html解析-HTMLParser

HTMLParser解析网页主要是通过继承HTMLParser类来编写自定义函数

from html.parser import HTMLParser
from html.entities import name2codepoint

class MyHTMLParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
       self.flag = 'N'
       
    #通过标记或属性个数，属性值来判断获取需要的元素
    def handle_starttag(self, tag, attrs):
        if tag=='a' and len(attrs)==3 and attrs[0][1]=='title':
            self.flag = 'Y'
        #print('<%s>' % tag)

    def handle_endtag(self, tag):
        self.flag = 'N'
        #print('</%s>' % tag)

    def handle_startendtag(self, tag, attrs):
        print('<%s/>' % tag)
   #获取元素的文本值
    def handle_data(self, data):
        if self.flag == 'Y':
            print("文章标题：{}".format(data))
        #print(data)

 #def handle_comment(self, data):
 #   pass
 #   #print('<!--', data, '-->')
# 解析类似这种&nbsp;
  #  def handle_entityref(self, name):
  #     pass
  #     #print('&%s;' % name)
# 解析&#1234
 # def handle_charref(self, name):
 #      pass
  #     #print('&#%s;' % name)
if __name_-='__main__':
    with open('result.html','r',encoding='utf-8') as f:
        files=f.read()
        f.close()
    parser = MyHTMLParser()
    parser.feed(files)