index',
  371. 'upload_date': '20140720',
  372. 'formats': 'mincount:11',
  373. },
  374. 'params': {
  375. # m3u8 downloads
  376. 'skip_download': True,
  377. },
  378. 'skip': 'video gone',
  379. },
  380. # google redirect
  381. {
  382. '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',
  383. 'info_dict': {
  384. 'id': 'cmQHVoWB5FY',
  385. 'ext': 'mp4',
  386. 'upload_date': '20130224',
  387. 'uploader_id': 'TheVerge',
  388. 'description': r're:^Chris Ziegler takes a look at the\.*',
  389. 'uploader': 'The Verge',
  390. 'title': 'First Firefox OS phones side-by-side',
  391. },
  392. 'params': {
  393. 'skip_download': False,
  394. }
  395. },
  396. {
  397. # redirect in Refresh HTTP header
  398. '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',
  399. 'info_dict': {
  400. 'id': 'pO8h3EaFRdo',
  401. 'ext': 'mp4',
  402. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  403. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  404. 'upload_date': '20150917',
  405. 'uploader_id': 'brtvofficial',
  406. 'uploader': 'Boiler Room',
  407. },
  408. 'params': {
  409. 'skip_download': False,
  410. },
  411. },
  412. {
  413. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  414. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  415. 'info_dict': {
  416. 'id': '13601338388002',
  417. 'ext': 'mp4',
  418. 'uploader': 'www.hodiho.fr',
  419. 'title': 'R\u00e9gis plante sa Jeep',
  420. }
  421. },
  422. # bandcamp page with custom domain
  423. {
  424. 'add_ie': ['Bandcamp'],
  425. 'url': 'http://bronyrock.com/track/the-pony-mash',
  426. 'info_dict': {
  427. 'id': '3235767654',
  428. 'ext': 'mp3',
  429. 'title': 'The Pony Mash',
  430. 'uploader': 'M_Pallante',
  431. },
  432. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  433. },
  434. {
  435. # embedded brightcove video
  436. # it also tests brightcove videos that need to set the 'Referer'
  437. # in the http requests
  438. 'add_ie': ['BrightcoveLegacy'],
  439. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  440. 'info_dict': {
  441. 'id': '2765128793001',
  442. 'ext': 'mp4',
  443. 'title': 'Le cours de bourse : l’analyse technique',
  444. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  445. 'uploader': 'BFM BUSINESS',
  446. },
  447. 'params': {
  448. 'skip_download': True,
  449. },
  450. },
  451. {
  452. # embedded with itemprop embedURL and video id spelled as `idVideo`
  453. 'add_id': ['BrightcoveLegacy'],
  454. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  455. 'info_dict': {
  456. 'id': '5255628253001',
  457. 'ext': 'mp4',
  458. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  459. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  460. 'uploader': 'BFM BUSINESS',
  461. 'uploader_id': '876450612001',
  462. 'timestamp': 1482255315,
  463. 'upload_date': '20161220',
  464. },
  465. 'params': {
  466. 'skip_download': True,
  467. },
  468. },
  469. {
  470. # https://github.com/ytdl-org/youtube-dl/issues/2253
  471. 'url': 'http://bcove.me/i6nfkrc3',
  472. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  473. 'info_dict': {
  474. 'id': '3101154703001',
  475. 'ext': 'mp4',
  476. 'title': 'Still no power',
  477. 'uploader': 'thestar.com',
  478. '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.',
  479. },
  480. 'add_ie': ['BrightcoveLegacy'],
  481. 'skip': 'video gone',
  482. },
  483. {
  484. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  485. 'md5': 'fb973ecf6e4a78a67453647444222983',
  486. 'info_dict': {
  487. 'id': '3414141473001',
  488. 'ext': 'mp4',
  489. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  490. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  491. 'uploader': 'Championat',
  492. },
  493. },
  494. {
  495. # https://github.com/ytdl-org/youtube-dl/issues/3541
  496. 'add_ie': ['BrightcoveLegacy'],
  497. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  498. 'info_dict': {
  499. 'id': '3866516442001',
  500. 'ext': 'mp4',
  501. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  502. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  503. 'uploader': 'SBS Broadcasting',
  504. },
  505. 'skip': 'Restricted to Netherlands',
  506. 'params': {
  507. 'skip_download': True, # m3u8 download
  508. },
  509. },
  510. {
  511. # Brightcove video in <iframe>
  512. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  513. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  514. 'info_dict': {
  515. 'id': '5360463607001',
  516. 'ext': 'mp4',
  517. 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
  518. 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
  519. 'uploader': 'United Nations',
  520. 'uploader_id': '1362235914001',
  521. 'timestamp': 1489593889,
  522. 'upload_date': '20170315',
  523. },
  524. 'add_ie': ['BrightcoveLegacy'],
  525. },
  526. {
  527. # Brightcove with alternative playerID key
  528. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  529. 'info_dict': {
  530. 'id': 'nmeth.2062_SV1',
  531. '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',
  532. },
  533. 'playlist': [{
  534. 'info_dict': {
  535. 'id': '2228375078001',
  536. 'ext': 'mp4',
  537. 'title': 'nmeth.2062-sv1',
  538. 'description': 'nmeth.2062-sv1',
  539. 'timestamp': 1363357591,
  540. 'upload_date': '20130315',
  541. 'uploader': 'Nature Publishing Group',
  542. 'uploader_id': '1964492299001',
  543. },
  544. }],
  545. },
  546. {
  547. # Brightcove with UUID in videoPlayer
  548. 'url': 'http://www8.hp.com/cn/zh/home.html',
  549. 'info_dict': {
  550. 'id': '5255815316001',
  551. 'ext': 'mp4',
  552. 'title': 'Sprocket Video - China',
  553. 'description': 'Sprocket Video - China',
  554. 'uploader': 'HP-Video Gallery',
  555. 'timestamp': 1482263210,
  556. 'upload_date': '20161220',
  557. 'uploader_id': '1107601872001',
  558. },
  559. 'params': {
  560. 'skip_download': True, # m3u8 download
  561. },
  562. 'skip': 'video rotates...weekly?',
  563. },
  564. {
  565. # Brightcove:new type [2].
  566. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  567. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  568. 'info_dict': {
  569. 'id': '5348741021001',
  570. 'ext': 'mp4',
  571. 'upload_date': '20170306',
  572. 'uploader_id': '4191638492001',
  573. 'timestamp': 1488769918,
  574. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  575. },
  576. },
  577. {
  578. # Alternative brightcove <video> attributes
  579. 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
  580. 'info_dict': {
  581. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  582. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  583. },
  584. 'playlist': [{
  585. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  586. 'info_dict': {
  587. 'id': '5311302538001',
  588. 'ext': 'mp4',
  589. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  590. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  591. 'timestamp': 1486321708,
  592. 'upload_date': '20170205',
  593. 'uploader_id': '800000640001',
  594. },
  595. 'only_matching': True,
  596. }],
  597. },
  598. {
  599. # Brightcove with UUID in videoPlayer
  600. 'url': 'http://www8.hp.com/cn/zh/home.html',
  601. 'info_dict': {
  602. 'id': '5255815316001',
  603. 'ext': 'mp4',
  604. 'title': 'Sprocket Video - China',
  605. 'description': 'Sprocket Video - China',
  606. 'uploader': 'HP-Video Gallery',
  607. 'timestamp': 1482263210,
  608. 'upload_date': '20161220',
  609. 'uploader_id': '1107601872001',
  610. },
  611. 'params': {
  612. 'skip_download': True, # m3u8 download
  613. },
  614. },
  615. # ooyala video
  616. {
  617. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  618. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  619. 'info_dict': {
  620. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  621. 'ext': 'mp4',
  622. 'title': '2cc213299525360.mov', # that's what we get
  623. 'duration': 238.231,
  624. },
  625. 'add_ie': ['Ooyala'],
  626. },
  627. {
  628. # ooyala video embedded with http://player.ooyala.com/iframe.js
  629. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  630. 'info_dict': {
  631. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  632. 'ext': 'mp4',
  633. 'title': '"Steve Jobs: Man in the Machine" trailer',
  634. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  635. 'duration': 135.427,
  636. },
  637. 'params': {
  638. 'skip_download': True,
  639. },
  640. 'skip': 'movie expired',
  641. },
  642. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  643. {
  644. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  645. 'info_dict': {
  646. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  647. 'ext': 'mp4',
  648. 'title': 'Steampunk Fest Comes to Honesdale',
  649. 'duration': 43.276,
  650. },
  651. 'params': {
  652. 'skip_download': True,
  653. }
  654. },
  655. # embed.ly video
  656. {
  657. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  658. 'info_dict': {
  659. 'id': '9ODmcdjQcHQ',
  660. 'ext': 'mp4',
  661. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  662. 'upload_date': '20140225',
  663. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  664. 'uploader': 'Tested',
  665. 'uploader_id': 'testedcom',
  666. },
  667. # No need to test YoutubeIE here
  668. 'params': {
  669. 'skip_download': True,
  670. },
  671. },
  672. # funnyordie embed
  673. {
  674. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  675. 'info_dict': {
  676. 'id': '18e820ec3f',
  677. 'ext': 'mp4',
  678. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  679. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  680. },
  681. # HEAD requests lead to endless 301, while GET is OK
  682. 'expected_warnings': ['301'],
  683. },
  684. # RUTV embed
  685. {
  686. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  687. 'info_dict': {
  688. 'id': '776940',
  689. 'ext': 'mp4',
  690. 'title': 'Охотское море стало целиком российским',
  691. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  692. },
  693. 'params': {
  694. # m3u8 download
  695. 'skip_download': True,
  696. },
  697. },
  698. # TVC embed
  699. {
  700. '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/',
  701. 'info_dict': {
  702. 'id': '55304',
  703. 'ext': 'mp4',
  704. 'title': 'Дошкольное воспитание',
  705. },
  706. },
  707. # SportBox embed
  708. {
  709. 'url': 'http://www.vestifinance.ru/articles/25753',
  710. 'info_dict': {
  711. 'id': '25753',
  712. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  713. },
  714. 'playlist': [{
  715. 'info_dict': {
  716. 'id': '370908',
  717. 'title': 'Госзаказ. День 3',
  718. 'ext': 'mp4',
  719. }
  720. }, {
  721. 'info_dict': {
  722. 'id': '370905',
  723. 'title': 'Госзаказ. День 2',
  724. 'ext': 'mp4',
  725. }
  726. }, {
  727. 'info_dict': {
  728. 'id': '370902',
  729. 'title': 'Госзаказ. День 1',
  730. 'ext': 'mp4',
  731. }
  732. }],
  733. 'params': {
  734. # m3u8 download
  735. 'skip_download': True,
  736. },
  737. },
  738. # Myvi.ru embed
  739. {
  740. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  741. 'info_dict': {
  742. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  743. 'ext': 'mp4',
  744. 'title': 'Ужастики, русский трейлер (2015)',
  745. 'thumbnail': r're:^https?://.*\.jpg$',
  746. 'duration': 153,
  747. }
  748. },
  749. # XHamster embed
  750. {
  751. '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',
  752. 'info_dict': {
  753. 'id': 'showthread',
  754. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  755. },
  756. 'playlist_mincount': 7,
  757. # This forum does not allow <iframe> syntaxes anymore
  758. # Now HTML tags are displayed as-is
  759. 'skip': 'No videos on this page',
  760. },
  761. # Embedded TED video
  762. {
  763. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  764. 'md5': '65fdff94098e4a607385a60c5177c638',
  765. 'info_dict': {
  766. 'id': '1969',
  767. 'ext': 'mp4',
  768. 'title': 'Hidden miracles of the natural world',
  769. 'uploader': 'Louie Schwartzberg',
  770. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  771. }
  772. },
  773. # nowvideo embed hidden behind percent encoding
  774. {
  775. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  776. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  777. 'info_dict': {
  778. 'id': '06e53103ca9aa',
  779. 'ext': 'flv',
  780. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  781. 'description': 'No description',
  782. },
  783. },
  784. # arte embed
  785. {
