闲着没事自己用爬虫写的一个岗位查询(拉钩网)在这里插入代码片
代码很少
import requestsi
import pymysql
import time
url = 'https://www.lagou.com/jobs/positionAjax.json?px=default&city=%E6%88%90%E9%83%BD&needAddtionalResult=false'
urls = 'https://www.lagou.com/jobs/list_python/p-city_252?px=default#filterBox'
headers = {'Host': 'www.lagou.com',
'Origin': 'https://www.lagou.com',
'Referer': 'https://www.lagou.com/jobs/list_python/p-city_252?px=default',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'}
user = input('请输入你要查询的岗位:')
pages = int(input('请输入页数:'))
print('客官请稍等,正在查询中......')
for page in range(pages):
time.sleep(0.5)
data = {'first': 'true',
'pn': page,
'kd': user}
session = requests.Session()
session.get(url=urls, headers=headers)
cookie = session.cookies
response = session.post(url=url, headers=headers, data=data, cookies=cookie).json()
result = response['content']['positionResult']['result']
for i in result:
job_title = i['positionName']
workYear = i['workYear']
salary = i['salary']
education = i['education']
positionAdvantage = i['positionAdvantage']
companyFullName = i['companyFullName']
industryField = i['industryField']
data_job = {}
data_job['岗位'] = job_title
data_job['经验'] = workYear
data_job['薪资'] = salary
data_job['学历'] = education
data_job['职位福利'] = positionAdvantage
data_job['公司'] = companyFullName
data_job['公司说书领域'] = industryField
print(data_job)