SF Patch # 103839 byt dougfort: Allow ';' in attributes
sgmllib does not recognize HTML attributes containing the semicolon
';' character. This may be in accordance with the HTML spec, but there
are sites that use it (excite.com) and the browsers I regularly use
(IE5, Netscape, Opera) all handle it. Doug Fort Downright Software LLC
diff --git a/Lib/sgmllib.py b/Lib/sgmllib.py
index 30acafd..1f8f3b8 100644
--- a/Lib/sgmllib.py
+++ b/Lib/sgmllib.py
@@ -38,7 +38,7 @@
attrfind = re.compile(
'[%s]*([a-zA-Z_][-.a-zA-Z_0-9]*)' % string.whitespace
+ ('([%s]*=[%s]*' % (string.whitespace, string.whitespace))
- + r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./:+*%?!&$\(\)_#=~]*))?')
+ + r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./:;+*%?!&$\(\)_#=~]*))?')
# SGML parser base class -- find tags and call handler functions.