  786. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  787. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  788. 'info_dict': {
  789. 'id': '048195-004_PLUS7-F',
  790. 'ext': 'flv',
  791. 'title': 'X:enius',
  792. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  793. 'upload_date': '20140320',
  794. },
  795. 'params': {
  796. 'skip_download': 'Requires rtmpdump'
  797. },
  798. 'skip': 'video gone',
  799. },
  800. # francetv embed
  801. {
  802. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  803. 'info_dict': {
  804. 'id': 'EV_30231',
  805. 'ext': 'mp4',
  806. 'title': 'Alcaline, le concert avec Calogero',
  807. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  808. 'upload_date': '20150226',
  809. 'timestamp': 1424989860,
  810. 'duration': 5400,
  811. },
  812. 'params': {
  813. # m3u8 downloads
  814. 'skip_download': True,
  815. },
  816. 'expected_warnings': [
  817. 'Forbidden'
  818. ]
  819. },
  820. # Condé Nast embed
  821. {
  822. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  823. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  824. 'info_dict': {
  825. 'id': '53501be369702d3275860000',
  826. 'ext': 'mp4',
  827. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  828. }
  829. },
  830. # Dailymotion embed
  831. {
  832. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  833. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  834. 'info_dict': {
  835. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  836. 'ext': 'mp4',
  837. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  838. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  839. 'uploader': 'Spi0n',
  840. 'uploader_id': 'xgditw',
  841. 'upload_date': '20140425',
  842. 'timestamp': 1398441542,
  843. },
  844. 'add_ie': ['Dailymotion'],
  845. },
  846. # DailyMail embed
  847. {
  848. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  849. 'info_dict': {
  850. 'id': '1495629',
  851. 'ext': 'mp4',
  852. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  853. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  854. },
  855. 'add_ie': ['DailyMail'],
  856. 'params': {
  857. 'skip_download': True,
  858. },
  859. },
  860. # YouTube embed
  861. {
  862. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  863. 'info_dict': {
  864. 'id': 'FXRb4ykk4S0',
  865. 'ext': 'mp4',
  866. 'title': 'The NBL Auction 2014',
  867. 'uploader': 'BADMINTON England',
  868. 'uploader_id': 'BADMINTONEvents',
  869. 'upload_date': '20140603',
  870. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  871. },
  872. 'add_ie': ['Youtube'],
  873. 'params': {
  874. 'skip_download': True,
  875. }
  876. },
  877. # MTVServices embed
  878. {
  879. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  880. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  881. 'info_dict': {
  882. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  883. 'ext': 'mp4',
  884. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  885. 'description': 'Two valets share their love for movie star Liam Neesons.',
  886. 'timestamp': 1349922600,
  887. 'upload_date': '20121011',
  888. },
  889. },
  890. # YouTube embed via <data-embed-url="">
  891. {
  892. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  893. 'info_dict': {
  894. 'id': '4vAffPZIT44',
  895. 'ext': 'mp4',
  896. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  897. 'uploader': 'Gameloft',
  898. 'uploader_id': 'gameloft',
  899. 'upload_date': '20140828',
  900. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  901. },
  902. 'params': {
  903. 'skip_download': True,
  904. }
  905. },
  906. # YouTube <object> embed
  907. {
  908. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  909. 'md5': '516718101ec834f74318df76259fb3cc',
  910. 'info_dict': {
  911. 'id': 'msN87y-iEx0',
  912. 'ext': 'webm',
  913. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  914. 'upload_date': '20080526',
  915. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  916. 'uploader': 'Christopher Sykes',
  917. 'uploader_id': 'ChristopherJSykes',
  918. },
  919. 'add_ie': ['Youtube'],
  920. },
  921. # Camtasia studio
  922. {
  923. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  924. 'playlist': [{
  925. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  926. 'info_dict': {
  927. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  928. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  929. 'ext': 'flv',
  930. 'duration': 2235.90,
  931. }
  932. }, {
  933. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  934. 'info_dict': {
  935. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  936. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  937. 'ext': 'flv',
  938. 'duration': 2235.93,
  939. }
  940. }],
  941. 'info_dict': {
  942. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  943. }
  944. },
  945. # Flowplayer
  946. {
  947. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  948. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  949. 'info_dict': {
  950. 'id': '5123ea6d5e5a7',
  951. 'ext': 'mp4',
  952. 'age_limit': 18,
  953. 'uploader': 'www.handjobhub.com',
  954. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  955. }
  956. },
  957. # Multiple brightcove videos
  958. # https://github.com/ytdl-org/youtube-dl/issues/2283
  959. {
  960. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  961. 'info_dict': {
  962. 'id': 'always-never',
  963. 'title': 'Always / Never - The New Yorker',
  964. },
  965. 'playlist_count': 3,
  966. 'params': {
  967. 'extract_flat': False,
  968. 'skip_download': True,
  969. }
  970. },
  971. # MLB embed
  972. {
  973. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  974. 'md5': '96f09a37e44da40dd083e12d9a683327',
  975. 'info_dict': {
  976. 'id': '33322633',
  977. 'ext': 'mp4',
  978. 'title': 'Ump changes call to ball',
  979. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  980. 'duration': 48,
  981. 'timestamp': 1401537900,
  982. 'upload_date': '20140531',
  983. 'thumbnail': r're:^https?://.*\.jpg$',
  984. },
  985. },
  986. # Wistia embed
  987. {
  988. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  989. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  990. 'info_dict': {
  991. 'id': '6e2wtrbdaf',
  992. 'ext': 'mov',
  993. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  994. 'description': 'a Paywall Videos video from Remilon',
  995. 'duration': 644.072,
  996. 'uploader': 'study.com',
  997. 'timestamp': 1459678540,
  998. 'upload_date': '20160403',
  999. 'filesize': 24687186,
  1000. },
  1001. },
  1002. {
  1003. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  1004. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  1005. 'info_dict': {
  1006. 'id': 'uxjb0lwrcz',
  1007. 'ext': 'mp4',
  1008. 'title': 'Conversation about Hexagonal Rails Part 1',
  1009. 'description': 'a Martin Fowler video from ThoughtWorks',
  1010. 'duration': 1715.0,
  1011. 'uploader': 'thoughtworks.wistia.com',
  1012. 'timestamp': 1401832161,
  1013. 'upload_date': '20140603',
  1014. },
  1015. },
  1016. # Wistia standard embed (async)
  1017. {
  1018. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  1019. 'info_dict': {
  1020. 'id': '807fafadvk',
  1021. 'ext': 'mp4',
  1022. 'title': 'Drip Brennan Dunn Workshop',
  1023. 'description': 'a JV Webinars video from getdrip-1',
  1024. 'duration': 4986.95,
  1025. 'timestamp': 1463607249,
  1026. 'upload_date': '20160518',
  1027. },
  1028. 'params': {
  1029. 'skip_download': True,
  1030. }
  1031. },
  1032. # Soundcloud embed
  1033. {
  1034. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  1035. 'info_dict': {
  1036. 'id': '174391317',
  1037. 'ext': 'mp3',
  1038. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  1039. 'uploader': 'Sophos Security',
  1040. 'title': 'Chet Chat 171 - Oct 29, 2014',
  1041. 'upload_date': '20141029',
  1042. }
  1043. },
  1044. # Soundcloud multiple embeds
  1045. {
  1046. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1047. 'info_dict': {
  1048. 'id': '52809',
  1049. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1050. },
  1051. 'playlist_mincount': 7,
  1052. },
  1053. # TuneIn station embed
  1054. {
  1055. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1056. 'info_dict': {
  1057. 'id': '204146',
  1058. 'ext': 'mp3',
  1059. 'title': 'CNRV',
  1060. 'location': 'Paris, France',
  1061. 'is_live': True,
  1062. },
  1063. 'params': {
  1064. # Live stream
  1065. 'skip_download': True,
  1066. },
  1067. },
  1068. # Livestream embed
  1069. {
  1070. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1071. 'info_dict': {
  1072. 'id': '67864563',
  1073. 'ext': 'flv',
  1074. 'upload_date': '20141112',
  1075. 'title': 'Rosetta #CometLanding webcast HL 10',
  1076. }
  1077. },
  1078. # Another Livestream embed, without 'new.' in URL
  1079. {
  1080. 'url': 'https://www.freespeech.org/',
  1081. 'info_dict': {
  1082. 'id': '123537347',
  1083. 'ext': 'mp4',
  1084. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1085. },
  1086. 'params': {
  1087. # Live stream
  1088. 'skip_download': True,
  1089. },
  1090. },
  1091. # LazyYT
  1092. {
  1093. 'url': 'https://skiplagged.com/',
  1094. 'info_dict': {
  1095. 'id': 'skiplagged',
  1096. 'title': 'Skiplagged: The smart way to find cheap flights',
  1097. },
  1098. 'playlist_mincount': 1,
  1099. 'add_ie': ['Youtube'],
  1100. },
  1101. # Cinchcast embed
  1102. {
  1103. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1104. 'info_dict': {
  1105. 'id': '7141703',
  1106. 'ext': 'mp3',
  1107. 'upload_date': '20141126',
  1108. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1109. }
  1110. },
  1111. # Cinerama player
  1112. {
  1113. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1114. 'info_dict': {
  1115. 'id': '730m_DandD_1901_512k',
  1116. 'ext': 'mp4',
  1117. 'uploader': 'www.abc.net.au',
  1118. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1119. }
  1120. },
  1121. # embedded viddler video
  1122. {
  1123. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1124. 'info_dict': {
  1125. 'id': '4d03aad9',
  1126. 'ext': 'mp4',
  1127. 'uploader': 'deadspin',
  1128. 'title': 'WALL-TO-GORTAT',
  1129. 'timestamp': 1422285291,
  1130. 'upload_date': '20150126',
  1131. },
  1132. 'add_ie': ['Viddler'],
  1133. },
  1134. # Libsyn embed
  1135. {
  1136. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1137. 'info_dict': {
  1138. 'id': '3377616',
  1139. 'ext': 'mp3',
  1140. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1141. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1142. 'upload_date': '20150220',
  1143. },
  1144. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1145. },
  1146. # jwplayer YouTube
  1147. {
  1148. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1149. 'info_dict': {
  1150. 'id': 'Mrj4DVp2zeA',
  1151. 'ext': 'mp4',
  1152. 'upload_date': '20150212',
  1153. 'uploader': 'The National Archives UK',
  1154. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1155. 'uploader_id': 'NationalArchives08',
  1156. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1157. },
  1158. },
  1159. # jwplayer rtmp
  1160. {
  1161. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1162. 'info_dict': {
  1163. 'id': 'live',
  1164. 'ext': 'flv',
  1165. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1166. 'uploader': 'www.suffolk.edu',
  1167. },
  1168. 'params': {
  1169. 'skip_download': True,
  1170. },
  1171. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1172. },
  1173. # Complex jwplayer
  1174. {
  1175. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1176. 'info_dict': {
  1177. 'id': 'videos',
  1178. 'ext': 'mp4',
  1179. 'title': 'king machine trailer 1',
  1180. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1181. 'thumbnail': r're:^https?://.*\.jpg$',
  1182. },
  1183. },
  1184. {
  1185. # JWPlayer config passed as variable
  1186. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1187. 'info_dict': {
  1188. 'id': '3326530_hq',
  1189. 'ext': 'mp4',
  1190. 'title': 'ARIELE | Tube Cup',
  1191. 'uploader': 'www.txxx.com',
  1192. 'age_limit': 18,
  1193. },
  1194. 'params': {
  1195. 'skip_download': True,
  1196. }
  1197. },
  1198. {
  1199. # JWPlatform iframe
  1200. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1201. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1202. 'info_dict': {
  1203. 'id': 'O0c5JcKT',
  1204. 'ext': 'mp4',
  1205. 'upload_date': '20171122',
  1206. 'timestamp': 1511366290,
  1207. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1208. },
