commit 2e3607c1e758865519b28066b8925f37203e2197
author Ezio Melotti <none@none> Thu Apr 07 22:03:31 2011 +0300
committer Ezio Melotti <none@none> Thu Apr 07 22:03:31 2011 +0300
tree ec09ce29a9dcc1bfa91e7e0f65428666332eda41
parent 9b5ac3efa64d72b54d4f1ab32a95c260b39ab98d

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

Lib/html/parser.py

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 @@
 # 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]*))?')