python 056 爬虫之爬取妹子图

风不会停息

以下为小甲鱼的代码， 虽然现在网站设置了反爬， 不能成功爬取了， 但可以参考代码思路：

1. import urllib.request
   
2. import os
   
3. import random
   
4. 
   
5. 
   
6. def url_open(url):
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')
   
9. 
   
10.     '''proxies = ['119.6.144.70:81', '111.1.36.9:80', '203.144.144.162:8080']
    
11.     proxy = random.choice(proxies)
    
12. 
    
13.     proxy_support = urllib.request.ProxyHandler({'http':proxy})
    
14.     opener = urllib.request.build_opener(proxy_support)
    
15.     urllib.request.install_opener(opener)'''
    
16. 
    
17.     response = urllib.request.urlopen(url)
    
18.     html = response.read()
    
19. 
    
20.     return html
    
21. 
    
22. 
    
23. def get_page(url):
    
24.     html = url_open(url).decode('utf-8')
    
25. 
    
26.     a = html.find('current-comment-page') + 23
    
27.     b = html.find(']', a)
    
28. 
    
29.     return html[a:b]
    
30. 
    
31. 
    
32. def find_imgs(url):
    
33.     html = url_open(url).decode('utf-8')
    
34.     img_addrs = []
    
35. 
    
36.     a = html.find('img src=')
    
37. 
    
38.     while a != -1:
    
39.         b = html.find('.jpg', a, a+255)
    
40.         if b != -1:
    
41.             img_addrs.append(html[a+9:b+4])
    
42.         else:
    
43.             b = a + 9
    
44. 
    
45.         a = html.find('img src=', b)
    
46. 
    
47.     return img_addrs
    
48. 
    
49. 
    
50. def save_imgs(folder, img_addrs):
    
51.     for each in img_addrs:
    
52.         filename = each.split('/')[-1]
    
53.         with open(filename, 'wb') as f:
    
54.             img = url_open(each)
    
55.             f.write(img)
    
56. 
    
57. 
    
58. def download_mm(folder='OOXX', pages=10):
    
59.     os.mkdir(folder)
    
60.     os.chdir(folder)
    
61. 
    
62.     url = "http://jandan.net/ooxx/"
    
63.     page_num = int(get_page(url))
    
64. 
    
65.     for i in range(pages):
    
66.         page_num -= i
    
67.         page_url = url + 'page-' + str(page_num) + '#comments'
    
68.         img_addrs = find_imgs(page_url)
    
69.         save_imgs(folder, img_addrs)
    
70. 
    
71. if __name__ == '__main__':
    
72.     download_mm()
    

复制代码

你可真厉害

楼主加油

jiajiaself

确实是反爬的问题，这个代码已经不能成功爬取了，感谢。请问您知道如何在此基础上修改以成功爬取吗？