如何从node.js中的url下载pdf文件？

Question

I am creating an application to download pdf files from url and show in my dashboard page as grid wise.

I am using node.js with express framework.

exports.pdf = function(req, response) {
    var url ="http://www.ieee.org/documents/ieeecopyrightform.pdf";

    http.get(url, function(res) {
     var chunks = [];
     res.on('data', function(chunk) {
     console.log('start');
     chunks.push(chunk);
    });

    res.on("end", function() {
      console.log('downloaded');
      var jsfile = new Buffer.concat(chunks).toString('base64');
      console.log('converted to base64');
      response.header("Access-Control-Allow-Origin", "*");
      response.header("Access-Control-Allow-Headers", "X-Requested-With");
      response.header('content-type', 'application/pdf');
     response.send(jsfile);
    });
    }).on("error", function() {
   console.log("error");
   }); 
};

Answer 1

For those looking to download a PDF server side, which is a bit of a different use case than the OP, here's how I did it using the request npm module:

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

async function downloadPDF(pdfURL, outputFilename) {
    let pdfBuffer = await request.get({uri: pdfURL, encoding: null});
    console.log("Writing downloaded PDF file to " + outputFilename + "...");
    fs.writeFileSync(outputFilename, pdfBuffer);
}

downloadPDF("https://www.ieee.org/content/dam/ieee-org/ieee/web/org/pubs/ecf_faq.pdf", "c:/temp/somePDF.pdf");

Answer 2

Simple solution I used to download pdf in node js is by npm i node-downloader-helper and just add downlaod url:

const { DownloaderHelper } = require('node-downloader-helper');

const download = new DownloaderHelper('url', __dirname);
download.on('end', () => console.log('Download Completed'))
download.start();

Answer 3

This will Help.

response.setHeader("Content-Type", "text/pdf");

This Link will help

Answer 4

try this full version pdf downloader with an explanation

"use strict";

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

// 1. commonjs module using `require` keyword
const fs = require("fs");
const path = require("path");
const { exit } = require("process");

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

const log = console.log;

// 2. custom download folder
const folder = path.resolve(__dirname, '../pdf');
// log('folder', folder);

// 3. check if the folder exists, if not create it
if (!fs.existsSync(folder)) {
  fs.mkdirSync(folder);
}

async function downloadPDF(url, filename) {
  log('🚧 pdf downloading ...');
  const pdfBuffer = await request.get({
    uri: url,
    encoding: null,
  });
  // 4. write file to local file system
  fs.writeFileSync(filename, pdfBuffer);
  log('✅ pdf download finished!');
  // 5. exit the terminal after download finished
  exit(0);
}

const url = 'https://cs193p.sites.stanford.edu/sites/g/files/sbiybj16636/files/media/file/l1.pdf';
const filename = folder + '/cs193p-2021-l1.pdf';
// log('filename =', filename);

downloadPDF(url, filename);

refs

https://nodejs.org/api/process.html#exit-codes

Answer 5

If anyone is having issues (like I was) actually getting the PDF to open in a PDF viewer when using the request module, try setting the encoding in your call to null. Something like this:

async function downloadPDF(pdfURL, outputFilename, token) {
const options = {
url: pdfURL,
headers: {
    'Content-Type': 'application/pdf',
    'Authorization': 'Bearer '+token,
},
encoding: null

}