下载百度贴吧出现问题

boyy

1. import urllib.request
   
2. import urllib.parse
   
3. import chardet
   
4. 
   
5. def response(fileurl,filename):
   
6.     print('正在加载%s'% filename)
   
7.     Requ=urllib.request.Request(fileurl)
   
8.     Requ.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.3368.400 QQBrowser/9.6.11974.400')
   
9.     res=urllib.request.urlopen(Requ).read()
   
10.     resde=chardet.detect(res)['encoding']
    
11.     if resde == 'GB2312':
    
12.         resde='GBK'
    
13.     name=res.decode(resde)
    
14.     return name,resde
    
15. 
    
16. def write_tie(html,resde,filename):
    
17.     print('正在保存%s' % filename)
    
18.     with open(filename,'w',encoding=resde)as f:
    
19.         f.write(html)
    
20.         print('-'*20)
    
21. 
    
22. 
    
23. def tieba_page(url,start_page,end_page):
    
24.     for i in range(start_page,end_page+1):
    
25.         pn=(i-1)*50
    
26.         filename='第%s页.html' % i
    
27.         fileurl=url+('&pn=%d' % pn)
    
28.         html,resde=response(fileurl,filename)
    
29.         write_tie(html,resde,filename)
    
30.    
    
31. 
    
32. 
    
33. if __name__=='__main__':
    
34.     kw=input('请输入贴吧名：')
    
35.     start_page=int(input('请输入起始页:'))
    
36.     end_page=int(input('请输入结束页:'))
    
37.     urld='https://tieba.baidu.com/f?'
    
38.     key=urllib.parse.urlencode({'kw':kw})
    
39.     print(type(key))
    
40.     url=urld+key
    
41.     tieba_page(url,start_page,end_page)
    

复制代码

Traceback (most recent call last):
  File "C:\Users\Administrator\Desktop\tieba\789.py", line 41, in <module>
    tieba_page(url,start_page,end_page)
  File "C:\Users\Administrator\Desktop\tieba\789.py", line 28, in tieba_page
    html,resde=response(fileurl,filename)
  File "C:\Users\Administrator\Desktop\tieba\789.py", line 13, in response
    name=res.decode(resde)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35-32\lib\encodings\cp1254.py", line 15, in decode
    return codecs.charmap_decode(input,errors,decoding_table)
UnicodeDecodeError: 'charmap' codec can't decode byte 0x90 in position 266: character maps to <undefined>

boyy

用这个chardet模块会出现问题，要是在read后面直接用utf-8解码就没有问题