Copying S3 objects from one account to other using Lambda python - amazon-web-services

Question

I'm using boto3 to copy files from s3 bucket from one account to other. I need a similar functionality like aws s3 sync. Please see my code. My company has decided to 'PULL' from other S3 bucket (source account). Please don't suggest replication, S3 batch, S3 trigger Lambda..etc. We have gone through all these options and my management do not want to do any configuration at source side. Can you please review this code and let me know if this code works for thousands of objects. Source bucket has nearly 10000 objects. We will create this lambda function in destination account and create a cloudwatch event to trigger the lambda once in a day.
I am checking ETag so that modified files will be copied across when this function is triggered.
Edit: I simplified my code just to see pagination works. It's working if I don't add client.copy(). If I add this line in for loop after reading 3,4 objects it's throwing "errorMessage": "2021-08-07T15:29:07.827Z 82757747-7b72-4f29-ae9f-22e95f969d6c Task timed out after 3.00 seconds". Please advise. Please note that 'test/' folder in my source bucket has around 1100 objects.
import os
import logging
import botocore
logger = logging.getLogger()
logger.setLevel(os.getenv('debug_level', 'INFO'))
client = boto3.client('s3')
def handler(event, context):
main(event, logger)
def main(event, logger):
try:
SOURCE_BUCKET = os.environ.get('SRC_BUCKET')
DEST_BUCKET = os.environ.get('DST_BUCKET')
REGION = os.environ.get('REGION')
prefix = 'test/'
# Create a reusable Paginator
paginator = client.get_paginator('list_objects_v2')
print ('after paginator')
# Create a PageIterator from the Paginator
page_iterator = paginator.paginate(Bucket=SOURCE_BUCKET,Prefix = prefix)
print ('after page iterator')
index = 0
for page in page_iterator:
for obj in page['Contents']:
index += 1
print ("I am looking for {} in the source bucket".format(obj['ETag']))
copy_source = {'Bucket': SOURCE_BUCKET, 'Key': obj['Key']}
client.copy(copy_source, DEST_BUCKET, obj['Key'])
logger.info("number of objects copied {}:".format(index))
except botocore.exceptions.ClientError as e:
raise

Answer 1

This version is working fine if I increase the Lambda timeout to 15 min and memory to 512MB. This checks if the source object already exists in destination before copying.
import boto3
import os
import logging
import botocore
from botocore.client import Config
logger = logging.getLogger()
logger.setLevel(os.getenv('debug_level', 'INFO'))
config = Config(connect_timeout=5, retries={'max_attempts': 0})
client = boto3.client('s3', config=config)
#client = boto3.client('s3')
def handler(event, context):
main(event, logger)
def main(event, logger):
try:
DEST_BUCKET = os.environ.get('DST_BUCKET')
SOURCE_BUCKET = os.environ.get('SRC_BUCKET')
REGION = os.environ.get('REGION')
prefix = ''
# Create a reusable Paginator
paginator = client.get_paginator('list_objects_v2')
print ('after paginator')
# Create a PageIterator from the Paginator
page_iterator_src = paginator.paginate(Bucket=SOURCE_BUCKET,Prefix = prefix)
page_iterator_dest = paginator.paginate(Bucket=DEST_BUCKET,Prefix = prefix)
print ('after page iterator')
index = 0
for page_source in page_iterator_src:
for obj_src in page_source['Contents']:
flag = "FALSE"
for page_dest in page_iterator_dest:
for obj_dest in page_dest['Contents']:
# checks if source ETag already exists in destination
if obj_src['ETag'] in obj_dest['ETag']:
flag = "TRUE"
break
if flag == "TRUE":
break
if flag != "TRUE":
index += 1
client.copy_object(Bucket=DEST_BUCKET, CopySource={'Bucket': SOURCE_BUCKET, 'Key': obj_src['Key']}, Key=obj_src['Key'],)
print ("source ETag {} and destination ETag {}".format(obj_src['ETag'],obj_dest['ETag']))
print ("source Key {} and destination Key {}".format(obj_src['Key'],obj_dest['Key']))
print ("Number of objects copied{}".format(index))
logger.info("number of objects copied {}:".format(index))
except botocore.exceptions.ClientError as e:
raise