  1209. 'add_ie': [JWPlatformIE.ie_key()],
  1210. },
  1211. {
  1212. # Video.js embed, multiple formats
  1213. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1214. 'info_dict': {
  1215. 'id': 'yygqldloqIk',
  1216. 'ext': 'mp4',
  1217. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1218. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1219. 'upload_date': '20130314',
  1220. 'uploader': 'PROстое3D',
  1221. 'uploader_id': 'PROstoe3D',
  1222. },
  1223. 'params': {
  1224. 'skip_download': True,
  1225. },
  1226. },
  1227. {
  1228. # Video.js embed, single format
  1229. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1230. 'info_dict': {
  1231. 'id': 'watch',
  1232. 'ext': 'mp4',
  1233. 'title': 'Step 1 - Good Foundation',
  1234. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1235. },
  1236. 'params': {
  1237. 'skip_download': True,
  1238. },
  1239. },
  1240. # rtl.nl embed
  1241. {
  1242. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1243. 'playlist_mincount': 5,
  1244. 'info_dict': {
  1245. 'id': 'aanslagen-kopenhagen',
  1246. 'title': 'Aanslagen Kopenhagen',
  1247. }
  1248. },
  1249. # Zapiks embed
  1250. {
  1251. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1252. 'info_dict': {
  1253. 'id': '118046',
  1254. 'ext': 'mp4',
  1255. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1256. }
  1257. },
  1258. # Kaltura embed (different embed code)
  1259. {
  1260. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1261. 'info_dict': {
  1262. 'id': '1_a52wc67y',
  1263. 'ext': 'flv',
  1264. 'upload_date': '20150127',
  1265. 'uploader_id': 'PremierMedia',
  1266. 'timestamp': int,
  1267. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1268. },
  1269. },
  1270. # Kaltura embed with single quotes
  1271. {
  1272. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1273. 'info_dict': {
  1274. 'id': '0_izeg5utt',
  1275. 'ext': 'mp4',
  1276. 'title': '35871',
  1277. 'timestamp': 1355743100,
  1278. 'upload_date': '20121217',
  1279. 'uploader_id': 'cplapp@learn360.com',
  1280. },
  1281. 'add_ie': ['Kaltura'],
  1282. },
  1283. {
  1284. # Kaltura embedded via quoted entry_id
  1285. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1286. 'info_dict': {
  1287. 'id': '0_utuok90b',
  1288. 'ext': 'mp4',
  1289. 'title': '06_matthew_brender_raj_dutt',
  1290. 'timestamp': 1466638791,
  1291. 'upload_date': '20160622',
  1292. },
  1293. 'add_ie': ['Kaltura'],
  1294. 'expected_warnings': [
  1295. 'Could not send HEAD request'
  1296. ],
  1297. 'params': {
  1298. 'skip_download': True,
  1299. }
  1300. },
  1301. {
  1302. # Kaltura embedded, some fileExt broken (#11480)
  1303. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1304. 'info_dict': {
  1305. 'id': '1_sgtvehim',
  1306. 'ext': 'mp4',
  1307. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1308. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1309. 'timestamp': 1321158993,
  1310. 'upload_date': '20111113',
  1311. 'uploader_id': 'kps1',
  1312. },
  1313. 'add_ie': ['Kaltura'],
  1314. },
  1315. {
  1316. # Kaltura iframe embed
  1317. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1318. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1319. 'info_dict': {
  1320. 'id': '0_f2cfbpwy',
  1321. 'ext': 'mp4',
  1322. 'title': 'I. M. Pei: A Centennial Celebration',
  1323. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1324. 'upload_date': '20170403',
  1325. 'uploader_id': 'batchUser',
  1326. 'timestamp': 1491232186,
  1327. },
  1328. 'add_ie': ['Kaltura'],
  1329. },
  1330. {
  1331. # Kaltura iframe embed, more sophisticated
  1332. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1333. 'info_dict': {
  1334. 'id': '1_9gzouybz',
  1335. 'ext': 'mp4',
  1336. 'title': 'lecture-05sep2017',
  1337. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1338. 'upload_date': '20170913',
  1339. 'uploader_id': 'eps2',
  1340. 'timestamp': 1505340777,
  1341. },
  1342. 'params': {
  1343. 'skip_download': True,
  1344. },
  1345. 'add_ie': ['Kaltura'],
  1346. },
  1347. {
  1348. # meta twitter:player
  1349. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1350. 'info_dict': {
  1351. 'id': '0_01b42zps',
  1352. 'ext': 'mp4',
  1353. 'title': 'Main Twerk (Video)',
  1354. 'upload_date': '20171208',
  1355. 'uploader_id': 'sebastian.salinas@thechive.com',
  1356. 'timestamp': 1512713057,
  1357. },
  1358. 'params': {
  1359. 'skip_download': True,
  1360. },
  1361. 'add_ie': ['Kaltura'],
  1362. },
  1363. # referrer protected EaglePlatform embed
  1364. {
  1365. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1366. 'info_dict': {
  1367. 'id': '582306',
  1368. 'ext': 'mp4',
  1369. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1370. 'thumbnail': r're:^https?://.*\.jpg$',
  1371. 'duration': 3382,
  1372. 'view_count': int,
  1373. },
  1374. 'params': {
  1375. 'skip_download': True,
  1376. },
  1377. },
  1378. # ClipYou (EaglePlatform) embed (custom URL)
  1379. {
  1380. 'url': 'http://muz-tv.ru/play/7129/',
  1381. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1382. 'info_dict': {
  1383. 'id': '12820',
  1384. 'ext': 'mp4',
  1385. 'title': "'O Sole Mio",
  1386. 'thumbnail': r're:^https?://.*\.jpg$',
  1387. 'duration': 216,
  1388. 'view_count': int,
  1389. },
  1390. 'params': {
  1391. 'skip_download': True,
  1392. },
  1393. 'skip': 'This video is unavailable.',
  1394. },
  1395. # Pladform embed
  1396. {
  1397. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1398. 'info_dict': {
  1399. 'id': '100183293',
  1400. 'ext': 'mp4',
  1401. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1402. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1403. 'thumbnail': r're:^https?://.*\.jpg$',
  1404. 'duration': 694,
  1405. 'age_limit': 0,
  1406. },
  1407. 'skip': 'HTTP Error 404: Not Found',
  1408. },
  1409. # Playwire embed
  1410. {
  1411. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1412. 'info_dict': {
  1413. 'id': '3519514',
  1414. 'ext': 'mp4',
  1415. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1416. 'thumbnail': r're:^https?://.*\.png$',
  1417. 'duration': 45.115,
  1418. },
  1419. },
  1420. # 5min embed
  1421. {
  1422. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1423. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1424. 'info_dict': {
  1425. 'id': '518726732',
  1426. 'ext': 'mp4',
  1427. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1428. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1429. 'timestamp': 1427237531,
  1430. 'uploader': 'Crunch Report',
  1431. 'upload_date': '20150324',
  1432. },
  1433. 'params': {
  1434. # m3u8 download
  1435. 'skip_download': True,
  1436. },
  1437. },
  1438. # Crooks and Liars embed
  1439. {
  1440. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1441. 'info_dict': {
  1442. 'id': '8RUoRhRi',
  1443. 'ext': 'mp4',
  1444. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1445. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1446. 'timestamp': 1428207000,
  1447. 'upload_date': '20150405',
  1448. 'uploader': 'Heather',
  1449. },
  1450. },
  1451. # Crooks and Liars external embed
  1452. {
  1453. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1454. 'info_dict': {
  1455. 'id': 'MTE3MjUtMzQ2MzA',
  1456. 'ext': 'mp4',
  1457. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1458. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1459. 'timestamp': 1265032391,
  1460. 'upload_date': '20100201',
  1461. 'uploader': 'Heather',
  1462. },
  1463. },
  1464. # NBC Sports vplayer embed
  1465. {
  1466. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1467. 'info_dict': {
  1468. 'id': 'ln7x1qSThw4k',
  1469. 'ext': 'flv',
  1470. 'title': "PFT Live: New leader in the 'new-look' defense",
  1471. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1472. 'uploader': 'NBCU-SPORTS',
  1473. 'upload_date': '20140107',
  1474. 'timestamp': 1389118457,
  1475. },
  1476. 'skip': 'Invalid Page URL',
  1477. },
  1478. # NBC News embed
  1479. {
  1480. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1481. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1482. 'info_dict': {
  1483. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1484. 'ext': 'mp4',
  1485. 'title': 'David Letterman: A Preview',
  1486. '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.',
  1487. 'upload_date': '20160609',
  1488. 'timestamp': 1465431544,
  1489. 'uploader': 'NBCU-NEWS',
  1490. },
  1491. },
  1492. # UDN embed
  1493. {
  1494. 'url': 'https://video.udn.com/news/300346',
  1495. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1496. 'info_dict': {
  1497. 'id': '300346',
  1498. 'ext': 'mp4',
  1499. 'title': '中一中男師變性 全校師生力挺',
  1500. 'thumbnail': r're:^https?://.*\.jpg$',
  1501. },
  1502. 'params': {
  1503. # m3u8 download
  1504. 'skip_download': True,
  1505. },
  1506. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1507. },
  1508. # Brightcove URL in single quotes
  1509. {
  1510. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1511. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1512. 'info_dict': {
  1513. 'id': '4255764656001',
  1514. 'ext': 'mp4',
  1515. 'title': 'SN Presents: Russell Martin, World Citizen',
  1516. 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
  1517. 'uploader': 'Rogers Sportsnet',
  1518. 'uploader_id': '1704050871',
  1519. 'upload_date': '20150525',
  1520. 'timestamp': 1432570283,
  1521. },
  1522. },
  1523. # Kinja embed
  1524. {
  1525. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1526. 'info_dict': {
  1527. 'id': '106351',
  1528. 'ext': 'mp4',
  1529. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1530. 'description': 'Migrated from OnionStudios',
  1531. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1532. 'uploader': 'clickhole',
  1533. 'upload_date': '20150527',
  1534. 'timestamp': 1432744860,
  1535. }
  1536. },
  1537. # SnagFilms embed
  1538. {
  1539. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1540. 'info_dict': {
  1541. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1542. 'ext': 'mp4',
  1543. 'title': '#whilewewatch',
  1544. }
  1545. },
  1546. # AdobeTVVideo embed
  1547. {
  1548. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1549. 'md5': '43662b577c018ad707a63766462b1e87',
  1550. 'info_dict': {
  1551. 'id': '2456',
  1552. 'ext': 'mp4',
  1553. 'title': 'New experience with Acrobat DC',
  1554. 'description': 'New experience with Acrobat DC',
  1555. 'duration': 248.667,
  1556. },
  1557. },
  1558. # BrightcoveInPageEmbed embed
  1559. {
  1560. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1561. 'info_dict': {
  1562. 'id': '4238694884001',
  1563. 'ext': 'flv',
  1564. 'title': 'Tabletop: Dread, Last Thoughts',
  1565. 'description': 'Tabletop: Dread, Last Thoughts',
  1566. 'duration': 51690,
  1567. },
  1568. },
  1569. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1570. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1571. {
  1572. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1573. 'info_dict': {
  1574. 'id': '4785848093001',
  1575. 'ext': 'mp4',
  1576. 'title': 'The Cardinal Pell Interview',
  1577. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1578. 'uploader': 'GlobeCast Australia - GlobeStream',
  1579. 'uploader_id': '2733773828001',
  1580. 'upload_date': '20160304',
  1581. 'timestamp': 1457083087,
  1582. },
  1583. 'params': {
  1584. # m3u8 downloads
  1585. 'skip_download': True,
  1586. },
  1587. },
  1588. {
  1589. # Brightcove embed with whitespace around attribute names
  1590. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1591. 'info_dict': {
  1592. 'id': '3167554373001',
  1593. 'ext': 'mp4',
  1594. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1595. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1596. 'uploader_id': '1079349493',
  1597. 'upload_date': '20140207',
  1598. 'timestamp': 1391810548,
  1599. },
  1600. 'params': {
  1601. 'skip_download': True,
  1602. },
  1603. },
  1604. # Another form of arte.tv embed
  1605. {
  1606. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1607. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1608. 'info_dict': {
  1609. 'id': '030273-562_PLUS7-F',
  1610. 'ext': 'mp4',
  1611. 'title': 'ARTE Reportage - Nulle part, en France',
  1612. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1613. 'upload_date': '20160409',
  1614. },
  1615. },
  1616. # LiveLeak embed
  1617. {
  1618. 'url': 'http://www.wykop.pl/link/3088787/',
  1619. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1620. 'info_dict': {
