def __iter__(self):
for token in HTMLTokenizer.__iter__(self):
token = self.sanitize_token(token)
if token:
yield token
def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
lowercaseElementName=True, lowercaseAttrName=True, **kwargs):
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
lowercaseElementName, lowercaseAttrName, **kwargs)