midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[extractor/common] Add support for dl8-* media tags (closes #27283)

Browse source
This commit is contained in:
Sergey M․ 2020-12-07 00:59:25 +07:00
parent 06bf2ac20f
commit 91dd25fe1e
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 5 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
youtube_dl/extractor/common.py
View file

@ -2513,7 +2513,8 @@ class InfoExtractor(object):
# amp-video and amp-audio are very similar to their HTML5 counterparts # amp-video and amp-audio are very similar to their HTML5 counterparts
# so we wll include them right here (see # so we wll include them right here (see
# https://www.ampproject.org/docs/reference/components/amp-video) # 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, '') media_tags = [(media_tag, media_type, '')
for media_tag, media_type for media_tag, media_type
in re.findall(r'(?s)(<%s[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)] in re.findall(r'(?s)(<%s[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]

4
youtube_dl/extractor/generic.py
View file

@ -2466,7 +2466,9 @@ class GenericIE(InfoExtractor):
# Sometimes embedded video player is hidden behind percent encoding # Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448) # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way # 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, # Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294 # see https://github.com/ytdl-org/youtube-dl/issues/21294