logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

pbs.py (36627B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  6. from .common import InfoExtractor
  7. from ..compat import compat_str
  8. from ..utils import (
  9.     ExtractorError,
  10.     determine_ext,
  11.     int_or_none,
  12.     float_or_none,
  13.     js_to_json,
  14.     orderedSet,
  15.     strip_jsonp,
  16.     strip_or_none,
  17.     unified_strdate,
  18.     url_or_none,
  19.     US_RATINGS,
  20. )
  23. class PBSIE(InfoExtractor):
  24.     _STATIONS = (
  25.         (r'(?:video|www|player)\.pbs\.org', 'PBS: Public Broadcasting Service'),  # http://www.pbs.org/
  26.         (r'video\.aptv\.org', 'APT - Alabama Public Television (WBIQ)'),  # http://aptv.org/
  27.         (r'video\.gpb\.org', 'GPB/Georgia Public Broadcasting (WGTV)'),  # http://www.gpb.org/
  28.         (r'video\.mpbonline\.org', 'Mississippi Public Broadcasting (WMPN)'),  # http://www.mpbonline.org
  29.         (r'video\.wnpt\.org', 'Nashville Public Television (WNPT)'),  # http://www.wnpt.org
  30.         (r'video\.wfsu\.org', 'WFSU-TV (WFSU)'),  # http://wfsu.org/
  31.         (r'video\.wsre\.org', 'WSRE (WSRE)'),  # http://www.wsre.org
  32.         (r'video\.wtcitv\.org', 'WTCI (WTCI)'),  # http://www.wtcitv.org
  33.         (r'video\.pba\.org', 'WPBA/Channel 30 (WPBA)'),  # http://pba.org/
  34.         (r'video\.alaskapublic\.org', 'Alaska Public Media (KAKM)'),  # http://alaskapublic.org/kakm
  35.         # (r'kuac\.org', 'KUAC (KUAC)'),  # http://kuac.org/kuac-tv/
  36.         # (r'ktoo\.org', '360 North (KTOO)'),  # http://www.ktoo.org/
  37.         # (r'azpm\.org', 'KUAT 6 (KUAT)'),  # http://www.azpm.org/
  38.         (r'video\.azpbs\.org', 'Arizona PBS (KAET)'),  # http://www.azpbs.org
  39.         (r'portal\.knme\.org', 'KNME-TV/Channel 5 (KNME)'),  # http://www.newmexicopbs.org/
  40.         (r'video\.vegaspbs\.org', 'Vegas PBS (KLVX)'),  # http://vegaspbs.org/
  41.         (r'watch\.aetn\.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'),  # http://www.aetn.org/
  42.         (r'video\.ket\.org', 'KET (WKLE)'),  # http://www.ket.org/
  43.         (r'video\.wkno\.org', 'WKNO/Channel 10 (WKNO)'),  # http://www.wkno.org/
  44.         (r'video\.lpb\.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'),  # http://www.lpb.org/
  45.         (r'videos\.oeta\.tv', 'OETA (KETA)'),  # http://www.oeta.tv
  46.         (r'video\.optv\.org', 'Ozarks Public Television (KOZK)'),  # http://www.optv.org/
  47.         (r'watch\.wsiu\.org', 'WSIU Public Broadcasting (WSIU)'),  # http://www.wsiu.org/
  48.         (r'video\.keet\.org', 'KEET TV (KEET)'),  # http://www.keet.org
  49.         (r'pbs\.kixe\.org', 'KIXE/Channel 9 (KIXE)'),  # http://kixe.org/
  50.         (r'video\.kpbs\.org', 'KPBS San Diego (KPBS)'),  # http://www.kpbs.org/
  51.         (r'video\.kqed\.org', 'KQED (KQED)'),  # http://www.kqed.org
  52.         (r'vids\.kvie\.org', 'KVIE Public Television (KVIE)'),  # http://www.kvie.org
  53.         (r'video\.pbssocal\.org', 'PBS SoCal/KOCE (KOCE)'),  # http://www.pbssocal.org/
  54.         (r'video\.valleypbs\.org', 'ValleyPBS (KVPT)'),  # http://www.valleypbs.org/
  55.         (r'video\.cptv\.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'),  # http://cptv.org
  56.         (r'watch\.knpb\.org', 'KNPB Channel 5 (KNPB)'),  # http://www.knpb.org/
  57.         (r'video\.soptv\.org', 'SOPTV (KSYS)'),  # http://www.soptv.org
  58.         # (r'klcs\.org', 'KLCS/Channel 58 (KLCS)'),  # http://www.klcs.org
  59.         # (r'krcb\.org', 'KRCB Television & Radio (KRCB)'),  # http://www.krcb.org
  60.         # (r'kvcr\.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'),  # http://kvcr.org
  61.         (r'video\.rmpbs\.org', 'Rocky Mountain PBS (KRMA)'),  # http://www.rmpbs.org
  62.         (r'video\.kenw\.org', 'KENW-TV3 (KENW)'),  # http://www.kenw.org
  63.         (r'video\.kued\.org', 'KUED Channel 7 (KUED)'),  # http://www.kued.org
