etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-25 02:45:12 +00:00
Code Issues Projects Releases Wiki Activity

PBS: make thirteen.org work

Browse source
This commit is contained in:
Roland Hieber 2024-10-06 21:11:14 +02:00
parent 869950690d
commit 1e7153125b
1 changed files with 17 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
yt_dlp/extractor/pbs.py
View file

@ -188,7 +188,7 @@ class PBSIE(InfoExtractor):
# Direct video URL # Direct video URL
(?:{})/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) | (?:{})/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
# Article with embedded player (or direct video) # Article with embedded player (or direct video)
(?:www\.)?pbs\.org/(?:[^/]+/){{1,5}}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) | (?:www\.)?(thirteen|pbs)\.org/(?:[^/]+/){{1,5}}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
# Player # Player
(?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+) (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)
) )
@ -197,6 +197,19 @@ class PBSIE(InfoExtractor):
_GEO_COUNTRIES = ['US'] _GEO_COUNTRIES = ['US']
_TESTS = [ _TESTS = [
{
'url': 'https://www.thirteen.org/programs/the-woodwrights-shop/carving-away-with-mary-may-tioglz/',
'info_dict': {
'id': '3004803331',
'ext': 'mp4',
'title': "The Woodwright's Shop - Carving Away with Mary May",
'description': 'md5:7cbaaaa8b9bcc78bd8f0e31911644e28',
'duration': 1606,
'display_id': 'carving-away-with-mary-may-tioglz',
'chapters': [],
'thumbnail': 'https://image.pbs.org/video-assets/NcnTxNl-asset-mezzanine-16x9-K0Keoyv.jpg',
},
},
{ {
'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/', 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
'md5': '372b12b670070de39438b946474df92f', 'md5': '372b12b670070de39438b946474df92f',
@ -214,8 +227,8 @@ class PBSIE(InfoExtractor):
{'start_time': 3588.0, 'end_time': 4355.0, 'title': 'The Withdrawal '}, {'start_time': 3588.0, 'end_time': 4355.0, 'title': 'The Withdrawal '},
{'start_time': 4354.0, 'end_time': 5051.0, 'title': 'ISIS on the March '}, {'start_time': 4354.0, 'end_time': 5051.0, 'title': 'ISIS on the March '},
], ],
'display_id': 'losing-iraq', 'display_id': 'losing-iraq',
'thumbnail': 'https://image.pbs.org/video-assets/pbs/frontline/138098/images/mezzanine_401.jpg', 'thumbnail': 'https://image.pbs.org/video-assets/pbs/frontline/138098/images/mezzanine_401.jpg',
}, },
}, },
{ {
@ -462,6 +475,7 @@ def _extract_webpage(self, url):
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
r'class="coveplayerid">([^<]+)<', # coveplayer r'class="coveplayerid">([^<]+)<', # coveplayer
r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/ r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
r'.*class="passportcoveplayer"[^>]+data-media="(\d+)', # https://www.thirteen.org/programs/the-woodwrights-shop/who-wrote-the-book-of-sloyd-fggvvq/
r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',", r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
r'<div[^>]+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/ r'<div[^>]+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/