python爬虫爬保研论坛

 
 
 

  
  
  #EE论坛爬虫
 
 
 
#by JerryFang
#2013.11.13

import re
import urllib2
import urllib
import cookielib

def visitpage(url):
    nr = urllib2.urlopen(url).read().decode('gbk')
    print nr
    z = re.compile('''<a href=.*?class="xi2">(.*?)</a>
''', re.S|re.MULTILINE)
    t = re.compile('''<em id=".*?">(.*?)</em>
''', re.S|re.MULTILINE)
    c = re.compile(ur'''<table.*?>(.*?)</table>

''', re.DOTALL|re.MULTILINE)

##    author = z.findall(nr)
##    time = t.findall(nr)
    cont = c.findall(nr)

##    print author
##    print time
    print cont
    raw_input('press any key')

loginurl =