代理ip问题

幽梦三影

1. import random
   
2. import urllib.request
   
3. import re
   
4. from bs4 import BeautifulSoup
   
5. 
   
6. ip = [
   
7. "221.228.17.172:8181",
   
8. "118.31.220.3:8080",
   
9. "61.135.217.7:80"
   
10. ]
    
11. user_pool = [
    
12. "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0",
    
13. "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; Maxthon/3.0)",
    
14. "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ;  QIHU 360EE)"
    
15. ]
    
16. current_ip = random.choice(ip)
    
17. current_user = random.choice(user_pool)
    
18. 
    
19. headers = ("User-Agent",current_user)
    
20. opener = urllib.request.build_opener()
    
21. opener.addheaders = [headers]
    
22. urllib.request.install_opener(opener)
    
23. 
    
24. p = urllib.request.ProxyHandler({"http":current_ip})
    
25. opener = urllib.request.build_opener(p,urllib.request.HTTPHandler)
    
26. urllib.request.install_opener(opener)
    
27. 
    
28. url = "http://www.taobao.com"
    
29. html = urllib.request.urlopen(url).read()
    
30. html = BeautifulSoup(html)
    
31. link = html.find_all("a",href = True)
    
32. #print(html)
    
33. for i in link:
    
34.     print(i.get("href"))

复制代码

用代理ip爬取淘宝连接却都是有道，还有小甲鱼在视频里说的爬取妹子图会出现其他的图到底是怎么回事

故梦L

你检查一下url，代理IP是避免服务器检测出你的访问是爬虫和封了ip，妹子图里的图片被加密了