前言

国资央企招聘平台集成了众多国企央企的招聘。写一个脚本实现一下各个岗位的招聘

接口

当抓包的时候发现，这些岗位信息都是通过接口发布的。因此可以通过获取这个接口的数据爬取。

编写代码：

'''
基于国资央企招聘平台的招聘信息。
https://cujiuye.iguopin.com/
'''


import requests
class get_guoqi_job():
    def __init__(self):
        self.url = "https://gp-api.iguopin.com/api/jobs/v1/list"

        self.headers = {
            "Content-Type": "application/json;charset=UTF-8",
            "Accept": "application/json, text/plain, */*",
            "Device": "pc",
            "Subsite": "cujiuye",
            "Version": "5.0.0",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
        }

    '''
    默认关键词 keyword = 网络安全 信息安全，工作数量爬取最大为200，页数为1，如果工作数量大于等于200，将page改为2再次爬取.
    直接调用 get_guoqi_job()
    关键词调用：
    get_guoqi_job('销售‘）
    '''

    def __call__(self,keyword='网络安全 信息安全',job_num=200 , page=1):
        data = {
            "page": page,
            "page_size": job_num,
            "keyword": keyword,
            "nature": ["115xW5oQ"]
        }

        response = requests.post(self.url, json=data, headers=self.headers)


        jobs = []
        # 打印响应的 JSON 内容
        res_json = response.json()

        data = res_json['data']
        # print(data)
        data_list = data['list']
        print(f'-------------有{len(data_list)}个相关{keyword}岗位正在校招-------------')
        num =1
        for company in data_list:
            job_id = company['job_id']
            job_url = 'https://www.iguopin.com/job/detail?id=' + str(job_id)
            job_name = company['job_name']
            company_name = company['company_name']
            salary = str(company['min_wage']) + '-' + str(company['max_wage'])
            education_cn = company['education_cn']
            contents = company['contents']
            area_cn = company['district_list'][0]['area_cn']
            start_end_time = company['start_time'] + '——' + company['end_time']
            company_info = company['company_info']['nature_cn']
            print('岗位：',job_name, '工作地点：', area_cn, '薪资：', salary, education_cn)
            print('公司：', company_name , company_info)
            print('岗位链接：', job_url)
            print('招聘时间：', start_end_time)
            print('职位要求：', contents)
            print(f'------------------------------------------------------{num}')
            num +=1
            job = {
                '岗位' : job_name,
                '工作地点': area_cn,
                '薪资': salary,
                '学历': education_cn,
                '公司信息': company_name + ' ' + company_info,
                '岗位链接：': job_url,
                '招聘时间':start_end_time,
                '职位要求': contents

            }
            jobs.append(job)
        return jobs

if __name__ == '__main__':

    get = get_guoqi_job()
    get()

效果：

网页爬虫

暂时不。