def __init__(self,
stream,
encoding=None,
parseMeta=True,
useChardet=True,
lowercaseElementName=False,
lowercaseAttrName=False):
# Change case matching defaults as we only output lowercase html anyway
# This solution doesn't seem ideal...
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
lowercaseElementName, lowercaseAttrName)
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)
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):
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
lowercaseElementName, lowercaseAttrName)
def __iter__(self):
for token in HTMLTokenizer.__iter__(self):
if token["type"] not in tag_types:
yield token
def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
lowercaseElementName=False, lowercaseAttrName=False):
#Change case matching defaults as we only output lowercase html anyway
#This solution doesn't seem ideal...
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
lowercaseElementName, lowercaseAttrName)
def parse(self, stream, output=True):
tokenizer = HTMLTokenizer(stream)
for token in tokenizer:
if output:
print(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)
self.unmatched_tags = []
def reset(self):
self.src = StringIO()
self.tokenizer = HTMLTokenizer(self.src)