How to download a file with Node.js (without using third-party libraries)?

问题

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.

回答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.

回答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);
  });
};

回答3:

As Michelle 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.

回答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);
    });
};

回答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.

回答6:

Maybe node.js has changed, but it seems there are some problems with the other solutions (using node v8.1.2):

1. You don't need to call file.close() in the finish event. Per default the fs.createWriteStream is set to autoClose: https://nodejs.org/api/fs.html#fs_fs_createwritestream_path_options
2. 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
3. Temp file is not deleted on statusCode !== 200
4. fs.unlink() without a callback is deprecated (outputs warning)
5. 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);
            }
        });
    });
}

回答7:

Solution with timeout, prevent memory leak :

The following code is based on Brandon Tilley's answer :

var http = require('http'),
    fs = require('fs');

var request = http.get("http://example12345.com/yourfile.html", function(response) {
    if (response.statusCode === 200) {
        var file = fs.createWriteStream("copy.html");
        response.pipe(file);
    }
    // Add timeout.
    request.setTimeout(12000, function () {
        request.abort();
    });
});

Don't make file when you get an error, and prefere to use timeout to close your request after X secondes.

回答8:

for those who came in search of es6-style promise based way, I guess it would be something like:

var http = require('http');
var fs = require('fs');

function pDownload(url, dest){
  var file = fs.createWriteStream(dest);
  return new Promise((resolve, reject) => {
    var responseSent = false; // flag to make sure that response is sent only once.
    http.get(url, response => {
      response.pipe(file);
      file.on('finish', () =>{
        file.close(() => {
          if(responseSent)  return;
          responseSent = true;
          resolve();
        });
      });
    }).on('error', err => {
        if(responseSent)  return;
        responseSent = true;
        reject(err);
    });
  });
}

//example
pDownload(url, fileLocation)
  .then( ()=> console.log('downloaded file no issues...'))
  .catch( e => console.error('error while downloading', e));

回答9:

Vince Yuan's code is great but it seems to be something wrong.

function download(url, dest, callback) {
    var file = fs.createWriteStream(dest);
    var request = http.get(url, function (response) {
        response.pipe(file);
        file.on('finish', function () {
            file.close(callback); // close() is async, call callback after close completes.
        });
        file.on('error', function (err) {
            fs.unlink(dest); // Delete the file async. (But we don't check the result)
            if (callback)
                callback(err.message);
        });
    });
}

回答10:

const download = (url, path) => new Promise((resolve, reject) => {
http.get(url, response => {
    const statusCode = response.statusCode;

    if (statusCode !== 200) {
        return reject('Download error!');
    }

    const writeStream = fs.createWriteStream(path);
    response.pipe(writeStream);

    writeStream.on('error', () => reject('Error writing to file!'));
    writeStream.on('finish', () => writeStream.close(resolve));
});}).catch(err => console.error(err));

回答11:

You can use https://github.com/douzi8/ajax-request#download

request.download('http://res.m.ctrip.com/html5/Content/images/57.png', 
  function(err, res, body) {}
);

回答12:

Hi，I think you can use child_process module and curl command.

const cp = require('child_process');

let download = async function(uri, filename){
    let command = `curl -o ${filename}  '${uri}'`;
    let result = cp.execSync(command);
};


async function test() {
    await download('http://zhangwenning.top/20181221001417.png', './20181221001417.png')
}

test()

In addition，when you want download large、multiple files，you can use cluster module to use more cpu cores.

回答13:

I prefer request() because you can use both http and https with it.

request('http://i3.ytimg.com/vi/J---aiyznGQ/mqdefault.jpg')
  .pipe(fs.createWriteStream('cat.jpg'))

回答14:

Download using promise, which resolve a readable stream. put extra logic to handle the redirect.

var http = require('http');
var promise = require('bluebird');
var url = require('url');
var fs = require('fs');
var assert = require('assert');

function download(option) {
    assert(option);
    if (typeof option == 'string') {
        option = url.parse(option);
    }

    return new promise(function(resolve, reject) {
        var req = http.request(option, function(res) {
            if (res.statusCode == 200) {
                resolve(res);
            } else {
                if (res.statusCode === 301 && res.headers.location) {
                    resolve(download(res.headers.location));
                } else {
                    reject(res.statusCode);
                }
            }
        })
        .on('error', function(e) {
            reject(e);
        })
        .end();
    });
}

download('http://localhost:8080/redirect')
.then(function(stream) {
    try {

        var writeStream = fs.createWriteStream('holyhigh.jpg');
        stream.pipe(writeStream);