  64.         (r'video\.wyomingpbs\.org', 'Wyoming PBS (KCWC)'),  # http://www.wyomingpbs.org
  65.         (r'video\.cpt12\.org', 'Colorado Public Television / KBDI 12 (KBDI)'),  # http://www.cpt12.org/
  66.         (r'video\.kbyueleven\.org', 'KBYU-TV (KBYU)'),  # http://www.kbyutv.org/
  67.         (r'video\.thirteen\.org', 'Thirteen/WNET New York (WNET)'),  # http://www.thirteen.org
  68.         (r'video\.wgbh\.org', 'WGBH/Channel 2 (WGBH)'),  # http://wgbh.org
  69.         (r'video\.wgby\.org', 'WGBY (WGBY)'),  # http://www.wgby.org
  70.         (r'watch\.njtvonline\.org', 'NJTV Public Media NJ (WNJT)'),  # http://www.njtvonline.org/
  71.         # (r'ripbs\.org', 'Rhode Island PBS (WSBE)'),  # http://www.ripbs.org/home/
  72.         (r'watch\.wliw\.org', 'WLIW21 (WLIW)'),  # http://www.wliw.org/
  73.         (r'video\.mpt\.tv', 'mpt/Maryland Public Television (WMPB)'),  # http://www.mpt.org
  74.         (r'watch\.weta\.org', 'WETA Television and Radio (WETA)'),  # http://www.weta.org
  75.         (r'video\.whyy\.org', 'WHYY (WHYY)'),  # http://www.whyy.org
  76.         (r'video\.wlvt\.org', 'PBS 39 (WLVT)'),  # http://www.wlvt.org/
  77.         (r'video\.wvpt\.net', 'WVPT - Your Source for PBS and More! (WVPT)'),  # http://www.wvpt.net
  78.         (r'video\.whut\.org', 'Howard University Television (WHUT)'),  # http://www.whut.org
  79.         (r'video\.wedu\.org', 'WEDU PBS (WEDU)'),  # http://www.wedu.org
  80.         (r'video\.wgcu\.org', 'WGCU Public Media (WGCU)'),  # http://www.wgcu.org/
  81.         # (r'wjct\.org', 'WJCT Public Broadcasting (WJCT)'),  # http://www.wjct.org
  82.         (r'video\.wpbt2\.org', 'WPBT2 (WPBT)'),  # http://www.wpbt2.org
  83.         (r'video\.wucftv\.org', 'WUCF TV (WUCF)'),  # http://wucftv.org
  84.         (r'video\.wuft\.org', 'WUFT/Channel 5 (WUFT)'),  # http://www.wuft.org
  85.         (r'watch\.wxel\.org', 'WXEL/Channel 42 (WXEL)'),  # http://www.wxel.org/home/
  86.         (r'video\.wlrn\.org', 'WLRN/Channel 17 (WLRN)'),  # http://www.wlrn.org/
  87.         (r'video\.wusf\.usf\.edu', 'WUSF Public Broadcasting (WUSF)'),  # http://wusf.org/
  88.         (r'video\.scetv\.org', 'ETV (WRLK)'),  # http://www.scetv.org
  89.         (r'video\.unctv\.org', 'UNC-TV (WUNC)'),  # http://www.unctv.org/
  90.         # (r'pbsguam\.org', 'PBS Guam (KGTF)'),  # http://www.pbsguam.org/
  91.         (r'video\.pbshawaii\.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'),  # http://www.pbshawaii.org/
  92.         (r'video\.idahoptv\.org', 'Idaho Public Television (KAID)'),  # http://idahoptv.org
  93.         (r'video\.ksps\.org', 'KSPS (KSPS)'),  # http://www.ksps.org/home/
  94.         (r'watch\.opb\.org', 'OPB (KOPB)'),  # http://www.opb.org
  95.         (r'watch\.nwptv\.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'),  # http://www.kwsu.org
  96.         (r'video\.will\.illinois\.edu', 'WILL-TV (WILL)'),  # http://will.illinois.edu/
  97.         (r'video\.networkknowledge\.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'),  # http://www.wsec.tv
  98.         (r'video\.wttw\.com', 'WTTW11 (WTTW)'),  # http://www.wttw.com/
  99.         # (r'wtvp\.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'),  # http://www.wtvp.org/
  100.         (r'video\.iptv\.org', 'Iowa Public Television/IPTV (KDIN)'),  # http://www.iptv.org/
  101.         (r'video\.ninenet\.org', 'Nine Network (KETC)'),  # http://www.ninenet.org
  102.         (r'video\.wfwa\.org', 'PBS39 Fort Wayne (WFWA)'),  # http://wfwa.org/
  103.         (r'video\.wfyi\.org', 'WFYI Indianapolis (WFYI)'),  # http://www.wfyi.org
  104.         (r'video\.mptv\.org', 'Milwaukee Public Television (WMVS)'),  # http://www.mptv.org
  105.         (r'video\.wnin\.org', 'WNIN (WNIN)'),  # http://www.wnin.org/
  106.         (r'video\.wnit\.org', 'WNIT Public Television (WNIT)'),  # http://www.wnit.org/
  107.         (r'video\.wpt\.org', 'WPT (WPNE)'),  # http://www.wpt.org/
  108.         (r'video\.wvut\.org', 'WVUT/Channel 22 (WVUT)'),  # http://wvut.org/
