python爬取招聘网站（智联，拉钩，Boss直聘）
2018-02-21 本文已影响347人
鸣人吃土豆
刚好最近有这需求,动手写了几个
就贴上代码算了
1.智联
- 将结果保存为python的一个数据框中
import requests
from requests.exceptions import RequestException
from bs4 import BeautifulSoup
import pandas as pd
import time
headers={
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
'Cookie':'adfbid=0; adfbid2=0; dywea=95841923.1684916627213906700.1518933348.1518933348.1518933348.1; dywec=95841923; dywez=95841923.1518933348.1.1.dywecsr=baidu|dyweccn=(organic)|dywecmd=organic; __utma=269921210.1045361993.1518933348.1518933348.1518933348.1; __utmc=269921210; __utmz=269921210.1518933348.1.1.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; firstchannelurl=https%3A//passport.zhaopin.com/account/register%3Fy7bRbP%3DdpDMrcLjtPLjtPLjmUUTAfiY8DxpsUXEmnJxKKhNBcL; userphoto=; userwork=4; bindmob=0; monitorlogin=Y; NTKF_T2D_CLIENTID=guestE1AB2AD1-7303-40C4-6AA7-A77C5CB910B4; dywem=95841923.y; qrcodekey=2063c159242c45a7b0a0a77188addaf4; Hm_lvt_38ba284938d5eddca645bb5e02a02006=1518933348,1518933526; lastchannelurl=https%3A//passport.zhaopin.com/findPassword/email/step2%3Freceiver%3D15606013006@163.com; JsNewlogin=1804437629; JSloginnamecookie=15606013006%40163%2Ecom; at=35348dc0332242e488a65f80546ef827; Token=35348dc0332242e488a65f80546ef827; rt=9e7c96030884411895b5209bfa279ab6; JSsUserInfo=24342e6955715d79443202754d6a5c710d6a5b68416b407409333979246b4c345b695d715d7944320575496a5a71076a5968416b4f74723344795c6b423444690b710479193208752c6a2571096ae21b3ef5a7ec09333079276b4c345b695d715d7944320575496a5a71076a5968416b4f74723344795c6b423444690b710479193208752a6a3f71096a58684a6b3874663348795b6b5c345a6948715a7940320975486a5071756a25684c6b4974093320792b6b4c34206925715b79453207754e6a5271066a5968486b4874093320793e6b4c345b69537138793d320e75496a5071616a39683f6b4474033340795c6b41345c6958715a7947320375496a5d71746a5868476b4a741c331679056b1c3451698; uiioit=3b622a6459640e644764466a5c6e556e5d64563854775d7751682c622a64596408644c646; usermob=4065416A5D6956784C7155745B6B5A66487A4165426A7; JSShowname=%e7%8e%8b%e9%b9%8f%e9%a3%9e; rinfo=JM014792091R90250002000_1; nTalk_CACHE_DATA={uid:kf_9051_ISME9754_601479209,tid:1518933400760526}; JSweixinNum=2; loginreleased=1; JSSearchModel=0; LastCity%5Fid=653; LastCity=%e6%9d%ad%e5%b7%9e; urlfrom=121126445; urlfrom2=121126445; adfcid=none; adfcid2=none; __utmt=1; Hm_lpvt_38ba284938d5eddca645bb5e02a02006=1518934020; LastJobTag=%e4%ba%94%e9%99%a9%e4%b8%80%e9%87%91%7c%e8%8a%82%e6%97%a5%e7%a6%8f%e5%88%a9%7c%e7%bb%a9%e6%95%88%e5%a5%96%e9%87%91%7c%e5%b8%a6%e8%96%aa%e5%b9%b4%e5%81%87%7c%e5%91%98%e5%b7%a5%e6%97%85%e6%b8%b8%7c%e9%a4%90%e8%a1%a5%7c%e5%ae%9a%e6%9c%9f%e4%bd%93%e6%a3%80%7c%e5%85%a8%e5%8b%a4%e5%a5%96%7c%e5%b9%b4%e5%ba%95%e5%8f%8c%e8%96%aa%7c%e9%ab%98%e6%b8%a9%e8%a1%a5%e8%b4%b4%7c%e4%ba%a4%e9%80%9a%e8%a1%a5%e5%8a%a9%7c%e5%bc%b9%e6%80%a7%e5%b7%a5%e4%bd%9c%7c%e9%80%9a%e8%ae%af%e8%a1%a5%e8%b4%b4%7c%e5%8a%a0%e7%8f%ad%e8%a1%a5%e5%8a%a9%7c%e5%8c%85%e4%bd%8f%7c%e5%b9%b4%e7%bb%88%e5%88%86%e7%ba%a2%7c%e8%a1%a5%e5%85%85%e5%8c%bb%e7%96%97%e4%bf%9d%e9%99%a9%7c%e5%8c%85%e5%90%83%7c%e6%88%bf%e8%a1%a5%7c%e6%af%8f%e5%b9%b4%e5%a4%9a%e6%ac%a1%e8%b0%83%e8%96%aa%7c%e5%88%9b%e4%b8%9a%e5%85%ac%e5%8f%b8%7c%e5%85%8d%e8%b4%b9%e7%8f%ad%e8