const getTextFromHtml = (t) =>
  t
    ?.split('>')
    ?.map((i) => i.split('<')[0])
    .filter((i) => !i.includes('=') && i.trim())
    .join('');

const test = '<p>This <strong>one</strong> <em>time</em>,</p><br /><blockquote>I went to</blockquote><ul><li>band <a href="https://workingclasshistory.com" rel="noopener noreferrer" target="_blank">camp</a>…</li></ul><p>I edited this as a reviewer just to double check</p>'

getTextFromHtml(test)
  // 'This onetime,I went toband camp…I edited this as a reviewer just to double check'

我自己创建了一个工作正则表达式：

str=str.replace(/(<\?[a-z]*(\s[^>]*)?\?(>|$)|<!\[[a-z]*\[|\]\]>|<!DOCTYPE[^>]*?(>|$)|<!--[\s\S]*?(-->|$)|<[a-z?!\/]([a-z0-9_:.])*(\s[^>]*)?(>|$))/gi, ''); 

另一个公认不如nickf或Shog9优雅的解决方案是从＜body＞标记开始递归遍历DOM并附加每个文本节点。

var bodyContent = document.getElementsByTagName('body')[0];
var result = appendTextNodes(bodyContent);

function appendTextNodes(element) {
    var text = '';

    // Loop through the childNodes of the passed in element
    for (var i = 0, len = element.childNodes.length; i < len; i++) {
        // Get a reference to the current child
        var node = element.childNodes[i];
        // Append the node's value if it's a text node
        if (node.nodeType == 3) {
            text += node.nodeValue;
        }
        // Recurse through the node's children, if there are any
        if (node.childNodes.length > 0) {
            appendTextNodes(node);
        }
    }
    // Return the final result
    return text;
}

用jQuery剥离html的一种更安全的方法是，首先使用jQuery.parseHTML创建DOM，忽略任何脚本，然后让jQuery构建元素，然后仅检索文本。

function stripHtml(unsafe) {
    return $($.parseHTML(unsafe)).text();
}

可以安全地从以下位置剥离html：

<img src="unknown.gif" onerror="console.log('running injections');">

以及其他漏洞。

nJoy！

下面的代码允许您保留一些html标记，同时剥离所有其他标记

function strip_tags(input, allowed) {

  allowed = (((allowed || '') + '')
    .toLowerCase()
    .match(/<[a-z][a-z0-9]*>/g) || [])
    .join(''); // making sure the allowed arg is a string containing only tags in lowercase (<a><b><c>)

  var tags = /<\/?([a-z][a-z0-9]*)\b[^>]*>/gi,
      commentsAndPhpTags = /<!--[\s\S]*?-->|<\?(?:php)?[\s\S]*?\?>/gi;

  return input.replace(commentsAndPhpTags, '')
      .replace(tags, function($0, $1) {
          return allowed.indexOf('<' + $1.toLowerCase() + '>') > -1 ? $0 : '';
      });
}

const strip=(text) =>{
    return (new DOMParser()?.parseFromString(text,"text/html"))
    ?.body?.textContent
}

const value=document.getElementById("idOfEl").value

const cleanText=strip(value)