爬虫POST请求自动登录

#获取token随机字符串

'''
1.访问登录页面获取token随机字符串
    请求URL：
            http://github.com/login
    请求方式：
           GET
    请求头：
          COOKIES
          User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36
2.解析并提取token字符串
#正则
<input type="hidden" name="authenticity_token" value="(.*?)" />          
'''

import requests
import  re
login_url='https://github.com/login'

#login页面的请求头信息

login_header={
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}

login_res=requests.get(url=login_url,headers=login_header)

#print(login_res.text)

#解析提取token字符串

authenticity_token=re.findall(
    '<input type="hidden" name="authenticity_token" value="(.*?)" />',
    login_res.text,
    re.S
)[0]
print(authenticity_token)

#获取login页面的cookies信息

#print(login_res.cookies)
login_cookies=login_res.cookies.get_dict()

#2.开始登陆github

session_url='http://github.com/session'

#请求头信息

session_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'
}

'''
POST请求自动登录github:
    请求URL：
            http://github.com/session
    请求方式:
            post
    请求头:
           cookie
           user-agent
    请求体：
          commit:Sign in
          utf8:✓
          authenticity_token:FLmfwPWcFB/gy50Y3lUfZduoWrRtTF9eWiAYWKwjlY9M4nFs9SvvqX3qQ/n1wJiaI5Blp1lHT7qe9m/kofrgcw==
          login:
          password:
          webauthn-support:unsupported
'''

#请求体信息

form_data={
          "commit":"Sign in",
          "utf8":"✓",
          "authenticity_token":authenticity_token,
          "login":"lzc01021033",
          "password":"lzc199901021033",
          "webauthn-support":"unsupported"
}
session_res=requests.post(url=session_url,
             headers=session_headers,
             cookies=login_cookies,
             data=form_data)
with open('github3.html','w',encoding='utf-8')as f:
 f.write(session_res.text)