模拟登录知乎思路【代码过时，但代码思路很优秀】

# -*- coding: utf-8 -*-
__author__ = 'bobby'

import requests
try:
    import cookielib
except:
    import http.cookiejar as cookielib

import re

session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename="cookies.txt")
try:
    session.cookies.load(ignore_discard=True)
except:
    print ("cookie未能加载")

agent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
header = {
    "HOST":"www.zhihu.com",
    "Referer": "https://www.zhizhu.com",
    'User-Agent': agent
}

def is_login():
    #通过个人中心页面返回状态码来判断是否为登录状态
    inbox_url = "https://www.zhihu.com/question/56250357/answer/148534773"
    response = session.get(inbox_url, headers=header, allow_redirects=False)#allow_redirects是否实现重定向
    if response.status_code != 200:
        return False
    else:
        return True

def get_xsrf():
    #获取xsrf code
    response = session.get("https://www.zhihu.com", headers=header)
    match_obj = re.match('.*name="_xsrf" value="(.*?)"', response.text)
    if match_obj:
        return (match_obj.group(1))
    else:
        return ""


def get_index():
    response = session.get("https://www.zhihu.com", headers=header)
    with open("index_page.html", "wb") as f:
        f.write(response.text.encode("utf-8"))
    print ("ok")

def get_captcha():
    import time
    t = str(int(time.time()*1000))
    captcha_url = "https://www.zhihu.com/captcha.gif?r={0}&type=login".format(t)#验证码的跳转地址
    t = session.get(captcha_url, headers=header)
    with open("captcha.jpg","wb") as f:
        f.write(t.content)
        f.close()

    from PIL import Image
    try:
        im = Image.open('captcha.jpg')
        im.show()
        im.close()
    except:
        pass

    captcha = input("输入验证码\n>")
    return captcha

def zhihu_login(account, password):
    #知乎登录
    if re.match("^1\d{10}",account):
        print ("手机号码登录")
        post_url = "https://www.zhihu.com/login/phone_num"
        post_data = {
            "_xsrf": get_xsrf(),
            "phone_num": account,
            "password": password,
            "captcha":get_captcha()
        }
    else:
        if "@" in account:
            #判断用户名是否为邮箱
            print("邮箱方式登录")
            post_url = "https://www.zhihu.com/login/email"
            post_data = {
                "_xsrf": get_xsrf(),
                "email": account,
                "password": password
            }

    response_text = session.post(post_url, data=post_data, headers=header)
    session.cookies.save()

zhihu_login("18782902568", "admin123")
# get_index()
is_login()

# get_captcha()

以上代码中cookie的相关用法

try:
    import cookielib
except:
    import http.cookiejar as cookielib      #python3中


.....

try:
    session.cookies.load(ignore_discard=True)            #下次登录时自动获取cookie
except:
    print ("cookie未能加载")
	
.......
	
session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename="cookies.txt")



response_text = session.post(post_url, data=post_data, headers=header)          #使用session登录表示一个长连接
session.cookies.save()
......