_htmlparser.py 文件源码

def handle_charref(self, name):
        # XXX workaround for a bug in HTMLParser. Remove this once
        # it's fixed in all supported versions.
        # http://bugs.python.org/issue13633
        if name.startswith('x'):
            real_name = int(name.lstrip('x'), 16)
        elif name.startswith('X'):
            real_name = int(name.lstrip('X'), 16)
        else:
            real_name = int(name)

        try:
            data = unichr(real_name)
        except (ValueError, OverflowError), e:
            data = u"\N{REPLACEMENT CHARACTER}"

        self.handle_data(data)