python爬虫将职友集招聘信息爬取后存入excle中

导入爬虫库

import requests
from bs4 import BeautifulSoup

导入操作excle的库

import xlwt
import xlrd
import xlutils

网页页面

代码

import requests
from bs4 import BeautifulSoup
import xlwt
import xlrd
import xlutils

#得到excle对象
book=xlwt.Workbook()
sheet=book.add_sheet('sheet1')

listall=[]#用于存储爬去的职位名称和薪资
#爬取1到29页所有的信息
for i in range(1,30):
    URL='https://www.jobui.com/jobs?jobKw=linux&cityKw=%E5%8C%97%E4%BA%AC&n='+str(i)
    #wb_data = requests.get(URL)
    headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'}
    wb_data = requests.get(URL, headers=headers)
    print(wb_data)#请求成功200
    soup = BeautifulSoup(wb_data.content, 'lxml')
    #print(soup)
    names=soup.select('div.astruct.cfix > div.aleft > div.m-box.j-jobInfo > div.j-recommendJob > div > div.job-content-box > div.job-content > div > a > h3')
    #print(names)
    prices=soup.select("div.astruct.cfix > div.aleft > div.m-box.j-jobInfo > div.j-recommendJob > div > div.job-content-box > div.job-content > div > div > span.job-pay-text")
    #print(prices)
    for n,p in zip(names,prices):
        listall.append([n.text,p.text])#信息存入listall列表中
        #print("招聘岗位为："+n.text+"，薪资为："+p.text)

#写入excle        
line=0  #控制的是行
for stu in listall:
    col=0
    for s in stu:
        sheet.write(line,col,s)#写入excle
        col+=1
    line+=1

book.save('linux.xls')#保存，和本python文件同目录

结果：