pppeteer多URLはって取ります.

基本的な使い方

'use strict';
const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  let imgArr = [];
  page.on('domcontentloaded', async () => {
    imgArr = await page.$$eval('img', img => {
      const arr = [];
      //               
      for (let i = 0; i < img.length; i++) {
        const obj = {
          width: img[i].width,
          naturalWidth: img[i].naturalWidth,
          height: img[i].height,
          naturalHeight: img[i].naturalHeight,
          isStandard: !((img[i].width * 10 <= img[i].naturalWidth || img[i].height * 10 <= img[i].naturalHeight)),
          url: img[i].src,
          level: 3,
          imageUrl: img[i].src,
          describeUrl: '',
          summary: `    ${img[i].width}x${img[i].height}          ${img[i].naturalWidth}x${img[i].naturalHeight}   `,
        };
        if (obj.width && obj.height) {
          arr.push(obj);
        }
      }
      return arr;
    });
  });
  await page.goto('https://www.npmjs.com/package/puppeteer', { waitUntil: 'networkidle0' });
  await browser.close();
  console.log('imgArr: ', imgArr);
})();

順序は変えられません

await pppeteer.launch()起動

await browser.newPage()page

を開く.

page.on傍受事件

await Page.gotoジャンプページ

await browser.close()クローズ

順番が変わりましたが、Page.on()モニターイベントは傍受できなくなります.
複数のURLの使い方
配列urlの上のすべてのピクチャーをよじ登って、そしてその真実な幅の高さを返します.

/* eslint-disable no-undef */
'use strict';
const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  let arr = [];

  const html = [ 'https://www.npmjs.com/package/puppeteer', 'https://www.iconfont.cn/search/index?searchType=icon&q=test' ];

  for (let i = 0; i < html.length; i++) {
    await page.goto(html[i], { waitUntil: 'domcontentloaded' });
    await page.waitForSelector('img', { timeout: 3000 });
    // eslint-disable-next-line no-loop-func
    const doms = await page.evaluate(() => {
      const arr = [ ...document.querySelectorAll('img') ];
      return arr.map(v => {
        return {
          naturalWidth: v.naturalWidth,
          naturalHeight: v.naturalHeight,
          width: v.width,
          height: v.height,
        };
      });
    });
    arr = [ ...arr, ...doms ];
  }
  await browser.close();
})();

この方法は大体overflowの答えを参考にしました.

Crawling multiple URL in a loop using pppeter

Looping through a set of urls in Pppeter

Pppeter-Prop way to loop through multiple URLs