这是什么原因啊

lorraine

1. import urllib.request
   
2. import os
   
3. 
   
4. def get_page(url):
   
5.     req = urllib.request.Request(url)
   
6.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 5.1; rv:47.0) Gecko/20100101 Firefox/47.0')
   
7.     response = urllib.request.urlopen(url)
   
8.     html = response.read().decode('utf-8')
   
9. 
   
10.     a = html.find('current-comment-page')+23
    
11.     b = html.find(']',a)
    
12.    
    
13.     print(html[a:b])
    
14. 
    
15. 
    
16. 
    
17. def find_imgs(url):
    
18.     pass
    
19. 
    
20. def save_imgs(folder,img_addrs):
    
21.     pass
    
22. 
    
23. 
    
24. def download_mm(folder='OOXX',pages = 10):
    
25.     os.mkdir(folder)
    
26.     os.chdir(folder)
    
27. 
    
28.     url = "http://jandan.net/ooxx"
    
29.     page_num = int(get_page(url))
    
30. 
    
31.     for i in range(pages):
    
32.         page_num -= i
    
33.         page_url = url +'page-'+str(page_num)+'#comments'
    
34.         img_addrs = find_imgs(page_url)
    
35.         save_imgs(folder,img_addrs)
    
36. 
    
37. if __name__=='__main__':
    
38.     download_mm()
    
39.         

复制代码

1. Traceback (most recent call last):
   
2.   File "E:\lorraine\01\Python\爬妹子图00.py", line 38, in <module>
   
3.     download_mm()
   
4.   File "E:\lorraine\01\Python\爬妹子图00.py", line 29, in download_mm
   
5.     page_num = int(get_page(url))
   
6.   File "E:\lorraine\01\Python\爬妹子图00.py", line 7, in get_page
   
7.     response = urllib.request.urlopen(url)
   
8.   File "C:\Python34\lib\urllib\request.py", line 161, in urlopen
   
9.     return opener.open(url, data, timeout)
   
10.   File "C:\Python34\lib\urllib\request.py", line 470, in open
    
11.     response = meth(req, response)
    
12.   File "C:\Python34\lib\urllib\request.py", line 580, in http_response
    
13.     'http', request, response, code, msg, hdrs)
    
14.   File "C:\Python34\lib\urllib\request.py", line 502, in error
    
15.     result = self._call_chain(*args)
    
16.   File "C:\Python34\lib\urllib\request.py", line 442, in _call_chain
    
17.     result = func(*args)
    
18.   File "C:\Python34\lib\urllib\request.py", line 685, in http_error_302
    
19.     return self.parent.open(new, timeout=req.timeout)
    
20.   File "C:\Python34\lib\urllib\request.py", line 470, in open
    
21.     response = meth(req, response)
    
22.   File "C:\Python34\lib\urllib\request.py", line 580, in http_response
    
23.     'http', request, response, code, msg, hdrs)
    
24.   File "C:\Python34\lib\urllib\request.py", line 508, in error
    
25.     return self._call_chain(*args)
    
26.   File "C:\Python34\lib\urllib\request.py", line 442, in _call_chain
    
27.     result = func(*args)
    
28.   File "C:\Python34\lib\urllib\request.py", line 588, in http_error_default
    
29.     raise HTTPError(req.full_url, code, msg, hdrs, fp)
    
30. urllib.error.HTTPError: HTTP Error 503: Service Temporarily Unavailable

复制代码

sunqiangzai

urllib.error.HTTPError: HTTP Error 503: Service Temporarily Unavailable
是不是网站没有响应？

lorraine

sunqiangzai 发表于 2016-8-7 21:17
urllib.error.HTTPError: HTTP Error 503: Service Temporarily Unavailable
是不是网站没有响应？

我也不知道，用浏览器又可以打开

云飘飘

好巧我也正学到这一节，也是503错误

lorraine

云飘飘 发表于 2016-8-7 22:04
好巧我也正学到这一节，也是503错误

aqqq

设置一个模拟浏览器，还有ip地址也代理一个

ABC23

https://baike.baidu.com/item/503错误/1827145
服务器出错。类似404NOT FOUND就是。