Python爬虫工具获取OJ平台的学习记录

 import webbrowser

    
 import re
    
 import urllib
    
  
    
 #获取hdu网页
    
 def getHtml_hdu(url):
    
     page = urllib.urlopen(url)
    
     html = page.read()
    
     #unicodehtml = html.decode("utf-8")
    
     #return unicodehtml
    
     return html
    
  
    
 #获取poj网页   
    
 def getHtml_poj(url):
    
     page = urllib.urlopen(url)
    
     html = page.read()
    
     #unicodehtml = html.decode("utf-8")
    
     #return unicodehtml
    
     return html
    
  
    
 #获取cug网页
    
 def getHtml_cug(url):
    
     page = urllib.urlopen(url)
    
     html = pa