python模拟登录微博 模拟用户登陆python

这里用到的库有两个

import requests
import re

登陆时首先要获取此时的session来维持对话，post请求时还需要请求头head

def postLoginsession():
    # 请求登陆的页面
    url = "https://passport.csdn.net/account/login"
    #请求头
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
    #获取session
    session = requests.session()
    ret = session.get(url, headers=headers)
    ret = repr(ret.text)  # 将获取到的ret页面内容解析成字符串以便得到lt内容
    # 匹配获取lt参数和excution参数
    lt = re.findall('name="lt" value="*(.*?)"', ret)[0]
    execution = re.findall('name="execution" value="*(.*?)"', ret)[0]
    post_data = {
        "username": "17861121396",
        "password": "wwx958260!!!",
        "lt": lt,
        "execution": execution,
        "_eventId": "submit"}
    r = session.post(url, headers=headers, data=post_data)
    return r.cookies

 获取session成功登陆后，利用session.get点击页面，获取一次session，可以得到访问后的页面

def getMycsdnsession(cookie):
    session2 = requests.session()
    session2.cookies = cookie
    return session2
def getHtml_str(session):
    url = "https://blog.csdn.net/efheoihfe"
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
    html_str = session.get(url, headers=headers)
    return html_str.text

if __name__ == '__main__':
    cookie = postLoginsession()
    session = getMycsdnsession(cookie)
    html = getHtml_str(session)
    print(html)