Function extractUrlsFromCheerio

packages/utils/src/internals/cheerio.ts:98–122

($: CheerioAPI, selector = 'a', baseUrl = '')

 * @return An array of absolute URLs
 */
export function extractUrlsFromCheerio($: CheerioAPI, selector = 'a', baseUrl = ''): string[] {
    const base = $('base').attr('href');
    const absoluteBaseUrl = base && tryAbsoluteURL(base, baseUrl);

    if (absoluteBaseUrl) {
        baseUrl = absoluteBaseUrl;
    }

    return $(selector)
        .map((_i, el) => $(el).attr('href'))
        .get()
        .filter(Boolean)
        .map((href) => {
            // Throw a meaningful error when only a relative URL would be extracted instead of waiting for the Request to fail later.
            const isHrefAbsolute = /^[a-z][a-z0-9+.-]*:/.test(href); // Grabbed this in 'is-absolute-url' package.
            if (!isHrefAbsolute && !baseUrl) {
                throw new Error(
                    `An extracted URL: ${href} is relative and baseUrl is not set. ` +
                        'Provide a baseUrl to automatically resolve relative URLs.',
                );
            }
            return baseUrl ? tryAbsoluteURL(href, baseUrl) : href;
        })
        .filter(Boolean) as string[];
}