diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-08-29 11:35:15 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-08-29 11:35:15 +0200 |
| commit | 0d75ae2ce313c5738b2bdd9602ab3cc15e78810d (patch) | |
| tree | 1f3f2014f8bbd9961e689b62c91e6792aed4b5f2 | |
| parent | 2891932bf0a01acc025246438f890dca57f91c6b (diff) | |
Fix detection of the webpage charset if it's declared using ' instead of "
Like in "<meta charset='utf-8'/>"
| -rw-r--r-- | youtube_dl/extractor/common.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index a2986cebe..77726ee24 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -150,7 +150,7 @@ class InfoExtractor(object): if m: encoding = m.group(1) else: - m = re.search(br'<meta[^>]+charset="?([^"]+)[ /">]', + m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]', webpage_bytes[:1024]) if m: encoding = m.group(1).decode('ascii') |