From 3d0ae02cc3d0b947ef6102b31f4b354eec9b543a Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Wed, 18 Apr 2012 08:45:51 -0400 Subject: Fixed a bug that made the HTMLParser treebuilder generate XML definitions ending with two question marks instead of one. [bug=984258] --- bs4/builder/_htmlparser.py | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'bs4/builder/_htmlparser.py') diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index c307ff8..3dee51b 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -96,6 +96,14 @@ class BeautifulSoupHTMLParser(HTMLParser): def handle_pi(self, data): self.soup.endData() + if data.endswith("?") and data.lower().startswith("xml"): + # "An XHTML processing instruction using the trailing '?' + # will cause the '?' to be included in data." - HTMLParser + # docs. + # + # Strip the question mark so we don't end up with two + # question marks. + data = data[:-1] self.soup.handle_data(data) self.soup.endData(ProcessingInstruction) -- cgit v1.2.3