]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/pbs.py
debian/changelog: Fix spelling of Re-enable to please lintian.
[youtubedl] / youtube_dl / extractor / pbs.py
index 8fb9b1849cfd96e5ce21ef2ffcffba200f8ba482..b490ef74c5fb768751d4598ff88e70a13d41c060 100644 (file)
@@ -8,52 +8,213 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
+    js_to_json,
     strip_jsonp,
+    strip_or_none,
     unified_strdate,
     US_RATINGS,
 )
 
 
 class PBSIE(InfoExtractor):
+    _STATIONS = (
+        (r'(?:video|www|player)\.pbs\.org', 'PBS: Public Broadcasting Service'),  # http://www.pbs.org/
+        (r'video\.aptv\.org', 'APT - Alabama Public Television (WBIQ)'),  # http://aptv.org/
+        (r'video\.gpb\.org', 'GPB/Georgia Public Broadcasting (WGTV)'),  # http://www.gpb.org/
+        (r'video\.mpbonline\.org', 'Mississippi Public Broadcasting (WMPN)'),  # http://www.mpbonline.org
+        (r'video\.wnpt\.org', 'Nashville Public Television (WNPT)'),  # http://www.wnpt.org
+        (r'video\.wfsu\.org', 'WFSU-TV (WFSU)'),  # http://wfsu.org/
+        (r'video\.wsre\.org', 'WSRE (WSRE)'),  # http://www.wsre.org
+        (r'video\.wtcitv\.org', 'WTCI (WTCI)'),  # http://www.wtcitv.org
+        (r'video\.pba\.org', 'WPBA/Channel 30 (WPBA)'),  # http://pba.org/
+        (r'video\.alaskapublic\.org', 'Alaska Public Media (KAKM)'),  # http://alaskapublic.org/kakm
+        # (r'kuac\.org', 'KUAC (KUAC)'),  # http://kuac.org/kuac-tv/
+        # (r'ktoo\.org', '360 North (KTOO)'),  # http://www.ktoo.org/
+        # (r'azpm\.org', 'KUAT 6 (KUAT)'),  # http://www.azpm.org/
+        (r'video\.azpbs\.org', 'Arizona PBS (KAET)'),  # http://www.azpbs.org
+        (r'portal\.knme\.org', 'KNME-TV/Channel 5 (KNME)'),  # http://www.newmexicopbs.org/
+        (r'video\.vegaspbs\.org', 'Vegas PBS (KLVX)'),  # http://vegaspbs.org/
+        (r'watch\.aetn\.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'),  # http://www.aetn.org/
+        (r'video\.ket\.org', 'KET (WKLE)'),  # http://www.ket.org/
+        (r'video\.wkno\.org', 'WKNO/Channel 10 (WKNO)'),  # http://www.wkno.org/
+        (r'video\.lpb\.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'),  # http://www.lpb.org/
+        (r'videos\.oeta\.tv', 'OETA (KETA)'),  # http://www.oeta.tv
+        (r'video\.optv\.org', 'Ozarks Public Television (KOZK)'),  # http://www.optv.org/
+        (r'watch\.wsiu\.org', 'WSIU Public Broadcasting (WSIU)'),  # http://www.wsiu.org/
+        (r'video\.keet\.org', 'KEET TV (KEET)'),  # http://www.keet.org
+        (r'pbs\.kixe\.org', 'KIXE/Channel 9 (KIXE)'),  # http://kixe.org/
+        (r'video\.kpbs\.org', 'KPBS San Diego (KPBS)'),  # http://www.kpbs.org/
+        (r'video\.kqed\.org', 'KQED (KQED)'),  # http://www.kqed.org
+        (r'vids\.kvie\.org', 'KVIE Public Television (KVIE)'),  # http://www.kvie.org
