//需要获取多个高校的录取分数线 //参考网站:http://www.dxsbb.com/news/list_168.html //cheerio const cheerio = require("cheerio"); const { title } = require("process"); async function main() { //获取学校列表页面html文本 let schoolHost = "http://www.dxsbb.com" let schoolListUrl="http://www.dxsbb.com/news/list_168.html"; let response1 = await fetch(schoolListUrl); let html1=await response1?.text(); //html文本解析为可控制的DOM选择器 const $ = cheerio.load(html1); // console.log($.html()); // console.log("----------------------------------------------") // console.log($("body>div.listBody>div.listareaL>div>div:nth-child(1)>div>ul>li").html()); let schoolList=[]; //遍历每个li元素 $('li').each((index,element)=>{ const aHref=$(element).find('a').attr('href');//获取a标签的href const h3Text=$(element).find('.b h3').text();//获取h3标签的文本 //将结果存入数组 if(!h3Text) return if(h3Text.indexOf("多少")>-1) return schoolList.push({href:aHref,title:h3Text}); }); console.log(schoolList); //方法一 for(let index=0;index{ let response2 = await fetch(`${schoolHost}${school.href}`) let html2 =await response2.text(); console.log(`解析${school.title},文本量${html2.length}`) }) } main();