test.py

# coding: utf-8

import urllib2
import urllib
import re



pat = re.compile(r'<div.*?class="content".*?ti.*?>(.*?)</div>', re.S)#有问题
nexturl1 = "http://www.qiushibaike.com/month/page/"
nexturl2 = "?s=4582723&slow"

count = 1

while count < 2:
    print "Page " + str(count) + "\n"
    myurl = nexturl1 + str(count) + nexturl2
    print myurl + "\n"
    myres = urllib2.urlopen(myurl)
    mypage = myres.read()
    ucpage = mypage.decode("utf-8") #转码

    mat = pat.findall(ucpage)
        
    count += 1;
    
    if len(mat):
        cnt = 1
        for item in mat:
            print 'No. '+ str(cnt) + "\n"
            print item + "\n"
            cnt += 1
            f = open('qb.txt', 'w+')
            item = item.replace(' ','').replace('\n','').replace('\r','')
            f.writelines(item)
            f.close()
        	
    else:
        print "no data"