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

hldh214

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()函数不应该传入参数,而是应该使用该函数的参数的默认值
3. 60行print一个函数内的变量,严重错误!应该print(url_opener(url))
语法规范:
1. PEP8的规范我就不谈了,基础的基础.
2. 第9行定义函数使用的形参和外部定义的变量重名,易引起帮你维护代码的人(我)的疑问.
3. 17和48行的reason不知道是故意还是为什么拼写成了reson
个人建议:
只是学习的话可以练练手写匹配ip地址的正则表达式,我观察了你给的获取代理的网页,代理分http和https两种,你可以重新写一个正则表达式来分开匹配这两种协议的代理ip,至于使用就不要太勉强,毕竟是免费的,不出错就很给面子了.
我的代码:

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

复制代码

仯仯

。，。

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