按照甲鱼老师写的爬虫怎么老是403错误，求大神帮忙看看

jiexinren

1. import urllib.request
   
2. import os
   
3. import random
   
4. 
   
5. def url_open(url):
   
6.     req=urllib.request.Request(url)
   
7.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.125 Safari/537.36')
   
8.    
   
9.     proxies=['203.190.251.116:80','218.89.170.114:8888','122.96.59.105:843','120.193.146.93:843','122.96.59.105:81','61.174.60.181:4824']
   
10.     proxy=random.choice(proxies)
    
11.    
    
12.     proxy_support=urllib.request.ProxyHandler({'http':proxy})
    
13.     opener=urllib.request.build_opener(proxy_support)
    
14.     urllib.request.install_opener(opener)
    
15.    
    
16.     response=urllib.request.urlopen(url)
    
17.     html=response.read()
    
18.    
    
19.     return html
    
20. 
    
21. def get_page(url):
    
22.     html=url_open(url).decode('utf-8')
    
23.     a=html.find('current-comment-page')+23
    
24.     b=html.find(']',a)
    
25.     return html[a:b]
    
26. 
    
27. def find_imgs(url):
    
28.     html=url_open(url).decode('utf-8')
    
29.     img_addrs=[]
    
30.    
    
31.     a=html.find('img src=')
    
32.    
    
33.     while a!=-1:
    
34.         b=html.final('.jpg',a,a+255)
    
35.         if b!=-1:
    
36.             img_addrs.append(html[a+9:b+4])
    
37.         else:
    
38.             b=a+9
    
39.         a=html.final('img src=',b)
    
40.     return img_addrs   
    
41. 
    
42. def save_imgs(folder,img_addrs):
    
43.     for each in img_addrs:
    
44.         filename=each.split('/')[-1]
    
45.         with open(filename,'wb') as f:
    
46.             img=url_open(each)
    
47.             f.write(img)
    
48. 
    
49. def download_mm(folder='ooxx',pages=10):
    
50.     os.mkdir(folder)
    
51.     os.chdir(folder)
    
52.    
    
53.     url="http://jandan.net/ooxx/"
    
54.     page_num=int(get_page(url))
    
55.    
    
56.     for i in range(pages):
    
57.         page_num-=i
    
58.         page_url=url+'page-'+str(page_num)+'#comments'
    
59.         img_addrs=find_imgs(page_url)
    
60.         save_imgs(folder, img_addrs)
    
61.         
    
62. if __name__=='__main__':
    
63.     download_mm()
    
64.    

复制代码