为什么模拟登录后还是停留在验证码环节

cc7756789w

1. #!/usr/bin/python
   
2. # -*- encoding:utf-8 -*-
   
3. import urllib
   
4. import urllib2
   
5. import re
   
6. import random
   
7. 
   
8. login_url = ' '
   
9. html = urllib2.urlopen(login_url).read()
   
10. 
    
11. def get_captcha(html):
    
12.     reg = r'<img id="captcha_image" src="(.*?)" alt="captcha" class="captcha_image"/>'
    
13.     c_reg = re.compile(reg)
    
14.     img = re.findall(reg, html)
    
15.     for x in img:
    
16.         urllib.urlretrieve(x, '%d.jpg' % random.randint(1,1000))
    
17. get_captcha(html)
    
18.    
    
19. 
    
20. captcha_id = re.findall(r'<input type="hidden" name="captcha-id" value="(.*?)"/>', html)
    
21. 
    
22. print captcha_id
    
23. 
    
24. captcha = raw_input('Please input captcha: ')
    
25. postdata = urllib.urlencode({
    
26.     'source':'index_nav',
    
27.     'form_email':'xx@qq.com',
    
28.     'form_password':'77xxxw',
    
29.     'captcha-solution':captcha,
    
30.     'captcha-id':captcha_id,
    
31.     'user_login':'登录',
    
32.     })
    
33. 
    
34. head = {
    
35.     'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64)\
    
36.     AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537.36',
    
37. }
    
38. 
    
39. 
    
40. req = urllib2.Request(
    
41.         url = login_url,
    
42.         data = postdata,
    
43.         headers = head
    
44.         )
    
45. result = urllib2.urlopen(req).read()
    
46. 
    
47. 
    
48. with open('a.html', 'w+') as f:
    
49.     f.write(result)

复制代码

bikong0411

抓包看看，报的什么错吧

qxhgd

本来就有验证码吧，python可以做验证码的识别吗？

33bubble

可以通过抓取页面cookie，绕过验证码识别

Linux_manne

你只是把 图片下载下来了 并 没有进行识别 啊