  109.         (r'video\.weiu\.net', 'WEIU/Channel 51 (WEIU)'),  # http://www.weiu.net
  110.         (r'video\.wqpt\.org', 'WQPT-TV (WQPT)'),  # http://www.wqpt.org
  111.         (r'video\.wycc\.org', 'WYCC PBS Chicago (WYCC)'),  # http://www.wycc.org
  112.         # (r'lakeshorepublicmedia\.org', 'Lakeshore Public Television (WYIN)'),  # http://lakeshorepublicmedia.org/
  113.         (r'video\.wipb\.org', 'WIPB-TV (WIPB)'),  # http://wipb.org
  114.         (r'video\.indianapublicmedia\.org', 'WTIU (WTIU)'),  # http://indianapublicmedia.org/tv/
  115.         (r'watch\.cetconnect\.org', 'CET  (WCET)'),  # http://www.cetconnect.org
  116.         (r'video\.thinktv\.org', 'ThinkTVNetwork (WPTD)'),  # http://www.thinktv.org
  117.         (r'video\.wbgu\.org', 'WBGU-TV (WBGU)'),  # http://wbgu.org
  118.         (r'video\.wgvu\.org', 'WGVU TV (WGVU)'),  # http://www.wgvu.org/
  119.         (r'video\.netnebraska\.org', 'NET1 (KUON)'),  # http://netnebraska.org
  120.         (r'video\.pioneer\.org', 'Pioneer Public Television (KWCM)'),  # http://www.pioneer.org
  121.         (r'watch\.sdpb\.org', 'SDPB Television (KUSD)'),  # http://www.sdpb.org
  122.         (r'video\.tpt\.org', 'TPT (KTCA)'),  # http://www.tpt.org
  123.         (r'watch\.ksmq\.org', 'KSMQ (KSMQ)'),  # http://www.ksmq.org/
  124.         (r'watch\.kpts\.org', 'KPTS/Channel 8 (KPTS)'),  # http://www.kpts.org/
  125.         (r'watch\.ktwu\.org', 'KTWU/Channel 11 (KTWU)'),  # http://ktwu.org
  126.         # (r'shptv\.org', 'Smoky Hills Public Television (KOOD)'),  # http://www.shptv.org
  127.         # (r'kcpt\.org', 'KCPT Kansas City Public Television (KCPT)'),  # http://kcpt.org/
  128.         # (r'blueridgepbs\.org', 'Blue Ridge PBS (WBRA)'),  # http://www.blueridgepbs.org/
  129.         (r'watch\.easttennesseepbs\.org', 'East Tennessee PBS (WSJK)'),  # http://easttennesseepbs.org
  130.         (r'video\.wcte\.tv', 'WCTE-TV (WCTE)'),  # http://www.wcte.org
  131.         (r'video\.wljt\.org', 'WLJT, Channel 11 (WLJT)'),  # http://wljt.org/
  132.         (r'video\.wosu\.org', 'WOSU TV (WOSU)'),  # http://wosu.org/
  133.         (r'video\.woub\.org', 'WOUB/WOUC (WOUB)'),  # http://woub.org/tv/index.php?section=5
  134.         (r'video\.wvpublic\.org', 'WVPB (WVPB)'),  # http://wvpublic.org/
  135.         (r'video\.wkyupbs\.org', 'WKYU-PBS (WKYU)'),  # http://www.wkyupbs.org
  136.         # (r'wyes\.org', 'WYES-TV/New Orleans (WYES)'),  # http://www.wyes.org
  137.         (r'video\.kera\.org', 'KERA 13 (KERA)'),  # http://www.kera.org/
  138.         (r'video\.mpbn\.net', 'MPBN (WCBB)'),  # http://www.mpbn.net/
  139.         (r'video\.mountainlake\.org', 'Mountain Lake PBS (WCFE)'),  # http://www.mountainlake.org/
  140.         (r'video\.nhptv\.org', 'NHPTV (WENH)'),  # http://nhptv.org/
  141.         (r'video\.vpt\.org', 'Vermont PBS (WETK)'),  # http://www.vpt.org
  142.         (r'video\.witf\.org', 'witf (WITF)'),  # http://www.witf.org
  143.         (r'watch\.wqed\.org', 'WQED Multimedia (WQED)'),  # http://www.wqed.org/
  144.         (r'video\.wmht\.org', 'WMHT Educational Telecommunications (WMHT)'),  # http://www.wmht.org/home/
  145.         (r'video\.deltabroadcasting\.org', 'Q-TV (WDCQ)'),  # http://www.deltabroadcasting.org
  146.         (r'video\.dptv\.org', 'WTVS Detroit Public TV (WTVS)'),  # http://www.dptv.org/
  147.         (r'video\.wcmu\.org', 'CMU Public Television (WCMU)'),  # http://www.wcmu.org
  148.         (r'video\.wkar\.org', 'WKAR-TV (WKAR)'),  # http://wkar.org/
  149.         (r'wnmuvideo\.nmu\.edu', 'WNMU-TV Public TV 13 (WNMU)'),  # http://wnmutv.nmu.edu
  150.         (r'video\.wdse\.org', 'WDSE - WRPT (WDSE)'),  # http://www.wdse.org/
  151.         (r'video\.wgte\.org', 'WGTE TV (WGTE)'),  # http://www.wgte.org
  152.         (r'video\.lptv\.org', 'Lakeland Public Television (KAWE)'),  # http://www.lakelandptv.org
  153.         # (r'prairiepublic\.org', 'PRAIRIE PUBLIC (KFME)'),  # http://www.prairiepublic.org/
