本文整理汇总了Python中html5lib.tokenizer.HTMLTokenizer类的典型用法代码示例。如果您正苦于以下问题:Python HTMLTokenizer类的具体用法?Python HTMLTokenizer怎么用?Python HTMLTokenizer使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了HTMLTokenizer类的5个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __iter__
def __iter__(self):
for token in HTMLTokenizer.__iter__(self):
token = self.sanitize_token(token)
if token:
yield token
示例2: __init__
def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
lowercaseElementName=True, lowercaseAttrName=True):
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
lowercaseElementName, lowercaseAttrName)
示例3: __init__
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)
示例4: __iter__
def __iter__(self):
for token in HTMLTokenizer.__iter__(self):
if token["type"] not in tag_types:
yield token
示例5: __init__
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 = []