如何用Node写页面爬虫的工具集

const puppeteer = require('puppeteer');

(async () => {
 const browser = await puppeteer.launch();
 const page = await browser.newPage();
 await page.goto('https://example.com');
 await page.screenshot({path: 'example.png'});

 await browser.close();
})();

const cheerio = require('cheerio')
const $ = cheerio.load('<h2 class="title">Hello world</h2>')

$('h2.title').text('Hello there!')
$('h2').addClass('welcome')

$.html()
//=> <h2 class="title welcome">Hello there!</h2>

const cheerio = require('cheerio');
const get = function(){/*HTTP get请求...*/}
(async ()=>{
 const html = await get(`http://example.com`);
 const $ = cheerio.load(html);
 const $dom_arr = $('a');
 $dom_arr.each((index, elem)=>{
  const url = $(elem).attr('href') || '';
  console.log(url);
 });
})();

// 声明环境
auto();
// 设备常亮
device.keepScreenDim();
// 调起APP
launchApp('头条');
sleep(10000);
// 找到某个频道，并点击进入
var rect = text('视频').findOnce().bounds();
var x = rect.centerX();
var y = rect.centerY();
click(x, y);
// 点击进入详情，使用代理抓取并处理请求...
...