  154.         (r'video\.kmos\.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'),  # http://www.kmos.org/
  155.         (r'watch\.montanapbs\.org', 'MontanaPBS (KUSM)'),  # http://montanapbs.org
  156.         (r'video\.krwg\.org', 'KRWG/Channel 22 (KRWG)'),  # http://www.krwg.org
  157.         (r'video\.kacvtv\.org', 'KACV (KACV)'),  # http://www.panhandlepbs.org/home/
  158.         (r'video\.kcostv\.org', 'KCOS/Channel 13 (KCOS)'),  # www.kcostv.org
  159.         (r'video\.wcny\.org', 'WCNY/Channel 24 (WCNY)'),  # http://www.wcny.org
  160.         (r'video\.wned\.org', 'WNED (WNED)'),  # http://www.wned.org/
  161.         (r'watch\.wpbstv\.org', 'WPBS (WPBS)'),  # http://www.wpbstv.org
  162.         (r'video\.wskg\.org', 'WSKG Public TV (WSKG)'),  # http://wskg.org
  163.         (r'video\.wxxi\.org', 'WXXI (WXXI)'),  # http://wxxi.org
  164.         (r'video\.wpsu\.org', 'WPSU (WPSU)'),  # http://www.wpsu.org
  165.         # (r'wqln\.org', 'WQLN/Channel 54 (WQLN)'),  # http://www.wqln.org
  166.         (r'on-demand\.wvia\.org', 'WVIA Public Media Studios (WVIA)'),  # http://www.wvia.org/
  167.         (r'video\.wtvi\.org', 'WTVI (WTVI)'),  # http://www.wtvi.org/
  168.         # (r'whro\.org', 'WHRO (WHRO)'),  # http://whro.org
  169.         (r'video\.westernreservepublicmedia\.org', 'Western Reserve PBS (WNEO)'),  # http://www.WesternReservePublicMedia.org/
  170.         (r'video\.ideastream\.org', 'WVIZ/PBS ideastream (WVIZ)'),  # http://www.wviz.org/
  171.         (r'video\.kcts9\.org', 'KCTS 9 (KCTS)'),  # http://kcts9.org/
  172.         (r'video\.basinpbs\.org', 'Basin PBS (KPBT)'),  # http://www.basinpbs.org
  173.         (r'video\.houstonpbs\.org', 'KUHT / Channel 8 (KUHT)'),  # http://www.houstonpublicmedia.org/
  174.         # (r'tamu\.edu', 'KAMU - TV (KAMU)'),  # http://KAMU.tamu.edu
  175.         # (r'kedt\.org', 'KEDT/Channel 16 (KEDT)'),  # http://www.kedt.org
  176.         (r'video\.klrn\.org', 'KLRN (KLRN)'),  # http://www.klrn.org
  177.         (r'video\.klru\.tv', 'KLRU (KLRU)'),  # http://www.klru.org
  178.         # (r'kmbh\.org', 'KMBH-TV (KMBH)'),  # http://www.kmbh.org
  179.         # (r'knct\.org', 'KNCT (KNCT)'),  # http://www.knct.org
  180.         # (r'ktxt\.org', 'KTTZ-TV (KTXT)'),  # http://www.ktxt.org
  181.         (r'video\.wtjx\.org', 'WTJX Channel 12 (WTJX)'),  # http://www.wtjx.org/
  182.         (r'video\.ideastations\.org', 'WCVE PBS (WCVE)'),  # http://ideastations.org/
  183.         (r'video\.kbtc\.org', 'KBTC Public Television (KBTC)'),  # http://kbtc.org
  184.     )
  186.     IE_NAME = 'pbs'
  187.     IE_DESC = 'Public Broadcasting Service (PBS) and member stations: %s' % ', '.join(list(zip(*_STATIONS))[1])
  189.     _VALID_URL = r'''(?x)https?://
  190.         (?:
  191.            # Direct video URL
  192.            (?:%s)/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
  193.            # Article with embedded player (or direct video)
  194.            (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
  195.            # Player
  196.            (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
  197.         )
  198.     ''' % '|'.join(list(zip(*_STATIONS))[0])
  200.     _GEO_COUNTRIES = ['US']
  202.     _TESTS = [
  203.         {
  204.             'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
  205.             'md5': '173dc391afd361fa72eab5d3d918968d',
  206.             'info_dict': {
  207.                 'id': '2365006249',
  208.                 'ext': 'mp4',
  209.                 'title': 'Constitution USA with Peter Sagal - A More Perfect Union',
  210.                 'description': 'md5:31b664af3c65fd07fa460d306b837d00',
  211.                 'duration': 3190,
  212.             },
  213.         },
  214.         {
  215.             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
  216.             'md5': '6f722cb3c3982186d34b0f13374499c7',
  217.             'info_dict': {
