Patch for an Issue #801

lib/core/common.py

@@ -3337,6 +3337,8 @@ def findPageForms(content, url, raise_=False, addToTargets=False):
 
     try:
         forms = ParseResponse(response, backwards_compat=False)
+    except UnicodeError:
+        pass
     except ParseError:
         warnMsg = "badly formed HTML at the given URL ('%s'). Going to filter it" % url
         logger.warning(warnMsg)

thirdparty/clientform/clientform.py

@@ -1124,6 +1124,7 @@ def _ParseFileEx(file, base_uri,
         if action is None:
             action = base_uri
         else:
+            action = unicode(action, "utf8") if action and not isinstance(action, unicode) else action
             action = _urljoin(base_uri, action)
         # would be nice to make HTMLForm class (form builder) pluggable
         form = HTMLForm(