%bd%a6%7c%e8%82%a1%e7%a5%a8%e6%9c%9f%e6%9d%83%7c%e4%b8%8d%e5%8a%a0%e7%8f%ad%7c%e4%bd%8f%e6%88%bf%e8%a1%a5%e8%b4%b4%7c14%e8%96%aa%7c%e6%97%a0%e8%af%95%e7%94%a8%e6%9c%9f%7c%e5%81%a5%e8%ba%ab%e4%bf%b1%e4%b9%90%e9%83%a8%7c%e9%87%87%e6%9a%96%e8%a1%a5%e8%b4%b4%7c%e5%85%8d%e6%81%af%e6%88%bf%e8%b4%b7; LastSearchHistory=%7b%22Id%22%3a%221dbaf98a-839e-407e-9b88-a11c1cf68354%22%2c%22Name%22%3a%22%e6%9d%ad%e5%b7%9e%22%2c%22SearchUrl%22%3a%22http%3a%2f%2fsou.zhaopin.com%2fjobs%2fsearchresult.ashx%22%2c%22SaveTime%22%3a%22%5c%2fDate(1518934276954%2b0800)%5c%2f%22%7d; SubscibeCaptcha=2AB0C06D9BFF47D0C33C835A13818B06; dyweb=95841923.62.9.1518933765171; __utmb=269921210.62.9.1518933765182'
}
url='http://sou.zhaopin.com/jobs/searchresult.ashx'
a= []
b=[]
c=[]
d=[]
e=[]
f=[]
g=[]
h=[]
i=[]
j=[]
k=[]
def get_one_page(url,headers,params):
try:
response = requests.get(url,headers=headers,params=params)
time.sleep(2)
if response.status_code==200:
return response.text
return None
except RequestException:
return None
def get_detail_info(html):
soup = BeautifulSoup(html,"lxml")
positions = soup.select('.zwmc a')
companys = soup.select("td.gsmc > a:nth-of-type(1)")
salarys = soup.select("td.zwyx")
locations = soup.select("td.gzdd")
release_dates = soup.select(".gxsj span")
company_natures = soup.select('li.newlist_deatil_two > span:nth-of-type(2)')
company_sizes = soup.select("li.newlist_deatil_two > span:nth-of-type(3)")
experiences = soup.select("li.newlist_deatil_two > span:nth-of-type(4)")
educations = soup.select("li.newlist_deatil_two > span:nth-of-type(5)")
dutys = soup.select("li.newlist_deatil_last")
urls = soup.select('td.zwmc > div > a')
for position,company,salary,location,release_date,company_nature,company_size,experience,education,duty,url in zip(
positions,companys,salarys,locations,release_dates,company_natures,company_sizes,experiences,educations,dutys,urls):
a.append(position.get_text())
b.append(company.get_text())
c.append(salary.get_text())
d.append(location.get_text())
e.append(release_date.get_text())
f.append(company_nature.get_text())
g.append(company_size.get_text())
h.append(experience.get_text())
i.append(education.get_text())
j.append(duty.get_text())
k.append(url.get("href"))
return(a,b,c,d,e,f,g,h,i,j,k)
def transform_into_dataframe(a,b,c,d,e,f,g,h,i,j,k):
data={
"position":a,
"company":b,
"salary":c,
"location":d,
"release_date":e,
"company_nature":f,
"company_size":g,
"experience":h,
"education":i,
"duty":j,
"url":k
}
position_data = pd.DataFrame(data)
return(position_data)
def main(url,headers,params):
html = get_one_page(url,headers,params)
a,b,c,d,e,f,g,h,i,j,k=get_detail_info(html)
position_data=transform_into_dataframe(a,b,c,d,e,f,g,h,i,j,k)
return(position_data)
if __name__=="__main__":
for page in range(1,11):
params = {
"jl":"杭州",
"kw":"数据分析",
"isadv":0,
"we":"0103",
"isfilter":1,
"p":page,
"sf":8001,
"st":10000
}
print("------------------第{}页抓取成功--------------".format(page))
position_data=main(url,headers,params)
2.拉钩
- 结果保存再mysql中
# -*- coding: utf-8 -*-
"""
Created on Sat Feb 17 23:14:47 2018
@author: Administrator
"""
import time
import requests
import pymysql
config={
"host":"127.0.0.1",
"user":"root",
"password":"root",