+        (r'video\.pbssocal\.org', 'PBS SoCal/KOCE (KOCE)'),  # http://www.pbssocal.org/
+        (r'video\.valleypbs\.org', 'ValleyPBS (KVPT)'),  # http://www.valleypbs.org/
+        (r'video\.cptv\.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'),  # http://cptv.org
+        (r'watch\.knpb\.org', 'KNPB Channel 5 (KNPB)'),  # http://www.knpb.org/
+        (r'video\.soptv\.org', 'SOPTV (KSYS)'),  # http://www.soptv.org
+        # (r'klcs\.org', 'KLCS/Channel 58 (KLCS)'),  # http://www.klcs.org
+        # (r'krcb\.org', 'KRCB Television & Radio (KRCB)'),  # http://www.krcb.org
+        # (r'kvcr\.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'),  # http://kvcr.org
+        (r'video\.rmpbs\.org', 'Rocky Mountain PBS (KRMA)'),  # http://www.rmpbs.org
+        (r'video\.kenw\.org', 'KENW-TV3 (KENW)'),  # http://www.kenw.org
+        (r'video\.kued\.org', 'KUED Channel 7 (KUED)'),  # http://www.kued.org
+        (r'video\.wyomingpbs\.org', 'Wyoming PBS (KCWC)'),  # http://www.wyomingpbs.org
+        (r'video\.cpt12\.org', 'Colorado Public Television / KBDI 12 (KBDI)'),  # http://www.cpt12.org/
+        (r'video\.kbyueleven\.org', 'KBYU-TV (KBYU)'),  # http://www.kbyutv.org/
+        (r'video\.thirteen\.org', 'Thirteen/WNET New York (WNET)'),  # http://www.thirteen.org
+        (r'video\.wgbh\.org', 'WGBH/Channel 2 (WGBH)'),  # http://wgbh.org
+        (r'video\.wgby\.org', 'WGBY (WGBY)'),  # http://www.wgby.org
+        (r'watch\.njtvonline\.org', 'NJTV Public Media NJ (WNJT)'),  # http://www.njtvonline.org/
+        # (r'ripbs\.org', 'Rhode Island PBS (WSBE)'),  # http://www.ripbs.org/home/
+        (r'watch\.wliw\.org', 'WLIW21 (WLIW)'),  # http://www.wliw.org/
+        (r'video\.mpt\.tv', 'mpt/Maryland Public Television (WMPB)'),  # http://www.mpt.org
+        (r'watch\.weta\.org', 'WETA Television and Radio (WETA)'),  # http://www.weta.org
+        (r'video\.whyy\.org', 'WHYY (WHYY)'),  # http://www.whyy.org
+        (r'video\.wlvt\.org', 'PBS 39 (WLVT)'),  # http://www.wlvt.org/
+        (r'video\.wvpt\.net', 'WVPT - Your Source for PBS and More! (WVPT)'),  # http://www.wvpt.net
+        (r'video\.whut\.org', 'Howard University Television (WHUT)'),  # http://www.whut.org
+        (r'video\.wedu\.org', 'WEDU PBS (WEDU)'),  # http://www.wedu.org
+        (r'video\.wgcu\.org', 'WGCU Public Media (WGCU)'),  # http://www.wgcu.org/
+        # (r'wjct\.org', 'WJCT Public Broadcasting (WJCT)'),  # http://www.wjct.org
+        (r'video\.wpbt2\.org', 'WPBT2 (WPBT)'),  # http://www.wpbt2.org
+        (r'video\.wucftv\.org', 'WUCF TV (WUCF)'),  # http://wucftv.org
+        (r'video\.wuft\.org', 'WUFT/Channel 5 (WUFT)'),  # http://www.wuft.org
+        (r'watch\.wxel\.org', 'WXEL/Channel 42 (WXEL)'),  # http://www.wxel.org/home/
+        (r'video\.wlrn\.org', 'WLRN/Channel 17 (WLRN)'),  # http://www.wlrn.org/
+        (r'video\.wusf\.usf\.edu', 'WUSF Public Broadcasting (WUSF)'),  # http://wusf.org/
