I am using the aws javascript sdk and for some reason I can access the entire buckets contents, but when I add a prefix I get null returned rather than a subset of those contents. For example, the following returns all bucket contents:
AWS.config.accessKeyId = this.s3.config["accessKeyId"];
AWS.config.secretAccessKey = this.s3.config["secretAccessKey"];
AWS.config.region = 'us-east-2';
var aws = new AWS.S3();
var all_params = {Bucket: 'bucket-name'};
new Promise(resolve => {
aws.listObjectsV2(all_params, function (err, url) {
console.log(url)
resolve(url)
});
})
The object returned contains 1000 records, most of them in the format Key: "clients/after_fronts/000...". However when I run the following, I get a null object:
AWS.config.accessKeyId = this.s3.config["accessKeyId"];
AWS.config.secretAccessKey = this.s3.config["secretAccessKey"];
AWS.config.region = 'us-east-2';
var key = "clients"
var aws = new AWS.S3();
var params = {Bucket: 'bucket-name', prefix: key};
return new Promise(resolve => {
aws.listObjectsV2(params, function (err, url) {
console.log(url)
resolve(url)
});
})
I thought it might be a permissions issue but I'm not sure why it returns data without a prefix and then no data with the prefix. What else could be going on?
Well, after staring at this for an hour I realized the docs call for Prefix not prefix and that capitalization made all the difference.
Related
I use Javascript to get the file names from AWS S3 bucket. After i get the complete list of file names from the bucket, i parse & manipulate it & list them in front-end. In this case, i want to get rid of the problem which will arise when the bucket with filled with huge amount of data (i.e) i'll run out of memory when i try to manipulate with a shocking amount of data. So, i only need the file names of the very first layer.
Example :
The complete object in S3 bucket :
{
new_folder: {...},
some_file.png: {...}
}
Here i only need the names -> new_folder, some_file.png
Below is the code which i use now :
const AWS = require('aws-sdk');
export default async function wasabiActions(dataObj) {
var accessKeyId = '************';
var secretAccessKey = '********************';
var wasabiEndpoint = new AWS.Endpoint('s3.us-west-1.wasabisys.com');
var s3 = await new AWS.S3({
endpoint: wasabiEndpoint,
accessKeyId: accessKeyId,
secretAccessKey: secretAccessKey
});
var params = {
Bucket: 'bucket_name',
};
s3.listObjectsV2(params, function(err, data) {
if (!err) {
var files = [];
data.Contents.forEach(function(element) {
files.push(element.Key.split('/').filter((name) => name.length > 0));
});
console.log(files);
var parsedData = wasabiDataParser(files);
console.log(parsedData);
}
});
}
Thanks in advance! :)
You can use pagination. Some AWS operations return results that are incomplete and require subsequent requests in order to attain the entire result set. Check here for more details. https://boto3.amazonaws.com/v1/documentation/api/latest/guide/paginators.html
I am working on a lambda function that would be invoked by a S3 PUT event and would display the metadata field of the s3 object. I tried to set the key and bucket as variable but when I run it I get a { BadRequest: null error. below is my code in javascript. when I hardcode the key and bucket it would work but not with variable passed in, can someone explain what am I doing wrong? thanks!
var AWS = require('aws-sdk');
var s3 = new AWS.S3();
exports.handler = function(event, context) {
var srcbucket = ("\'" + (event.Records[0].s3.object.key).toString() + "\'");
var srcKey = ("\'" + (event.Records[0].s3.bucket.name).toString() + "\'");
console.log (srcKey);
s3.headObject(
{
Bucket : srcbucket,
Key: srcKey
},
function(err, data)
{
if (err)
{
console.log(err);
context.done('Error', 'Error getting s3 object: ' + err);
}
else
{
var data = JSON.stringify(this.httpResponse.headers['x-amz-meta-checksum']).replace(/\"/g, "");
console.log (data.replace(/\"/g, ""));
}
First, your variable is mixed up. The srcbucket is pointer to object's Key, and vice versa.
