python 爬糗事百科

糗事百科网站段子爬取，糗事百科是我见过的最简单的网站了！！！

 #-*-coding:utf8-*-

 import requests
 import re
 import sys
 reload(sys)
 sys.setdefaultencoding("utf-8")

 url = 'http://www.qiushibaike.com/hot/page/'

 page = 

 urls = []

 f = open("happy.txt",'w')

 for i in range(,):
     u = url+str(i) +'/'
     urls.append(u)
     # print urls[i-]
     html = requests.get(urls[i-])

     content = re.findall('<span>(.*?)</span>',html.text,re.S)

     for item in content :
         if item[]!='<':
             print item
             f.writelines(str(item)+'\n\n')

 f.close()