diff options
author | Senthil Kumaran <orsenthil@gmail.com> | 2010-12-28 15:55:16 +0000 |
---|---|---|
committer | Senthil Kumaran <orsenthil@gmail.com> | 2010-12-28 15:55:16 +0000 |
commit | 9fb73ba7ee16a8aa4e60057e45e0065fb108c455 (patch) | |
tree | 7247087eb77277a26adc53e70d837d39a0c5adab /Lib/html | |
parent | 8e96c6aefa4d9528ee15401304f9f0be7c540dd8 (diff) | |
download | cpython-9fb73ba7ee16a8aa4e60057e45e0065fb108c455.tar.gz |
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 8d275ab315..21ebbc3eaf 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 |