# coding: utf-8

 import urllib2

 import re

 import time

 def getDL(page):

     url = 'http://www.xicidaili.com/nt/{}'.format(page)

     header = {

         'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'

     }

     req=urllib2.Request(url, headers=header)

     res=urllib2.urlopen(req)

     html=res.read()

     srclist=re.findall(r'<tr class=(.|\n)*?<td>(\d+\.\d+\.\d+\.\d+)</td>(.|\n)*?<td>(\d+)</td>(.|\n)*?<td>(HTTP|HTTPS)</td>', html)

     xlist = []

     for item in srclist:

         xlist.append((item[5],item[1],item[3]))

     return xlist

 def testDL(ipstr):

     proxy= urllib2.ProxyHandler({'http':"{}:{}".format(ipstr[1], ipstr[2])})

     opener=urllib2.build_opener(proxy)

     urllib2.install_opener(opener)

     try:

         testUrl = 'http://httpbin.org/ip'

         testUrl = 'http://2017.ip138.com/ic.asp'

         req=urllib2.Request(testUrl)

         res=urllib2.urlopen(req).read()

         print "********************* √ {}    -- {}".format(ipstr, res)

         with open("ok.txt","a") as f:

             f.write("{} {} {}\n".format(ipstr[0], ipstr[1], ipstr[2]))

             f.close()

     except Exception as e:

         print "******** ×, {} -- {}".format(ipstr, e)

     time.sleep(1)

 def startTask():

     for page in xrange(5):

         list=getDL(page+1)

         for item in list:

             testDL(item)

 if __name__ == '__main__':

     startTask()