How to download a file with Node.js (without using third-party libraries)?
How do I download a file with Node.js without using third-party libraries?
I don’t need anything special. I only want to download a file from a given URL, and then save it to a given directory.
Solutions/Answers:
Solution 1:
You can create an HTTP GET
request and pipe its response
into a writable file stream:
const http = require('http');
const fs = require('fs');
const file = fs.createWriteStream("file.jpg");
const request = http.get("http://i3.ytimg.com/vi/J---aiyznGQ/mqdefault.jpg", function(response) {
response.pipe(file);
});
If you want to support gathering information on the command line–like specifying a target file or directory, or URL–check out something like Commander.
Solution 2:
Don’t forget to handle errors! The following code is based on Augusto Roman’s answer.
var http = require('http');
var fs = require('fs');
var download = function(url, dest, cb) {
var file = fs.createWriteStream(dest);
var request = http.get(url, function(response) {
response.pipe(file);
file.on('finish', function() {
file.close(cb); // close() is async, call cb after close completes.
});
}).on('error', function(err) { // Handle errors
fs.unlink(dest); // Delete the file async. (But we don't check the result)
if (cb) cb(err.message);
});
};
Solution 3:
As Brandon Tilley said, but with the appropriate control flow:
var http = require('http');
var fs = require('fs');
var download = function(url, dest, cb) {
var file = fs.createWriteStream(dest);
var request = http.get(url, function(response) {
response.pipe(file);
file.on('finish', function() {
file.close(cb);
});
});
}
Without waiting for the finish
event, naive scripts may end up with an incomplete file.
Edit: Thanks to @Augusto Roman for pointing out that cb
should be passed to file.close
, not called explicitly.
Solution 4:
Speaking of handling errors, it’s even better listening to request errors too. I’d even validate by checking response code. Here it’s considered success only for 200 response code, but other codes might be good.
const fs = require('fs');
const http = require('http');
const download = (url, dest, cb) => {
const file = fs.createWriteStream(dest);
const request = http.get(url, (response) => {
// check if response is success
if (response.statusCode !== 200) {
return cb('Response status was ' + response.statusCode);
}
response.pipe(file);
});
// close() is async, call cb after close completes
file.on('finish', () => file.close(cb));
// check for request error too
request.on('error', (err) => {
fs.unlink(dest);
return cb(err.message);
});
file.on('error', (err) => { // Handle errors
fs.unlink(dest); // Delete the file async. (But we don't check the result)
return cb(err.message);
});
};
Despite the relative simplicity of this code, I would advise to use the request module as it handles many more protocols (hello HTTPS!) which aren’t natively supported by http
.
That would be done like so:
const fs = require('fs');
const request = require('request');
const download = (url, dest, cb) => {
const file = fs.createWriteStream(dest);
const sendReq = request.get(url);
// verify response code
sendReq.on('response', (response) => {
if (response.statusCode !== 200) {
return cb('Response status was ' + response.statusCode);
}
sendReq.pipe(file);
});
// close() is async, call cb after close completes
file.on('finish', () => file.close(cb));
// check for request errors
sendReq.on('error', (err) => {
fs.unlink(dest);
return cb(err.message);
});
file.on('error', (err) => { // Handle errors
fs.unlink(dest); // Delete the file async. (But we don't check the result)
return cb(err.message);
});
};
Solution 5:
gfxmonk’s answer has a very tight data race between the callback and the file.close()
completing. file.close()
actually takes a callback that is called when the close has completed. Otherwise, immediate uses of the file may fail (very rarely!).
A complete solution is:
var http = require('http');
var fs = require('fs');
var download = function(url, dest, cb) {
var file = fs.createWriteStream(dest);
var request = http.get(url, function(response) {
response.pipe(file);
file.on('finish', function() {
file.close(cb); // close() is async, call cb after close completes.
});
});
}
Without waiting for the finish event, naive scripts may end up with an incomplete file. Without scheduling the cb
callback via close, you may get a race between accessing the file and the file actually being ready.
Solution 6:
Maybe node.js has changed, but it seems there are some problems with the other solutions (using node v8.1.2):
- You don’t need to call
file.close()
in thefinish
event. Per default thefs.createWriteStream
is set to autoClose: https://nodejs.org/api/fs.html#fs_fs_createwritestream_path_options file.close()
should be called on error. Maybe this is not needed when the file is deleted (unlink()
), but normally it is: https://nodejs.org/api/stream.html#stream_readable_pipe_destination_options- Temp file is not deleted on
statusCode !== 200
fs.unlink()
without a callback is deprecated (outputs warning)- If
dest
file exists; it is overridden
Below is a modified solution (using ES6 and promises) which handles these problems.
const http = require("http");
const fs = require("fs");
function download(url, dest) {
return new Promise((resolve, reject) => {
const file = fs.createWriteStream(dest, { flags: "wx" });
const request = http.get(url, response => {
if (response.statusCode === 200) {
response.pipe(file);
} else {
file.close();
fs.unlink(dest, () => {}); // Delete temp file
reject(`Server responded with ${response.statusCode}: ${response.statusMessage}`);
}
});
request.on("error", err => {
file.close();
fs.unlink(dest, () => {}); // Delete temp file
reject(err.message);
});
file.on("finish", () => {
resolve();
});
file.on("error", err => {
file.close();
if (err.code === "EEXIST") {
reject("File already exists");
} else {
fs.unlink(dest, () => {}); // Delete temp file
reject(err.message);
}
});
});
}