From 6a4d1f367240db447be71842006ed0bfe12f8abe Mon Sep 17 00:00:00 2001 From: user706 <39215612+user706@users.noreply.github.com> Date: Fri, 28 Dec 2018 23:50:22 +0100 Subject: [PATCH] fix extractor for national jukebox --- youtube_dl/extractor/libraryofcongress.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index 03f205144..44e37664e 100644 --- a/youtube_dl/extractor/libraryofcongress.py +++ b/youtube_dl/extractor/libraryofcongress.py @@ -16,7 +16,7 @@ from ..utils import ( class LibraryOfCongressIE(InfoExtractor): IE_NAME = 'loc' IE_DESC = 'Library of Congress' - _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P[0-9a-z_.]+)' + _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|jukebox/recordings/detail/id/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P[0-9a-z_.]+)' _TESTS = [{ # embedded via
.+?)\1', r']+id=(["\'])uuid-(?P.+?)\1', r']+data-uuid=(["\'])(?P.+?)\1', - r'mediaObjectId\s*:\s*(["\'])(?P.+?)\1', + r'"?mediaObjectId"?\s*:\s*(["\'])(?P.+?)\1', r'data-tab="share-media-(?P[0-9A-F]{32})"'), webpage, 'media id', group='id')