Function to format an HTML string of ul/li into a nested object with a specific format

user_8717298 0
Viewed 57

Trying to convert html_string (could have more nested ul li elements) into ideal_data_output

let html_string = `<ul><li><p>one</p></li><li><p>two</p><ul><li><p>a</p></li><li><p>b</p></li><li><p>c</p></li></ul></li></ul>`;

let ideal_data_output = [
        { name: 'one' },
        {
            list: [
                {
                    name: 'a'
                },
                {
                    name: 'b'
                },
                {
                    name: 'c'
                }
            ],
            name: 'two'
        }
    ];

My attempt

// create an array from string
let html_tag_array = html_string.split('<');

// function to turn html_tag_array into ideal_data_output
const html_to_data = (arr) => {
        
function recursive(data, str_array) {
    if (str_array == '') return data;
    let str = str_array.shift();
    let temp_obj = {
        name: null
    };
    if (str.slice(0, 3) == 'ul>') {
        temp_obj['list'] = [];
        data.push(temp_obj);
        return recursive(data[data.length - 1].list, str_array);
    }
    if (str.slice(0, 2) == 'p>') {
        temp_obj.name = str.slice(2);
        data.push(temp_obj);
    }
    return recursive(data, str_array);
    }
    return recursive([], arr);
};

This is unsuccessful resulting in output below

0: { name: "a" }
1: { name: "b" }
2: { name: "c" }

What is the best way to approach this type of problem? I am creating an issue with recursive(data[data.length - 1], how best to properly format this function call?

recursion reduce arrays javascript string
2 Answers

This should be done with a DOM parser.

Assuming the HTML structure always has the text in a separate p element, and its only possible next sibling node is an ul node, you can use this recursive function:

const dfs = ul =>
    Array.from(ul.children, ({children: [{textContent: name}, lu]}) =>
        lu ? { list: dfs(lu), name } : { name }
    );

const html_string = `<ul><li><p>one</p></li><li><p>two</p><ul><li><p>a</p></li><li><p>b</p></li><li><p>c</p></li></ul></li></ul>`;
const {body} = new DOMParser().parseFromString(html_string, "text/html");
const result = dfs(body.children[0]); // Assumed to be the UL
console.log(result);

user_54598390

This simple search and replace solution solves it. Some trick with the commas, but no biggie. It's already was a tree structure, so json-ing it was doable. Fastest solution.

var str = `
<ul>
    <li>
        <p>one</p>
    </li>
    <li>
        <p>two</p>
        <ul>
            <li>
                <p>a</p>
            </li>
            <li>
                <p>b</p>
            </li>
            <li>
                <p>c</p>
            </li>
        </ul>
    </li>
</ul>
`;

str = str.replace(/<\/p>\s*<ul>/g, '</p>,\n\t\t<ul>');
str = str.replace(/<\/li>\s*<li>/g, '</li>,\n\t\t<li>');

str = str.replace(/<ul>/g, "list: [");
str = str.replace(/<\/ul>/g, "]");

str = str.replace(/<li>/g, "{");
str = str.replace(/<\/li>/g, "}");

str = str.replace(/<p>/g, "name: '");
str = str.replace(/<\/p>/g, "'");

// done! now just prettifying
var obj = eval("{" + str + "}")
str = JSON.stringify(obj, null, 4);
console.log(str)
.as-console-wrapper {
  max-height: 100% !important;
}

user_38073650
Related