http被禁用了怎么搞，求各位帮忙看下哪里出错了

yechuang

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 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')
   
8. 
   
9.     response = urllib.request.urlopen(url)
   
10.     html = response.read()
    
11.     print(url)
    
12.     return html
    
13. 
    
14. 
    
15. def get_page(url):
    
16.     html = url_open(url).decode('utf-8')
    
17. 
    
18.     a = teml.find('current-comment-page') + 23
    
19.     b = html.find(']', a)
    
20. 
    
21.     return html[a:b]
    
22. 
    
23. 
    
24. def find_imgs(url):
    
25.     html = url_open(url).decode('utf-8')
    
26.     img_addes = []
    
27. 
    
28.     a = html.find('img src=')
    
29. 
    
30.     while a != -1:
    
31.         b = html.find(' .jpg', a, a+255)
    
32.         if b != -1:
    
33.             img_addrs.append(html[a+9:b+4])
    
34.         else:
    
35.             b = a + 9
    
36. 
    
37.         a = html.find('img src=', b)
    
38. 
    
39.     return img_addrs
    
40. 
    
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()

复制代码

shuofxz

听说煎蛋网已经禁止爬虫了。。。
不过你可以试试伪装成浏览器，添加下面的代码，或者更多（小甲鱼老师在55课有讲隐藏）

1.     data['type'] = 'AUTO'
   
2.     data['i'] = content
   
3.     data['doctype'] = 'json'
   
4.     data['xmlVersion'] = '1.8'
   
5.     data['keyfrom'] = 'fanyi.web'
   
6.     data['ue'] = 'UTF-8'
   
7.     data['action'] = 'FY_BY_CLICKBUTTON'
   
8.     data['typoResult'] = 'true'

复制代码

再有一种你把网址改成www.chunmm.com，不过要根据实际审查元素相应的修改一些代码

wei_Y

浏览器里打开也是403么。

yechuang

wei_Y 发表于 2016-3-13 16:41
浏览器里打开也是403么。

不是啊，有网络的