  218.                 'id': '2365297690',
  219.                 'ext': 'mp4',
  220.                 'title': 'FRONTLINE - Losing Iraq',
  221.                 'description': 'md5:5979a4d069b157f622d02bff62fbe654',
  222.                 'duration': 5050,
  223.             },
  224.         },
  225.         {
  226.             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
  227.             'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
  228.             'info_dict': {
  229.                 'id': '2201174722',
  230.                 'ext': 'mp4',
  231.                 'title': 'PBS NewsHour - Cyber Schools Gain Popularity, but Quality Questions Persist',
  232.                 'description': 'md5:86ab9a3d04458b876147b355788b8781',
  233.                 'duration': 801,
  234.             },
  235.         },
  236.         {
  237.             'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
  238.             'md5': 'c62859342be2a0358d6c9eb306595978',
  239.             'info_dict': {
  240.                 'id': '2365297708',
  241.                 'ext': 'mp4',
  242.                 'title': 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
  243.                 'description': 'md5:657897370e09e2bc6bf0f8d2cd313c6b',
  244.                 'duration': 6559,
  245.                 'thumbnail': r're:^https?://.*\.jpg$',
  246.             },
  247.         },
  248.         {
  249.             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
  250.             'md5': '908f3e5473a693b266b84e25e1cf9703',
  251.             'info_dict': {
  252.                 'id': '2365160389',
  253.                 'display_id': 'killer-typhoon',
  254.                 'ext': 'mp4',
  255.                 'description': 'md5:c741d14e979fc53228c575894094f157',
  256.                 'title': 'NOVA - Killer Typhoon',
  257.                 'duration': 3172,
  258.                 'thumbnail': r're:^https?://.*\.jpg$',
  259.                 'upload_date': '20140122',
  260.                 'age_limit': 10,
  261.             },
  262.         },
  263.         {
  264.             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
  265.             'info_dict': {
  266.                 'id': 'united-states-of-secrets',
  267.             },
  268.             'playlist_count': 2,
  269.         },
  270.         {
  271.             'url': 'http://www.pbs.org/wgbh/americanexperience/films/great-war/',
  272.             'info_dict': {
  273.                 'id': 'great-war',
  274.             },
  275.             'playlist_count': 3,
  276.         },
  277.         {
  278.             'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
  279.             'info_dict': {
  280.                 'id': '2276541483',
  281.                 'display_id': 'player',
  282.                 'ext': 'mp4',
  283.                 'title': 'American Experience - Death and the Civil War, Chapter 1',
  284.                 'description': 'md5:67fa89a9402e2ee7d08f53b920674c18',
  285.                 'duration': 682,
  286.                 'thumbnail': r're:^https?://.*\.jpg$',
  287.             },
  288.             'params': {
  289.                 'skip_download': True,  # requires ffmpeg
  290.             },
  291.         },
  292.         {
  293.             'url': 'http://www.pbs.org/video/2365245528/',
  294.             'md5': '115223d41bd55cda8ae5cd5ed4e11497',
  295.             'info_dict': {
  296.                 'id': '2365245528',
  297.                 'display_id': '2365245528',
  298.                 'ext': 'mp4',
  299.                 'title': 'FRONTLINE - United States of Secrets (Part One)',
  300.                 'description': 'md5:55756bd5c551519cc4b7703e373e217e',
  301.                 'duration': 6851,
  302.                 'thumbnail': r're:^https?://.*\.jpg$',
  303.             },
  304.         },
  305.         {
  306.             # Video embedded in iframe containing angle brackets as attribute's value (e.g.
