Python 爬取拉钩网工作岗位

如果拉钩网html页面做了调整,需要重新调整代码

代码如下

#/usr/bin/env python3
#coding:utf-8
import sys
import json
import requests

"""
Usage:
        python3 lagou.py  <Number> <positionName>

"""

def get_jobs(pn=1,kw="python"):
        url = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'
        payload = {"first":"false","pn":pn,"kd":kw}
        #payload = {'needAddtionalResult':'false'}
        rr = requests.post(url,data=payload)
        #print(r.json())
        jobs_data = rr.json()
        #print(jobs_data["content"]["positionResult"]["result"][0])
        jobs = jobs_data["content"]["positionResult"]["result"]

        for i in jobs:
                print("学历：" + i["education"])
                print("城市：" + i["city"])
        #       print("福利：" + i["companyLabelList"])
                print("薪资：" + i["salary"])
                print("职位：" + i["positionName"])
                print("要求：" + i["positionAdvantage"])
                print("经验：" + i["workYear"])
                print("链接：" + "https://www.lagou.com/jobs/" + str(i["positionId"]) + ".html")
                print()

if __name__ == '__main__':
        #pn表示页数，kw表示关键词搜索
        pn = sys.argv[1]
        kw = sys.argv[2]
        get_jobs(pn,kw)

 

转载于:https://www.cnblogs.com/linyouyi/p/11409869.html