Apply diff.txt from SF patch http://www.python.org/sf/561478

doerwalter · doerwalter · commit 88a20baa7749 · 2002-06-06T17:01:21.000Z
This uses cgi.parse_header() in Checker.checkforhtml(), so that
webchecker recognises the mime type text/html even if options
are specified.
diff --git a/Tools/webchecker/webchecker.py b/Tools/webchecker/webchecker.py
@@ -117,6 +117,7 @@
 import urllib
 import urlparse
 import sgmllib
+import cgi
 
 import mimetypes
 import robotparser
@@ -543,7 +544,7 @@ def openpage(self, url_pair):
 
     def checkforhtml(self, info, url):
         if info.has_key('content-type'):
-            ctype = string.lower(info['content-type'])
+            ctype = string.lower(cgi.parse_header(info['content-type'])[0])
         else:
             if url[-1:] == "/":
                 return 1
