爬取前程无忧网

最新推荐文章于 2024-07-09 14:45:02 发布

啃西瓜的小煤球

最新推荐文章于 2024-07-09 14:45:02 发布

阅读量1.6k

点赞数

分类专栏： Python

本文链接：https://blog.csdn.net/A1010574609/article/details/101015597

版权

Python 专栏收录该内容

23 篇文章 0 订阅

订阅专栏

这种写法会报错误

"""
目标内容：
职位名称--公司名称--地点--薪资--发布时间
内容处理：
地点只要市，不要区
薪资转成数字类型
"""
import requests,re,time
from lxml import etree

for page in range(1,101):
    url = 'https://search.51job.com/list/010000%252C020000%252C030200%252C040000%252C180200,000000,0000,00,9,99,python,2,'+str(page)+'.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='
    response = requests.get(url)
    root = etree.HTML(response.content)

    job_list = root.xpath("//div[@id='resultList']/div[@class='el']")
    for job in job_list:
        #岗位名称
        name = job.xpath("p/span/a/@title")
        name = name[0] if name else '暂不显示'

        #公司名称
        company = job.xpath("span[@class='t2']/a/text()")
        company = company[0] if company else '暂不显示'

        #工作地点
        address = job.xpath("span[@class='t3']/text()")
        address = address[0] if address else '暂不显示'
        address = address.split('-')[0]

        #薪资
        money = job.xpath("span[@class='t4']/text()")
        # if len(money) == 0:
        #     money = '面议'
        # else:
        #     money = money[0]
        #简化写法
        money = money[0] if money else '面议'
        min_money = 0
        max_money = 0
        if '-' in money:
            pattern = re.compile('[-万/月千]')
            result = pattern.split(money)
            if '万' in money:
                min_money = float(result[0]) * 10000
                max_money = float(result[1]) * 10000
            elif '千' in money:
                min_money = float(result[0]) * 1000
                max_money = float(result[1]) * 1000
            if '年' in money:
                min_money = min_money // 12
                max_money = max_money // 12
        min_money = str(min_money)
        max_money = str(max_money)

        #发布日期
        date = job.xpath("span[@class='t5']/text()")
        date = date[0] if date else '暂不显示'
        print(name,company,address,min_money+'-'+max_money,date)
        # time.sleep(3)

        file = open('前程无忧.csv','a',encoding='gb18030')
        file.write(name+','+company+','+address+','+min_money+','+max_money+','+date)
        file.write('\n')
        file.close()