joplin-notes/joplin notion extension/Web Development/nodejs/HTML parser.md

HTML parser

• jsdom It's an npm library that can take html as input and let you do things like document.querySelector on it inside of NodeJS without running a sandboxed browser instance
• node-html-parser : like jsdom https://www.npmjs.com/package/node-html-parser eg

    import { parse } from 'node-html-parser';
  
    const root = parse('<ul id="list"><li>Hello World</li></ul>');
  
    console.log(root.firstChild.structure);
    // ul#list
    //   li
    //     #text
  
    console.log(root.querySelector('#list'));
    // { tagName: 'ul',
    //   rawAttrs: 'id="list"',
    //   childNodes:
    //    [ { tagName: 'li',
    //        rawAttrs: '',
    //        childNodes: [Object],
    //        classNames: [] } ],
    //   id: 'list',
    //   classNames: [] }
    console.log(root.toString());
    // <ul id="list"><li>Hello World</li></ul>
    root.set_content('<li>Hello World</li>');
    root.toString();	// <li>Hello World</li>