使用Javascript和Regular表达式获取html正文中的内容

const parser = new DOMParser();
const htmlDoc = parser.parseFromString(htmlString, 'text/html');

const textContent = htmlDoc.body.textContent;
const regex = /需要匹配的正则表达式/;
const matchedContent = textContent.match(regex);

const result = [];
if (matchedContent) {
  result.push(matchedContent);
}

function getContentFromHtml(htmlString, regex) {
  const parser = new DOMParser();
  const htmlDoc = parser.parseFromString(htmlString, 'text/html');
  const textContent = htmlDoc.body.textContent;
  const matchedContent = textContent.match(regex);
  const result = [];

  if (matchedContent) {
    result.push(matchedContent);
  }

  return result;
}

const htmlString = '<div><p>这是一段文本。</p><p>这是另一段文本。</p></div>';
const regex = /文本/g;
const content = getContentFromHtml(htmlString, regex);
console.log(content);