  1621. 'id': '874_1459135191',
  1622. 'ext': 'mp4',
  1623. 'title': 'Man shows poor quality of new apartment building',
  1624. 'description': 'The wall is like a sand pile.',
  1625. 'uploader': 'Lake8737',
  1626. },
  1627. 'add_ie': [LiveLeakIE.ie_key()],
  1628. },
  1629. # Another LiveLeak embed pattern (#13336)
  1630. {
  1631. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1632. 'info_dict': {
  1633. 'id': '2eb_1496309988',
  1634. 'ext': 'mp4',
  1635. 'title': 'Thief robs place where everyone was armed',
  1636. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1637. 'uploader': 'brazilwtf',
  1638. },
  1639. 'add_ie': [LiveLeakIE.ie_key()],
  1640. },
  1641. # Duplicated embedded video URLs
  1642. {
  1643. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1644. 'info_dict': {
  1645. 'id': '149298443_480_16c25b74_2',
  1646. 'ext': 'mp4',
  1647. 'title': 'vs. Blue Orange Spring Game',
  1648. 'uploader': 'www.hudl.com',
  1649. },
  1650. },
  1651. # twitter:player:stream embed
  1652. {
  1653. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1654. 'info_dict': {
  1655. 'id': 'master',
  1656. 'ext': 'mp4',
  1657. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1658. 'uploader': 'www.rtl.be',
  1659. },
  1660. 'params': {
  1661. # m3u8 downloads
  1662. 'skip_download': True,
  1663. },
  1664. },
  1665. # twitter:player embed
  1666. {
  1667. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1668. 'md5': 'a3e0df96369831de324f0778e126653c',
  1669. 'info_dict': {
  1670. 'id': '4909620399001',
  1671. 'ext': 'mp4',
  1672. 'title': 'What Do Black Holes Sound Like?',
  1673. 'description': 'what do black holes sound like',
  1674. 'upload_date': '20160524',
  1675. 'uploader_id': '29913724001',
  1676. 'timestamp': 1464107587,
  1677. 'uploader': 'TheAtlantic',
  1678. },
  1679. 'add_ie': ['BrightcoveLegacy'],
  1680. },
  1681. # Facebook <iframe> embed
  1682. {
  1683. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1684. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1685. 'info_dict': {
  1686. 'id': '599637780109885',
  1687. 'ext': 'mp4',
  1688. 'title': 'Facebook video #599637780109885',
  1689. },
  1690. },
  1691. # Facebook <iframe> embed, plugin video
  1692. {
  1693. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1694. 'info_dict': {
  1695. 'id': '1754168231264132',
  1696. 'ext': 'mp4',
  1697. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1698. 'uploader': 'Tariq Ramadan (official)',
  1699. 'timestamp': 1496758379,
  1700. 'upload_date': '20170606',
  1701. },
  1702. 'params': {
  1703. 'skip_download': True,
  1704. },
  1705. },
  1706. # Facebook API embed
  1707. {
  1708. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1709. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1710. 'info_dict': {
  1711. 'id': '10153467542406923',
  1712. 'ext': 'mp4',
  1713. 'title': 'Facebook video #10153467542406923',
  1714. },
  1715. },
  1716. # Wordpress "YouTube Video Importer" plugin
  1717. {
  1718. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1719. 'md5': 'd16797741b560b485194eddda8121b48',
  1720. 'info_dict': {
  1721. 'id': 'HNTXWDXV9Is',
  1722. 'ext': 'mp4',
  1723. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1724. 'upload_date': '20160627',
  1725. 'uploader_id': 'GENOCIDE8GENERAL10',
  1726. 'uploader': 'cylus cyrus',
  1727. },
  1728. },
  1729. {
  1730. # video stored on custom kaltura server
  1731. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1732. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1733. 'info_dict': {
  1734. 'id': '0_1iotm5bh',
  1735. 'ext': 'mp4',
  1736. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1737. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1738. 'uploader_id': 'videos.expansion@el-mundo.net',
  1739. 'upload_date': '20150429',
  1740. 'timestamp': 1430303472,
  1741. },
  1742. 'add_ie': ['Kaltura'],
  1743. },
  1744. {
  1745. # multiple kaltura embeds, nsfw
  1746. 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
  1747. 'info_dict': {
  1748. 'id': 'kamila-avec-video-jaime-sadomie',
  1749. 'title': "Kamila avec vídeo “J'aime sadomie”",
  1750. },
  1751. 'playlist_count': 8,
  1752. },
  1753. {
  1754. # Non-standard Vimeo embed
  1755. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1756. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1757. 'info_dict': {
  1758. 'id': '148867247',
  1759. 'ext': 'mp4',
  1760. 'title': 'Understanding the web - Teaser',
  1761. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1762. 'upload_date': '20151214',
  1763. 'uploader': 'OpenClassrooms',
  1764. 'uploader_id': 'openclassrooms',
  1765. },
  1766. 'add_ie': ['Vimeo'],
  1767. },
  1768. {
  1769. # generic vimeo embed that requires original URL passed as Referer
  1770. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1771. 'only_matching': True,
  1772. },
  1773. {
  1774. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1775. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1776. 'info_dict': {
  1777. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1778. 'ext': 'mp4',
  1779. 'title': 'Big Buck Bunny',
  1780. 'description': 'Royalty free test video',
  1781. 'timestamp': 1432816365,
  1782. 'upload_date': '20150528',
  1783. 'is_live': False,
  1784. },
  1785. 'params': {
  1786. 'skip_download': True,
  1787. },
  1788. 'add_ie': [ArkenaIE.ie_key()],
  1789. },
  1790. {
  1791. '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/',
  1792. 'info_dict': {
  1793. 'id': '1c7141f46c',
  1794. 'ext': 'mp4',
  1795. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1796. },
  1797. 'params': {
  1798. 'skip_download': True,
  1799. },
  1800. 'add_ie': [Vbox7IE.ie_key()],
  1801. },
  1802. {
  1803. # DBTV embeds
  1804. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1805. 'info_dict': {
  1806. 'id': '43254897',
  1807. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1808. },
  1809. 'playlist_mincount': 3,
  1810. },
  1811. {
  1812. # Videa embeds
  1813. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1814. 'info_dict': {
  1815. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1816. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1817. },
  1818. 'playlist_mincount': 2,
  1819. },
  1820. {
  1821. # 20 minuten embed
  1822. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1823. 'info_dict': {
  1824. 'id': '523629',
  1825. 'ext': 'mp4',
  1826. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1827. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1828. },
  1829. 'params': {
  1830. 'skip_download': True,
  1831. },
  1832. 'add_ie': [TwentyMinutenIE.ie_key()],
  1833. },
  1834. {
  1835. # VideoPress embed
  1836. 'url': 'https://en.support.wordpress.com/videopress/',
  1837. 'info_dict': {
  1838. 'id': 'OcobLTqC',
  1839. 'ext': 'm4v',
  1840. 'title': 'IMG_5786',
  1841. 'timestamp': 1435711927,
  1842. 'upload_date': '20150701',
  1843. },
  1844. 'params': {
  1845. 'skip_download': True,
  1846. },
  1847. 'add_ie': [VideoPressIE.ie_key()],
  1848. },
  1849. {
  1850. # Rutube embed
  1851. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1852. 'info_dict': {
  1853. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1854. 'ext': 'flv',
  1855. 'title': 'Магаззино: Казань 2',
  1856. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1857. 'uploader': 'Магаззино',
  1858. 'upload_date': '20170228',
  1859. 'uploader_id': '996642',
  1860. },
  1861. 'params': {
  1862. 'skip_download': True,
  1863. },
  1864. 'add_ie': [RutubeIE.ie_key()],
  1865. },
  1866. {
  1867. # ThePlatform embedded with whitespaces in URLs
  1868. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1869. 'only_matching': True,
  1870. },
  1871. {
  1872. # Senate ISVP iframe https
  1873. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1874. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1875. 'info_dict': {
  1876. 'id': 'govtaff020316',
  1877. 'ext': 'mp4',
  1878. 'title': 'Integrated Senate Video Player',
  1879. },
  1880. 'add_ie': [SenateISVPIE.ie_key()],
  1881. },
  1882. {
  1883. # Limelight embeds (1 channel embed + 4 media embeds)
  1884. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1885. 'info_dict': {
  1886. 'id': 'FacilitatorTraining2017',
  1887. 'title': 'Facilitator Training 2017',
  1888. },
  1889. 'playlist_mincount': 5,
  1890. },
  1891. {
  1892. # Limelight embed (LimelightPlayerUtil.embed)
  1893. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1894. 'info_dict': {
  1895. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1896. 'ext': 'mp4',
  1897. 'title': '07448641',
  1898. 'timestamp': 1499890639,
  1899. 'upload_date': '20170712',
  1900. },
  1901. 'params': {
  1902. 'skip_download': True,
  1903. },
  1904. 'add_ie': ['LimelightMedia'],
  1905. },
  1906. {
  1907. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1908. 'info_dict': {
  1909. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1910. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1911. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1912. },
  1913. 'playlist_mincount': 4,
  1914. },
  1915. {
  1916. # WashingtonPost embed
  1917. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1918. 'info_dict': {
  1919. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1920. 'ext': 'mp4',
  1921. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1922. 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
  1923. 'timestamp': 1455216756,
  1924. 'uploader': 'The Washington Post',
  1925. 'upload_date': '20160211',
  1926. },
  1927. 'add_ie': [WashingtonPostIE.ie_key()],
  1928. },
  1929. {
  1930. # Mediaset embed
  1931. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1932. 'info_dict': {
  1933. 'id': '720642',
  1934. 'ext': 'mp4',
  1935. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1936. },
  1937. 'params': {
  1938. 'skip_download': True,
  1939. },
  1940. 'add_ie': [MediasetIE.ie_key()],
  1941. },
  1942. {
  1943. # JOJ.sk embeds
  1944. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1945. 'info_dict': {
  1946. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1947. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1948. },
  1949. 'playlist_mincount': 5,
  1950. 'add_ie': [JojIE.ie_key()],
  1951. },
  1952. {
  1953. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1954. 'url': 'https://tvrain.ru/amp/418921/',
  1955. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1956. 'info_dict': {
  1957. 'id': '418921',
  1958. 'ext': 'mp4',
  1959. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1960. },
  1961. },
  1962. {
  1963. # vzaar embed
  1964. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1965. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1966. 'info_dict': {
  1967. 'id': '8707641',
  1968. 'ext': 'mp4',
  1969. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1970. },
  1971. },
  1972. {
  1973. # multiple HTML5 videos on one page
  1974. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1975. 'info_dict': {
  1976. 'id': 'keyscenarios',
  1977. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1978. },
  1979. 'playlist_count': 4,
  1980. },
  1981. {
  1982. # vshare embed
  1983. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1984. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1985. 'info_dict': {
  1986. 'id': '0f64ce6',
  1987. 'title': 'vl14062007715967',
  1988. 'ext': 'mp4',
  1989. }
  1990. },
  1991. {
  1992. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1993. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1994. 'info_dict': {
  1995. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1996. 'ext': 'mp4',
  1997. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1998. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1999. 'timestamp': 1474354800,
  2000. 'upload_date': '20160920',
  2001. }
  2002. },
  2003. {
  2004. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  2005. 'info_dict': {
  2006. 'id': '1731611',
  2007. 'ext': 'mp4',
  2008. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  2009. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  2010. 'timestamp': 1516100691,
  2011. 'upload_date': '20180116',
  2012. },
  2013. 'params': {
  2014. 'skip_download': True,
  2015. },
  2016. 'add_ie': [SpringboardPlatformIE.ie_key()],
  2017. },
  2018. {
  2019. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  2020. 'info_dict': {
  2021. 'id': 'uPDB5I9wfp8',
  2022. 'ext': 'webm',
