From 6c882aa8991383e1c39a6457cbde5dcab260bff5 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 21 Nov 2018 09:44:10 +0100 Subject: [PATCH] [loc] relax _VALID_URL regex and improve formats extraction --- youtube_dl/extractor/libraryofcongress.py | 37 +++++++++++++++-------- 1 file changed, 24 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index 40295a30b..1e5c82c66 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[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|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') data = self._download_json( 'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id, - video_id)['mediaObject'] + media_id)['mediaObject'] derivative = data['derivatives'][0] media_url = derivative['derivativeUrl'] @@ -89,25 +96,29 @@ class LibraryOfCongressIE(InfoExtractor): if ext not in ('mp4', 'mp3'): media_url += '.mp4' if is_video else '.mp3' - if 'vod/mp4:' in media_url: - formats = [{ - 'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8', + formats = [] + if '/vod/mp4:' in media_url: + formats.append({ + 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8', 'format_id': 'hls', 'ext': 'mp4', 'protocol': 'm3u8_native', 'quality': 1, - }] - elif 'vod/mp3:' in media_url: - formats = [{ - 'url': media_url.replace('vod/mp3:', ''), - 'vcodec': 'none', - }] + }) + http_format = { + 'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url), + 'format_id': 'http', + 'quality': 1, + } + if not is_video: + http_format['vcodec'] = 'none' + formats.append(http_format) download_urls = set() for m in re.finditer( r']+value=(["\'])(?P.+?)\1[^>]+data-file-download=[^>]+>\s*(?P.+?)(?:(?: |\s+)\((?P.+?)\))?\s*<', webpage): format_id = m.group('id').lower() - if format_id == 'gif': + if format_id in ('gif', 'jpeg'): continue download_url = m.group('url') if download_url in download_urls: