mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-10 00:58:17 +02:00
[generic] Recognize html5 video in the format '<video src=".+?"' and only unquote the url when extracting the id (fixes #1372)
This commit is contained in:
parent
6b95b065be
commit
08e291b54d
@ -153,7 +153,7 @@ def _real_extract(self, url):
|
||||
mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
|
||||
if mobj is None:
|
||||
# HTML5 video
|
||||
mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL)
|
||||
mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||
|
||||
@ -162,9 +162,9 @@ def _real_extract(self, url):
|
||||
if mobj.group(1) is None:
|
||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||
|
||||
video_url = compat_urllib_parse.unquote(mobj.group(1))
|
||||
video_url = mobj.group(1)
|
||||
video_url = compat_urlparse.urljoin(url, video_url)
|
||||
video_id = os.path.basename(video_url)
|
||||
video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
|
||||
|
||||
# here's a fun little line of code for you:
|
||||
video_extension = os.path.splitext(video_id)[1][1:]
|
||||
|
Loading…
Reference in New Issue
Block a user