>>> p = """
... <HTML>
... <HEAD>
... </HEAD>
... <BODY>
... <script type=text/javascript>
... rgvij="></if";
... </script>
... </BODY>
... </html>
... """
>>> soup = BeautifulSoup(p)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
NameError: name 'BeautifulSoup' is not defined
>>> from BeautifulSoup import BeautifulSoup
>>> soup = BeautifulSoup(p)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/arthur/honeynet/code/js_decode/python/lib/python2.5/site-packages/BeautifulSoup.py", line 1499, in __init__
'th' : ['tr'],
File "/Users/arthur/honeynet/code/js_decode/python/lib/python2.5/site-packages/BeautifulSoup.py", line 1230, in __init__
"""We need to pop up to the previous tag of this type, unless
File "/Users/arthur/honeynet/code/js_decode/python/lib/python2.5/site-packages/BeautifulSoup.py", line 1263, in _feed
#If we encounter one of the nesting reset triggers
File "/opt/local/Library/Frameworks/Python.framework/Versions/2.5/lib/python2.5/HTMLParser.py", line 108, in feed
self.goahead(0)
File "/opt/local/Library/Frameworks/Python.framework/Versions/2.5/lib/python2.5/HTMLParser.py", line 150, in goahead
k = self.parse_endtag(i)
File "/opt/local/Library/Frameworks/Python.framework/Versions/2.5/lib/python2.5/HTMLParser.py", line 314, in parse_endtag
self.error("bad end tag: %r" % (rawdata[i:j],))
File "/opt/local/Library/Frameworks/Python.framework/Versions/2.5/lib/python2.5/HTMLParser.py", line 115, in error
raise HTMLParseError(message, self.getpos())
HTMLParser.HTMLParseError: bad end tag: u'</if";\n</script>', at line 7, column 9
>>>
This works correctly in 3.0.x series.
This happens even if the Javascript is inside <!-- -->. I think at least this case should be handled, because the contents of HTML comments are easy enough to ignore (easier than contents of strings within Javascript blocks).