commit: 91dd25fe1e18aa3f617005799a8f5018a551c7dd
parent 06bf2ac20f2fb64df9f6e4cd1dba267b25effd22
Author: Sergey M․ <dstftw@gmail.com>
Date: Mon, 7 Dec 2020 00:59:25 +0700
[extractor/common] Add support for dl8-* media tags (closes #27283)
Diffstat:
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -2513,7 +2513,8 @@ 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)'
+ # For dl8-* tags see https://delight-vr.com/documentation/dl8-video/
+ _MEDIA_TAG_NAME_RE = r'(?:(?:amp|dl8(?:-live)?)-)?(video|audio)'
media_tags = [(media_tag, media_type, '')
for media_tag, media_type
in re.findall(r'(?s)(<%s[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -2466,7 +2466,9 @@ class GenericIE(InfoExtractor):
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
- webpage = compat_urllib_parse_unquote(webpage)
+ # FIXME: unescaping the whole page may break URLs, commenting out for now.
+ # There probably should be a second run of generic extractor on unescaped webpage.
+ # webpage = compat_urllib_parse_unquote(webpage)
# Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294
