Fixed a bug in which short Unicode input was improperly encoded to ASCII when checking whether or not it was a file on

  disk. [bug=1227016]

1 files changed, 9 insertions, 1 deletions

diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py
index 4b80f79..ca8d8b8 100644
--- a/bs4/builder/_htmlparser.py
+++ b/bs4/builder/_htmlparser.py
@@ -45,7 +45,15 @@ HTMLPARSER = 'html.parser'
 class BeautifulSoupHTMLParser(HTMLParser):
     def handle_starttag(self, name, attrs):
         # XXX namespace
-        self.soup.handle_starttag(name, None, None, dict(attrs))
+        attr_dict = {}
+        for key, value in attrs:
+            # Change None attribute values to the empty string
+            # for consistency with the other tree builders.
+            if value is None:
+                value = ''
+            attr_dict[key] = value
+            attrvalue = '""'
+        self.soup.handle_starttag(name, None, None, attr_dict)
 
     def handle_endtag(self, name):
         self.soup.handle_endtag(name)