以下代码怎么改，才能实现用自动收集的IP来访问网页吖？

欣欣celin

1. import urllib.request as r
   
2. from urllib.error import URLError
   
3. import random
   
4. import re
   
5. 
   
6. 
   
7. iplist = {} #存放IP和端口
   
8. 
   
9. def open_url(url='http://www.xicidaili.com/wn/'):
   
10.     req = r.Request(url)
    
11.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36')
    
12.     try:
    
13.         page = r.urlopen(req)
    
14.     except URLError as e:
    
15.         if hasattr(e, 'reason'):
    
16.             print('we failed to reach a server,')
    
17.             print('reson: ', e.reason)
    
18.         elif hasattr(e, 'code'):
    
19.             print('the server could not fulfill the request,')
    
20.             print('error code:', e.code)
    
21.     else:
    
22.         html = page.read().decode('utf-8')
    
23.         return html
    
24. 
    
25. 
    
26. def get_ip(html):
    
27.     p = r'(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])'
    
28. #'?:'表示：非bu获组
    
29.     #要修正：iplist.append(re.findall(p, html))
    
30.     return iplist
    
31. 
    
32. def url_opener(url):   
    
33.     req = r.Request(url)
    
34.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36')
    
35. 
    
36.     proxies = get_ip(open_url(url))
    
37.     proxy = random.choice(proxies)
    
38.     proxy_support = r.ProxyHandler({'http':proxy})
    
39. 
    
40.     opener = r.build_opener(proxy_support)
    
41.     r.install_opener(opener)
    
42.    
    
43.     try:
    
44.         response = r.urlopen(url)
    
45.     except URLError as e:
    
46.         if hasattr(e, 'reason'):
    
47.             print('we failed to reach a server,')
    
48.             print('reson: ', e.reason)
    
49.         elif hasattr(e, 'code'):
    
50.             print('the server could not fulfill the request,')
    
51.             print('error code:', e.code)        
    
52.     else:
    
53.         html2 = response.read()
    
54. 
    
55.         return html2
    
56. 
    
57. if __name__=='__main__':
    
58.     url = input('请输入要打开的网页：')
    
59.     url_opener(url)
    
60.     print(html2)
    
61.    
    

复制代码

欣欣celin

hldh214 发表于 2015-12-31 14:11
致命错误:
1. 27行预编译正则表达式语法错误,需要使用re.compile()来预编译.
2. 36行open_url()函数不应 ...

谢谢指教