freexs.cn

gistfile1.txt

import urllib2
import re

for i in range(100000):
    try:
        response = urllib2.urlopen('http://www.freexs.cn/info/%s.htm' % i)
        t = re.findall('<h1>([\S\s]+?)</h1>', response.read())[0]
        print i, t
    except:
        print i