1 # *-* coding: utf-8 *-*
 2 import BeautifulSoup
 3 import requests
 4 import time
 5 
 6 # to check if the ip proxy can work
 7 URL_CHECK = ‘http://1212.ip138.com/ic.asp‘
 8 RESPONSE_TIME = 2
 9 IP_LOCAL = ‘120.236.174.144‘
10 
11 # this is the pages of the website "http://www.ip181.com/daili/1.html"
12 # you can check out in the browser.
13 # the program will crawl the ip proxy from pages [start_page, end_page]
14 # as: [1,2], it will crawl the page 1 and page 2.
15 start_page = input(‘Please input your start page to crawl: ‘)
16 end_page = input(‘Please input your end page to crawl: ‘)
17 
18 
19 s = requests.Session()
20 
21 # check if the exit IP is changed
22 def check_a_ip(ip):
23     start = time.time()
24     try:
25         connection = s.get(URL_CHECK, headers={
26             ‘Host‘: ‘1212.ip138.com‘,
27             ‘Referer‘: ‘http://www.ip138.com/‘,
28             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"
29         }, proxies={‘http‘: ‘http://‘ + ip}, timeout=RESPONSE_TIME)
30         res = connection.content
31         # print res
32 
33         soup = BeautifulSoup.BeautifulSoup(res)
34         ip_return = soup.findAll(‘center‘)[0].text.split(‘[‘)[1].split(‘]‘)[0]
35         return ip_return != IP_LOCAL, ‘%.6f‘ % (time.time() - start)
36     except Exception, e:
37         # print ‘<ERROR>‘
38         # print e
39         return False, ‘-1‘
40 
41 url = ‘http://www.ip181.com/daili/%s.html‘
42 ip_proxy_file = open(‘proxy.txt‘, ‘w‘)
43 ip_proxy_file.write(‘ip_port,response_time\n‘)
44 ip_proxy_file.close()
45 
46 for i in range(int(start_page), int(end_page) + 1):
47     ip_proxy_file = open(‘proxy.txt‘, ‘a‘)
48 
49     connection_crawl = s.get(url % str(i),headers = {
50         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"
51         })
52     soup_crawl = BeautifulSoup.BeautifulSoup(connection_crawl.content)
53 
54     # parse each page,find the good ip proxy
55     trs = soup_crawl.findAll(‘tr‘)
56     for tr in trs[1:len(trs)]:
57         tds = tr.findAll(‘td‘)
58         ip = tds[0].contents[0] + ‘:‘ + tds[1].contents[0]
59         is_good, res_time = check_a_ip(ip)
60         if is_good:
61             ip_proxy_file.write(ip + ‘,‘ + res_time + ‘\n‘)
62 
63     print ‘%s : Finish to crawl the page %d.  %s‘ % (time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()), i, url % str(i))
64     ip_proxy_file.close()