pdf-crawler/src/index.js

A simple Node.js version pdf download crawler

"use strict";

/**
 *
 * @author xgqfrms
 * @license MIT
 * @copyright xgqfrms
 * @created 2022-04-01
 * @modified
 *
 * @description Node.js pdf download crawler
 * @augments
 * @example
 * @link
 *
 */

const fs = require("fs");
// const path = require("path");
const { exit } = require("process");

const request = require("request-promise-native");

const log = console.log;

// const folder = path.resolve(__dirname, '../pdf');

// if (!fs.existsSync(folder)) {
//   fs.mkdirSync(folder);
// }

async function downloadPDF(url, filename) {
  log('🚧 pdf downloading ...');
  const pdfBuffer = await request.get({
    uri: url,
    encoding: null,
  });
  // fs.writeFileSync(`${folder}/${filename}`, pdfBuffer);
  fs.writeFileSync(filename, pdfBuffer);
  log('✅ pdf download finished!');
  exit(0);
}

module.exports = {
  downloadPDF,
};

// export {
//   downloadPDF,
// };

// export default downloadPDF;