+        (r'video\.scetv\.org', 'ETV (WRLK)'),  # http://www.scetv.org
+        (r'video\.unctv\.org', 'UNC-TV (WUNC)'),  # http://www.unctv.org/
+        # (r'pbsguam\.org', 'PBS Guam (KGTF)'),  # http://www.pbsguam.org/
+        (r'video\.pbshawaii\.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'),  # http://www.pbshawaii.org/
+        (r'video\.idahoptv\.org', 'Idaho Public Television (KAID)'),  # http://idahoptv.org
+        (r'video\.ksps\.org', 'KSPS (KSPS)'),  # http://www.ksps.org/home/
+        (r'watch\.opb\.org', 'OPB (KOPB)'),  # http://www.opb.org
+        (r'watch\.nwptv\.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'),  # http://www.kwsu.org
+        (r'video\.will\.illinois\.edu', 'WILL-TV (WILL)'),  # http://will.illinois.edu/
+        (r'video\.networkknowledge\.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'),  # http://www.wsec.tv
+        (r'video\.wttw\.com', 'WTTW11 (WTTW)'),  # http://www.wttw.com/
+        # (r'wtvp\.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'),  # http://www.wtvp.org/
+        (r'video\.iptv\.org', 'Iowa Public Television/IPTV (KDIN)'),  # http://www.iptv.org/
+        (r'video\.ninenet\.org', 'Nine Network (KETC)'),  # http://www.ninenet.org
+        (r'video\.wfwa\.org', 'PBS39 Fort Wayne (WFWA)'),  # http://wfwa.org/
+        (r'video\.wfyi\.org', 'WFYI Indianapolis (WFYI)'),  # http://www.wfyi.org
+        (r'video\.mptv\.org', 'Milwaukee Public Television (WMVS)'),  # http://www.mptv.org
+        (r'video\.wnin\.org', 'WNIN (WNIN)'),  # http://www.wnin.org/
+        (r'video\.wnit\.org', 'WNIT Public Television (WNIT)'),  # http://www.wnit.org/
+        (r'video\.wpt\.org', 'WPT (WPNE)'),  # http://www.wpt.org/
+        (r'video\.wvut\.org', 'WVUT/Channel 22 (WVUT)'),  # http://wvut.org/
+        (r'video\.weiu\.net', 'WEIU/Channel 51 (WEIU)'),  # http://www.weiu.net
+        (r'video\.wqpt\.org', 'WQPT-TV (WQPT)'),  # http://www.wqpt.org
+        (r'video\.wycc\.org', 'WYCC PBS Chicago (WYCC)'),  # http://www.wycc.org
+        # (r'lakeshorepublicmedia\.org', 'Lakeshore Public Television (WYIN)'),  # http://lakeshorepublicmedia.org/
+        (r'video\.wipb\.org', 'WIPB-TV (WIPB)'),  # http://wipb.org
+        (r'video\.indianapublicmedia\.org', 'WTIU (WTIU)'),  # http://indianapublicmedia.org/tv/
+        (r'watch\.cetconnect\.org', 'CET  (WCET)'),  # http://www.cetconnect.org
+        (r'video\.thinktv\.org', 'ThinkTVNetwork (WPTD)'),  # http://www.thinktv.org
+        (r'video\.wbgu\.org', 'WBGU-TV (WBGU)'),  # http://wbgu.org
+        (r'video\.wgvu\.org', 'WGVU TV (WGVU)'),  # http://www.wgvu.org/
+        (r'video\.netnebraska\.org', 'NET1 (KUON)'),  # http://netnebraska.org
+        (r'video\.pioneer\.org', 'Pioneer Public Television (KWCM)'),  # http://www.pioneer.org
+        (r'watch\.sdpb\.org', 'SDPB Television (KUSD)'),  # http://www.sdpb.org
