diff options
Diffstat (limited to 'Lib/HTMLParser.py')
| -rw-r--r-- | Lib/HTMLParser.py | 33 |
1 files changed, 27 insertions, 6 deletions
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py index 8380466e33..7cee47a7c5 100644 --- a/Lib/HTMLParser.py +++ b/Lib/HTMLParser.py @@ -175,6 +175,9 @@ class HTMLParser(markupbase.ParserBase): i = self.updatepos(i, k) continue else: + if ";" in rawdata[i:]: #bail by consuming &# + self.handle_data(rawdata[0:2]) + i = self.updatepos(i, 2) break elif startswith('&', i): match = entityref.match(rawdata, i) @@ -358,12 +361,30 @@ class HTMLParser(markupbase.ParserBase): self.error("unknown declaration: %r" % (data,)) # Internal -- helper to remove special character quoting + entitydefs = None def unescape(self, s): if '&' not in s: return s - s = s.replace("<", "<") - s = s.replace(">", ">") - s = s.replace("'", "'") - s = s.replace(""", '"') - s = s.replace("&", "&") # Must be last - 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 unichr(c) + else: + # Cannot use name2codepoint directly, because HTMLParser supports apos, + # which is not part of HTML 4 + import htmlentitydefs + if HTMLParser.entitydefs is None: + entitydefs = HTMLParser.entitydefs = {'apos':u"'"} + for k, v in htmlentitydefs.name2codepoint.iteritems(): + entitydefs[k] = unichr(v) + try: + return self.entitydefs[s] + except KeyError: + return '&'+s+';' + + return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s) |