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 = 1

urls = []

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

for i in range(1,10):
    u = url+str(i) +'/'
    urls.append(u)
    # print urls[i-1]
    html = requests.get(urls[i-1])

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

    for item in content :
        if item[0]!='<':
            print item
            f.writelines(str(item)+'\n\n')

f.close()