+        (r'video\.tpt\.org', 'TPT (KTCA)'),  # http://www.tpt.org
+        (r'watch\.ksmq\.org', 'KSMQ (KSMQ)'),  # http://www.ksmq.org/
+        (r'watch\.kpts\.org', 'KPTS/Channel 8 (KPTS)'),  # http://www.kpts.org/
+        (r'watch\.ktwu\.org', 'KTWU/Channel 11 (KTWU)'),  # http://ktwu.org
+        # (r'shptv\.org', 'Smoky Hills Public Television (KOOD)'),  # http://www.shptv.org
+        # (r'kcpt\.org', 'KCPT Kansas City Public Television (KCPT)'),  # http://kcpt.org/
+        # (r'blueridgepbs\.org', 'Blue Ridge PBS (WBRA)'),  # http://www.blueridgepbs.org/
+        (r'watch\.easttennesseepbs\.org', 'East Tennessee PBS (WSJK)'),  # http://easttennesseepbs.org
+        (r'video\.wcte\.tv', 'WCTE-TV (WCTE)'),  # http://www.wcte.org
+        (r'video\.wljt\.org', 'WLJT, Channel 11 (WLJT)'),  # http://wljt.org/
+        (r'video\.wosu\.org', 'WOSU TV (WOSU)'),  # http://wosu.org/
+        (r'video\.woub\.org', 'WOUB/WOUC (WOUB)'),  # http://woub.org/tv/index.php?section=5
+        (r'video\.wvpublic\.org', 'WVPB (WVPB)'),  # http://wvpublic.org/
+        (r'video\.wkyupbs\.org', 'WKYU-PBS (WKYU)'),  # http://www.wkyupbs.org
+        # (r'wyes\.org', 'WYES-TV/New Orleans (WYES)'),  # http://www.wyes.org
+        (r'video\.kera\.org', 'KERA 13 (KERA)'),  # http://www.kera.org/
+        (r'video\.mpbn\.net', 'MPBN (WCBB)'),  # http://www.mpbn.net/
+        (r'video\.mountainlake\.org', 'Mountain Lake PBS (WCFE)'),  # http://www.mountainlake.org/
+        (r'video\.nhptv\.org', 'NHPTV (WENH)'),  # http://nhptv.org/
+        (r'video\.vpt\.org', 'Vermont PBS (WETK)'),  # http://www.vpt.org
+        (r'video\.witf\.org', 'witf (WITF)'),  # http://www.witf.org
+        (r'watch\.wqed\.org', 'WQED Multimedia (WQED)'),  # http://www.wqed.org/
+        (r'video\.wmht\.org', 'WMHT Educational Telecommunications (WMHT)'),  # http://www.wmht.org/home/
+        (r'video\.deltabroadcasting\.org', 'Q-TV (WDCQ)'),  # http://www.deltabroadcasting.org
+        (r'video\.dptv\.org', 'WTVS Detroit Public TV (WTVS)'),  # http://www.dptv.org/
+        (r'video\.wcmu\.org', 'CMU Public Television (WCMU)'),  # http://www.wcmu.org
+        (r'video\.wkar\.org', 'WKAR-TV (WKAR)'),  # http://wkar.org/
+        (r'wnmuvideo\.nmu\.edu', 'WNMU-TV Public TV 13 (WNMU)'),  # http://wnmutv.nmu.edu
+        (r'video\.wdse\.org', 'WDSE - WRPT (WDSE)'),  # http://www.wdse.org/
+        (r'video\.wgte\.org', 'WGTE TV (WGTE)'),  # http://www.wgte.org
+        (r'video\.lptv\.org', 'Lakeland Public Television (KAWE)'),  # http://www.lakelandptv.org
+        # (r'prairiepublic\.org', 'PRAIRIE PUBLIC (KFME)'),  # http://www.prairiepublic.org/
+        (r'video\.kmos\.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'),  # http://www.kmos.org/
+        (r'watch\.montanapbs\.org', 'MontanaPBS (KUSM)'),  # http://montanapbs.org
