@mashakujou/manhwaweb-scraper/index.js

Scraper ligero para obtener datos de capítulos de Manhwaweb desde su API pública

const axios = require('axios');

let debug = false;

function setDebug(flag) {
  debug = !!flag;
}

function logDebug(...args) {
  if (debug) console.log('[DEBUG]', ...args);
}

function slug(url) {
  const s = url.split('/').pop();
  logDebug('slug:', s);
  return s;
}

function urls(id) {
  const base = 'https://manhwawebbackend-production.up.railway.app/chapters';
  const result = {
    see: `${base}/see/${id}`,
    seeprev: `${base}/seeprevpost/${id}`
  };
  logDebug('urls:', result);
  return result;
}

async function full(url) {
  const id = slug(url);
  const { see, seeprev } = urls(id);
  logDebug('full: fetching see and seeprev');

  try {
    const [seeRes, seeprevRes] = await Promise.all([
      axios.get(see),
      axios.get(seeprev)
    ]);
    logDebug('full: responses received');
    return {
      title: `${seeRes.data.name} ${seeRes.data.chapter?.chapter || ''}`,
      imgs: seeRes.data.chapter?.img || [],
      prev: seeprevRes.data.chapterAnterior || null,
      next: seeprevRes.data.chapterSiguiente || null,
      raw: { see: seeRes.data, seeprevpost: seeprevRes.data }
    };
  } catch (err) {
    logDebug('full: error', err.message);
    throw new Error('Error: ' + err.message);
  }
}

async function images(url) {
  const id = slug(url);
  const { see } = urls(id);
  logDebug('images: fetching images');

  try {
    const res = await axios.get(see);
    logDebug('images: response received, images count:', (res.data.chapter?.img || []).length);
    return res.data.chapter?.img || [];
  } catch (err) {
    logDebug('images: error', err.message);
    throw new Error('Error: ' + err.message);
  }
}

async function prevNext(url) {
  const id = slug(url);
  const { seeprev } = urls(id);
  logDebug('prevNext: fetching prev and next chapters');

  try {
    const res = await axios.get(seeprev);
    logDebug('prevNext: response received');
    return {
      prev: res.data.chapterAnterior || null,
      next: res.data.chapterSiguiente || null
    };
  } catch (err) {
    logDebug('prevNext: error', err.message);
    throw new Error('Error: ' + err.message);
  }
}

async function seriesInfo(input) {
  const id = typeof input === 'string' && input.includes('manhwa/')
    ? input.split('/').pop()
    : input;
  const base = 'https://manhwawebbackend-production.up.railway.app/series/info';
  logDebug('seriesInfo: fetching info for id', id);

  try {
    const res = await axios.get(`${base}/${id}`);
    logDebug('seriesInfo: response received');
    return res.data;
  } catch (err) {
    logDebug('seriesInfo: error', err.message);
    throw new Error('Error: ' + err.message);
  }
}

async function search(q, p = 0, includeFirstChapter = false) {
  const url = `https://manhwawebbackend-production.up.railway.app/manhwa/library?buscar=${encodeURIComponent(q)}&estado=&tipo=&erotico=&demografia=&order_item=alfabetico&order_dir=desc&page=${p}&generes=`;
  logDebug('search: fetching search results for query', q);

  try {
    const { data } = await axios.get(url);
    if (!data?.data) {
      logDebug('search: no data found');
      return { results: [], totalPages: 0 };
    }

    const perPage = 20;
    const totalItems = data.total || data.data.length;
    const totalPages = Math.ceil(totalItems / perPage);

    const results = data.data.map(item => {
      const serieUrl = `https://manhwaweb.com/manhwa/${item._id}`;
      const chapterUrl = `https://manhwaweb.com/leer/${item._id}-1`;

      return {
        title: item.the_real_name,
        url: serieUrl,
        ...(includeFirstChapter && { firstChapterUrl: chapterUrl })
      };
    });

    logDebug('search: results count', results.length);
    return { results, totalPages };
  } catch (e) {
    logDebug('search: error', e.message);
    return { results: [], totalPages: 0 };
  }
}

module.exports = {
  slug,
  urls,
  full,
  images,
  prevNext,
  seriesInfo,
  search,
  setDebug
};