Secondly, you may want remove the additional quote ' that was applied to the variable.
var srcbucket = event.Records[0].s3.bucket.name;
var srcKey = event.Records[0].s3.object.key;
I am successfully uploading an image to my Amazon S3 bucket, but when I go to the URL that it is generated, my image is instantly downloaded instead of being displayed in the browser. My code is below:
var fs = require('fs');
var AWS = require('aws-sdk');
AWS.config = new AWS.Config();
AWS.config.accessKeyId = "MY_ACCESS_KEY";
AWS.config.secretAccessKey = "MY_SECRET_KEY";
AWS.config.region = "us-west-2";
AWS.config.apiVersions = {
"s3": "2006-03-01"
}
var s3 = new AWS.S3();
var bodystream = fs.createReadStream('./meme1.png');
var params = {
'Bucket': 'MY_BUCKET_NAME',
'Key': 'uploads/images/' + 'Img4.png',
'Body': bodystream,
'ContentEncoding': 'base64',
'ContentType ': 'image/png',
'ACL':'public-read-write'
};
s3.upload(params, function(err, data){
console.log('RESPONSE: ', err, data);
});
Some other posts say to make sure the ContentType property of the params object is correct but I am pretty sure that mine is correct. How do I fix this and make the image display in the browser instead of downloading?
You are missing the Content Disposition, by default it's "attachement" which means the file is being downloaded instead of displayed.
ContentDisposition: inline
(Answering this Question for Googlers)
I'm trying to use Amazon's S3 service, I managed to upload GZipped files to my bucket but I can't retrieve them. I tried using the code example that I've found here, everything works fine when I'm uploading the files, but I can't download them.
This is my upload code:
var s3 = new AWS.S3();
s3.headBucket({Bucket: bucketName}, function (err) {
if (err) s3.createBucket({Bucket: bucketName}, cb);
var body = fs.createReadStream(file).pipe(zlib.createGzip());
s3.upload({Bucket: bucketName, Key: key, Body: body}).send(cb);
});
ANd this is my download code:
var s3 = new AWS.S3();
var params = {Bucket: bucketName, Key: key};
var outFile = require('fs').createWriteStream(file);
s3.getObject(params).createReadStream().pipe(zlib.createGunzip()).pipe(outFile);
But I get error throw new Error('Cannot switch to old mode now.'); on the last line.
and I can't figure out how to fix it, I'm using node 0.10.25(and I can't change it).
So I tried using this:
var params = {Bucket: bucketName, Key: key};
s3.getObject(params, function(err, data) {
var outFile = require('fs').createWriteStream(file);
var read = AWS.util.buffer.toStream(data.Body);
read.pipe(zlib.createGzip()).pipe(outFile);
read.on('end', function(){cb();});
});
but often I get error 104(unexpected end of input).
Anyone has some ideas?
Unexpected end of input is perhaps due to pipe getting closed prematurely or some other error was encountered in the middle of reading a fixed-size block or data structure.
You can look at - https://github.com/minio/minio-js instead as well as an alternative, it is fully written in Streams2 style.
Here is an example.
$ npm install minio
$ cat >> get-object.js << EOF
var Minio = require('minio')
var fs = require('fs')
// find out your s3 end point here:
// http://docs.aws.amazon.com/general/latest/gr/rande.html#s3_region
var s3Client = new Minio({
url: 'https://<your-s3-endpoint>',
accessKey: 'YOUR-ACCESSKEYID',
secretKey: 'YOUR-SECRETACCESSKEY'
})
var outFile = fs.createWriteStream('test.txt');
s3Client.getObject('mybucket', 'my-key', function(e, dataStream) {
if (e) {
return console.log(e)
}
dataStream.pipe(outFile)
})
EOF
I was wondering if I could set up a lambda function for AWS, triggered whenever a new text file is uploaded into an s3 bucket. In the function, I would like to get the contents of the text file and process it somehow. I was wondering if this was possible...?