  307.             # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
  308.             # https://github.com/ytdl-org/youtube-dl/issues/7059)
  309.             'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
  310.             'md5': '59b0ef5009f9ac8a319cc5efebcd865e',
  311.             'info_dict': {
  312.                 'id': '2365546844',
  313.                 'display_id': 'a-chefs-life-season-3-episode-5-prickly-business',
  314.                 'ext': 'mp4',
  315.                 'title': "A Chef's Life - Season 3, Ep. 5: Prickly Business",
  316.                 'description': 'md5:c0ff7475a4b70261c7e58f493c2792a5',
  317.                 'duration': 1480,
  318.                 'thumbnail': r're:^https?://.*\.jpg$',
  319.             },
  320.         },
  321.         {
  322.             # Frontline video embedded via flp2012.js
  323.             'url': 'http://www.pbs.org/wgbh/pages/frontline/the-atomic-artists',
  324.             'info_dict': {
  325.                 'id': '2070868960',
  326.                 'display_id': 'the-atomic-artists',
  327.                 'ext': 'mp4',
  328.                 'title': 'FRONTLINE - The Atomic Artists',
  329.                 'description': 'md5:f677e4520cfacb4a5ce1471e31b57800',
  330.                 'duration': 723,
  331.                 'thumbnail': r're:^https?://.*\.jpg$',
  332.             },
  333.             'params': {
  334.                 'skip_download': True,  # requires ffmpeg
  335.             },
  336.         },
  337.         {
  338.             # Serves hd only via wigget/partnerplayer page
  339.             'url': 'http://www.pbs.org/video/2365641075/',
  340.             'md5': 'fdf907851eab57211dd589cf12006666',
  341.             'info_dict': {
  342.                 'id': '2365641075',
  343.                 'ext': 'mp4',
  344.                 'title': 'FRONTLINE - Netanyahu at War',
  345.                 'duration': 6852,
  346.                 'thumbnail': r're:^https?://.*\.jpg$',
  347.                 'formats': 'mincount:8',
  348.             },
  349.         },
  350.         {
  351.             # https://github.com/ytdl-org/youtube-dl/issues/13801
  352.             'url': 'https://www.pbs.org/video/pbs-newshour-full-episode-july-31-2017-1501539057/',
  353.             'info_dict': {
  354.                 'id': '3003333873',
  355.                 'ext': 'mp4',
  356.                 'title': 'PBS NewsHour - full episode July 31, 2017',
  357.                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  358.                 'duration': 3265,
  359.                 'thumbnail': r're:^https?://.*\.jpg$',
  360.             },
  361.             'params': {
  362.                 'skip_download': True,
  363.             },
  364.         },
  365.         {
  366.             'url': 'http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/',
  367.             'info_dict': {
  368.                 'id': '2365936247',
  369.                 'ext': 'mp4',
  370.                 'title': 'Antiques Roadshow - Indianapolis, Hour 2',
  371.                 'description': 'md5:524b32249db55663e7231b6b8d1671a2',
  372.                 'duration': 3180,
  373.                 'thumbnail': r're:^https?://.*\.jpg$',
  374.             },
  375.             'params': {
  376.                 'skip_download': True,
  377.             },
  378.             'expected_warnings': ['HTTP Error 403: Forbidden'],
  379.         },
  380.         {
  381.             'url': 'https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/',
  382.             'info_dict': {
  383.                 'id': '3007193718',
  384.                 'ext': 'mp4',
  385.                 'title': "Victoria - A Soldier's Daughter / The Green-Eyed Monster",
  386.                 'description': 'md5:37efbac85e0c09b009586523ec143652',
  387.                 'duration': 6292,
  388.                 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
  389.             },
  390.             'params': {
  391.                 'skip_download': True,
  392.             },
  393.             'expected_warnings': ['HTTP Error 403: Forbidden'],
  394.         },
  395.         {
  396.             'url': 'https://player.pbs.org/partnerplayer/tOz9tM5ljOXQqIIWke53UA==/',
  397.             'info_dict': {
  398.                 'id': '3011407934',
  399.                 'ext': 'mp4',
  400.                 'title': 'Stories from the Stage - Road Trip',
  401.                 'duration': 1619,
  402.                 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
  403.             },
  404.             'params': {
  405.                 'skip_download': True,
  406.             },
  407.             'expected_warnings': ['HTTP Error 403: Forbidden'],
  408.         },
  409.         {
  410.             'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
  411.             'only_matching': True,
  412.         },
  413.         {
  414.             'url': 'http://watch.knpb.org/video/2365616055/',
  415.             'only_matching': True,
  416.         },
  417.         {
  418.             'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
  419.             'only_matching': True,
  420.         }
  421.     ]
  422.     _ERRORS = {
  423.         101: 'We\'re sorry, but this video is not yet available.',
  424.         403: 'We\'re sorry, but this video is not available in your region due to right restrictions.',
  425.         404: 'We are experiencing technical difficulties that are preventing us from playing the video at this time. Please check back again soon.',
  426.         410: 'This video has expired and is no longer available for online streaming.',
  427.     }
  429.     def _real_initialize(self):
  430.         cookie = (self._download_json(
  431.             'http://localization.services.pbs.org/localize/auto/cookie/',
  432.             None, headers=self.geo_verification_headers(), fatal=False) or {}).get('cookie')
  433.         if cookie:
  434.             station = self._search_regex(r'#?s=\["([^"]+)"', cookie, 'station')
  435.             if station:
  436.                 self._set_cookie('.pbs.org', 'pbsol.station', station)
  438.     def _extract_webpage(self, url):
  439.         mobj = re.match(self._VALID_URL, url)
  441.         description = None
  443.         presumptive_id = mobj.group('presumptive_id')
  444.         display_id = presumptive_id
  445.         if presumptive_id:
  446.             webpage = self._download_webpage(url, display_id)
  448.             description = strip_or_none(self._og_search_description(
  449.                 webpage, default=None) or self._html_search_meta(
  450.                 'description', webpage, default=None))
