mozilla/readability を使った本文抽出サンプル

index.js

import puppeteer from 'puppeteer'
const Readability = require("readability");
import { JSDOM } from 'jsdom'

const URL = 'url'

(async () => {
  const browser = await puppeteer.launch({
    args: [
      '--no-sandbox',
      '--disable-setuid-sandbox',
      '--lang=ja,en-US,en'
    ]
  });
  const page = await browser.newPage();
  await page.goto(url);
  const html = await page.evaluate(() => {
    return document.body.innerHTML
  })

  const dom = new JSDOM(html)
  const content = new Readability(dom.window.document).parse()
  console.log(content)
  await browser.close();
})();