[已解决]按照小甲鱼讲的写煎蛋的爬虫，但是一直报错，是因为什么

mgiftdc

1. import urllib.request
   
2. import os
   
3. 
   
4. def url_open(url):
   
5.     head = {}
   
6.     head['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'
   
7.     req = urllib.request.Request(url,head)
   
8.     #req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36')
   
9.     response = urllib.request.urlopen(url)
   
10.     html = response.read()
    
11.    
    
12.     return html
    
13. 
    
14. def get_page(url):
    
15.    
    
16.     html = url_open(url).decode('utf-8')
    
17.     a = html.find('current-comment-page')+23
    
18.     b = html.find(']',a)
    
19.     return html[a:b]
    
20. 
    
21.    
    
22. def find_imgs(url):
    
23.     html = url_open(url).decode('utf-8')
    
24.     img_addrs = []
    
25.     a = html.find('img src=')
    
26.     while a != -1:
    
27.         b = html.find('.jpg',a,a+255)
    
28. 
    
29.         if b !=-1:
    
30.             img_addrs.append(html[a+9:b+4])
    
31.         else:
    
32.             b = a+9
    
33. 
    
34.         a = html.find('img src=',b)
    
35.         
    
36.     return img_addrs
    
37.         
    
38.    
    
39. 
    
40. def save_imgs(folder,img_addrs):
    
41.     for each in img_addrs:
    
42.         filename = each.split('/')[-1]
    
43.         with open(filename,'wb') as f:
    
44.             img = url_open(each)
    
45.             f.write(img)
    
46.         
    
47. 
    
48. def download_mm(folder = 'ooxx',pages = 10):
    
49.     os.mkdir(folder)
    
50.     os.chdir(folder)
    
51.     url = 'http://jandan.net/ooxx/'
    
52.     page_num = int(get_page(url))
    
53. 
    
54.     for i in range(pages):
    
55.         page_num -= i
    
56.         page_url = url +'page'+str(page_num)+'#comments'
    
57.         img_addrs = find_imgs(page_url)
    
58.         save_imgs(folder,img_addrs)
    
59. 
    
60. if __name__ == '__main__':
    
61.     download_mm()
    
62.         
    

复制代码

Traceback (most recent call last):
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\download_mm.py", line 61, in <module>
    download_mm()
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\download_mm.py", line 52, in download_mm
    page_num = int(get_page(url))
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\download_mm.py", line 16, in get_page
    html = url_open(url).decode('utf-8')
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\download_mm.py", line 9, in url_open
    response = urllib.request.urlopen(url)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 163, in urlopen
    return opener.open(url, data, timeout)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 472, in open
    response = meth(req, response)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 582, in http_response
    'http', request, response, code, msg, hdrs)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 504, in error
    result = self._call_chain(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 444, in _call_chain
    result = func(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 696, in http_error_302
    return self.parent.open(new, timeout=req.timeout)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 472, in open
    response = meth(req, response)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 582, in http_response
    'http', request, response, code, msg, hdrs)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 510, in error
    return self._call_chain(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 444, in _call_chain
    result = func(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 590, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 503: Service Temporarily Unavailable
>>>
我浏览器里能打开煎蛋呀，这是怎么回事呢

最佳答案

月排行榜 / 总排行榜

无符号整形

2016-9-18 12:29:17

煎蛋反爬虫了，改改头信息再试。

跳转到最佳答案楼层

无符号整形

煎蛋反爬虫了，改改头信息再试。