"database":"pachong",
"charset":"utf8"
}
def lagou(page):
headers = {'Referer':'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90?city=%E6%9D%AD%E5%B7%9E&cl=false&fromSearch=true&labelWords=&suginput=', 'Origin':'https://www.lagou.com', 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
'Accept':'application/json, text/javascript, */*; q=0.01',
'Cookie':'JSESSIONID=ABAAABAAAGFABEFE8A2337F3BAF09DBCC0A8594ED74C6C0; user_trace_token=20180122215242-849e2a04-ff7b-11e7-a5c6-5254005c3644; LGUID=20180122215242-849e3549-ff7b-11e7-a5c6-5254005c3644; index_location_city=%E5%8C%97%E4%BA%AC; _gat=1; TG-TRACK-CODE=index_navigation; _gid=GA1.2.1188502030.1516629163; _ga=GA1.2.667506246.1516629163; LGSID=20180122215242-849e3278-ff7b-11e7-a5c6-5254005c3644; LGRID=20180122230310-5c6292b3-ff85-11e7-a5d5-5254005c3644; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1516629163,1516629182; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1516633389; SEARCH_ID=8d3793ec834f4b0e8e680572b83eb968'
}
dates={'first':'true',
'pn': page,
'kd':"数据分析"}
url='https://www.lagou.com/jobs/positionAjax.json?city=%E6%9D%AD%E5%B7%9E&needAddtionalResult=false&isSchoolJob=0'
resp = requests.post(url,data=dates,headers=headers)
print(resp.content.decode('utf-8'))
result=resp.json()['content']['positionResult']['result']
db = pymysql.connect(**config)
positionName = []
for i in result:
print(i)
count=0
positionName.append(i['positionName'])
timeNow = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
#连接数据库
cursor = db.cursor()
if i['businessZones']:
businessZones = "".join(i['businessZones'])
else:
businessZones=""
if i['companyLabelList']:
companyLabelList = "".join(i['companyLabelList'])
else:
companyLabelList=""
if i['industryLables']:
industryLables = "".join(i['industryLables'])
else:
industryLables=""
if i['positionLables']:
positionLables = "".join(i['positionLables'])
else:
positionLables=""
sql = "insert into lagou(positionName,workYear,salary,companyShortName\
,companyIdInLagou,education,jobNature,positionIdInLagou,createTimeInLagou\
,city,industryField,positionAdvantage,companySize,score,positionLables\
,industryLables,publisherId,financeStage,companyLabelList,district,businessZones\
,companyFullName,firstType,secondType,isSchoolJob,subwayline\
,stationname,linestaion,resumeProcessRate,createByMe,keyByMe\
)VALUES (%s,%s,%s,%s, \
%s,%s,%s,%s,%s\
,%s,%s,%s,%s,%s,%s,%s\
,%s,%s,%s,%s,%s\
,%s,%s,%s,%s,%s\
,%s,%s,%s,%s,%s\
)"
cursor.execute(sql,(i['positionName'],i['workYear'],i['salary'],i['companyShortName']
,i['companyId'],i['education'],i['jobNature'],i['positionId'],i['createTime']
,i['city'],i['industryField'],i['positionAdvantage'],i['companySize'],i['score'],positionLables
,industryLables,i['publisherId'],i['financeStage'],companyLabelList,i['district'],businessZones
,i['companyFullName'],i['firstType'],i['secondType'],i['isSchoolJob'],i['subwayline']
,i['stationname'],i['linestaion'],i['resumeProcessRate'],timeNow,"数据分析"
))
db.commit() #提交数据
cursor.close()
count=count+1
db.close()
def main(pages):
page = 1
while page<=pages:
print('---------------------第',page,'页--------------------')
lagou(page)
page=page+1
if __name__ == '__main__':
