在 NodeJs 中将 HTML 转换为文本（在浏览器之外）

Question

如何使用 NodeJS 有效地将 html 转换为文本，即在浏览器之外？我还想将 ä 等实体转换为 ä 等，而不仅仅是从 html 中删除标签。

这是一个函数 convertHtmlToText 的 JEST 单元测试，它执行此转换：

it('when extract from partial html should extract text', () => {
  const html = `<p>&nbsp;&auml;&uuml;
\t<img alt="" src="http://www.test.org:80/imageupload/userfiles/2/images/world med new - 2022.jpg" style="width: 2000px; height: 1047px; max-width: 100%; height: auto;" /></p>
<p>
\tAn evening of music, silence and guiding thoughts to help us experience inner peace, connect with the Divine and share loving vibrations with the world. Join millions of people throughout the world to contribute in creating a wave of peace.</p>
<div>
\t&nbsp;</div>
<div>
\t<strong>Please join ....</strong></div>
<div>
\t&nbsp;</div>
<div>
\t<strong>Watch live:&nbsp;<a href="https://test.org/watchlive" target="_blank">test.org/watchlive</a></strong></div>`
  const text = convertHtmlToText(html)
  console.log(text)
  expect(text).toContain("ä");
  expect(text).toContain("ü");
  expect.not.stringContaining("<")
  expect.not.stringContaining(">")
});

Answer 1

这个问题的一个可能的解决方案是使用一个库，例如：jsdom

这是删除标签并从任何 html 文本转换实体的函数：

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

const convertHtmlToText = (html) => {
  if(!html) {
    return ""
  }
  const dom = new JSDOM(html)
  const textContent = dom.window.document.documentElement.textContent
  // removing unnecessary spaces
  return textContent.replace(/\s+/gm, ' ').trim()
}

module.exports = {
  convertHtmlToText
}

Answer 2

let HTMLContent = `<div> my&apos; <a href="profile/lol">profile</a></div>`;

let strippedHtml = decodeHTMLEntities(HTMLContent.replace(/<[^>]+>/g, ''));
console.log(strippedHtml)

function decodeHTMLEntities(text) {
  var entities = [
    ['amp', '&'],
    ['apos', '\''],
    ['#x27', '\''],
    ['#x2F', '/'],
    ['#39', '\''],
    ['#47', '/'],
    ['lt', '<'],
    ['gt', '>'],
    ['nbsp', ' '],
    ['quot', '"']
  ];

  for (var i = 0, max = entities.length; i < max; ++i) {
    text = text.replace(new RegExp('&' + entities[i][0] + ';', 'g'), entities[i][1]);
  }
  return text;
}

试试这个