  2023. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  2024. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  2025. 'upload_date': '20160219',
  2026. 'uploader': 'Pocoyo - Português (BR)',
  2027. 'uploader_id': 'PocoyoBrazil',
  2028. },
  2029. 'add_ie': [YoutubeIE.ie_key()],
  2030. 'params': {
  2031. 'skip_download': True,
  2032. },
  2033. },
  2034. {
  2035. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  2036. 'info_dict': {
  2037. 'id': 'vMDE4NzI1Mjgt690b',
  2038. 'ext': 'mp4',
  2039. 'title': 'Котята',
  2040. },
  2041. 'add_ie': [YapFilesIE.ie_key()],
  2042. 'params': {
  2043. 'skip_download': True,
  2044. },
  2045. },
  2046. {
  2047. # CloudflareStream embed
  2048. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  2049. 'info_dict': {
  2050. 'id': '31c9291ab41fac05471db4e73aa11717',
  2051. 'ext': 'mp4',
  2052. 'title': '31c9291ab41fac05471db4e73aa11717',
  2053. },
  2054. 'add_ie': [CloudflareStreamIE.ie_key()],
  2055. 'params': {
  2056. 'skip_download': True,
  2057. },
  2058. },
  2059. {
  2060. # PeerTube embed
  2061. 'url': 'https://joinpeertube.org/fr/home/',
  2062. 'info_dict': {
  2063. 'id': 'home',
  2064. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2065. },
  2066. 'playlist_count': 2,
  2067. },
  2068. {
  2069. # Indavideo embed
  2070. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2071. 'info_dict': {
  2072. 'id': '1693903',
  2073. 'ext': 'mp4',
  2074. 'title': 'Így kell otthon hamburgert sütni',
  2075. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2076. 'timestamp': 1426330212,
  2077. 'upload_date': '20150314',
  2078. 'uploader': 'StreetKitchen',
  2079. 'uploader_id': '546363',
  2080. },
  2081. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2082. 'params': {
  2083. 'skip_download': True,
  2084. },
  2085. },
  2086. {
  2087. # APA embed via JWPlatform embed
  2088. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2089. 'info_dict': {
  2090. 'id': 'jjv85FdZ',
  2091. 'ext': 'mp4',
  2092. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2093. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2094. 'thumbnail': r're:^https?://.*\.jpg$',
  2095. 'duration': 254,
  2096. 'timestamp': 1519211149,
  2097. 'upload_date': '20180221',
  2098. },
  2099. 'params': {
  2100. 'skip_download': True,
  2101. },
  2102. },
  2103. {
  2104. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2105. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2106. 'info_dict': {
  2107. 'id': '83645793',
  2108. 'title': 'Lock up and get excited',
  2109. 'ext': 'mp4'
  2110. },
  2111. 'skip': 'TODO: fix nested playlists processing in tests',
  2112. },
  2113. {
  2114. # Viqeo embeds
  2115. 'url': 'https://viqeo.tv/',
  2116. 'info_dict': {
  2117. 'id': 'viqeo',
  2118. 'title': 'All-new video platform',
  2119. },
  2120. 'playlist_count': 6,
  2121. },
  2122. {
  2123. # Squarespace video embed, 2019-08-28
  2124. 'url': 'http://ootboxford.com',
  2125. 'info_dict': {
  2126. 'id': 'Tc7b_JGdZfw',
  2127. 'title': 'Out of the Blue, at Childish Things 10',
  2128. 'ext': 'mp4',
  2129. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2130. 'uploader_id': 'helendouglashouse',
  2131. 'uploader': 'Helen & Douglas House',
  2132. 'upload_date': '20140328',
  2133. },
  2134. 'params': {
  2135. 'skip_download': True,
  2136. },
  2137. },
  2138. # {
  2139. # # Zype embed
  2140. # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2141. # 'info_dict': {
  2142. # 'id': '5b400b834b32992a310622b9',
  2143. # 'ext': 'mp4',
  2144. # 'title': 'Smoky Barbecue Favorites',
  2145. # 'thumbnail': r're:^https?://.*\.jpe?g',
  2146. # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  2147. # 'upload_date': '20170909',
  2148. # 'timestamp': 1504915200,
  2149. # },
  2150. # 'add_ie': [ZypeIE.ie_key()],
  2151. # 'params': {
  2152. # 'skip_download': True,
  2153. # },
  2154. # },
  2155. {
  2156. # videojs embed
  2157. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2158. 'info_dict': {
  2159. 'id': 'shell',
  2160. 'ext': 'mp4',
  2161. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2162. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2163. 'thumbnail': r're:^https?://.*\.jpg$',
  2164. },
  2165. 'params': {
  2166. 'skip_download': True,
  2167. },
  2168. 'expected_warnings': ['Failed to download MPD manifest'],
  2169. },
  2170. {
  2171. # DailyMotion embed with DM.player
  2172. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2173. 'info_dict': {
  2174. 'id': 'k6aKkGHd9FJs4mtJN39',
  2175. 'ext': 'mp4',
  2176. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2177. 'description': 'This video is private.',
  2178. 'uploader_id': 'x1jf30l',
  2179. 'uploader': 'beIN SPORTS USA',
  2180. 'upload_date': '20190528',
  2181. 'timestamp': 1559062971,
  2182. },
  2183. 'params': {
  2184. 'skip_download': True,
  2185. },
  2186. },
  2187. # {
  2188. # # TODO: find another test
  2189. # # http://schema.org/VideoObject
  2190. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2191. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2192. # 'info_dict': {
  2193. # 'id': 'nyvTSJMKId',
  2194. # 'ext': 'mp4',
  2195. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2196. # 'description': '#love for cats.',
  2197. # 'timestamp': 1461244995,
  2198. # 'upload_date': '20160421',
  2199. # },
  2200. # 'params': {
  2201. # 'force_generic_extractor': True,
  2202. # },
  2203. # }
  2204. ]
  2205. def report_following_redirect(self, new_url):
  2206. """Report information extraction."""
  2207. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2208. def _extract_rss(self, url, video_id, doc):
  2209. playlist_title = doc.find('./channel/title').text
  2210. playlist_desc_el = doc.find('./channel/description')
  2211. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2212. NS_MAP = {
  2213. 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
  2214. }
  2215. entries = []
  2216. for it in doc.findall('./channel/item'):
  2217. next_url = None
  2218. enclosure_nodes = it.findall('./enclosure')
  2219. for e in enclosure_nodes:
  2220. next_url = e.attrib.get('url')
  2221. if next_url:
  2222. break
  2223. if not next_url:
  2224. next_url = xpath_text(it, 'link', fatal=False)
  2225. if not next_url:
  2226. continue
  2227. def itunes(key):
  2228. return xpath_text(
  2229. it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
  2230. default=None)
  2231. duration = itunes('duration')
  2232. explicit = itunes('explicit')
  2233. if explicit == 'true':
  2234. age_limit = 18
  2235. elif explicit == 'false':
  2236. age_limit = 0
  2237. else:
  2238. age_limit = None
  2239. entries.append({
  2240. '_type': 'url_transparent',
  2241. 'url': next_url,
  2242. 'title': it.find('title').text,
  2243. 'description': xpath_text(it, 'description', default=None),
  2244. 'timestamp': unified_timestamp(
  2245. xpath_text(it, 'pubDate', default=None)),
  2246. 'duration': int_or_none(duration) or parse_duration(duration),
  2247. 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
  2248. 'episode': itunes('title'),
  2249. 'episode_number': int_or_none(itunes('episode')),
  2250. 'season_number': int_or_none(itunes('season')),
  2251. 'age_limit': age_limit,
  2252. })
  2253. return {
  2254. '_type': 'playlist',
  2255. 'id': url,
  2256. 'title': playlist_title,
  2257. 'description': playlist_desc,
  2258. 'entries': entries,
  2259. }
  2260. def _extract_camtasia(self, url, video_id, webpage):
  2261. """ Returns None if no camtasia video can be found. """
  2262. camtasia_cfg = self._search_regex(
  2263. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2264. webpage, 'camtasia configuration file', default=None)
  2265. if camtasia_cfg is None:
  2266. return None
  2267. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2268. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2269. camtasia_cfg = self._download_xml(
  2270. camtasia_url, video_id,
  2271. note='Downloading camtasia configuration',
  2272. errnote='Failed to download camtasia configuration')
  2273. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2274. entries = []
  2275. for n in fileset_node.getchildren():
  2276. url_n = n.find('./uri')
  2277. if url_n is None:
  2278. continue
  2279. entries.append({
  2280. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2281. 'title': '%s - %s' % (title, n.tag),
  2282. 'url': compat_urlparse.urljoin(url, url_n.text),
  2283. 'duration': float_or_none(n.find('./duration').text),
  2284. })
  2285. return {
  2286. '_type': 'playlist',
  2287. 'entries': entries,
  2288. 'title': title,
  2289. }
  2290. def _real_extract(self, url):
  2291. if url.startswith('//'):
  2292. return self.url_result(self.http_scheme() + url)
  2293. parsed_url = compat_urlparse.urlparse(url)
  2294. if not parsed_url.scheme:
  2295. default_search = self._downloader.params.get('default_search')
  2296. if default_search is None:
  2297. default_search = 'fixup_error'
  2298. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2299. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2300. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2301. return self.url_result('http://' + url)
  2302. elif default_search != 'fixup_error':
  2303. if default_search == 'auto_warning':
  2304. if re.match(r'^(?:url|URL)$', url):
  2305. raise ExtractorError(
  2306. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2307. expected=True)
  2308. else:
  2309. self._downloader.report_warning(
  2310. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2311. return self.url_result('ytsearch:' + url)
  2312. if default_search in ('error', 'fixup_error'):
  2313. raise ExtractorError(
  2314. '%r is not a valid URL. '
  2315. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2316. % (url, url), expected=True)
  2317. else:
  2318. if ':' not in default_search:
  2319. default_search += ':'
  2320. return self.url_result(default_search + url)
  2321. url, smuggled_data = unsmuggle_url(url)
  2322. force_videoid = None
  2323. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2324. if smuggled_data and 'force_videoid' in smuggled_data:
  2325. force_videoid = smuggled_data['force_videoid']
  2326. video_id = force_videoid
  2327. else:
  2328. video_id = self._generic_id(url)
  2329. self.to_screen('%s: Requesting header' % video_id)
  2330. head_req = HEADRequest(url)
  2331. head_response = self._request_webpage(
  2332. head_req, video_id,
  2333. note=False, errnote='Could not send HEAD request to %s' % url,
  2334. fatal=False)
  2335. if head_response is not False:
  2336. # Check for redirect
  2337. new_url = head_response.geturl()
  2338. if url != new_url:
  2339. self.report_following_redirect(new_url)
  2340. if force_videoid:
  2341. new_url = smuggle_url(
  2342. new_url, {'force_videoid': force_videoid})
  2343. return self.url_result(new_url)
  2344. full_response = None
  2345. if head_response is False:
  2346. request = sanitized_Request(url)
  2347. request.add_header('Accept-Encoding', '*')
  2348. full_response = self._request_webpage(request, video_id)
  2349. head_response = full_response
  2350. info_dict = {
  2351. 'id': video_id,
  2352. 'title': self._generic_title(url),
  2353. 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
  2354. }
  2355. # Check for direct link to a video
  2356. content_type = head_response.headers.get('Content-Type', '').lower()
  2357. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2358. if m:
  2359. format_id = compat_str(m.group('format_id'))
  2360. if format_id.endswith('mpegurl'):
  2361. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2362. elif format_id == 'f4m':
  2363. formats = self._extract_f4m_formats(url, video_id)
  2364. else:
  2365. formats = [{
  2366. 'format_id': format_id,
  2367. 'url': url,
  2368. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2369. }]
  2370. info_dict['direct'] = True
  2371. self._sort_formats(formats)
  2372. info_dict['formats'] = formats
  2373. return info_dict
  2374. if not self._downloader.params.get('test', False) and not is_intentional:
  2375. force = self._downloader.params.get('force_generic_extractor', False)
  2376. self._downloader.report_warning(
  2377. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2378. if not full_response:
  2379. request = sanitized_Request(url)
  2380. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2381. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2382. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2383. # that will always result in downloading the whole file that is not desirable.
