html dom 知乎,使用jsdom 和cheerio 爬取知乎日报

推荐使用cheerio, api 接口简单易于使用

const $ = require('cheerio')

const {JSDOM} = require("jsdom");

const axios = require('axios')

async function getHtml(url) {

return (await axios.get(url)).data

}

async function jsdom(html) {

const dom = new JSDOM(html);

let links = dom.window.document.querySelectorAll("a.link-button")

// for (let i of [...links])

// console.log(i.text)

return [...links].map(i => i.text)

}

async function cheerio(html) {

let dom = $.load(html)

let links = dom('a.link-button')

return links.map(

(i, el) => {

// console.log(i, $(el).text())

return $(el).text()

}

)

}

async function start() {

const url = 'http://daily.zhihu.com/'

let html = await getHtml(url)

let a1 = await jsdom(html)

let a2 = await cheerio(html)

console.log(a1.length, a2.length)

for (let i = 0; i < a1.length; i++) {

console.log(a1[i], '---', a2[i])

}

}

start()