From 15038b22ea020ea79928af2831c4b1dff869bcd4 Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Sun, 15 Jul 2018 08:27:40 -0400 Subject: Stop data loss when encountering an empty numeric entity, and possibly in other cases. Thanks to tos.kamiya for the fix. [bug=1698503] --- bs4/builder/_htmlparser.py | 1 + 1 file changed, 1 insertion(+) (limited to 'bs4/builder/_htmlparser.py') diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index 71604c5..ef9fd1e 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -224,6 +224,7 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder): parser.soup = self.soup try: parser.feed(markup) + parser.close() except HTMLParseError, e: warnings.warn(RuntimeWarning( "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help.")) -- cgit v1.2.3