diff options
| author | Ezio Melotti <none@none> | 2011-04-07 19:03:31 (GMT) |
|---|---|---|
| committer | Ezio Melotti <none@none> | 2011-04-07 19:03:31 (GMT) |
| commit | 2e3607c1e758865519b28066b8925f37203e2197 (patch) | |
| tree | ec09ce29a9dcc1bfa91e7e0f65428666332eda41 /Lib/html | |
| parent | 9b5ac3efa64d72b54d4f1ab32a95c260b39ab98d (diff) | |
| download | cpython-2e3607c1e758865519b28066b8925f37203e2197.zip cpython-2e3607c1e758865519b28066b8925f37203e2197.tar.gz cpython-2e3607c1e758865519b28066b8925f37203e2197.tar.bz2 | |
#7311: fix html.parser to accept non-ASCII attribute values.
Diffstat (limited to 'Lib/html')
| -rw-r--r-- | Lib/html/parser.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 21ebbc3..a3586eb 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -28,7 +28,7 @@ tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') # make it correctly strict without breaking backward compatibility. attrfind = re.compile( r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' - r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?') + r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?') attrfind_tolerant = re.compile( r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[^>\s]*))?') |