模拟登陆国内著名知识交流网站

#!/usr/bin/python
# -*- coding: utf-8 -*-

import requests
from bs4 import BeautifulSoup
import cookielib
import json

HomePage = ‘https://www.zXXXu.com/‘ # 主页网址
# = r‘zhihu_cookies.txt‘

session = requests.session()

cookie = cookielib.CookieJar()  #这个方法可以暂存cookie
‘‘‘
session.cookies = cookielib.MozillaCookieJar(filename)  #这个方法是将cookie放入文件中
try:
    session.cookies.load(filename=filename, ignore_discard=True, ignore_expirex=True)  #gnore_discard的意思是即使cookies将被丢弃也将它保存下来，ignore_expires的意思是如果在该文件中cookies已经存在，则覆盖原文件写入，
except:
    print ‘Cookie can not load!‘
‘‘‘

headers = {‘Connection‘: ‘keep-alive‘,
            ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘,
            ‘Accept-Language‘: ‘en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3‘,
            ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36‘,
            ‘Accept-Encoding‘: ‘gzip, deflate, sdch‘,
            ‘Host‘: ‘www.zXXXu.com‘,
           }



def get_xsrf():
    text = session.get(HomePage, headers=headers).text
    soup = BeautifulSoup(text, ‘html.parser‘)
    result = soup.find(‘div‘, class_=‘view view-signin‘).find(‘input‘)[‘value‘]
    return result


#获取验证码
def get_captcha():
    pass


def login_zhihu(phone, passwd):
    login_url = HomePage+‘/login/phone_num‘
    data = {
        ‘_xsrf‘: ‘%s‘ % get_xsrf(),
        ‘password‘: passwd,
        ‘phone_num‘: phone,
        ‘captcha_type‘: ‘cn‘
    }
    result = session.post(login_url, data=data, headers=headers)
    print json.loads(result.text)[‘msg‘]  # result的body是son格式，而‘msg‘的值是登录状态
    return


if __name__ == ‘__main__‘:
    phone = raw_input(‘Please input phone_num: ‘)
    passwd = raw_input(‘Please input password: ‘)
    url = HomePage + ‘/settings/profile‘   # 登录后才可以访问自己的profile
    login_zhihu(phone, passwd)
    resp_status = session.get(url, headers=headers, allow_redirects=False).status_code  # 此处关闭了跳转的操作
    print resp_status  # 返回结果是访问状态码