Mercurial > cpython-lru_cache-weakref
diff Lib/html/parser.py @ 67189:3546ce1aa355 3.1
Merged revisions 87542 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/branches/py3k
........
r87542 | senthil.kumaran | 2010-12-28 23:55:16 +0800 (Tue, 28 Dec 2010) | 3 lines
Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax
........
| author | Senthil Kumaran <orsenthil@gmail.com> |
|---|---|
| date | Tue, 28 Dec 2010 16:10:56 +0000 |
| parents | 6144760e8350 |
| children | 829c541033ac 3c9232a684ae |
line wrap: on
line diff
--- a/Lib/html/parser.py Tue Dec 28 15:42:23 2010 +0000 +++ b/Lib/html/parser.py Tue Dec 28 16:10:56 2010 +0000 @@ -367,13 +367,16 @@ return s def replaceEntities(s): s = s.groups()[0] - if s[0] == "#": - s = s[1:] - if s[0] in ['x','X']: - c = int(s[1:], 16) - else: - c = int(s) - return chr(c) + try: + if s[0] == "#": + s = s[1:] + if s[0] in ['x','X']: + c = int(s[1:], 16) + else: + c = int(s) + return chr(c) + except ValueError: + return '&#'+ s +';' else: # Cannot use name2codepoint directly, because HTMLParser # supports apos, which is not part of HTML 4