跟着小甲鱼视频编写爬虫图片代码，运行后报错400：Bad request?求指导这是什么问题...

panda900209

爬虫煎蛋图片代码如下：

1. import urllib.request
   
2. import os
   
3. 
   
4. def url_open(url):
   
5.    
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36')
   
8.     response = urllib.request.urlopen(url)
   
9.     html = response.read()
   
10.    
    
11.     return html
    
12. 
    
13. def get_page(url):
    
14.    
    
15.     html = url_open(url).decode('utf-8')
    
16. 
    
17.     a = html.find('current-comment-page') + 23
    
18.     b = html.find(']',a)
    
19.    
    
20.     return html[a:b]
    
21. 
    
22. def find_imgs(url):   
    
23.     html = url_open(url).decode('utf-8')
    
24.     img_addrs = []
    
25. 
    
26.     a = html.find('img style="max-height: 750px; max-width: 480px;" src='）#检查元素后，得到的src在style后，这个如何处理？
    
27.     while a != -1:
    
28.         b = html.find('.jpg',a,a+255)
    
29.         if b != -1:
    
30.             img_addrs.append(html[a+53:b+4])
    
31.         else:
    
32.             b = a + 53
    
33.         
    
34.         a = html.find('img style="max-height: 750px; max-width: 480px;" src=',b)
    
35.         
    
36.     return img_addrs
    
37. 
    
38. def save_imgs(folder,img_addrs):
    
39.     for each in img_addrs:
    
40.         filename = each.split('/')[-1]
    
41.         with open(filename,'wb') as f:
    
42.             img = open_url(each)
    
43.             f.write(img)
    
44. 
    
45. def download_mm(folder = 'mm',pages = 5):
    
46.     os.mkdir(folder)
    
47.     os.chdir(folder)
    
48. 
    
49.     url = "http://jandan.net/ooxx/"
    
50.     page_num = int(get_page(url))
    
51. 
    
52.     for i in range(pages):
    
53.         page_num -= i
    
54.         page_url = url + 'page- ' + str(page_num) + '#comments'
    
55.         img_addrs = find_imgs(page_url)
    
56.         save_imgs(folder,img_addrs)
    
57. 
    
58. if __name__ == '__main__':
    
59.     download_mm()
    

复制代码

运行后报出来的错误如下：


求指导，这是啥问题。谢谢啦

SongQing

+++++++++++++++++++++++++++1
试了好多个代理ip了，要么是400 Bad Request，要么就是连接时间过长，或者直接被禁止了