  451.             upload_date = unified_strdate(self._search_regex(
  452.                 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
  453.                 webpage, 'upload date', default=None))
  455.             # tabbed frontline videos
  456.             MULTI_PART_REGEXES = (
  457.                 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"',
  458.                 r'<a[^>]+href=["\']#(?:video-|part)\d+["\'][^>]+data-cove[Ii]d=["\'](\d+)',
  459.             )
  460.             for p in MULTI_PART_REGEXES:
  461.                 tabbed_videos = orderedSet(re.findall(p, webpage))
  462.                 if tabbed_videos:
  463.                     return tabbed_videos, presumptive_id, upload_date, description
  465.             MEDIA_ID_REGEXES = [
  466.                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
  467.                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
  468.                 r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
  469.                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
  470.                 r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
  471.                 r'<div[^>]+\bdata-cove-id=["\'](\d+)"',  # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/
  472.                 r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)',  # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/
  473.             ]
  475.             media_id = self._search_regex(
  476.                 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
  477.             if media_id:
  478.                 return media_id, presumptive_id, upload_date, description
  480.             # Frontline video embedded via flp
  481.             video_id = self._search_regex(
  482.                 r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None)
  483.             if video_id:
  484.                 # pkg_id calculation is reverse engineered from
  485.                 # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
  486.                 prg_id = self._search_regex(
  487.                     r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
  488.                 if 'q' in prg_id:
  489.                     prg_id = prg_id.split('q')[1]
  490.                 prg_id = int(prg_id, 16)
  491.                 getdir = self._download_json(
  492.                     'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
  493.                     presumptive_id, 'Downloading getdir JSON',
  494.                     transform_source=strip_jsonp)
  495.                 return getdir['mid'], presumptive_id, upload_date, description
  497.             for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
  498.                 url = self._search_regex(
  499.                     r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,
  500.                     'player URL', default=None, group='url')
  501.                 if url:
  502.                     break
  504.             if not url:
  505.                 url = self._og_search_url(webpage)
  507.             mobj = re.match(
  508.                 self._VALID_URL, self._proto_relative_url(url.strip()))
  510.         player_id = mobj.group('player_id')
  511.         if not display_id:
  512.             display_id = player_id
  513.         if player_id:
  514.             player_page = self._download_webpage(
  515.                 url, display_id, note='Downloading player page',
  516.                 errnote='Could not download player page')
  517.             video_id = self._search_regex(
  518.                 r'<div\s+id=["\']video_(\d+)', player_page, 'video ID',
  519.                 default=None)
  520.             if not video_id:
  521.                 video_info = self._extract_video_data(
  522.                     player_page, 'video data', display_id)
  523.                 video_id = compat_str(
  524.                     video_info.get('id') or video_info['contentID'])
  525.         else:
  526.             video_id = mobj.group('id')
  527.             display_id = video_id
  529.         return video_id, display_id, None, description
  531.     def _extract_video_data(self, string, name, video_id, fatal=True):
  532.         return self._parse_json(
  533.             self._search_regex(
  534.                 [r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
  535.                  r'window\.videoBridge\s*=\s*({.+?});'],
  536.                 string, name, default='{}'),
  537.             video_id, transform_source=js_to_json, fatal=fatal)
  539.     def _real_extract(self, url):
  540.         video_id, display_id, upload_date, description = self._extract_webpage(url)
  542.         if isinstance(video_id, list):
  543.             entries = [self.url_result(
  544.                 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
  545.                 for vid_id in video_id]
  546.             return self.playlist_result(entries, display_id)
  548.         info = None
  549.         redirects = []
  550.         redirect_urls = set()
  552.         def extract_redirect_urls(info):
  553.             for encoding_name in ('recommended_encoding', 'alternate_encoding'):
  554.                 redirect = info.get(encoding_name)
  555.                 if not redirect:
  556.                     continue
  557.                 redirect_url = redirect.get('url')
  558.                 if redirect_url and redirect_url not in redirect_urls:
  559.                     redirects.append(redirect)
  560.                     redirect_urls.add(redirect_url)
  561.             encodings = info.get('encodings')
  562.             if isinstance(encodings, list):
  563.                 for encoding in encodings:
  564.                     encoding_url = url_or_none(encoding)
  565.                     if encoding_url and encoding_url not in redirect_urls:
  566.                         redirects.append({'url': encoding_url})
  567.                         redirect_urls.add(encoding_url)
  569.         chapters = []
  570.         # Player pages may also serve different qualities
  571.         for page in ('widget/partnerplayer', 'portalplayer'):
  572.             player = self._download_webpage(
  573.                 'http://player.pbs.org/%s/%s' % (page, video_id),
  574.                 display_id, 'Downloading %s page' % page, fatal=False)
  575.             if player:
  576.                 video_info = self._extract_video_data(
  577.                     player, '%s video data' % page, display_id, fatal=False)
  578.                 if video_info:
  579.                     extract_redirect_urls(video_info)
  580.                     if not info:
  581.                         info = video_info
