From 1e7153125b0f767b07b75aa8d0b7134c1a23b247 Mon Sep 17 00:00:00 2001 From: Roland Hieber Date: Sun, 6 Oct 2024 21:11:14 +0200 Subject: [PATCH] PBS: make thirteen.org work --- yt_dlp/extractor/pbs.py | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/pbs.py b/yt_dlp/extractor/pbs.py index 77994b7fe..b772f9871 100644 --- a/yt_dlp/extractor/pbs.py +++ b/yt_dlp/extractor/pbs.py @@ -188,7 +188,7 @@ class PBSIE(InfoExtractor): # Direct video URL (?:{})/(?:(?:vir|port)alplayer|video)/(?P[0-9]+)(?:[?/]|$) | # Article with embedded player (or direct video) - (?:www\.)?pbs\.org/(?:[^/]+/){{1,5}}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | + (?:www\.)?(thirteen|pbs)\.org/(?:[^/]+/){{1,5}}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P[^/]+) ) @@ -197,6 +197,19 @@ class PBSIE(InfoExtractor): _GEO_COUNTRIES = ['US'] _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/', 'md5': '372b12b670070de39438b946474df92f', @@ -214,8 +227,8 @@ class PBSIE(InfoExtractor): {'start_time': 3588.0, 'end_time': 4355.0, 'title': 'The Withdrawal '}, {'start_time': 4354.0, 'end_time': 5051.0, 'title': 'ISIS on the March '}, ], - 'display_id': 'losing-iraq', - 'thumbnail': 'https://image.pbs.org/video-assets/pbs/frontline/138098/images/mezzanine_401.jpg', + 'display_id': 'losing-iraq', + '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'class="coveplayerid">([^<]+)<', # coveplayer r']+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'', # jwplayer r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',", r']+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/