  2384. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2385. # to accept raw bytes and being able to download only a chunk.
  2386. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2387. # after HEAD request finishes, but not sure if we can rely on this.
  2388. request.add_header('Accept-Encoding', '*')
  2389. full_response = self._request_webpage(request, video_id)
  2390. first_bytes = full_response.read(512)
  2391. # Is it an M3U playlist?
  2392. if first_bytes.startswith(b'#EXTM3U'):
  2393. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2394. self._sort_formats(info_dict['formats'])
  2395. return info_dict
  2396. # Maybe it's a direct link to a video?
  2397. # Be careful not to download the whole thing!
  2398. if not is_html(first_bytes):
  2399. self._downloader.report_warning(
  2400. 'URL could be a direct video link, returning it as such.')
  2401. info_dict.update({
  2402. 'direct': True,
  2403. 'url': url,
  2404. })
  2405. return info_dict
  2406. webpage = self._webpage_read_content(
  2407. full_response, url, video_id, prefix=first_bytes)
  2408. self.report_extraction(video_id)
  2409. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2410. try:
  2411. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2412. if doc.tag == 'rss':
  2413. return self._extract_rss(url, video_id, doc)
  2414. elif doc.tag == 'SmoothStreamingMedia':
  2415. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2416. self._sort_formats(info_dict['formats'])
  2417. return info_dict
  2418. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2419. smil = self._parse_smil(doc, url, video_id)
  2420. self._sort_formats(smil['formats'])
  2421. return smil
  2422. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2423. return self.playlist_result(
  2424. self._parse_xspf(
  2425. doc, video_id, xspf_url=url,
  2426. xspf_base_url=full_response.geturl()),
  2427. video_id)
  2428. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2429. info_dict['formats'] = self._parse_mpd_formats(
  2430. doc,
  2431. mpd_base_url=full_response.geturl().rpartition('/')[0],
  2432. mpd_url=url)
  2433. self._sort_formats(info_dict['formats'])
  2434. return info_dict
  2435. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2436. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2437. self._sort_formats(info_dict['formats'])
  2438. return info_dict
  2439. except compat_xml_parse_error:
  2440. pass
  2441. # Is it a Camtasia project?
  2442. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2443. if camtasia_res is not None:
  2444. return camtasia_res
  2445. # Sometimes embedded video player is hidden behind percent encoding
  2446. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2447. # Unescaping the whole page allows to handle those cases in a generic way
  2448. # FIXME: unescaping the whole page may break URLs, commenting out for now.
  2449. # There probably should be a second run of generic extractor on unescaped webpage.
  2450. # webpage = compat_urllib_parse_unquote(webpage)
  2451. # Unescape squarespace embeds to be detected by generic extractor,
  2452. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2453. webpage = re.sub(
  2454. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2455. lambda x: unescapeHTML(x.group(0)), webpage)
  2456. # it's tempting to parse this further, but you would
  2457. # have to take into account all the variations like
  2458. # Video Title - Site Name
  2459. # Site Name | Video Title
  2460. # Video Title - Tagline | Site Name
  2461. # and so on and so forth; it's just not practical
  2462. video_title = self._og_search_title(
  2463. webpage, default=None) or self._html_search_regex(
  2464. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2465. default='video')
  2466. # Try to detect age limit automatically
  2467. age_limit = self._rta_search(webpage)
  2468. # And then there are the jokers who advertise that they use RTA,
  2469. # but actually don't.
  2470. AGE_LIMIT_MARKERS = [
  2471. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2472. ]
  2473. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2474. age_limit = 18
  2475. # video uploader is domain name
  2476. video_uploader = self._search_regex(
  2477. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2478. video_description = self._og_search_description(webpage, default=None)
  2479. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2480. info_dict.update({
  2481. 'title': video_title,
  2482. 'description': video_description,
  2483. 'thumbnail': video_thumbnail,
  2484. 'age_limit': age_limit,
  2485. })
  2486. # Look for Brightcove Legacy Studio embeds
  2487. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2488. if bc_urls:
  2489. entries = [{
  2490. '_type': 'url',
  2491. 'url': smuggle_url(bc_url, {'Referer': url}),
  2492. 'ie_key': 'BrightcoveLegacy'
  2493. } for bc_url in bc_urls]
  2494. return {
  2495. '_type': 'playlist',
  2496. 'title': video_title,
  2497. 'id': video_id,
  2498. 'entries': entries,
  2499. }
  2500. # Look for Brightcove New Studio embeds
  2501. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2502. if bc_urls:
  2503. return self.playlist_from_matches(
  2504. bc_urls, video_id, video_title,
  2505. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2506. ie='BrightcoveNew')
  2507. # Look for Nexx embeds
  2508. nexx_urls = NexxIE._extract_urls(webpage)
  2509. if nexx_urls:
  2510. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2511. # Look for Nexx iFrame embeds
  2512. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2513. if nexx_embed_urls:
  2514. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2515. # Look for ThePlatform embeds
  2516. tp_urls = ThePlatformIE._extract_urls(webpage)
  2517. if tp_urls:
  2518. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2519. # Look for embedded rtl.nl player
  2520. matches = re.findall(
  2521. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2522. webpage)
  2523. if matches:
  2524. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2525. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2526. if vimeo_urls:
  2527. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2528. vid_me_embed_url = self._search_regex(
  2529. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2530. webpage, 'vid.me embed', default=None)
  2531. if vid_me_embed_url is not None:
  2532. return self.url_result(vid_me_embed_url, 'Vidme')
  2533. # Look for YouTube embeds
  2534. youtube_urls = YoutubeIE._extract_urls(webpage)
  2535. if youtube_urls:
  2536. return self.playlist_from_matches(
  2537. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2538. matches = DailymotionIE._extract_urls(webpage)
  2539. if matches:
  2540. return self.playlist_from_matches(matches, video_id, video_title)
  2541. # Look for embedded Dailymotion playlist player (#3822)
  2542. m = re.search(
  2543. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2544. if m:
  2545. playlists = re.findall(
  2546. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2547. if playlists:
  2548. return self.playlist_from_matches(
  2549. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2550. # Look for DailyMail embeds
  2551. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2552. if dailymail_urls:
  2553. return self.playlist_from_matches(
  2554. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2555. # Look for Teachable embeds, must be before Wistia
  2556. teachable_url = TeachableIE._extract_url(webpage, url)
  2557. if teachable_url:
  2558. return self.url_result(teachable_url)
  2559. # Look for embedded Wistia player
  2560. wistia_urls = WistiaIE._extract_urls(webpage)
  2561. if wistia_urls:
  2562. playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
  2563. for entry in playlist['entries']:
  2564. entry.update({
  2565. '_type': 'url_transparent',
  2566. 'uploader': video_uploader,
  2567. })
  2568. return playlist
  2569. # Look for SVT player
  2570. svt_url = SVTIE._extract_url(webpage)
  2571. if svt_url:
  2572. return self.url_result(svt_url, 'SVT')
  2573. # Look for Bandcamp pages with custom domain
  2574. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2575. if mobj is not None:
  2576. burl = unescapeHTML(mobj.group(1))
  2577. # Don't set the extractor because it can be a track url or an album
  2578. return self.url_result(burl)
  2579. # Look for embedded Vevo player
  2580. mobj = re.search(
  2581. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2582. if mobj is not None:
  2583. return self.url_result(mobj.group('url'))
  2584. # Look for embedded Viddler player
  2585. mobj = re.search(
  2586. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2587. webpage)
  2588. if mobj is not None:
  2589. return self.url_result(mobj.group('url'))
  2590. # Look for NYTimes player
  2591. mobj = re.search(
  2592. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2593. webpage)
  2594. if mobj is not None:
  2595. return self.url_result(mobj.group('url'))
  2596. # Look for Libsyn player
  2597. mobj = re.search(
  2598. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2599. if mobj is not None:
  2600. return self.url_result(mobj.group('url'))
  2601. # Look for Ooyala videos
  2602. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2603. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2604. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2605. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2606. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2607. if mobj is not None:
  2608. embed_token = self._search_regex(
  2609. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2610. webpage, 'ooyala embed token', default=None)
  2611. return OoyalaIE._build_url_result(smuggle_url(
  2612. mobj.group('ec'), {
  2613. 'domain': url,
  2614. 'embed_token': embed_token,
  2615. }))
  2616. # Look for multiple Ooyala embeds on SBN network websites
  2617. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2618. if mobj is not None:
  2619. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2620. if embeds:
  2621. return self.playlist_from_matches(
  2622. embeds, video_id, video_title,
  2623. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2624. # Look for Aparat videos
  2625. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2626. if mobj is not None:
  2627. return self.url_result(mobj.group(1), 'Aparat')
  2628. # Look for MPORA videos
  2629. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2630. if mobj is not None:
  2631. return self.url_result(mobj.group(1), 'Mpora')
  2632. # Look for embedded Facebook player
  2633. facebook_urls = FacebookIE._extract_urls(webpage)
  2634. if facebook_urls:
  2635. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2636. # Look for embedded VK player
  2637. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2638. if mobj is not None:
  2639. return self.url_result(mobj.group('url'), 'VK')
  2640. # Look for embedded Odnoklassniki player
  2641. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2642. if odnoklassniki_url:
  2643. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2644. # Look for embedded ivi player
  2645. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2646. if mobj is not None:
  2647. return self.url_result(mobj.group('url'), 'Ivi')
  2648. # Look for embedded Huffington Post player
  2649. mobj = re.search(
  2650. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2651. if mobj is not None:
  2652. return self.url_result(mobj.group('url'), 'HuffPost')
  2653. # Look for embed.ly
  2654. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2655. if mobj is not None:
  2656. return self.url_result(mobj.group('url'))
  2657. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2658. if mobj is not None:
  2659. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2660. # Look for funnyordie embed
  2661. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2662. if matches:
  2663. return self.playlist_from_matches(
  2664. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2665. # Look for BBC iPlayer embed
  2666. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2667. if matches:
  2668. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2669. # Look for embedded RUTV player
  2670. rutv_url = RUTVIE._extract_url(webpage)
  2671. if rutv_url:
  2672. return self.url_result(rutv_url, 'RUTV')
  2673. # Look for embedded TVC player
  2674. tvc_url = TVCIE._extract_url(webpage)
  2675. if tvc_url:
  2676. return self.url_result(tvc_url, 'TVC')
  2677. # Look for embedded SportBox player
  2678. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2679. if sportbox_urls:
  2680. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2681. # Look for embedded XHamster player
  2682. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2683. if xhamster_urls:
  2684. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2685. # Look for embedded TNAFlixNetwork player
  2686. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2687. if tnaflix_urls:
  2688. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2689. # Look for embedded PornHub player
