从任意嵌套的HTML中提取所有文本

function extractTextFromHTML(node) {
  var result = [];

  function extract(node) {
    if (node.nodeType === Node.TEXT_NODE) {
      result.push(node.textContent.trim());
    }

    var children = node.childNodes;
    for (var i = 0; i < children.length; i++) {
      extract(children[i]);
    }
  }

  extract(node);

  return result;
}

// 示例用法
var html = "<div><p>Hello, <strong>world!</strong></p></div>";
var div = document.createElement("div");
div.innerHTML = html;

var texts = extractTextFromHTML(div);
console.log(texts);

["Hello,", "world!"]