diff Lib/HTMLParser.py @ 69160:7d4dea76c476 2.7

#7311: fix HTMLParser to accept non-ASCII attribute values.
author Ezio Melotti
date Tue, 05 Apr 2011 20:40:52 +0300
parents 05cccd4257a2
children 02a4535c0a6c
line wrap: on
line diff
--- a/Lib/HTMLParser.py	Tue Apr 05 15:24:34 2011 +0200
+++ b/Lib/HTMLParser.py	Tue Apr 05 20:40:52 2011 +0300
@@ -26,7 +26,7 @@
 tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
 attrfind = re.compile(
     r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
-    r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?')
+    r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
 
 locatestarttagend = re.compile(r"""
   <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name