gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[pbs] Add support for new URL schema (closes #13801)

Browse source
This commit is contained in:
Sergey M․ 2017-08-03 23:19:59 +07:00
parent 8cda78ef72
commit 183062a4ab
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 19 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
youtube_dl/extractor/pbs.py
View file

@ -189,7 +189,7 @@ class PBSIE(InfoExtractor):
# Direct video URL # Direct video URL
(?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? | (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
# Article with embedded player (or direct video) # Article with embedded player (or direct video)
(?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) | (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
# Player # Player
(?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
) )
@ -345,6 +345,21 @@ class PBSIE(InfoExtractor):
'formats': 'mincount:8', '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', 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
'only_matching': True, 'only_matching': True,
@ -433,6 +448,9 @@ class PBSIE(InfoExtractor):
if url: if url:
break break
if not url:
url = self._og_search_url(webpage)
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
player_id = mobj.group('player_id') player_id = mobj.group('player_id')