拉钩 翻页 方法

import requests


headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
    'Referer': 'https://www.lagou.com/jobs/list_python%E7%88%AC%E8%99%AB?labelWords=&fromSearch=true&suginput=', # 来源 （防盗链？）
           }


for page in range(1,11):
    # 翻页处理
    data = {
        'first': ' true',
        'pn': page,
        'kd': ' python爬虫',
    }



    def get_cookie(url):
        '''获取不断变化的 cookie'''
        session = requests.session()
        session.get(url,headers=headers)
        cookies = session.cookies
        cookies_1 = cookies.get_dict()
        return cookies_1




    def get_mess(url1,cookies_1,data):
        '''获取数据保存'''
        print('正在获取第{}页数据'.format(page))
        resp = requests.post(url1,headers=headers,data=data,cookies=cookies_1).json()  # json数据 类型 字典
        lists = resp['content']['positionResult']['result']
        for list in lists:
            # 公司名称
            companyFullName = list['companyFullName']
            # 岗位
            positionName = list['positionName']
            # 规模
            companySize = list['companySize']
            # 薪资
            salary = list['salary']

            print("\t正在保存公司信息:",companyFullName)


            #   数据保存
            path = r'C:\Users\DELL\Desktop\python_wd\拉钩.csv'
            with open(path,'a',encoding='utf-8')as f:
                f.write('{},{},{},{}\n'.format(companyFullName,positionName,companySize,salary))



    # 主函数
    def main():
        url = 'https://www.lagou.com/jobs/list_python%E7%88%AC%E8%99%AB?labelWords=&fromSearch=true&suginput='
        url1 = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'
        cookies_1 = get_cookie(url)
        get_mess(url1,cookies_1,data)




    if __name__ == '__main__':
        main()