summaryrefslogtreecommitdiff
path: root/bs4/builder/_htmlparser.py
diff options
context:
space:
mode:
Diffstat (limited to 'bs4/builder/_htmlparser.py')
-rw-r--r--bs4/builder/_htmlparser.py7
1 files changed, 6 insertions, 1 deletions
diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py
index ef9fd1e..eff30ff 100644
--- a/bs4/builder/_htmlparser.py
+++ b/bs4/builder/_htmlparser.py
@@ -152,7 +152,12 @@ class BeautifulSoupHTMLParser(HTMLParser):
if character is not None:
data = character
else:
- data = "&%s;" % name
+ # If this were XML, it would be ambiguous whether "&foo"
+ # was an character entity reference with a missing
+ # semicolon or the literal string "&foo". Since this is
+ # HTML, we have a complete list of all character entity references,
+ # and this one wasn't found, so assume it's the literal string "&foo".
+ data = "&%s" % name
self.handle_data(data)
def handle_comment(self, data):