python 提取页面标签 /源码－－－－－简单代码

# ! /usr/bin/env python
#  -*- coding: utf-8 -*-


import  urllib                                       
sock  =  urllib.urlopen( " http://www.bitunion.org/ " ) 
html   =  sock.read()                            
sock.close()
html  =  unicode(html  , " gbk "  )
print  html

# !/usr/bin/env python
from  sgmllib  import  SGMLParser

import  urllib                                    
sock  =  urllib.urlopen( " http://www.bitunion.org/ " ) 
html  =  sock.read()
sock.close()
html  =  unicode(html  , " gbk "  )
# print html 
s  =   html
class  Parse(SGMLParser):
     def  reset(self):
        self.found_title  =  0
        SGMLParser.reset(self)
     def  start_title(self, attrs):
        self.found_title  +=   1
     def  end_title(self):
        self.found_title  -=   1
     def  handle_data(self, text):
         if  self.found_title  >  0:
             print   ' Title: %s '   %  text

p  =  Parse()
p.feed(s) 
 

 


最后注视