Roxedus/ytdl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[generic] Recognize html5 video in the format '<video src=".+?"' and only unquote the url when extracting the id (fixes #1372)

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-09-05 18:02:17 +02:00
parent 6b95b065be
commit 08e291b54d
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
youtube_dl/extractor/generic.py
View File

@ -153,7 +153,7 @@ class GenericIE(InfoExtractor):
mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
if mobj is None: if mobj is None:
# HTML5 video # 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: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError(u'Invalid URL: %s' % url)
@ -162,9 +162,9 @@ class GenericIE(InfoExtractor):
if mobj.group(1) is None: if mobj.group(1) is None:
raise ExtractorError(u'Invalid URL: %s' % url) 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_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: # here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:] video_extension = os.path.splitext(video_id)[1][1:]