def innerHTML(self):
""" charset is the desired output charset """
result = u''
for c in self.children:
result += smart_unicode(c, encoding = self.charset[0])
return result
def innerHTML(self):
""" charset is the desired output charset """
result = u''
for c in self.children:
result += smart_unicode(c, encoding=self.charset[0])
return result
def url_unquote(string):
def decoder(x):
return x.group(1).decode("hex")
## we can use this to handle arbitrary levels of quoting
try:
string = re.sub("%(..)", decoder, string)
except: pass
## references seem to _always_ be encoded using utf8 - even if the
## page is encoded using a different charset??? This whole quoting
## thing is very confusing.
return smart_unicode(string, 'utf8')
def url_unquote(string):
def decoder(x):
return x.group(1).decode("hex")
## we can use this to handle arbitrary levels of quoting
try:
string = re.sub("%(..)", decoder, string)
except:
pass
## references seem to _always_ be encoded using utf8 - even if the
## page is encoded using a different charset??? This whole quoting
## thing is very confusing.
return smart_unicode(string, 'utf8')
def __getitem__(self, item):
return smart_unicode(self.attributes[item.lower()], self.charset[0],'ignore')
def __unicode__(self):
return smart_unicode(self.__str__(), encoding = self.charset[0])
def __unicode__(self):
return smart_unicode(self.__str__(), encoding=self.charset[0])
def __getitem__(self, item):
return smart_unicode(self.attributes[item.lower()], self.charset[0],
'ignore')