For example, if I upload foo.txt, with contents foobarbaz, I would like to somehow get foobarbaz in my lambda function so I can do stuff with it. I know I can get metadata from getObject, or a similar method.
Thanks!
The S3 object key and bucket name are passed into your Lambda function via the event parameter. You can then get the object from S3 and read its contents.
Basic code to retrieve bucket and object key from the Lambda event is as follows:
exports.handler = function(event, context, callback) {
const bkt = event.Records[0].s3.bucket.name;
const key = decodeURIComponent(event.Records[0].s3.object.key.replace(/\+/g, ' '));
};
Once you have the bucket and key, you can call getObject to retrieve the object:
const AWS = require('aws-sdk');
const s3 = new AWS.S3();
exports.handler = function(event, context, callback) {
// Retrieve the bucket & key for the uploaded S3 object that
// caused this Lambda function to be triggered
const Bucket = event.Records[0].s3.bucket.name;
const Key = decodeURIComponent(event.Records[0].s3.object.key.replace(/\+/g, ' '));
// Retrieve the object
s3.getObject({ Bucket, Key }, function(err, data) {
if (err) {
console.log(err, err.stack);
callback(err);
} else {
console.log("Raw text:\n" + data.Body.toString('ascii'));
callback(null, null);
}
});
};
Here's an updated JavaScript example using ES6-style code and promises, minus error-handling:
const AWS = require('aws-sdk');
const s3 = new AWS.S3();
exports.handler = async (event, context) => {
const Bucket = event.Records[0].s3.bucket.name;
const Key = decodeURIComponent(event.Records[0].s3.object.key.replace(/\+/g, ' '));
const data = await s3.getObject({ Bucket, Key }).promise();
console.log("Raw text:\n" + data.Body.toString('ascii'));
};
A number of posters have asked for the equivalent in Java, so here's an example:
package example;
import java.net.URLDecoder;
import com.amazonaws.services.lambda.runtime.Context;
import com.amazonaws.services.lambda.runtime.RequestHandler;
import com.amazonaws.services.lambda.runtime.events.S3Event;
import com.amazonaws.services.s3.AmazonS3;
import com.amazonaws.services.s3.AmazonS3Client;
import com.amazonaws.services.s3.event.S3EventNotification.S3EventNotificationRecord;
public class S3GetTextBody implements RequestHandler<S3Event, String> {
public String handleRequest(S3Event s3event, Context context) {
try {
S3EventNotificationRecord record = s3event.getRecords().get(0);
// Retrieve the bucket & key for the uploaded S3 object that
// caused this Lambda function to be triggered
String bkt = record.getS3().getBucket().getName();
String key = record.getS3().getObject().getKey().replace('+', ' ');
key = URLDecoder.decode(key, "UTF-8");
// Read the source file as text
AmazonS3 s3Client = new AmazonS3Client();
String body = s3Client.getObjectAsString(bkt, key);
System.out.println("Body: " + body);
return "ok";
} catch (Exception e) {
System.err.println("Exception: " + e);
return "error";
}
}
}
I am using lambda function with a python 3.6 environment.
The code below will read the contents of a file main.txt inside bucket my_s3_bucket. Make sure to replace name of bucket and file name according to your needs.
def lambda_handler(event, context):
# TODO implement
import boto3
s3 = boto3.client('s3')
data = s3.get_object(Bucket='my_s3_bucket', Key='main.txt')
contents = data['Body'].read()
print(contents)
You can use data.Body.toString('ascii') to get the contents of the text file, assuming that the text file was encoded used ascii format. You can also pass other encoding types to the function. Check out Node-Buffer for further details.
The new AWS SDK v3 means that the files are read back as a readable stream. You'll need to take that into consideration from now on as well.
https://carova.io/snippets/read-data-from-aws-s3-with-nodejs