一些代理ip有需要的可以直接用

Chysial

1. import urllib.request
   
2. import re
   
3. import os
   
4. import random
   
5. def url_open(url):
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header("user-agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36")
   
8.     proxies = ["125.108.123.66:9000","183.166.103.45:9999","115.195.84.31:8118","61.178.149.237:59042"]
   
9.     proxy = random.choice(proxies)
   
10.     proxy_support = urllib.request.ProxyHandler({'http':proxy})
    
11.     opener = urllib.request.build_opener(proxy_support)
    
12.     urllib.request.install_opener(opener)
    
13.     response = urllib.request.urlopen(req)
    
14.     html = response.read().decode("utf-8")
    
15.     return html
    
16. def split_addrs_port(temp_str):
    
17.     [a,b] = temp_str.split(">",2)
    
18.     [c,d] =b.split("<",2)
    
19.     return c
    
20.    
    
21. def get_addrs_port(url):
    
22.     html = url_open(url)
    
23.     compile_ip = re.compile(r'("IP">(([0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}([0-1]?\d?\d|2[0-4]\d|25[0-5])<)')
    
24.     compile_port = re.compile(r""PORT">\d{0,5}<")
    
25.     url_addrs_temp = compile_ip.findall(html)
    
26.     url_port_temp= compile_port.findall(html)
    
27.     list_addrs_port = []
    
28.     for i in range(len(url_addrs_temp)):
    
29.         url_addrs = split_addrs_port(str(url_addrs_temp[i][0]))
    
30.         url_port = split_addrs_port(str(url_port_temp[i]))
    
31.         url_addrs_port = url_addrs + ":" + url_port
    
32.         list_addrs_port.append(url_addrs_port)
    
33.     return list_addrs_port
    
34. 
    
35. def save_addrs_port(addrs_port):
    
36.     with open("ip_port.txt","a") as f:
    
37.         for each in addrs_port:
    
38.             f.write(str(each) + "\n")
    
39.    
    
40. 
    
41. def download_url(folder = "proxy_support", pages = "10"):
    
42.     os.chdir("C:\\Users\\Chysial\\Desktop")
    
43.     '''os.mkdir(folder)'''
    
44.     os.chdir(folder)
    
45. 
    
46. 
    
47.     for i in range(int(pages)):
    
48.         page_num =i+1
    
49.         url = "https://www.kuaidaili.com/free/inha/"
    
50.         pages_url = url +str(page_num)
    
51.         url_addrs_port = get_addrs_port(pages_url)
    
52.         save_addrs_port(url_addrs_port)
    
53.         print(url_addrs_port)
    
54. 
    
55. if __name__ == "__main__":
    
56.     download_url()
    
57. 
    
58.    
    
59. 
    

复制代码

Chysial

修改版的，可以直接用，不会出现错误的ip爬取

1. import urllib.request
   
2. import re
   
3. import os
   
4. import random
   
5. import urllib.error
   
6. 
   
7. def url_open(url):
   
8.     req = urllib.request.Request(url)
   
9.     req.add_header("user-agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36")
   
10.     proxies = ["125.108.123.66:9000","183.166.103.45:9999","115.195.84.31:8118","61.178.149.237:59042"]
    
11.     proxy = random.choice(proxies)
    
12.     proxy_support = urllib.request.ProxyHandler({'http':proxy})
    
13.     opener = urllib.request.build_opener(proxy_support)
    
14.     urllib.request.install_opener(opener)
    
15.     response = urllib.request.urlopen(req)
    
16.     html = response.read().decode("utf-8")
    
17.     return html
    
18. 
    
19.    
    
20. def split_addrs_port(temp_str):
    
21.     [a,b] = temp_str.split(">",2)
    
22.     [c,d] =b.split("<",2)
    
23.     return c
    
24.    
    
25. def get_addrs_port(url):
    
26.     html = url_open(url)
    
27.     compile_ip = re.compile(r'("IP">(([0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}([0-1]?\d?\d|2[0-4]\d|25[0-5])<)')
    
28.     compile_port = re.compile(r""PORT">\d{0,5}<")
    
29.     url_addrs_temp = compile_ip.findall(html)
    
30.     url_port_temp= compile_port.findall(html)
    
31.     list_addrs_port = []
    
32.     for i in range(len(url_addrs_temp)):
    
33.         url_addrs = split_addrs_port(str(url_addrs_temp[i][0]))
    
34.         url_port = split_addrs_port(str(url_port_temp[i]))
    
35.         url_addrs_port = url_addrs + ":" + url_port
    
36.         list_addrs_port.append(url_addrs_port)
    
37.     return list_addrs_port
    
38. 
    
39. def save_addrs_port(addrs_port):
    
40.     with open("ip_port.txt","a") as f:
    
41.         for each in addrs_port:
    
42.             f.write(str(each) + "\n")
    
43.    
    
44. 
    
45. def download_url(folder = "proxy_support3", pages = "10"):
    
46.     os.chdir("C:\\Users\\Chysial\\Desktop")
    
47.     os.mkdir(folder)
    
48.     os.chdir(folder)
    
49.     url = "https://www.kuaidaili.com/free/inha/"
    
50.     url_list = []
    
51.     for i in range(int(pages)):
    
52.         page_num =i+1
    
53.         pages_url = url + str(page_num)
    
54.         try:
    
55.             url_addrs_port = get_addrs_port(pages_url)
    
56.             save_addrs_port(url_addrs_port)
    
57.             print(url_addrs_port)
    
58.         except urllib.error.HTTPError as e:
    
59.             print(e.code)
    
60.             continue
    
61. 
    
62.       
    
63. 
    
64. if __name__ == "__main__":
    
65.     download_url()
    
66. 
    
67.    
    
68. 
    

复制代码