原创:Python爬虫实战之爬取代理ip

时间：2024-04-15 00:51:24

　　编程的快乐只有在运行成功的那一刻才知道QAQ

　　目标网站:https://www.kuaidaili.com/free/inha/  #若有侵权请联系我

　　因为上面的代理都是http的所以没写这个判断

　　代码如下:

 #!/usr/bin/env python

 # -*- coding: utf-8 -*-

 import urllib.request

 import re

 import time

 n = 1

 headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}

 def web(url):

     req=urllib.request.Request(url=url,headers=headers)

     response = urllib.request.urlopen(url)

     html = response.read().decode('UTF-8','ignore')

     ip = r'[0-9]+(?:\.[0-9]+){3}'

     port = r'"PORT">(\d{0,1}\d{0,1}\d{0,1}\d{0,1}\d)<'

     out = re.findall(ip,html)

     out1 = re.findall(port,html)

     i = 0

     dictionary = {}

     while i <= 14:

         dictionary[0] = (out[i],out1[i])

         store(dictionary)

         i += 1

     print(out,'\n',out1)

 def store(dictionary):

     with open('ip.txt','a') as f:

         c = 'ip:' + dictionary[0][0] + '\tport:' + dictionary[0][1] + '\n'

         f.write(c)

         print('store successfully')

 while n <= 3313:

     url1 = "https://www.kuaidaili.com/free/inha/"

     url = url1 + str(n) +'/'

     web(url)

     time.sleep(5)

     n += 1

相关文章