+        (r'video\.krwg\.org', 'KRWG/Channel 22 (KRWG)'),  # http://www.krwg.org
+        (r'video\.kacvtv\.org', 'KACV (KACV)'),  # http://www.panhandlepbs.org/home/
+        (r'video\.kcostv\.org', 'KCOS/Channel 13 (KCOS)'),  # www.kcostv.org
+        (r'video\.wcny\.org', 'WCNY/Channel 24 (WCNY)'),  # http://www.wcny.org
+        (r'video\.wned\.org', 'WNED (WNED)'),  # http://www.wned.org/
+        (r'watch\.wpbstv\.org', 'WPBS (WPBS)'),  # http://www.wpbstv.org
+        (r'video\.wskg\.org', 'WSKG Public TV (WSKG)'),  # http://wskg.org
+        (r'video\.wxxi\.org', 'WXXI (WXXI)'),  # http://wxxi.org
+        (r'video\.wpsu\.org', 'WPSU (WPSU)'),  # http://www.wpsu.org
+        # (r'wqln\.org', 'WQLN/Channel 54 (WQLN)'),  # http://www.wqln.org
+        (r'on-demand\.wvia\.org', 'WVIA Public Media Studios (WVIA)'),  # http://www.wvia.org/
+        (r'video\.wtvi\.org', 'WTVI (WTVI)'),  # http://www.wtvi.org/
+        # (r'whro\.org', 'WHRO (WHRO)'),  # http://whro.org
+        (r'video\.westernreservepublicmedia\.org', 'Western Reserve PBS (WNEO)'),  # http://www.WesternReservePublicMedia.org/
+        (r'video\.ideastream\.org', 'WVIZ/PBS ideastream (WVIZ)'),  # http://www.wviz.org/
+        (r'video\.kcts9\.org', 'KCTS 9 (KCTS)'),  # http://kcts9.org/
+        (r'video\.basinpbs\.org', 'Basin PBS (KPBT)'),  # http://www.basinpbs.org
+        (r'video\.houstonpbs\.org', 'KUHT / Channel 8 (KUHT)'),  # http://www.houstonpublicmedia.org/
+        # (r'tamu\.edu', 'KAMU - TV (KAMU)'),  # http://KAMU.tamu.edu
+        # (r'kedt\.org', 'KEDT/Channel 16 (KEDT)'),  # http://www.kedt.org
+        (r'video\.klrn\.org', 'KLRN (KLRN)'),  # http://www.klrn.org
+        (r'video\.klru\.tv', 'KLRU (KLRU)'),  # http://www.klru.org
+        # (r'kmbh\.org', 'KMBH-TV (KMBH)'),  # http://www.kmbh.org
+        # (r'knct\.org', 'KNCT (KNCT)'),  # http://www.knct.org
+        # (r'ktxt\.org', 'KTTZ-TV (KTXT)'),  # http://www.ktxt.org
+        (r'video\.wtjx\.org', 'WTJX Channel 12 (WTJX)'),  # http://www.wtjx.org/
+        (r'video\.ideastations\.org', 'WCVE PBS (WCVE)'),  # http://ideastations.org/
+        (r'video\.kbtc\.org', 'KBTC Public Television (KBTC)'),  # http://kbtc.org
+    )
+
+    IE_NAME = 'pbs'
+    IE_DESC = 'Public Broadcasting Service (PBS) and member stations: %s' % ', '.join(list(zip(*_STATIONS))[1])
+
     _VALID_URL = r'''(?x)https?://
         (?:
            # Direct video URL
-           video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+           (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
            # Article with embedded player (or direct video)
            (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
-           video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
+           (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
-    '''
+    ''' % '|'.join(list(zip(*_STATIONS))[0])
 
     _TESTS = [
         {
             'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
-            'md5': 'ce1888486f0908d555a8093cac9a7362',
+            'md5': '173dc391afd361fa72eab5d3d918968d',
             'info_dict': {
                 'id': '2365006249',
                 'ext': 'mp4',
                 'title': 'Constitution USA with Peter Sagal - A More Perfect Union',
-                'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
+                'description': 'md5:31b664af3c65fd07fa460d306b837d00',
                 'duration': 3190,
             },
-            'params': {
-                'skip_download': True,  # requires ffmpeg
-            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
-            'md5': '143c98aa54a346738a3d78f54c925321',
+            'md5': '6f722cb3c3982186d34b0f13374499c7',
             'info_dict': {
                 'id': '2365297690',
                 'ext': 'mp4',
                 'title': 'FRONTLINE - Losing Iraq',
-                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+                'description': 'md5:5979a4d069b157f622d02bff62fbe654',
                 'duration': 5050,
             },
-            'params': {
-                'skip_download': True,  # requires ffmpeg
-            }
         },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
@@ -62,7 +223,7 @@ class PBSIE(InfoExtractor):
                 'id': '2201174722',
                 'ext': 'mp4',
                 'title': 'PBS NewsHour - Cyber Schools Gain Popularity, but Quality Questions Persist',
-                'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
+                'description': 'md5:86ab9a3d04458b876147b355788b8781',
                 'duration': 801,
             },
         },
@@ -72,14 +233,11 @@ class PBSIE(InfoExtractor):
             'info_dict': {
                 'id': '2365297708',
                 'ext': 'mp4',
-                'description': 'md5:68d87ef760660eb564455eb30ca464fe',
                 'title': 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
+                'description': 'md5:657897370e09e2bc6bf0f8d2cd313c6b',
                 'duration': 6559,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
-            'params': {
-                'skip_download': True,  # requires ffmpeg
-            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
@@ -95,9 +253,6 @@ class PBSIE(InfoExtractor):
                 'upload_date': '20140122',
                 'age_limit': 10,
             },
-            'params': {
-                'skip_download': True,  # requires ffmpeg
-            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
@@ -113,7 +268,7 @@ class PBSIE(InfoExtractor):
                 'display_id': 'player',
                 'ext': 'mp4',
                 'title': 'American Experience - Death and the Civil War, Chapter 1',
-                'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
+                'description': 'md5:67fa89a9402e2ee7d08f53b920674c18',
                 'duration': 682,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
@@ -122,38 +277,33 @@ class PBSIE(InfoExtractor):
             },
         },
         {
-            'url': 'http://video.pbs.org/video/2365367186/',
+            'url': 'http://www.pbs.org/video/2365245528/',
+            'md5': '115223d41bd55cda8ae5cd5ed4e11497',
             'info_dict': {
-                'id': '2365367186',
-                'display_id': '2365367186',
+                'id': '2365245528',
+                'display_id': '2365245528',
                 'ext': 'mp4',
-                'title': 'To Catch A Comet - Full Episode',
-                'description': 'On November 12, 2014, billions of kilometers from Earth, spacecraft orbiter Rosetta and lander Philae did what no other had dared to attempt \u2014 land on the volatile surface of a comet as it zooms around the sun at 67,000 km/hr. The European Space Agency hopes this mission can help peer into our past and unlock secrets of our origins.',
-                'duration': 3342,
+                'title': 'FRONTLINE - United States of Secrets (Part One)',
+                'description': 'md5:55756bd5c551519cc4b7703e373e217e',
+                'duration': 6851,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
-            'params': {
-                'skip_download': True,  # requires ffmpeg
-            },
-            'skip': 'Expired',
         },
         {
             # Video embedded in iframe containing angle brackets as attribute's value (e.g.
             # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
             # https://github.com/rg3/youtube-dl/issues/7059)
             'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
+            'md5': '59b0ef5009f9ac8a319cc5efebcd865e',
             'info_dict': {
                 'id': '2365546844',
                 'display_id': 'a-chefs-life-season-3-episode-5-prickly-business',
                 'ext': 'mp4',
                 'title': "A Chef's Life - Season 3, Ep. 5: Prickly Business",
-                'description': 'md5:61db2ddf27c9912f09c241014b118ed1',
+                'description': 'md5:c0ff7475a4b70261c7e58f493c2792a5',
                 'duration': 1480,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
-            'params': {
-                'skip_download': True,  # requires ffmpeg
-            },
         },
         {
             # Frontline video embedded via flp2012.js
@@ -163,13 +313,34 @@ class PBSIE(InfoExtractor):
                 'display_id': 'the-atomic-artists',
                 'ext': 'mp4',
                 'title': 'FRONTLINE - The Atomic Artists',
-                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+                'description': 'md5:f677e4520cfacb4a5ce1471e31b57800',
                 'duration': 723,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
             'params': {
                 'skip_download': True,  # requires ffmpeg
             },
+        },
+        {
+            # Serves hd only via wigget/partnerplayer page
+            'url': 'http://www.pbs.org/video/2365641075/',
+            'md5': 'fdf907851eab57211dd589cf12006666',
+            'info_dict': {
+                'id': '2365641075',
+                'ext': 'mp4',
+                'title': 'FRONTLINE - Netanyahu at War',
+                'duration': 6852,
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'formats': 'mincount:8',
+            },
+        },
+        {
+            'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://watch.knpb.org/video/2365616055/',
+            'only_matching': True,
         }
     ]
     _ERRORS = {
@@ -182,31 +353,41 @@ class PBSIE(InfoExtractor):
     def _extract_webpage(self, url):
         mobj = re.match(self._VALID_URL, url)
 
