Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

Use AWS lambda function to convert S3 file from zip to gzip using boto3 python

I need to convert a .zip file from S3 to a .gzip file using boto3 python in an AWS lambda function. Any suggestions on how to do this?

Here is what I have so far:

import json
import boto3
import zipfile
import gzip

s3 = boto3.resource('s3')

def lambda_handler(event, context):

    bucket = event['Records'][0]['s3']['bucket']['name']
    key = event['Records'][0]['s3']['object']['key']

    try: 
        s3Obj = s3.Object(bucket_name=bucket, key=key)
        response = s3Obj.get()
        data = response['Body'].read()
        zipToGzip = gzip.open(data, 'wb')
        zipToGzip.write(s3.upload_file(bucket, (s3 + '.gz')))
        zipToGzip.close()
    except Exception as e:
        print(e)
        print('Error getting object {} from bucket {}. Make sure they exist and your bucket is in the same region as this function.'.format(key, bucket))
        raise e
like image 508
Scotty Avatar asked Oct 14 '15 15:10

Scotty


1 Answers

OK, got it figured out. Thanks for your input Lee.

import json
import boto3
import zipfile
import gzip

print('Loading function')

s3 = boto3.resource('s3')
s3_client = boto3.client('s3')

def lambda_handler(event, context):

    # Get the object from the event and show its content type
    bucket = event['Records'][0]['s3']['bucket']['name']
    key = event['Records'][0]['s3']['object']['key']

    try: 
        s3_client.download_file(bucket, key, '/tmp/file.zip')
        zfile = zipfile.ZipFile('/tmp/file.zip')
        namelist = zfile.namelist()

        if len(namelist) >1:
            pass
            #alertme()

        for filename in namelist:
            data = zfile.read(filename)
            f = open('/tmp/' + str(filename), 'wb')
            f.write(data)
            f.close()

        zipToGzip = gzip.open('/tmp/data.gz', 'wb')
        zipToGzip.write(data)
        zipToGzip.close()
        s3_client.upload_file('/tmp/data.gz', bucket, key + '.gz')
        s3_client.delete_object(Bucket=bucket, Key=key)
    except Exception as e:
        print(e)
        print('Error getting object {} from bucket {}. Make sure they exist and your bucket is in the same region as this function.'.format(key, bucket))
        raise e
like image 142
Scotty Avatar answered Oct 12 '22 15:10

Scotty