main(13) #输入要爬取的页数
3.Boss直聘
# -*- coding: utf-8 -*-
"""
Created on Wed Feb 21 13:08:53 2018
@author: Administrator
"""
import requests
from bs4 import BeautifulSoup
import time
import pandas as pd
from requests.exceptions import RequestException
import re
url = 'https://www.zhipin.com/c101210100/e_104-d_203-y_3-h_101210100/'
a= []
b=[]
c=[]
d=[]
e=[]
f=[]
g=[]
h=[]
i=[]
j=[]
k=[]
headers = {
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Referer':'https://login.zhipin.com/',
'Cookie':'lastCity=101210100; JSESSIONID=""; __g=-; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1519187438; __c=1519187447; __l=r=https%3A%2F%2Fwww.zhipin.com%2Fc101210100%2F&l=%2Fwww.zhipin.com%2Fjob_detail%2F%3Fquery%3D%25E6%2595%25B0%25E6%258D%25AE%25E5%2588%2586%25E6%259E%2590%26scity%3D101210100%26industry%3D%26position%3D; t=WPoHbF09MPblJoh; wt=WPoHbF09MPblJoh; __a=95524263.1519187442.1519187442.1519187447.17.2.16.17; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1519189678',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36'
}
def get_one_page(url,headers,params):
try:
response = requests.get(url,headers=headers,params=params)
time.sleep(2)
if response.status_code==200:
return response.text
return None
except RequestException:
return None
def get_detail_info(html):
soup=BeautifulSoup(html,"lxml")
positions = soup.select('div.job-title')
companys = soup.select("div.info-company > div > h3 > a")
salarys = soup.select("div.info-primary > h3 > a > span")
pattern = re.compile("<li.*?</h3>\s*<p>(.*?)<em.*?em>(.*?)<em.*?em>(.*?)</p>.*?<a href.*?</h3>\s*<p>.*?<em.*?em>(.*?)<em class.*?</em>(.*?)</p>.*?</li>",re.S)
re_datas=re.findall(pattern,html)
release_dates = soup.select("div > div.info-publis > p")
dutys = soup.select("div > div.info-primary > h3 > a > div.info-detail > p")
urls = soup.select('div > div.info-primary > h3 > a')
for position,company,salary,re_data,release_date,duty,url in zip(positions,companys,salarys,re_datas,release_dates,dutys,urls):
a.append(position.get_text()) #position
b.append(company.get_text()) #company
c.append(salary.get_text()) #salary
d.append(re_data[0]) #location
e.append(release_date.get_text()) #release_date
f.append(re_data[3]) #company_nature
g.append(re_data[4]) #company_size
h.append(re_data[1]) #experience
i.append(re_data[2]) #education
j.append(duty.get_text()) #duty
k.append('https://www.zhipin.com'+str(url.get("href"))) #url
return(a,b,c,d,e,f,g,h,i,j,k)
def transform_into_dataframe(a,b,c,d,e,f,g,h,i,j,k):
data = {
"position":a,
"company":b,
"salary":c,
"location":d,
"release_date":e,
"company_nature":f,
"company_size":g,
"experience":h,
"education":i,
"duty":j,
"url":k
}
position_data_zhipin = pd.DataFrame(data)
return position_data_zhipin
def main(url,headers,params):
html=get_one_page(url,headers=headers,params=params)
a,b,c,d,e,f,g,h,i,j,k=get_detail_info(html)
position_data_zhipin = transform_into_dataframe(a,b,c,d,e,f,g,h,i,j,k)
return(position_data_zhipin)
if __name__=='__main__':
for page in range(1,11):
params = {
'query':'数据分析',
'page':page,
'ka':'page-{}'.format(page)
}
print("------------------第{}页抓取成功--------------".format(page))
position_data_zhipin=main(url,headers,params)
```
