[extractor/common] Eliminate media tag name regex duplication

pull/27331/head
Sergey M․ 4 years ago
parent 6ad0d8781e
commit 06bf2ac20f
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

@ -2513,15 +2513,16 @@ class InfoExtractor(object):
# amp-video and amp-audio are very similar to their HTML5 counterparts
# so we wll include them right here (see
# https://www.ampproject.org/docs/reference/components/amp-video)
_MEDIA_TAG_NAME_RE = r'(?:amp-)?(video|audio)'
media_tags = [(media_tag, media_type, '')
for media_tag, media_type
in re.findall(r'(?s)(<(?:amp-)?(video|audio)[^>]*/>)', webpage)]
in re.findall(r'(?s)(<%s[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]
media_tags.extend(re.findall(
# We only allow video|audio followed by a whitespace or '>'.
# Allowing more characters may end up in significant slow down (see
# https://github.com/ytdl-org/youtube-dl/issues/11979, example URL:
# http://www.porntrex.com/maps/videositemap.xml).
r'(?s)(<(?P<tag>(?:amp-)?(video|audio))(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
r'(?s)(<(?P<tag>%s)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>' % _MEDIA_TAG_NAME_RE, webpage))
for media_tag, _, media_type, media_content in media_tags:
media_info = {
'formats': [],

Loading…
Cancel
Save