+        description = None
+
         presumptive_id = mobj.group('presumptive_id')
         display_id = presumptive_id
         if presumptive_id:
             webpage = self._download_webpage(url, display_id)
 
+            description = strip_or_none(self._og_search_description(
+                webpage, default=None) or self._html_search_meta(
+                'description', webpage, default=None))
             upload_date = unified_strdate(self._search_regex(
                 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
                 webpage, 'upload date', default=None))
 
             # tabbed frontline videos
-            tabbed_videos = re.findall(
-                r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
-            if tabbed_videos:
-                return tabbed_videos, presumptive_id, upload_date
+            MULTI_PART_REGEXES = (
+                r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"',
+                r'<a[^>]+href=["\']#video-\d+["\'][^>]+data-coveid=["\'](\d+)',
+            )
+            for p in MULTI_PART_REGEXES:
+                tabbed_videos = re.findall(p, webpage)
+                if tabbed_videos:
+                    return tabbed_videos, presumptive_id, upload_date, description
 
             MEDIA_ID_REGEXES = [
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
+                r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
             ]
 
             media_id = self._search_regex(
                 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
             if media_id:
-                return media_id, presumptive_id, upload_date
+                return media_id, presumptive_id, upload_date, description
 
             # Fronline video embedded via flp
             video_id = self._search_regex(
@@ -223,7 +404,7 @@ class PBSIE(InfoExtractor):
                     'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
                     presumptive_id, 'Downloading getdir JSON',
                     transform_source=strip_jsonp)
-                return getdir['mid'], presumptive_id, upload_date
+                return getdir['mid'], presumptive_id, upload_date, description
 
             for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
                 url = self._search_regex(
@@ -247,10 +428,10 @@ class PBSIE(InfoExtractor):
             video_id = mobj.group('id')
             display_id = video_id
 
-        return video_id, display_id, None
+        return video_id, display_id, None, description
 
     def _real_extract(self, url):
-        video_id, display_id, upload_date = self._extract_webpage(url)
+        video_id, display_id, upload_date, description = self._extract_webpage(url)
 
         if isinstance(video_id, list):
             entries = [self.url_result(
@@ -258,22 +439,44 @@ class PBSIE(InfoExtractor):
                 for vid_id in video_id]
             return self.playlist_result(entries, display_id)
 
-        info = self._download_json(
-            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
-            display_id)
+        info = None
+        redirects = []
+        redirect_urls = set()
+
+        def extract_redirect_urls(info):
+            for encoding_name in ('recommended_encoding', 'alternate_encoding'):
+                redirect = info.get(encoding_name)
+                if not redirect:
+                    continue
+                redirect_url = redirect.get('url')
+                if redirect_url and redirect_url not in redirect_urls:
+                    redirects.append(redirect)
+                    redirect_urls.add(redirect_url)
+
+        # Player pages may also serve different qualities
+        for page in ('widget/partnerplayer', 'portalplayer'):
+            player = self._download_webpage(
+                'http://player.pbs.org/%s/%s' % (page, video_id),
+                display_id, 'Downloading %s page' % page, fatal=False)
+            if player:
+                video_info = self._parse_json(
+                    self._search_regex(
+                        r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
+                        player, '%s video data' % page, default='{}'),
+                    display_id, transform_source=js_to_json, fatal=False)
+                if video_info:
+                    extract_redirect_urls(video_info)
+                    if not info:
+                        info = video_info
 
