Handle the Content-Type header a little more appropriately: if it
contains options, drop them to get the major/minor content type.
Modified from the supplied patch to support more whitespace variation.
Closes SF patch #613605.
diff --git a/Tools/webchecker/webchecker.py b/Tools/webchecker/webchecker.py
index fd7f578..e8d0ed7 100755
--- a/Tools/webchecker/webchecker.py
+++ b/Tools/webchecker/webchecker.py
@@ -544,6 +544,9 @@
def checkforhtml(self, info, url):
if info.has_key('content-type'):
ctype = cgi.parse_header(info['content-type'])[0].lower()
+ if ';' in ctype:
+ # handle content-type: text/html; charset=iso8859-1 :
+ ctype = ctype.split(';', 1)[0].strip()
else:
if url[-1:] == "/":
return 1