1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-21 09:41:50 +00:00

[extractor/common] Improved support for HTML5 subtitles

Ref: #10625

In a strict sense, <track>s with kind=captions are not subtitles. [1]
openload misuses this attribute, and I guess there will be more
examples, so I add it to common.py.

Also allow extracting information for subtitles-only <video> or <audio>
tags, which is the case of openload.

[1] https://www.w3.org/TR/html5/embedded-content-0.html#attr-track-kind
This commit is contained in:
Yen Chi Hsuan 2016-09-24 14:20:42 +08:00
parent e6332059ac
commit 5968d7d2fe
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
2 changed files with 8 additions and 2 deletions

View file

@ -1,3 +1,9 @@
vesion <unreleased>
Core
+ Improved support for HTML5 subtitles
version 2016.09.24 version 2016.09.24
Core Core

View file

@ -1828,7 +1828,7 @@ class InfoExtractor(object):
for track_tag in re.findall(r'<track[^>]+>', media_content): for track_tag in re.findall(r'<track[^>]+>', media_content):
track_attributes = extract_attributes(track_tag) track_attributes = extract_attributes(track_tag)
kind = track_attributes.get('kind') kind = track_attributes.get('kind')
if not kind or kind == 'subtitles': if not kind or kind in ('subtitles', 'captions'):
src = track_attributes.get('src') src = track_attributes.get('src')
if not src: if not src:
continue continue
@ -1836,7 +1836,7 @@ class InfoExtractor(object):
media_info['subtitles'].setdefault(lang, []).append({ media_info['subtitles'].setdefault(lang, []).append({
'url': absolute_url(src), 'url': absolute_url(src),
}) })
if media_info['formats']: if media_info['formats'] or media_info['subtitles']:
entries.append(media_info) entries.append(media_info)
return entries return entries