  582.                 if not chapters:
  583.                     raw_chapters = video_info.get('chapters') or []
  584.                     if not raw_chapters:
  585.                         for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player):
  586.                             chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False)
  587.                             if not chapter:
  588.                                 continue
  589.                             raw_chapters.append(chapter)
  590.                     for chapter in raw_chapters:
  591.                         start_time = float_or_none(chapter.get('start_time'), 1000)
  592.                         duration = float_or_none(chapter.get('duration'), 1000)
  593.                         if start_time is None or duration is None:
  594.                             continue
  595.                         chapters.append({
  596.                             'start_time': start_time,
  597.                             'end_time': start_time + duration,
  598.                             'title': chapter.get('title'),
  599.                         })
  601.         formats = []
  602.         http_url = None
  603.         for num, redirect in enumerate(redirects):
  604.             redirect_id = redirect.get('eeid')
  606.             redirect_info = self._download_json(
  607.                 '%s?format=json' % redirect['url'], display_id,
  608.                 'Downloading %s video url info' % (redirect_id or num),
  609.                 headers=self.geo_verification_headers())
  611.             if redirect_info['status'] == 'error':
  612.                 message = self._ERRORS.get(
  613.                     redirect_info['http_code'], redirect_info['message'])
  614.                 if redirect_info['http_code'] == 403:
  615.                     self.raise_geo_restricted(
  616.                         msg=message, countries=self._GEO_COUNTRIES)
  617.                 raise ExtractorError(
  618.                     '%s said: %s' % (self.IE_NAME, message), expected=True)
  620.             format_url = redirect_info.get('url')
  621.             if not format_url:
  622.                 continue
  624.             if determine_ext(format_url) == 'm3u8':
  625.                 formats.extend(self._extract_m3u8_formats(
  626.                     format_url, display_id, 'mp4', m3u8_id='hls', fatal=False))
  627.             else:
  628.                 formats.append({
  629.                     'url': format_url,
  630.                     'format_id': redirect_id,
  631.                 })
  632.                 if re.search(r'^https?://.*(?:\d+k|baseline)', format_url):
  633.                     http_url = format_url
  634.         self._remove_duplicate_formats(formats)
  635.         m3u8_formats = list(filter(
  636.             lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
  637.             formats))
  638.         if http_url:
  639.             for m3u8_format in m3u8_formats:
  640.                 bitrate = self._search_regex(r'(\d+)k', m3u8_format['url'], 'bitrate', default=None)
  641.                 # Lower qualities (150k and 192k) are not available as HTTP formats (see [1]),
  642.                 # we won't try extracting them.
  643.                 # Since summer 2016 higher quality formats (4500k and 6500k) are also available
  644.                 # albeit they are not documented in [2].
  645.                 # 1. https://github.com/ytdl-org/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656
  646.                 # 2. https://projects.pbs.org/confluence/display/coveapi/COVE+Video+Specifications
  647.                 if not bitrate or int(bitrate) < 400:
  648.                     continue
  649.                 f_url = re.sub(r'\d+k|baseline', bitrate + 'k', http_url)
  650.                 # This may produce invalid links sometimes (e.g.
  651.                 # http://www.pbs.org/wgbh/frontline/film/suicide-plan)
  652.                 if not self._is_valid_url(f_url, display_id, 'http-%sk video' % bitrate):
  653.                     continue
  654.                 f = m3u8_format.copy()
  655.                 f.update({
  656.                     'url': f_url,
  657.                     'format_id': m3u8_format['format_id'].replace('hls', 'http'),
  658.                     'protocol': 'http',
  659.                 })
  660.                 formats.append(f)
  661.         self._sort_formats(formats)
  663.         rating_str = info.get('rating')
  664.         if rating_str is not None:
  665.             rating_str = rating_str.rpartition('-')[2]
  666.         age_limit = US_RATINGS.get(rating_str)
  668.         subtitles = {}
  669.         closed_captions_url = info.get('closed_captions_url')
  670.         if closed_captions_url:
  671.             subtitles['en'] = [{
  672.                 'ext': 'ttml',
  673.                 'url': closed_captions_url,
  674.             }]
  675.             mobj = re.search(r'/(\d+)_Encoded\.dfxp', closed_captions_url)
  676.             if mobj:
  677.                 ttml_caption_suffix, ttml_caption_id = mobj.group(0, 1)
  678.                 ttml_caption_id = int(ttml_caption_id)
  679.                 subtitles['en'].extend([{
  680.                     'url': closed_captions_url.replace(
  681.                         ttml_caption_suffix, '/%d_Encoded.srt' % (ttml_caption_id + 1)),
  682.                     'ext': 'srt',
  683.                 }, {
  684.                     'url': closed_captions_url.replace(
  685.                         ttml_caption_suffix, '/%d_Encoded.vtt' % (ttml_caption_id + 2)),
  686.                     'ext': 'vtt',
  687.                 }])
  689.         # info['title'] is often incomplete (e.g. 'Full Episode', 'Episode 5', etc)
  690.         # Try turning it to 'program - title' naming scheme if possible
  691.         alt_title = info.get('program', {}).get('title')
  692.         if alt_title:
  693.             info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + r'[\s\-:]+', '', info['title'])
  695.         description = info.get('description') or info.get(
  696.             'program', {}).get('description') or description
  698.         return {
  699.             'id': video_id,
  700.             'display_id': display_id,
  701.             'title': info['title'],
  702.             'description': description,
  703.             'thumbnail': info.get('image_url'),
  704.             'duration': int_or_none(info.get('duration')),
  705.             'age_limit': age_limit,
  706.             'upload_date': upload_date,
  707.             'formats': formats,
  708.             'subtitles': subtitles,
  709.             'chapters': chapters,
  710.         }