  2690. pornhub_urls = PornHubIE._extract_urls(webpage)
  2691. if pornhub_urls:
  2692. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2693. # Look for embedded DrTuber player
  2694. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2695. if drtuber_urls:
  2696. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2697. # Look for embedded RedTube player
  2698. redtube_urls = RedTubeIE._extract_urls(webpage)
  2699. if redtube_urls:
  2700. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2701. # Look for embedded Tube8 player
  2702. tube8_urls = Tube8IE._extract_urls(webpage)
  2703. if tube8_urls:
  2704. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2705. # Look for embedded Mofosex player
  2706. mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
  2707. if mofosex_urls:
  2708. return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
  2709. # Look for embedded Spankwire player
  2710. spankwire_urls = SpankwireIE._extract_urls(webpage)
  2711. if spankwire_urls:
  2712. return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
  2713. # Look for embedded YouPorn player
  2714. youporn_urls = YouPornIE._extract_urls(webpage)
  2715. if youporn_urls:
  2716. return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
  2717. # Look for embedded Tvigle player
  2718. mobj = re.search(
  2719. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2720. if mobj is not None:
  2721. return self.url_result(mobj.group('url'), 'Tvigle')
  2722. # Look for embedded TED player
  2723. mobj = re.search(
  2724. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2725. if mobj is not None:
  2726. return self.url_result(mobj.group('url'), 'TED')
  2727. # Look for embedded Ustream videos
  2728. ustream_url = UstreamIE._extract_url(webpage)
  2729. if ustream_url:
  2730. return self.url_result(ustream_url, UstreamIE.ie_key())
  2731. # Look for embedded arte.tv player
  2732. arte_urls = ArteTVEmbedIE._extract_urls(webpage)
  2733. if arte_urls:
  2734. return self.playlist_from_matches(arte_urls, video_id, video_title)
  2735. # Look for embedded francetv player
  2736. mobj = re.search(
  2737. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2738. webpage)
  2739. if mobj is not None:
  2740. return self.url_result(mobj.group('url'))
  2741. # Look for embedded Myvi.ru player
  2742. myvi_url = MyviIE._extract_url(webpage)
  2743. if myvi_url:
  2744. return self.url_result(myvi_url)
  2745. # Look for embedded soundcloud player
  2746. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2747. if soundcloud_urls:
  2748. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2749. # Look for tunein player
  2750. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2751. if tunein_urls:
  2752. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2753. # Look for embedded mtvservices player
  2754. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2755. if mtvservices_url:
  2756. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2757. # Look for embedded yahoo player
  2758. mobj = re.search(
  2759. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2760. webpage)
  2761. if mobj is not None:
  2762. return self.url_result(mobj.group('url'), 'Yahoo')
  2763. # Look for embedded sbs.com.au player
  2764. mobj = re.search(
  2765. r'''(?x)
  2766. (?:
  2767. <meta\s+property="og:video"\s+content=|
  2768. <iframe[^>]+?src=
  2769. )
  2770. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2771. webpage)
  2772. if mobj is not None:
  2773. return self.url_result(mobj.group('url'), 'SBS')
  2774. # Look for embedded Cinchcast player
  2775. mobj = re.search(
  2776. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2777. webpage)
  2778. if mobj is not None:
  2779. return self.url_result(mobj.group('url'), 'Cinchcast')
  2780. mobj = re.search(
  2781. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2782. webpage)
  2783. if not mobj:
  2784. mobj = re.search(
  2785. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2786. webpage)
  2787. if mobj is not None:
  2788. return self.url_result(mobj.group('url'), 'MLB')
  2789. mobj = re.search(
  2790. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2791. webpage)
  2792. if mobj is not None:
  2793. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2794. mobj = re.search(
  2795. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2796. webpage)
  2797. if mobj is not None:
  2798. return self.url_result(mobj.group('url'), 'Livestream')
  2799. # Look for Zapiks embed
  2800. mobj = re.search(
  2801. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2802. if mobj is not None:
  2803. return self.url_result(mobj.group('url'), 'Zapiks')
  2804. # Look for Kaltura embeds
  2805. kaltura_urls = KalturaIE._extract_urls(webpage)
  2806. if kaltura_urls:
  2807. return self.playlist_from_matches(
  2808. kaltura_urls, video_id, video_title,
  2809. getter=lambda x: smuggle_url(x, {'source_url': url}),
  2810. ie=KalturaIE.ie_key())
  2811. # Look for EaglePlatform embeds
  2812. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2813. if eagleplatform_url:
  2814. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2815. # Look for ClipYou (uses EaglePlatform) embeds
  2816. mobj = re.search(
  2817. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2818. if mobj is not None:
  2819. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2820. # Look for Pladform embeds
  2821. pladform_url = PladformIE._extract_url(webpage)
  2822. if pladform_url:
  2823. return self.url_result(pladform_url)
  2824. # Look for Videomore embeds
  2825. videomore_url = VideomoreIE._extract_url(webpage)
  2826. if videomore_url:
  2827. return self.url_result(videomore_url)
  2828. # Look for Webcaster embeds
  2829. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2830. if webcaster_url:
  2831. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2832. # Look for Playwire embeds
  2833. mobj = re.search(
  2834. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2835. if mobj is not None:
  2836. return self.url_result(mobj.group('url'))
  2837. # Look for 5min embeds
  2838. mobj = re.search(
  2839. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2840. if mobj is not None:
  2841. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2842. # Look for Crooks and Liars embeds
  2843. mobj = re.search(
  2844. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2845. if mobj is not None:
  2846. return self.url_result(mobj.group('url'))
  2847. # Look for NBC Sports VPlayer embeds
  2848. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2849. if nbc_sports_url:
  2850. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2851. # Look for NBC News embeds
  2852. nbc_news_embed_url = re.search(
  2853. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2854. if nbc_news_embed_url:
  2855. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2856. # Look for Google Drive embeds
  2857. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2858. if google_drive_url:
  2859. return self.url_result(google_drive_url, 'GoogleDrive')
  2860. # Look for UDN embeds
  2861. mobj = re.search(
  2862. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2863. if mobj is not None:
  2864. return self.url_result(
  2865. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2866. # Look for Senate ISVP iframe
  2867. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2868. if senate_isvp_url:
  2869. return self.url_result(senate_isvp_url, 'SenateISVP')
  2870. # Look for Kinja embeds
  2871. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  2872. if kinja_embed_urls:
  2873. return self.playlist_from_matches(
  2874. kinja_embed_urls, video_id, video_title)
  2875. # Look for OnionStudios embeds
  2876. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2877. if onionstudios_url:
  2878. return self.url_result(onionstudios_url)
  2879. # Look for ViewLift embeds
  2880. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2881. if viewlift_url:
  2882. return self.url_result(viewlift_url)
  2883. # Look for JWPlatform embeds
  2884. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2885. if jwplatform_urls:
  2886. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2887. # Look for Digiteka embeds
  2888. digiteka_url = DigitekaIE._extract_url(webpage)
  2889. if digiteka_url:
  2890. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2891. # Look for Arkena embeds
  2892. arkena_url = ArkenaIE._extract_url(webpage)
  2893. if arkena_url:
  2894. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2895. # Look for Piksel embeds
  2896. piksel_url = PikselIE._extract_url(webpage)
  2897. if piksel_url:
  2898. return self.url_result(piksel_url, PikselIE.ie_key())
  2899. # Look for Limelight embeds
  2900. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2901. if limelight_urls:
  2902. return self.playlist_result(
  2903. limelight_urls, video_id, video_title, video_description)
  2904. # Look for Anvato embeds
  2905. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2906. if anvato_urls:
  2907. return self.playlist_result(
  2908. anvato_urls, video_id, video_title, video_description)
  2909. # Look for AdobeTVVideo embeds
  2910. mobj = re.search(
  2911. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2912. webpage)
  2913. if mobj is not None:
  2914. return self.url_result(
  2915. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2916. 'AdobeTVVideo')
  2917. # Look for Vine embeds
  2918. mobj = re.search(
  2919. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2920. webpage)
  2921. if mobj is not None:
  2922. return self.url_result(
  2923. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2924. # Look for VODPlatform embeds
  2925. mobj = re.search(
  2926. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
  2927. webpage)
  2928. if mobj is not None:
  2929. return self.url_result(
  2930. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2931. # Look for Mangomolo embeds
  2932. mobj = re.search(
  2933. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  2934. (?:
  2935. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  2936. player\.mangomolo\.com/v1
  2937. )/
  2938. (?:
  2939. video\?.*?\bid=(?P<video_id>\d+)|
  2940. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2941. ).+?)\1''', webpage)
  2942. if mobj is not None:
  2943. info = {
  2944. '_type': 'url_transparent',
  2945. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2946. 'title': video_title,
  2947. 'description': video_description,
  2948. 'thumbnail': video_thumbnail,
  2949. 'uploader': video_uploader,
  2950. }
  2951. video_id = mobj.group('video_id')
  2952. if video_id:
  2953. info.update({
  2954. 'ie_key': 'MangomoloVideo',
  2955. 'id': video_id,
  2956. })
  2957. else:
  2958. info.update({
  2959. 'ie_key': 'MangomoloLive',
  2960. 'id': mobj.group('channel_id'),
  2961. })
  2962. return info
  2963. # Look for Instagram embeds
  2964. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2965. if instagram_embed_url is not None:
  2966. return self.url_result(
  2967. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2968. # Look for LiveLeak embeds
  2969. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2970. if liveleak_urls:
  2971. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2972. # Look for 3Q SDN embeds
  2973. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2974. if threeqsdn_url:
  2975. return {
  2976. '_type': 'url_transparent',
  2977. 'ie_key': ThreeQSDNIE.ie_key(),
  2978. 'url': self._proto_relative_url(threeqsdn_url),
  2979. 'title': video_title,
  2980. 'description': video_description,
  2981. 'thumbnail': video_thumbnail,
  2982. 'uploader': video_uploader,
  2983. }
  2984. # Look for VBOX7 embeds
  2985. vbox7_url = Vbox7IE._extract_url(webpage)
  2986. if vbox7_url:
  2987. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2988. # Look for DBTV embeds
  2989. dbtv_urls = DBTVIE._extract_urls(webpage)
  2990. if dbtv_urls:
  2991. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2992. # Look for Videa embeds
  2993. videa_urls = VideaIE._extract_urls(webpage)
  2994. if videa_urls:
  2995. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2996. # Look for 20 minuten embeds
  2997. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2998. if twentymin_urls:
  2999. return self.playlist_from_matches(
  3000. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  3001. # Look for VideoPress embeds
  3002. videopress_urls = VideoPressIE._extract_urls(webpage)
  3003. if videopress_urls:
  3004. return self.playlist_from_matches(
  3005. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  3006. # Look for Rutube embeds
  3007. rutube_urls = RutubeIE._extract_urls(webpage)
  3008. if rutube_urls:
  3009. return self.playlist_from_matches(
  3010. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  3011. # Look for WashingtonPost embeds
  3012. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  3013. if wapo_urls:
  3014. return self.playlist_from_matches(
