(猎聘网招聘)(猎聘网招聘官方网站)

数据获取的渠道：企业内部，机台，网站 etc...， 现使用R的rvest包进行网络数据的爬取

code:

library(rvest)

library(stringr)

library(tidyr)

library(dplyr)

url<-"https://www.liepin.com/zhaopin/?ckid=cbff44f512ec6739&fromSearchBtn=2&degradeFlag=0&init=-1&headckid=cbff44f512ec6739&curPage=0"

page<-read_html(url)

# get positon

position<-page%>%html_nodes("ul.sojob-list div.sojob-item-main div.job-info h3")%>%html_text(trim=TRUE)

p<-position%>%data.frame()

names(p)<-c("position")

# get area

area<-page%>%html_nodes("ul.sojob-list div.sojob-item-main div.job-info a.area")%>%html_text(trim=TRUE)

a<-area%>%data.frame()

names(a)<-c("area")

# 提取了salary education experience

experience<-page%>%html_nodes("ul.sojob-list div.sojob-item-main div.job-info p.condition span")%>%html_text(trim=TRUE)

names(e)<-c("exp")

dt<-matrix(,length(experience)/3,3)

colnames(dt)<-c("salary","education","experence")

for(n in 1:3){

j<-1

i<-1

while(i<length(experience)){

dt[j,n]<-experience[i]

j<j+1

i<-i+3

}

}

# 循环查询

for(n in 1:10){

url<-str_c("https://www.liepin.com/zhaopin/?ckid=cbff44f512ec6739&fromSearchBtn=2&degradeFlag=0&init=-1&headckid=cbff44f512ec6739&curPage=","a")

page<-read_html(url)

position<-page%>%html_nodes("ul.sojob-list div.sojob-item-main div.job-info h3")%>%html_text(trim=TRUE)

p1<-position%>%data.frame()

names(p1)<-c("position")

p<-rbind(p,p1)

#area

area<-page%>%html_nodes("ul.sojob-list div.sojob-item-main div.job-info a.area")%>%html_text(trim=TRUE)

a1<-position%>%data.frame()

names(a1)<-c("area")

a<-rbind(a,a1)

#experience

experience<-page%>%html_nodes("ul.sojob-list div.sojob-item-main div.job-info p.condition span")%>%html_text(trim=TRUE)

dt1<-matrix(,length(experience)/3,3)

colnames(dt1)<-c("salary","education","experence")

for(d in 1:3){

j<-1

i<-1

while(i<=length(e)){

dt[j,d]<-e[i]

j<-j+1

i<-i+3

}

}

dt<-rbind(dt,dt1)

}

work_info<-data.frame(p,a,dt)

}

# 数据可视化：

略...