@devmehq/open-graph-extractor/utils.js

Extract Open Graph and Twitter Card info off from html

"use strict";
/*
 * validates the url
 * @param string var - the url we want to scrape
 */
Object.defineProperty(exports, "__esModule", { value: true });
exports.removeNestedUndefinedValues = exports.isThisANonHTMLUrl = exports.isImageTypeValid = exports.findImageTypeFromUrl = exports.isUrlValid = void 0;
function isUrlValid(url) {
    // todo check image urls
    return true;
    return typeof url === 'string' && url.length > 0 && url.indexOf('http') === 0 && url.indexOf(' ') === -1;
}
exports.isUrlValid = isUrlValid;
/*
 * forces url to start with http://
 * @param string var - the url we want to scrape
 */
/*
 * validate timeout - how long should we wait for a request
 * @param number var - the time we want to wait
 */
/*
 * findImageTypeFromUrl
 * @param string url - image url
 */
function findImageTypeFromUrl(url) {
    let type = url.split('.').pop();
    [type] = type.split('?');
    return type;
}
exports.findImageTypeFromUrl = findImageTypeFromUrl;
/*
 * isImageTypeValid
 * @param string type - image type
 */
function isImageTypeValid(type) {
    const validImageTypes = ['apng', 'bmp', 'gif', 'ico', 'cur', 'jpg', 'jpeg', 'jfif', 'pjpeg', 'pjp', 'png', 'svg', 'tif', 'tiff', 'webp'];
    return validImageTypes.includes(type);
}
exports.isImageTypeValid = isImageTypeValid;
/*
 * isThisANonHTMLPage
 * @param string url - url of site
 */
function isThisANonHTMLUrl(url) {
    const invalidImageTypes = [
        '.doc',
        '.docx',
        '.xls',
        '.xlsx',
        '.ppt',
        '.pptx',
        '.3gp',
        '.avi',
        '.mov',
        '.mp4',
        '.m4v',
        '.m4a',
        '.mp3',
        '.mkv',
        '.ogv',
        '.ogm',
        '.ogg',
        '.oga',
        '.webm',
        '.wav',
        '.bmp',
        '.gif',
        '.jpg',
        '.jpeg',
        '.png',
        '.webp',
        '.zip',
        '.rar',
        '.tar',
        '.tar.gz',
        '.tgz',
        '.tar.bz2',
        '.tbz2',
        '.txt',
        '.pdf',
    ];
    const extension = findImageTypeFromUrl(url);
    return invalidImageTypes.some((type) => `.${extension}`.includes(type));
}
exports.isThisANonHTMLUrl = isThisANonHTMLUrl;
/*
 * removeNestedUndefinedValues
 * @param object - an object
 */
function removeNestedUndefinedValues(object) {
    Object.entries(object).forEach(([key, value]) => {
        if (value && typeof value === 'object')
            removeNestedUndefinedValues(value);
        else if (value === undefined)
            delete object[key];
    });
    return object;
}
exports.removeNestedUndefinedValues = removeNestedUndefinedValues;