Python3爬取猎聘网招聘信息_猎聘招聘方数据抓取-CSDN博客

本文链接：https://blog.csdn.net/weixin_43528343/article/details/89026578

#爬取猎聘网金融行业分类下银行的4000条招聘数据，并存入csv文件
#requests,lxml是第三方库，需要额外安装
#下方有修改后的版本
import requests,csv,time
from lxml import etree
from requests.exceptions import RequestException
 
url ='https://www.liepin.com/zhaopin/?headckid=4ba8c02991d96408&industries=130'
num=1

def get_one_page(url):
    try:
        headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return etree.HTML(response.text)
        return None
    except RequestException:
        return None
 
def parse_one_page(html):#使用xpath定位数据
    for job in html.xpath('//div[@class="sojob-item-main clearfix"]'):
        city=job.xpath('div/p/a/text()')[0].strip()
        name=job.xpath('div/h3/a/text()')[0].strip()
        url=job.xpath('div/h3/a/@href')[0].strip()
        firm=job.xpath('div//p[@class="company-name"]/a/text()')[0].strip()
        salary=job.xpath('div/p/span/text()')[0].strip()
        exper=job.xpath('div/p//span[3]/text()')[0].strip()
        edu=job.xpath('div/p//span[2]/text()')[0].strip()
        time=job.xpath('div//p[@class="