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 fd7f578b31badc3d74f67a43d71bec60ca47cb2f..e8d0ed746fe0932c3e7b4a65fe8718d2a936c77f 100755 (executable)
--- a/Tools/webchecker/webchecker.py
+++ b/Tools/webchecker/webchecker.py
@@ -544,6 +544,9 @@ class Checker:
     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