  3015. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  3016. # Look for Mediaset embeds
  3017. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  3018. if mediaset_urls:
  3019. return self.playlist_from_matches(
  3020. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  3021. # Look for JOJ.sk embeds
  3022. joj_urls = JojIE._extract_urls(webpage)
  3023. if joj_urls:
  3024. return self.playlist_from_matches(
  3025. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  3026. # Look for megaphone.fm embeds
  3027. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  3028. if mpfn_urls:
  3029. return self.playlist_from_matches(
  3030. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  3031. # Look for vzaar embeds
  3032. vzaar_urls = VzaarIE._extract_urls(webpage)
  3033. if vzaar_urls:
  3034. return self.playlist_from_matches(
  3035. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  3036. channel9_urls = Channel9IE._extract_urls(webpage)
  3037. if channel9_urls:
  3038. return self.playlist_from_matches(
  3039. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  3040. vshare_urls = VShareIE._extract_urls(webpage)
  3041. if vshare_urls:
  3042. return self.playlist_from_matches(
  3043. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  3044. # Look for Mediasite embeds
  3045. mediasite_urls = MediasiteIE._extract_urls(webpage)
  3046. if mediasite_urls:
  3047. entries = [
  3048. self.url_result(smuggle_url(
  3049. compat_urlparse.urljoin(url, mediasite_url),
  3050. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  3051. for mediasite_url in mediasite_urls]
  3052. return self.playlist_result(entries, video_id, video_title)
  3053. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  3054. if springboardplatform_urls:
  3055. return self.playlist_from_matches(
  3056. springboardplatform_urls, video_id, video_title,
  3057. ie=SpringboardPlatformIE.ie_key())
  3058. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  3059. if yapfiles_urls:
  3060. return self.playlist_from_matches(
  3061. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  3062. vice_urls = ViceIE._extract_urls(webpage)
  3063. if vice_urls:
  3064. return self.playlist_from_matches(
  3065. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  3066. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  3067. if xfileshare_urls:
  3068. return self.playlist_from_matches(
  3069. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  3070. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  3071. if cloudflarestream_urls:
  3072. return self.playlist_from_matches(
  3073. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  3074. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  3075. if peertube_urls:
  3076. return self.playlist_from_matches(
  3077. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  3078. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  3079. if indavideo_urls:
  3080. return self.playlist_from_matches(
  3081. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  3082. apa_urls = APAIE._extract_urls(webpage)
  3083. if apa_urls:
  3084. return self.playlist_from_matches(
  3085. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  3086. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  3087. if foxnews_urls:
  3088. return self.playlist_from_matches(
  3089. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  3090. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3091. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3092. webpage)]
  3093. if sharevideos_urls:
  3094. return self.playlist_from_matches(
  3095. sharevideos_urls, video_id, video_title)
  3096. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3097. if viqeo_urls:
  3098. return self.playlist_from_matches(
  3099. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3100. expressen_urls = ExpressenIE._extract_urls(webpage)
  3101. if expressen_urls:
  3102. return self.playlist_from_matches(
  3103. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3104. zype_urls = ZypeIE._extract_urls(webpage)
  3105. if zype_urls:
  3106. return self.playlist_from_matches(
  3107. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3108. # Look for HTML5 media
  3109. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3110. if entries:
  3111. if len(entries) == 1:
  3112. entries[0].update({
  3113. 'id': video_id,
  3114. 'title': video_title,
  3115. })
  3116. else:
  3117. for num, entry in enumerate(entries, start=1):
  3118. entry.update({
  3119. 'id': '%s-%s' % (video_id, num),
  3120. 'title': '%s (%d)' % (video_title, num),
  3121. })
  3122. for entry in entries:
  3123. self._sort_formats(entry['formats'])
  3124. return self.playlist_result(entries, video_id, video_title)
  3125. jwplayer_data = self._find_jwplayer_data(
  3126. webpage, video_id, transform_source=js_to_json)
  3127. if jwplayer_data:
  3128. try:
  3129. info = self._parse_jwplayer_data(
  3130. jwplayer_data, video_id, require_title=False, base_url=url)
  3131. return merge_dicts(info, info_dict)
  3132. except ExtractorError:
  3133. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3134. pass
  3135. # Video.js embed
  3136. mobj = re.search(
  3137. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3138. webpage)
  3139. if mobj is not None:
  3140. sources = self._parse_json(
  3141. mobj.group(1), video_id, transform_source=js_to_json,
  3142. fatal=False) or []
  3143. if not isinstance(sources, list):
  3144. sources = [sources]
  3145. formats = []
  3146. for source in sources:
  3147. src = source.get('src')
  3148. if not src or not isinstance(src, compat_str):
  3149. continue
  3150. src = compat_urlparse.urljoin(url, src)
  3151. src_type = source.get('type')
  3152. if isinstance(src_type, compat_str):
  3153. src_type = src_type.lower()
  3154. ext = determine_ext(src).lower()
  3155. if src_type == 'video/youtube':
  3156. return self.url_result(src, YoutubeIE.ie_key())
  3157. if src_type == 'application/dash+xml' or ext == 'mpd':
  3158. formats.extend(self._extract_mpd_formats(
  3159. src, video_id, mpd_id='dash', fatal=False))
  3160. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3161. formats.extend(self._extract_m3u8_formats(
  3162. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3163. m3u8_id='hls', fatal=False))
  3164. else:
  3165. formats.append({
  3166. 'url': src,
  3167. 'ext': (mimetype2ext(src_type)
  3168. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3169. })
  3170. if formats:
  3171. self._sort_formats(formats)
  3172. info_dict['formats'] = formats
  3173. return info_dict
  3174. # Looking for http://schema.org/VideoObject
  3175. json_ld = self._search_json_ld(
  3176. webpage, video_id, default={}, expected_type='VideoObject')
  3177. if json_ld.get('url'):
  3178. return merge_dicts(json_ld, info_dict)
  3179. def check_video(vurl):
  3180. if YoutubeIE.suitable(vurl):
  3181. return True
  3182. if RtmpIE.suitable(vurl):
  3183. return True
  3184. vpath = compat_urlparse.urlparse(vurl).path
  3185. vext = determine_ext(vpath)
  3186. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3187. def filter_video(urls):
  3188. return list(filter(check_video, urls))
  3189. # Start with something easy: JW Player in SWFObject
  3190. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3191. if not found:
  3192. # Look for gorilla-vid style embedding
  3193. found = filter_video(re.findall(r'''(?sx)
  3194. (?:
  3195. jw_plugins|
  3196. JWPlayerOptions|
  3197. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3198. )
  3199. .*?
  3200. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3201. if not found:
  3202. # Broaden the search a little bit
  3203. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3204. if not found:
  3205. # Broaden the findall a little bit: JWPlayer JS loader
  3206. found = filter_video(re.findall(
  3207. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3208. if not found:
  3209. # Flow player
  3210. found = filter_video(re.findall(r'''(?xs)
  3211. flowplayer\("[^"]+",\s*
  3212. \{[^}]+?\}\s*,
  3213. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3214. ["']?url["']?\s*:\s*["']([^"']+)["']
  3215. ''', webpage))
  3216. if not found:
  3217. # Cinerama player
  3218. found = re.findall(
  3219. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3220. if not found:
  3221. # Try to find twitter cards info
  3222. # twitter:player:stream should be checked before twitter:player since
  3223. # it is expected to contain a raw stream (see
  3224. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3225. found = filter_video(re.findall(
  3226. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3227. if not found:
  3228. # We look for Open Graph info:
  3229. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3230. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3231. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3232. if m_video_type is not None:
  3233. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3234. if not found:
  3235. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3236. found = re.search(
  3237. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3238. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3239. webpage)
  3240. if not found:
  3241. # Look also in Refresh HTTP header
  3242. refresh_header = head_response.headers.get('Refresh')
  3243. if refresh_header:
  3244. # In python 2 response HTTP headers are bytestrings
  3245. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3246. refresh_header = refresh_header.decode('iso-8859-1')
  3247. found = re.search(REDIRECT_REGEX, refresh_header)
  3248. if found:
  3249. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3250. if new_url != url:
  3251. self.report_following_redirect(new_url)
  3252. return {
  3253. '_type': 'url',
  3254. 'url': new_url,
  3255. }
  3256. else:
  3257. found = None
  3258. if not found:
  3259. # twitter:player is a https URL to iframe player that may or may not
  3260. # be supported by youtube-dl thus this is checked the very last (see
  3261. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3262. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3263. if embed_url and embed_url != url:
  3264. return self.url_result(embed_url)
  3265. if not found:
  3266. raise UnsupportedError(url)
  3267. entries = []
  3268. for video_url in orderedSet(found):
  3269. video_url = unescapeHTML(video_url)
  3270. video_url = video_url.replace('\\/', '/')
  3271. video_url = compat_urlparse.urljoin(url, video_url)
  3272. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3273. # Sometimes, jwplayer extraction will result in a YouTube URL
  3274. if YoutubeIE.suitable(video_url):
  3275. entries.append(self.url_result(video_url, 'Youtube'))
  3276. continue
  3277. # here's a fun little line of code for you:
  3278. video_id = os.path.splitext(video_id)[0]
  3279. entry_info_dict = {
  3280. 'id': video_id,
  3281. 'uploader': video_uploader,
  3282. 'title': video_title,
  3283. 'age_limit': age_limit,
  3284. }
  3285. if RtmpIE.suitable(video_url):
  3286. entry_info_dict.update({
  3287. '_type': 'url_transparent',
  3288. 'ie_key': RtmpIE.ie_key(),
  3289. 'url': video_url,
  3290. })
  3291. entries.append(entry_info_dict)
  3292. continue
  3293. ext = determine_ext(video_url)
  3294. if ext == 'smil':
  3295. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3296. elif ext == 'xspf':
  3297. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3298. elif ext == 'm3u8':
  3299. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3300. elif ext == 'mpd':
  3301. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3302. elif ext == 'f4m':
  3303. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3304. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3305. # Just matching .ism/manifest is not enough to be reliably sure
  3306. # whether it's actually an ISM manifest or some other streaming
  3307. # manifest since there are various streaming URL formats
  3308. # possible (see [1]) as well as some other shenanigans like
  3309. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3310. # so on.
  3311. # Thus the most reasonable way to solve this is to delegate
  3312. # to generic extractor in order to look into the contents of
  3313. # the manifest itself.
  3314. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3315. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3316. entry_info_dict = self.url_result(
  3317. smuggle_url(video_url, {'to_generic': True}),
  3318. GenericIE.ie_key())
  3319. else:
  3320. entry_info_dict['url'] = video_url
  3321. if entry_info_dict.get('formats'):
  3322. self._sort_formats(entry_info_dict['formats'])
  3323. entries.append(entry_info_dict)
  3324. if len(entries) == 1:
  3325. return entries[0]
  3326. else:
  3327. for num, e in enumerate(entries, start=1):
  3328. # 'url' results don't have a title
  3329. if e.get('title') is not None:
  3330. e['title'] = '%s (%d)' % (e['title'], num)
  3331. return {
  3332. '_type': 'playlist',
  3333. 'entries': entries,
  3334. }