mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-13 14:37:43 +01:00
Allow downloading videos with other characters in their titles
Especially html entities
This commit is contained in:
parent
f5ebb61495
commit
9cf98a2bcc
@ -3694,9 +3694,10 @@ def _real_extract(self, url):
|
|||||||
videourl = 'http://store.steampowered.com/video/%s/' % gameID
|
videourl = 'http://store.steampowered.com/video/%s/' % gameID
|
||||||
webpage = self._download_webpage(videourl, gameID)
|
webpage = self._download_webpage(videourl, gameID)
|
||||||
mweb = re.finditer(urlRE, webpage)
|
mweb = re.finditer(urlRE, webpage)
|
||||||
namesRE = r'<span class=\"title\">(?P<videoName>[\w:/\.\?=\+\s-]+)</span>'
|
namesRE = r'<span class="title">(?P<videoName>.+)</span>'
|
||||||
titles = list(re.finditer(namesRE, webpage))
|
titles = list(re.finditer(namesRE, webpage))
|
||||||
videos = []
|
videos = []
|
||||||
|
unescaper = compat_html_parser.HTMLParser()
|
||||||
for vid,vtitle in zip(mweb,titles):
|
for vid,vtitle in zip(mweb,titles):
|
||||||
video_id = vid.group('videoID')
|
video_id = vid.group('videoID')
|
||||||
title = vtitle.group('videoName')
|
title = vtitle.group('videoName')
|
||||||
@ -3707,7 +3708,7 @@ def _real_extract(self, url):
|
|||||||
'id':video_id,
|
'id':video_id,
|
||||||
'url':video_url,
|
'url':video_url,
|
||||||
'ext': 'flv',
|
'ext': 'flv',
|
||||||
'title': title
|
'title': unescaper.unescape(title)
|
||||||
}
|
}
|
||||||
videos.append(info)
|
videos.append(info)
|
||||||
return videos
|
return videos
|
||||||
|
Loading…
Reference in New Issue
Block a user