unzip archive from S3 on AWS Lambda, in place, retain contentType

aws-lambda-unzipper.py

import os
import sys
import re
import boto3
import zipfile

#Expand on this based on which filetypes you expect to recieve
mimeTypes = {
    ".html": "text/html",
    ".png": "image/png",
    ".jpg": "image/jpg"
}

def unzip(event, context):
    source_bucket = event['Records'][0]['s3']['bucket']['name']
    source_key = event['Records'][0]['s3']['object']['key']
    destination_bucket = source_bucket
    destination_key = os.path.dirname(source_key)

    temp_zip = '/tmp/file.zip'
    
    s3_client = boto3.client('s3')

    print("downloading {}".format(source_key))
    
    s3_client.download_file(source_bucket, source_key, temp_zip)
    zfile = zipfile.ZipFile(temp_zip)
    
    file_list = [( name, 
                   '/tmp/' + os.path.basename(name),
                    destination_key + "/" + os.path.basename(name))
                for name in zfile.namelist()]

    print("got names {}".format("; ".join([n for n,b,d in file_list])))
    print(file_list)

    for file_name, local_path, s3_key in file_list:
        data = zfile.read(file_name)
        with open(local_path, 'wb') as f:
            f.write(data)
            del(data) # free up some memory

        extension = split_tup = os.path.splitext(s3_key)[1];
        contentType = mimeTypes[extension]
        s3_client.upload_file(local_path, destination_bucket, s3_key, ExtraArgs={'ContentType': contentType})
        os.remove(local_path)

    return {"files": ['s3://' + destination_bucket + '/' + s for f,l,s in file_list]}