diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2018-07-15 08:27:40 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2018-07-15 08:27:40 -0400 |
| commit | 15038b22ea020ea79928af2831c4b1dff869bcd4 (patch) | |
| tree | 9b1104a2a07a14aaa7e522b3f3cf88ace387206f /bs4/builder/_htmlparser.py | |
| parent | a0457769bbdc682569dd41a48ae5acb1f21481cb (diff) | |
Stop data loss when encountering an empty numeric entity, and
possibly in other cases. Thanks to tos.kamiya for the fix. [bug=1698503]
Diffstat (limited to 'bs4/builder/_htmlparser.py')
| -rw-r--r-- | bs4/builder/_htmlparser.py | 1 |
1 files changed, 1 insertions, 0 deletions
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.")) |