Update libs

libs/bs4/builder/__init__.py

@@ -147,18 +147,29 @@ class TreeBuilder(object):
 
         Modifies its input in place.
         """
+        if not attrs:
+            return attrs
         if self.cdata_list_attributes:
             universal = self.cdata_list_attributes.get('*', [])
             tag_specific = self.cdata_list_attributes.get(
-                tag_name.lower(), [])
-            for cdata_list_attr in itertools.chain(universal, tag_specific):
-                if cdata_list_attr in dict(attrs):
-                    # Basically, we have a "class" attribute whose
-                    # value is a whitespace-separated list of CSS
-                    # classes. Split it into a list.
-                    value = attrs[cdata_list_attr]
-                    values = whitespace_re.split(value)
-                    attrs[cdata_list_attr] = values
+                tag_name.lower(), None)
+            for attr in attrs.keys():
+                if attr in universal or (tag_specific and attr in tag_specific):
+                    # We have a "class"-type attribute whose string
+                    # value is a whitespace-separated list of
+                    # values. Split it into a list.
+                    value = attrs[attr]
+                    if isinstance(value, basestring):
+                        values = whitespace_re.split(value)
+                    else:
+                        # html5lib sometimes calls setAttributes twice
+                        # for the same tag when rearranging the parse
+                        # tree. On the second call the attribute value
+                        # here is already a list.  If this happens,
+                        # leave the value alone rather than trying to
+                        # split it again.
+                        values = value
+                    attrs[attr] = values
         return attrs
 
 class SAXTreeBuilder(TreeBuilder):
@@ -287,6 +298,9 @@ def register_treebuilders_from(module):
             # Register the builder while we're at it.
             this_module.builder_registry.register(obj)
 
+class ParserRejectedMarkup(Exception):
+    pass
+
 # Builders are registered in reverse order of priority, so that custom
 # builder registrations will take precedence. In general, we want lxml
 # to take precedence over html5lib, because it's faster. And we only