X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/d9d7cd0e85dc712461d9185db9df9d6c900a573b..9113dfef91df19343cf76c6274dd0a85258c1004:/youtube_dl/extractor/pbs.py diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 16cc667..f11d5da 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -187,9 +187,9 @@ class PBSIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?: # Direct video URL - (?:%s)/(?:viralplayer|video)/(?P[0-9]+)/? | + (?:%s)/(?:(?:vir|port)alplayer|video)/(?P[0-9]+)(?:[?/]|$) | # Article with embedded player (or direct video) - (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | + (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P[^/]+)/ ) @@ -345,6 +345,21 @@ class PBSIE(InfoExtractor): 'formats': 'mincount:8', }, }, + { + # https://github.com/rg3/youtube-dl/issues/13801 + 'url': 'https://www.pbs.org/video/pbs-newshour-full-episode-july-31-2017-1501539057/', + 'info_dict': { + 'id': '3003333873', + 'ext': 'mp4', + 'title': 'PBS NewsHour - full episode July 31, 2017', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 3265, + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true', 'only_matching': True, @@ -352,6 +367,10 @@ class PBSIE(InfoExtractor): { 'url': 'http://watch.knpb.org/video/2365616055/', 'only_matching': True, + }, + { + 'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=', + 'only_matching': True, } ] _ERRORS = { @@ -402,6 +421,7 @@ class PBSIE(InfoExtractor): r'class="coveplayerid">([^<]+)<', # coveplayer r']+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/ r'', # jwplayer + r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',", ] media_id = self._search_regex( @@ -433,6 +453,9 @@ class PBSIE(InfoExtractor): if url: break + if not url: + url = self._og_search_url(webpage) + mobj = re.match(self._VALID_URL, url) player_id = mobj.group('player_id')