python爬虫系列(2.3-requests库模拟用户登录)

一、模拟登录拉钩网

import re import requests class LoginLaGou(object): """ 模拟登录拉钩网 """ def __init__(self): self.headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36', 'Referer': 'https://passport.lagou.com/login/login.html' } self.data = { 'isValidate': 'true', 'username': '181****1666', 'password': 'root', 'request_form_verifyCode': '', 'submit': '' } self.lagou = 'https://www.lagou.com/' self.login_index_url = 'https://passport.lagou.com/login/login.html' self.login_url = 'https://passport.lagou.com/login/login.json' self.session = requests.session() def login_html(self): """ 登录页面获取token认证 :return: """ response = self.session.get(url=self.login_index_url, headers=self.headers) if response.status_code == 200: X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token.*?=.*?'(.*?)'", response.text, re.S)[0] X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code.*?=.*?'(.*?)'", response.text, re.S)[0] self.headers['X-Anit-Forge-Code'] = X_Anti_Forge_Code self.headers['X-Anit-Forge-Token'] = X_Anti_Forge_Token def login(self): """ 登录接口 :return: """ self.login_html() # 先访问登录页面 response = self.session.post(url=self.login_url, headers=self.headers, data=self.data) print(response.text) print(response.cookies.get_dict()) if __name__ == "__main__": lagou = LoginLaGou() lagou.login()

二、模拟登录github

import re import requests class LoginGitHub(object): """ 模拟登录github """ def __init__(self): self.headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36', 'Referer': 'https://github.com/' } self.data = { 'commit': 'Sign in', 'utf8': '✓', 'authenticity_token': '', 'login': 'root', 'password': '123456', } self.github = 'https://github.com/login' self.login_url = 'https://github.com/session' self.session = requests.session() def login_html(self): """ 获取登录的csrf_token :return: """ response = self.session.get(url=self.github, headers=self.headers) authenticity_token = re.findall('.*?name="authenticity_token".*?value="(.*?)"', response.text, re.S)[0] self.data['authenticity_token'] = authenticity_token def login(self): """ 登录github :return: """ self.login_html() # 先获取csrf_token response = self.session.post(url=self.login_url, headers=self.headers, data=self.data) print(response.text) if __name__ == "__main__": github = LoginGitHub() github.login()

三、更多博主文章请访问