diff options
| author | Senthil Kumaran <orsenthil@gmail.com> | 2010-12-28 15:55:16 (GMT) |
|---|---|---|
| committer | Senthil Kumaran <orsenthil@gmail.com> | 2010-12-28 15:55:16 (GMT) |
| commit | 164540fee1f5909364e0758bbb948ee6f7387f14 (patch) | |
| tree | 1b8e4bac5472f3c350384e3c6daa293dbfae17c5 /Lib/html | |
| parent | 3b4499c5c7718a2aca8558b857dfe02cc4a80cd9 (diff) | |
| download | cpython-164540fee1f5909364e0758bbb948ee6f7387f14.zip cpython-164540fee1f5909364e0758bbb948ee6f7387f14.tar.gz cpython-164540fee1f5909364e0758bbb948ee6f7387f14.tar.bz2 | |
Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax
Diffstat (limited to 'Lib/html')
| -rw-r--r-- | Lib/html/parser.py | 17 |
1 files changed, 10 insertions, 7 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 8d275ab..21ebbc3 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -434,13 +434,16 @@ class HTMLParser(_markupbase.ParserBase): 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 |