第53讲 爬虫

raimond

1. import urllib.request
   
2. import chardet
   
3. 
   
4. def main():
   
5.     i = 0
   
6. 
   
7.     with open("urls.txt", 'r') as f:
   
8.         urls = f.read().splitlines()
   
9. 
   
10.     for each_url in urls:
    
11.         response = urllib.request.urlopen(each_url)
    
12.         html = response.read()
    
13. 
    
14.         encode = chardet.detect(html)['encoding']
    
15.         if encode == 'GB2312':
    
16.             encode = 'GBK'
    
17. 
    
18.         i += 1
    
19.         filename = 'url_%d.txt'% i
    
20. 
    
21.         with open(filename, 'w', encoding = encode) as each_file:
    
22.             each_file.write(html.decode(encode, 'ignore'))
    
23. 
    
24. if __name__ == '__main__':
    
25.     main()

复制代码

==================== RESTART: C:/Users/user/Desktop/df.py ====================
Traceback (most recent call last):
  File "C:/Users/user/Desktop/df.py", line 25, in <module>
    main()
  File "C:/Users/user/Desktop/df.py", line 22, in main
    each_file.write(html.decode(encode))
TypeError: decode() argument 1 must be str, not None
>>>
上面是什么原因报错？

waitforlove

TypeError: decode() argument 1 must be str, not None