模拟豆瓣登录

# -*- coding:utf-8 -*-
import requests
from HTMLParser  import HTMLParser
from PIL import Image
class doubancilnt(object):
    def __init__(self):
        headers={'Referer':'https://www.google.com.ph/',
                 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.87 Safari/537.36'}
        self.session =requests.session()
        self.session.headers.update(headers)
    def login(self,username,password,
              source='index_nav',
              redir = 'https://www.douban.com/',
              login='登录',
              ):
              url='https://accounts.douban.com/login'
              r = self.session.get(url)
              captcha_url,captcha_id =_get_captcha(r.content)
              print captcha_id
              print captcha_url
              if captcha_id:
                  img_html=self.session.get(captcha_url)
                  with open('captcha.jpg','wb') as f:
                      f.write(img_html.content)
                  try:
                      im=Image.open('captcha.jpg')
                      im.show()
                      im.close()
                  except:
                      print 'error'
                  captcha_solution = raw_input ('please imput solution %s:'%captcha_url)





              data={ 'source':source,
                    'redir':redir,
                    'form_email':username,
                     'form_password':password,
                    'login':login,}
              headers={'Referer':'https://www.google.com.ph/',
                      'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.87 Safari/537.36'}
              if captcha_id:
                  data['captacha-id']=captcha_id
                  data['captacha-soution']=captcha_solution
              r=self.session.post(url,data=data,headers=headers)
              print self.session.cookies.items()
def _attr(attrs,attrname):
    for attr in attrs:
        if attr[0] == attrname:
            return  attr[1]
    return  None

def _get_captcha(content):
    class CaptchaPaser(HTMLParser):
        def __init__(self):
            HTMLParser.__init__(self)
            self.captcha_url= None
            self.captcha_id = None
        def handle_starttag(self, tag, attrs):
            if tag =='img'and _attr(attrs,'id')=='captcha_image' and _attr(attrs,'class')=='captcha_image':
                self.captcha_url=_attr(attrs,'src')
            if tag=='input' and _attr(attrs,'type')=='hidden' and _attr(attrs,'name')=='captcha-id':
                self.captcha_id=_attr(attrs,'value')
    p=CaptchaPaser()
    p.feed(content)#回解析html<div>
    return  p.captcha_url,p.captcha_id
if __name__=='__main__':
    C=doubancilnt()
    C.login('576433951@qq.com','mima')