Created
August 29, 2017 16:26
-
-
Save hobu/8e215e7180a313bdbd0242b1bbac786e to your computer and use it in GitHub Desktop.
Copy from RequesterPays buckets to your bucket
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import boto3 | |
| import argparse | |
| import logging | |
| from multiprocessing.pool import ThreadPool | |
| from functools import partial | |
| resource = boto3.client('s3') | |
| client = boto3.client('s3') | |
| def splitbucket(key): | |
| first, second = key.split('//') | |
| # bucket is first item, key is the rest | |
| keys = second.split('/') | |
| bucket = keys[0] | |
| key = '/'.join(keys[1:]) | |
| if args.verbose: | |
| logging.debug("Split bucket '%s' with key '%s'" % (bucket, key)) | |
| return (bucket, key) | |
| def get_objects(args): | |
| if args.verbose: | |
| logging.debug("Listing bucket '%s' with key '%s'" % (args.source_bucket, args.source_key)) | |
| paginator = client.get_paginator('list_objects') | |
| pageresponse = paginator.paginate(Bucket=args.source_bucket, | |
| Prefix=args.source_key, | |
| RequestPayer='requester') | |
| keys = [] | |
| for pageobject in pageresponse: | |
| for obj in pageobject["Contents"]: | |
| keys.append(obj) | |
| return keys | |
| def copy(obj, args): | |
| source_key = obj['Key'] | |
| fname = source_key.split('/')[-1] | |
| destination_key = args.destination_key + '/' + fname | |
| if args.verbose: | |
| logging.debug("Copy from '%s' with key '%s' to '%s' with key '%s' " % (args.source_bucket, source_key, args.destination_bucket, args.destination_key)) | |
| client.copy_object(CopySource={'Bucket':args.source_bucket, 'Key':source_key}, | |
| Bucket=args.destination_bucket, | |
| Key = destination_key, | |
| RequestPayer='requester') | |
| def main(args): | |
| if args.verbose: | |
| logging.debug("Fetching bucket '%s' to '%s'" % (args.source, args.destination)) | |
| args.source_bucket, args.source_key = splitbucket(args.source) | |
| args.destination_bucket, args.destination_key = splitbucket(args.destination) | |
| keys = get_objects(args) | |
| pool = ThreadPool(args.processes) | |
| results = pool.map(partial(copy, args=args), keys) | |
| # for key in keys: | |
| # copy(key, args) | |
| if __name__ == '__main__': | |
| parser = argparse.ArgumentParser(description = 'Copy a RequesterPays bucket to another bucket') | |
| parser.add_argument('source', help='RequesterPays bucket to copy') | |
| parser.add_argument('destination', help='Destination bucket') | |
| parser.add_argument('--processes', help='Number of processes to use', type=int) | |
| parser.add_argument('-v', '--verbose', help='Verbose', action="store_true") | |
| parser.set_defaults(processes=1, type=int) | |
| args = parser.parse_args() | |
| if args.verbose: | |
| logging.basicConfig(level=logging.DEBUG) | |
| # rp-copy.py s3://my-rp-bucket/key s3://my-own-bucket/key -v --processes 5 | |
| main(args) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment