豆瓣url的登录问题

zy8818

1. import re
   
2. import urllib.request
   
3. from http.cookiejar import CookieJar
   
4. 
   
5. # 豆瓣的登录url
   
6. loginurl = 'https://www.douban.com/accounts/login'
   
7. cookie = CookieJar()
   
8. opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor)
   
9. 
   
10. data = {
    
11.     "form_email":"your email",
    
12.     "form_password":"your password",
    
13.     "source":"index_nav"
    
14. }
    
15. data = {}
    
16. data['form_email'] = '你的账号'
    
17. data['form_password'] = '你的密码'
    
18. data['source'] = 'index_nav'
    
19. 
    
20. response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
    
21. 
    
22. #验证成功跳转至登录页
    
23. if response.geturl() == "https://www.douban.com/accounts/login":
    
24.     html = response.read().decode()
    
25.    
    
26.     #验证码图片地址
    
27.     imgurl = re.search('<img id="captcha_image" src="(.+?)" alt="captcha" class="captcha_image"/>', html)
    
28.     if imgurl:
    
29.         url = imgurl.group(1)
    
30.         # 将验证码图片保存至同目录下
    
31.         res = urllib.request.urlretrieve(url, 'v.jpg')
    
32. 
    
33.         # 获取captcha-id参数
    
34.         captcha = re.search('<input type="hidden" name="captcha-id" value="(.+?)"/>' ,html)
    
35. 
    
36.         if captcha:
    
37.             vcode = input('请输入图片上的验证码：')
    
38.             data["captcha-solution"] = vcode
    
39.             data["captcha-id"] = captcha.group(1)
    
40.             data["user_login"] = "登录"
    
41. 
    
42.             # 提交验证码验证
    
43.             response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
    
44. 
    
45.             # 登录成功跳转至首页 '''
    
46.             if response.geturl() == "http://www.douban.com/":
    
47.                 print('登录成功！')

复制代码

Traceback (most recent call last):
  File "C:/Users/Administrator/AppData/Local/Programs/Python/Python38/111.py", line 20, in <module>
    response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 640, in http_response
    response = self.parent.error(
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 418:
一大堆的红字

suchocolate

得加header。你的教程有点老了，建议用requests学爬虫。

1. from urllib import request
   
2. 
   
3. url = 'https://www.douban.com/accounts/login'
   
4. headers = {'User-Agent': 'Firefox'}
   
5. req = request.Request(url, headers=headers)
   
6. r = request.urlopen(req)
   
7. print(r.read().decode('utf-8'))

复制代码

或

1. from urllib import request
   
2. url = 'https://www.douban.com/accounts/login'
   
3. opener = request.build_opener()
   
4. opener.addheaders = [('User-agent', 'Firefox')]
   
5. response = opener.open(url)
   
6. r = response.read().decode('utf-8')
   
7. print(r)

复制代码