SF Patch # 103839 byt dougfort: Allow ';' in attributes

gvanrossum · gvanrossum · commit b68c24566261 · 2001-02-19T18:39:09.000Z
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
@@ -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.
