mirror of
https://github.com/GAM-team/GAM.git
synced 2026-07-04 21:01:36 +00:00
Handle misidentified codepoint (#281)
This commit is contained in:
@@ -384,7 +384,11 @@ class _DeHTMLParser(HTMLParser):
|
|||||||
self.__text.append(unichr(int(name[1:], 16)) if name.startswith('x') else unichr(int(name)))
|
self.__text.append(unichr(int(name[1:], 16)) if name.startswith('x') else unichr(int(name)))
|
||||||
|
|
||||||
def handle_entityref(self, name):
|
def handle_entityref(self, name):
|
||||||
self.__text.append(unichr(name2codepoint[name]))
|
cp = name2codepoint.get(name)
|
||||||
|
if cp:
|
||||||
|
self.__text.append(unichr(cp))
|
||||||
|
else:
|
||||||
|
self.__text.append(u'&'+name)
|
||||||
|
|
||||||
def handle_starttag(self, tag, attrs):
|
def handle_starttag(self, tag, attrs):
|
||||||
if tag == 'p':
|
if tag == 'p':
|
||||||
|
|||||||
Reference in New Issue
Block a user