    } catch(e) {
        console.error(e);
    }
});

回答15:

If you are using express use res.download() method. otherwise fs module use.

app.get('/read-android', function(req, res) {
   var file = "/home/sony/Documents/docs/Android.apk";
    res.download(file) 
}); 

(or)

   function readApp(req,res) {
      var file = req.fileName,
          filePath = "/home/sony/Documents/docs/";
      fs.exists(filePath, function(exists){
          if (exists) {     
            res.writeHead(200, {
              "Content-Type": "application/octet-stream",
              "Content-Disposition" : "attachment; filename=" + file});
            fs.createReadStream(filePath + file).pipe(res);
          } else {
            res.writeHead(400, {"Content-Type": "text/plain"});
            res.end("ERROR File does NOT Exists.ipa");
          }
        });  
    }

回答16:

Path : img type : jpg random uniqid

    function resim(url) {

    var http = require("http");
    var fs = require("fs");
    var sayi = Math.floor(Math.random()*10000000000);
    var uzanti = ".jpg";
    var file = fs.createWriteStream("img/"+sayi+uzanti);
    var request = http.get(url, function(response) {
  response.pipe(file);
});

        return sayi+uzanti;
}

回答17:

Without library it could be buggy just to point out. Here are a few:

• Can't handle http redirection, like this url https://calibre-ebook.com/dist/portable which is binary.
• http module can't https url, you will get Protocol "https:" not supported.

Here my suggestion:

• Call system tool like wget or curl
• use some tool like node-wget-promise which also very simple to use. var wget = require('node-wget-promise'); wget('http://nodejs.org/images/logo.svg');

回答18:

function download(url, dest, cb) {

  var request = http.get(url, function (response) {

    const settings = {
      flags: 'w',
      encoding: 'utf8',
      fd: null,
      mode: 0o666,
      autoClose: true
    };

    // response.pipe(fs.createWriteStream(dest, settings));
    var file = fs.createWriteStream(dest, settings);
    response.pipe(file);

    file.on('finish', function () {
      let okMsg = {
        text: `File downloaded successfully`
      }
      cb(okMsg);
      file.end(); 
    });
  }).on('error', function (err) { // Handle errors
    fs.unlink(dest); // Delete the file async. (But we don't check the result)
    let errorMsg = {
      text: `Error in file downloadin: ${err.message}`
    }
    if (cb) cb(errorMsg);
  });
};

回答19:

You can try using res.redirect to the https file download url, and then it will be downloading the file.

Like: res.redirect('https//static.file.com/file.txt');

回答20:

var fs = require('fs'),
    request = require('request');

var download = function(uri, filename, callback){
    request.head(uri, function(err, res, body){
    console.log('content-type:', res.headers['content-type']);
    console.log('content-length:', res.headers['content-length']);
    request(uri).pipe(fs.createWriteStream(filename)).on('close', callback);

    }); 
};   

download('https://www.cryptocompare.com/media/19684/doge.png', 'icons/taskks12.png', function(){
    console.log('done');
});

回答21:

Here's yet another way to handle it without 3rd party dependency and also searching for redirects:

        var download = function(url, dest, cb) {
            var file = fs.createWriteStream(dest);
            https.get(url, function(response) {
                if ([301,302].indexOf(response.statusCode) !== -1) {
                    body = [];
                    download(response.headers.location, dest, cb);
                  }
              response.pipe(file);
              file.on('finish', function() {
                file.close(cb);  // close() is async, call cb after close completes.
              });
            });
          }

回答22:

We can use the download node module and its very simple, please refer below https://www.npmjs.com/package/download

回答23:

var requestModule=require("request");

requestModule(filePath).pipe(fs.createWriteStream('abc.zip'));

来源：https://stackoverflow.com/questions/11944932/how-to-download-a-file-with-node-js-without-using-third-party-libraries