Motor de Extracción Multimedia con Cheerio y Node.js: Web Scraping de Alto Rendimiento y Resiliente

import * as cheerio from 'cheerio';

/**
 * @typedef {Object} MediaItem
 * @property {string} url
 * @property {string} alt
 */

/**
 * @typedef {Object} ExtractedMedia
 * @property {MediaItem[]} images
 * @property {string[]} videos
 * @property {string[]} audios
 */

/**
 * Resuelve URLs relativas y maneja errores de parseo de forma segura.
 * @param {string|undefined} relativeOrAbsoluteUrl 
 * @param {string} baseUrl 
 * @returns {string|null}
 */
const safeResolveUrl = (relativeOrAbsoluteUrl, baseUrl) => {
  if (!relativeOrAbsoluteUrl || typeof relativeOrAbsoluteUrl !== 'string') return null;
  
  const cleanUrl = relativeOrAbsoluteUrl.trim();
  if (cleanUrl.startsWith('data:')) return cleanUrl;

  try {
    return new URL(cleanUrl, baseUrl).href;
  } catch {
    return null;
  }
};

/**
 * Parsea cadenas srcset para obtener la URL de mejor candidato.
 * @param {string|undefined} srcset 
 * @returns {string|null}
 */
const parseSrcset = (srcset) => {
  if (!srcset) return null;
  const candidates = srcset.split(',').map((item) => item.trim().split(' ')[0]);
  return candidates.pop() || null;
};

/**
 * Motor Principal de Extracción Multimedia
 * @param {string} html - Documento HTML crudo.
 * @param {string} baseUrl - URL base para resolver rutas relativas.
 * @returns {ExtractedMedia}
 */
export const extractMedia = (html, baseUrl) => {
  if (!html || typeof html !== 'string') {
    return { images: [], videos: [], audios: [] };
  }

  const $ = cheerio.load(html);
  
  const images = [];
  const imageSet = new Set();
  const videoSet = new Set();
  const audioSet = new Set();

  // 1. Extracción de Imágenes con soporte de Lazy Loading y srcset
  $('img').each((_, el) => {
    const node = $(el);
    const rawSrc = 
      node.attr('src') || 
      node.attr('data-src') || 
      node.attr('data-lazy-src') || 
      node.attr('data-original') ||
      parseSrcset(node.attr('srcset'));

    const resolvedUrl = safeResolveUrl(rawSrc, baseUrl);

    if (resolvedUrl && !imageSet.has(resolvedUrl)) {
      imageSet.add(resolvedUrl);
      images.push({
        url: resolvedUrl,
        alt: node.attr('alt')?.trim() || 'Sin descripción'
      });
    }
  });

  // 2. Extracción de Videos (Evita duplicados con Set)
  $('video, video source').each((_, el) => {
    const rawSrc = $(el).attr('src');
    const resolvedUrl = safeResolveUrl(rawSrc, baseUrl);

    if (resolvedUrl) {
      videoSet.add(resolvedUrl);
    }
  });

  // 3. Extracción de Audios
  $('audio, audio source').each((_, el) => {
    const rawSrc = $(el).attr('src');
    const resolvedUrl = safeResolveUrl(rawSrc, baseUrl);

    if (resolvedUrl) {
      audioSet.add(resolvedUrl);
    }
  });

  return {
    images,
    videos: Array.from(videoSet),
    audios: Array.from(audioSet)
  };
};