Read file from aws s3 bucket using node fs

Question

I am attempting to read a file that is in a aws s3 bucket using

fs.readFile(file, function (err, contents) {
  var myLines = contents.Body.toString().split(         


        

Answer 1

This will do it:

new AWS.S3().getObject({ Bucket: this.awsBucketName, Key: keyName }, function(err, data)
{
    if (!err)
        console.log(data.Body.toString());
});

Answer 2

Since you seem to want to process an S3 text file line-by-line. Here is a Node version that uses the standard readline module and AWS' createReadStream()

const readline = require('readline');

const rl = readline.createInterface({
    input: s3.getObject(params).createReadStream()
});

rl.on('line', function(line) {
    console.log(line);
})
.on('close', function() {
});

Answer 3

With the new version of sdk, the accepted answer does not work - it does not wait for the object to be downloaded. The following code snippet will help with the new version:

// dependencies

const AWS = require('aws-sdk');

// get reference to S3 client

const s3 = new AWS.S3();

exports.handler = async (event, context, callback) => {

var bucket = "TestBucket"

var key = "TestKey"

   try {

      const params = {
            Bucket: Bucket,
            Key: Key
        };

       var theObject = await s3.getObject(params).promise();

    } catch (error) {
        console.log(error);
        return;
    }  
}

Answer 4

If you want to save memory and want to obtain each row as a json object, then you can use fast-csv to create readstream and can read each row as a json object as follows:

const csv = require('fast-csv');
const AWS = require('aws-sdk');

const credentials = new AWS.Credentials("ACCESSKEY", "SECRETEKEY", "SESSIONTOKEN");
AWS.config.update({
    credentials: credentials, // credentials required for local execution
    region: 'your_region'
});
const dynamoS3Bucket = new AWS.S3();
const stream = dynamoS3Bucket.getObject({ Bucket: 'your_bucket', Key: 'example.csv' }).createReadStream();

var parser = csv.fromStream(stream, { headers: true }).on("data", function (data) {
    parser.pause();  //can pause reading using this at a particular row
    parser.resume(); // to continue reading
    console.log(data);
}).on("end", function () {
    console.log('process finished');
});

Answer 5

I couldn't figure why yet, but the createReadStream/pipe approach didn't work for me. I was trying to download a large CSV file (300MB+) and I got duplicated lines. It seemed a random issue. The final file size varied in each attempt to download it.

I ended up using another way, based on AWS JS SDK examples:

var s3 = new AWS.S3();
var params = {Bucket: 'myBucket', Key: 'myImageFile.jpg'};
var file = require('fs').createWriteStream('/path/to/file.jpg');

s3.getObject(params).
    on('httpData', function(chunk) { file.write(chunk); }).
    on('httpDone', function() { file.end(); }).
    send();

This way, it worked like a charm.

Answer 6

I prefer Buffer.from(data.Body).toString('utf8'). It supports encoding parameters. With other AWS services (ex. Kinesis Streams) someone may want to replace 'utf8' encoding with 'base64'.

new AWS.S3().getObject(
  { Bucket: this.awsBucketName, Key: keyName }, 
  function(err, data) {
    if (!err) {
      const body = Buffer.from(data.Body).toString('utf8');
      console.log(body);
    }
  }
);