我正在创建一个node.js脚本来解析网站内容。在使用返回的HTML之前,我想删除一些元素和属性。但是,当尝试从jsdom检索HTML时,仅返回undefined
。这似乎是在修改HTML之前发生的。如何使用jsdom修改HTML并返回它?
const jsdom = require('jsdom');
...
var htmlString = `<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><html lang=en><head>...`
paresHTML(htmlString);
function parseHTML(htmlString) {
const dom = new jsdom.JSDOM(htmlString);
console.log(dom.window.document.innerHTML); // This returns undefined
dom.window.document.querySelectorAll('script').forEach(element => element.remove());
dom.window.document.querySelectorAll('head').forEach(element => element.remove());
dom.window.document.querySelectorAll('link').forEach(element => element.remove());
dom.window.document.querySelectorAll('style').forEach(element => element.remove());
dom.window.document.querySelectorAll('iframe').forEach(element => element.remove());
dom.window.document.querySelectorAll('noscript').forEach((element) => {
var replacement = dom.window.document.createElement('div');
replacement.setAttribute('class', 'noscript');
replacement.innerHTML = element.innerHTML;
element.parentNode.replaceChild(replacement, element);
});
dom.window.document.querySelectorAll('img[src]').forEach((element) => {
const src = element.getAttribute('src');
element.setAttribute('data-src', src);
element.removeAttribute('src');
});
dom.window.document.querySelectorAll('[style]').forEach((element) => {
element.removeAttribute('style');
});
return dom.window.document.innerHTML; // This also returns undefined
}
console.log(document.innerHTML);