爬取应届生网站数据

爬取应届生网站数据

爬取应届生

import csv
import requests
from lxml import etree
from nonebot import on_command, CommandSession#创建csv
f=open('result1111_qita3.csv','w',encoding='utf-8',newline='') 
csv_writer = csv.writer(f) 
csv_writer.writerow(["详情网址","公司名称","职位名称","工作地点","信息来源","时间"])getstring='.html'
(getstring)
r.encoding = 'gbk'
html = etree.)
html_text=html.xpath('/html/body/div[4]/div/div[2]/div[1]/p/span[1]/text()')#数组
pagenum=int(int(html_text[0][1:][:-1])/150)#一页150条

getstring='.html'
(getstring)
r.encoding = 'gbk'
html = etree.)
html_url_dic=html.xpath('//*[@class="jobli"]/td[1]/a/@href')
html_name_dic=html.x