爬虫模拟登录豆瓣

网络爬虫——模拟登录豆瓣

# -*- coding: utf-8 -*-
"""
Created on Sat Apr 01 13:44:51 2017

@author: 马晶义
"""

import requests
import re
headers = {
    "Host":"www.douban.com",
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36",
    "Accept-Language":"zh-CN,zh;q=0.8,zh-TW;q=0.6",
    "Accept-Encoding":"gzip, deflate, sdch, br",
    "Connection":"keep-alive"
    }

def login():
    login_str = u'登录'
    data = {
    #'ck':'GiW5',
    'source':'None',
    #'redir':'https://movie.douban.com/',
    'form_email':'xxxxxx',
    'form_password':'xxxxx',
    #'captcha_solution':captcha_solution,
    #'captcha_id':captcha_id,
    'login':login_str
    }
    login_url = 'https://www.douban.com/accounts/login'
    session = requests.session()
    html = session.get(login_url,headers=headers).text
    captcha_img_pattern = r'(?<=<img id="captcha_image" src=\").*?(?=\")'
    captcha_image_url = re.search(captcha_img_pattern,html,re.S|re.M|re.I)
    if captcha_image_url is not None:
        captcha_image_url = captcha_image_url.group()
        print captcha_image_url
        #captcha_image = session.get(captcha_image_url).text
        captcha_image = requests.get(captcha_image_url,headers=headers).content
        document ='login_captcha_douban.jpg' 
        file_ = open(document,'wb')
        file_.write(captcha_image)
        file_.close()
        captcha_solution = raw_input('captcha_solution:')
        data['captcha-solution'] = captcha_solution
        #获取captcha_id
        captcha_id_pattern = r'(?<=<input type="hidden" name="captcha-id" value=\").*?(?=\"/>)'
        captcha_id = re.search(captcha_id_pattern,html,re.S|re.M|re.I)
        if captcha_id is None:
            print 'captcha_id error'
        else:
            captcha_id = captcha_id.group()
            data['captcha-id'] = captcha_id
    session.post(login_url,headers=headers,data=data)
    print data
    print session.cookies.items()
    return session


def main():
    session = login()
    usinfo = session.get('https://www.douban.com/people/146365045/',headers=headers).text
    #输出你的用户名
    print (re.search(r'(?<=<title>).*?(?=</title>)',usinfo,re.M|re.I|re.S)).group()
    usinfo = usinfo.encode('utf-8')  #保存你个人信息页面
    file_=open('use.html','wb')
    file_.write(usinfo)
    file_.close()

main()