#7311: fix html.parser to accept non-ASCII attribute values.

This commit is contained in:
Ezio Melotti 2011-04-07 22:03:31 +03:00
parent 9b5ac3efa6
commit 2e3607c1e7
3 changed files with 20 additions and 1 deletions

View file

@ -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]*))?')