pyhton爬取代理IP的问题

若余相思

1. import re
   
2. import os
   
3. import urllib.request
   
4. from urllib.error import HTTPError, URLError
   
5. 
   
6. 
   
7. def open_url(url):
   
8.     req = urllib.request.Request(url)
   
9.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36')
   
10.     try:
    
11.         response = urllib.request.urlopen(req)
    
12.     except (HTTPError, URLError) as e:
    
13.         print(e)
    
14.     try:
    
15.         html = response.read().decode('utf-8')
    
16.     except UnboundLocalError as e:
    
17.         print(e)
    
18. 
    
19.     return html
    
20. 
    
21. def save_file(html):
    
22.     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])'
    
23.     ip_list = re.findall(p, html)
    
24.     for each in ip_list:
    
25.        print(eachh)
    
26. if __name__ == "__main__":
    
27.     url = "https://cn.proxy.com"
    
28.     save_file(open_url(url))

复制代码

这几个异常如何解决？

若余相思

研究了一下，原来是url失效了，自己太粗心了