def handle_data(self, data):
'''
获取标签中的文本信息
:param data:文本信息
:return:
'''
if len(data.replace(" ", "").replace("\n", "")) > 0:
# print("tag_data:{0},len:{1}".format(data, len(data)))
# 父方法获取对应的文本
HTMLParser.handle_data(self, data)
# 新建文本节点
node = wn.TextNode()
# 为其赋值标签和父节点等信息
node.tag = "text"
node.father = self.now
node.content = data
node.index = node.father.index + 1
node.path = node.father.path + "-" + "{0}[{1}]".format("text", len(node.father.children) + 1)
# 设定其特别的类型
node.type = "text"
# 将其加入父节点的子节点列表中
self.now.children.append(node)
# 保留其父节点完整的content属性
self.now.content += data
def _strip_tags(self, html):
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(html)
parser.close()
return ''.join(result)
def _strip_tags(self, html):
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(html)
parser.close()
return ''.join(result)
def strip_html(text):
if text is None:
return ''
parts = []
parser = HTMLParser()
parser.handle_data = parts.append
parser.feed(text)
return ''.join(parts)
def strip_tags(html):
html = html.strip()
html = html.strip("\n")
result = []
parse = HTMLParser()
parse.handle_data = result.append
parse.feed(html)
parse.close()
return "".join(result)
def strip_tags(self, htmlStr):
htmlStr = htmlStr.strip()
htmlStr = htmlStr.strip("\n")
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(htmlStr)
parser.close()
return ''.join(result)
def strip_tags(html):
from html.parser import HTMLParser
html = html.strip()
html = html.strip("\n")
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(html)
parser.close()
return ''.join(result)
def strip_tags(html):
"""
Python中过滤HTML标签的函数
"""
html = html.strip()
parser = HTMLParser()
result = []
parser.handle_data = result.append
parser.feed(html)
parser.close()
return result
def strip_tags(html):
'''
Removes html tags from a string
'''
from html.parser import HTMLParser
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(html)
parser.close()
return ''.join(result)
def strip_tags(html):
if html:
html = html.strip()
html = html.strip("\n")
result = []
parse = HTMLParser()
parse.handle_data = result.append
parse.feed(html)
parse.close()
return "".join(result)
return ''
def html_strip(html):
html = html.replace("#", '')
html = html.replace(">", '')
html = html.replace("-", '')
html = html.replace("*", '')
html = html.strip()
html = html.strip("\n")
result = []
parse = HTMLParser()
parse.handle_data = result.append
parse.feed(html)
parse.close()
return "".join(result)
def strip_tags(html):
# Python中过滤HTML标签的函数
# >>> str_text=strip_tags("<font color=red>hello</font>")
# >>> print str_text
# hello
from html.parser import HTMLParser
html = html.strip()
html = html.strip("\n")
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(html)
parser.close()
return ''.join(result)
def strip_tags(self, htmlStr):
'''
使用HTMLParser进行html标签过滤
:param htmlStr:
'''
self.htmlStr = htmlStr
htmlStr = htmlStr.strip()
htmlStr = htmlStr.strip("\n")
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(htmlStr)
parser.close()
return ''.join(result)
def strip_tags_parser(self, html):
"""
去除文本中的HTML标签.用到了HTMLParser
使用示例：
str_text=strip_tags("<font color=red>hello</font>")
:return: String
"""
from html.parser import HTMLParser
html = html.strip('\n')
html = html.strip('\t')
html = html.strip(' ')
html = html.strip()
result = []
parser = HTMLParser()
parser.handle_data = result.append
parser.feed(html)
parser.close()
return '$'.join(result)
def fetch_words_from_source(source):
pq = PyQuery(source)
data = HTMLParser.handle_data(pq)
return tag.text()
def handle_data(self, data):
HTMLParser.handle_data(self, data)
print('data is ... %s ' % data)
