# -*- coding: utf-8 -*-
"""
有反爬提示“您操作太频繁,请稍后再访问”,加headers也无效。必须登录,且登录地址必须选正确,否则生成的cookie无效。
"""
import requests
#请求网站
url='https://www.lagou.com/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false'
urls='https://www.lagou.com/jobs/list_python'
#对网址发请求
data={
'first':'true',
'pn':'1',#页数
'kd':'python'#职位名
}
#加headers
headers={
'Host':'www.lagou.com',
'Origin':'https://www.lagou.com',
'Referer':'https://www.lagou.com/jobs/list_python',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/82.0.4068.4 Safari/537.36'
}
#让用户先登录,再保持用户的登录状态,来会话保持session
session=requests.Session()
session.get(url=urls,headers=headers)
cookie=session.cookies
#代用记信息,再请求
response=session.post(url=url,headers=headers,data=data,cookies=cookie).json()
result=response['content']['positionResult']['result']
for i in result:
companyName=i['companyFullName']
print(companyName)
f=open('lagou.csv','a',encoding='utf-8')
f.write('{}\n'.format(companyName))
f.close()