原创:Python爬虫实战之爬取代理ip

 1 #!/usr/bin/env python
 2 # -*- coding: utf-8 -*-
 3 import urllib.request
 4 import re
 5 import time
 6 n = 1
 7 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'}
 8 def web(url):
 9     req=urllib.request.Request(url=url,headers=headers)
10     response = urllib.request.urlopen(url)
11     html = response.read().decode('UTF-8','ignore')
12     ip = r'[0-9]+(?:\.[0-9]+){3}'
13     port = r'"PORT">(\d{0,1}\d{0,1}\d{0,1}\d{0,1}\d)<'
14     out = re.findall(ip,html)
15     out1 = re.findall(port,html)
16     i = 0
17     dictionary = {}
18     while i <= 14:
19         dictionary[out[i]] = out1[i]
20         store(dictionary)
21         i += 1
22     print(out,'\n',out1)
23 def store(dictionary):
24     for key in dictionary:
25         with open('ip.txt','a') as f:
26             c = 'ip:' + key + '\tport:' + dictionary[key] + '\n'
27             f.write(c)
28             print('store successfully')        
29 while n <= 3313:
30     url1 = "https://www.kuaidaili.com/free/intr/"
31     url = url1 + str(n) +'/'
32     web(url)
33     time.sleep(5)
34     n += 1