python实现对某招聘网接口测试获取平台信息

"""通过接口测试的技术获取某招聘网平台的资料"""
url = "https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false"
def getHeaders():
headers = {
"Content-Type": "application/json;charset=UTF-8",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36",
"Cookie": "JSESSIONID=ABAAABAAAIAACBI2438D04CF91400F1FF0A2B38358AFFA5; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1550930753; _ga=GA1.2.193872554.1550930753; _gat=1; user_trace_token=20190223220617-301cdfdc-3774-11e9-af96-525400f775ce; LGSID=20190223220617-301ce139-3774-11e9-af96-525400f775ce; PRE_UTM=; PRE_HOST=cn.bing.com; PRE_SITE=https%3A%2F%2Fcn.bing.com%2F; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2F; LGUID=20190223220617-301ce2a8-3774-11e9-af96-525400f775ce; _gid=GA1.2.1796885419.1550930753; index_location_city=%E5%85%A8%E5%9B%BD; SEARCH_ID=a0ad1593bd14438d8a205a17a17f95c1; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1550930826; LGRID=20190223220730-5b9c7593-3774-11e9-af96-525400f775ce; TG-TRACK-CODE=search_code",
"Referer": "https://www.lagou.com/jobs/list_%E8%87%AA%E5%8A%A8%E5%8C%96%E6%B5%8B%E8%AF%95%E5%B7%A5%E7%A8%8B%E5%B8%88?labelWords=&fromSearch=true&suginput="
}
return headers

def lagou(page=2):
positions = []
r = requests.post(
url=url,
headers=getHeaders(),
data={"first": False,"pn": page,"kd": "自动化测试工程师"})
text = r.text
print(text)
for i in range(0,15):
city = r.json()#["content"]["positionResult"]["result"][i]["city"]
print(city)
positionAdvantage = r.json()["content"]["positionResult"]["result"][i]["positionAdvantage"]
workYear = r.json()["content"]["positionResult"]["result"][i]["workYear"]
companyFullName = r.json()["content"]["positionResult"]["result"][i]["companyFullName"]
education = r.json()["content"]["positionResult"]["result"][i]["education"]
district = r.json()["content"]["positionResult"]["result"][i]["district"]
salary = r.json()["content"]["positionResult"]["result"][i]["salary"]
companySize = r.json()["content"]["positionResult"]["result"][i]["companySize"]
companyLabelList = r.json()["content"]["positionResult"]["result"][i]["companyLabelList"]
positionLables = r.json()["content"]["positionResult"]["result"][i]["positionLables"]
position = {
"城市":city,
"区域":district,
"学历":education,
"工作年限":workYear,
"薪资":salary,
"公司名称":companyFullName,
"公司大小":companySize,
"公司标签":companyLabelList,
"工作标签":positionLables,
"公司福利":positionAdvantage
}
positions.append(position)
return positions
lagou()
def writeCsv():
headers = ["城市", "区域", "学历", "工作年限", "薪资", "公司名称", "公司大小", "公司标签", "工作标签","公司福利"]
for item in range(1,31):
positions = lagou(page=item)
with open("lagou.cvs","a") as f:
writer = csv.DictWriter(f,headers)
writer.writeheader()
writer.writerows(positions)

writeCsv()
上一篇:破解拉勾网反爬虫-3月25


下一篇:二手房数据预处理与分析