diff options
Diffstat (limited to 'bs4/builder/_htmlparser.py')
| -rw-r--r-- | bs4/builder/_htmlparser.py | 8 |
1 files changed, 8 insertions, 0 deletions
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) |