         formats = []
-        for encoding_name in ('recommended_encoding', 'alternate_encoding'):
-            redirect = info.get(encoding_name)
-            if not redirect:
-                continue
-            redirect_url = redirect.get('url')
-            if not redirect_url:
-                continue
+        http_url = None
+        for num, redirect in enumerate(redirects):
+            redirect_id = redirect.get('eeid')
 
             redirect_info = self._download_json(
-                redirect_url + '?format=json', display_id,
-                'Downloading %s video url info' % encoding_name)
+                '%s?format=json' % redirect['url'], display_id,
+                'Downloading %s video url info' % (redirect_id or num))
 
             if redirect_info['status'] == 'error':
                 raise ExtractorError(
@@ -288,12 +491,41 @@ class PBSIE(InfoExtractor):
 
             if determine_ext(format_url) == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
-                    format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
+                    format_url, display_id, 'mp4', m3u8_id='hls', fatal=False))
             else:
                 formats.append({
                     'url': format_url,
-                    'format_id': redirect.get('eeid'),
+                    'format_id': redirect_id,
                 })
+                if re.search(r'^https?://.*(?:\d+k|baseline)', format_url):
+                    http_url = format_url
+        self._remove_duplicate_formats(formats)
+        m3u8_formats = list(filter(
+            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            formats))
+        if http_url:
+            for m3u8_format in m3u8_formats:
+                bitrate = self._search_regex(r'(\d+)k', m3u8_format['url'], 'bitrate', default=None)
+                # Lower qualities (150k and 192k) are not available as HTTP formats (see [1]),
+                # we won't try extracting them.
+                # Since summer 2016 higher quality formats (4500k and 6500k) are also available
+                # albeit they are not documented in [2].
+                # 1. https://github.com/rg3/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656
+                # 2. https://projects.pbs.org/confluence/display/coveapi/COVE+Video+Specifications
+                if not bitrate or int(bitrate) < 400:
+                    continue
+                f_url = re.sub(r'\d+k|baseline', bitrate + 'k', http_url)
+                # This may produce invalid links sometimes (e.g.
+                # http://www.pbs.org/wgbh/frontline/film/suicide-plan)
+                if not self._is_valid_url(f_url, display_id, 'http-%sk video' % bitrate):
+                    continue
+                f = m3u8_format.copy()
+                f.update({
+                    'url': f_url,
+                    'format_id': m3u8_format['format_id'].replace('hls', 'http'),
+                    'protocol': 'http',
+                })
+                formats.append(f)
         self._sort_formats(formats)
 
         rating_str = info.get('rating')
@@ -308,6 +540,19 @@ class PBSIE(InfoExtractor):
                 'ext': 'ttml',
                 'url': closed_captions_url,
             }]
+            mobj = re.search(r'/(\d+)_Encoded\.dfxp', closed_captions_url)
+            if mobj:
+                ttml_caption_suffix, ttml_caption_id = mobj.group(0, 1)
+                ttml_caption_id = int(ttml_caption_id)
+                subtitles['en'].extend([{
+                    'url': closed_captions_url.replace(
+                        ttml_caption_suffix, '/%d_Encoded.srt' % (ttml_caption_id + 1)),
+                    'ext': 'srt',
+                }, {
+                    'url': closed_captions_url.replace(
+                        ttml_caption_suffix, '/%d_Encoded.vtt' % (ttml_caption_id + 2)),
+                    'ext': 'vtt',
+                }])
 
         # info['title'] is often incomplete (e.g. 'Full Episode', 'Episode 5', etc)
         # Try turning it to 'program - title' naming scheme if possible
@@ -315,11 +560,14 @@ class PBSIE(InfoExtractor):
         if alt_title:
             info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + '[\s\-:]+', '', info['title'])
 
+        description = info.get('description') or info.get(
+            'program', {}).get('description') or description
+
         return {
             'id': video_id,
             'display_id': display_id,
             'title': info['title'],
-            'description': info['program'].get('description'),
+            'description': description,
             'thumbnail': info.get('image_url'),
             'duration': int_or_none(info.get('duration')),
             'age_limit': age_limit,