S3 access logs to CSV

s3_log_to_csv.py

  # /// script
# requires-python = ">=3.13"
# dependencies = [
#     "s3-log-parse",
# ]
# ///

import argparse
import sys
import csv

from s3logparse import s3logparse


def main():
    """
    Command line tool for processing S3 access logs
    """
    argparser = argparse.ArgumentParser()
    argparser.add_argument(
        'infile',
        nargs='?',
        type=argparse.FileType('r'),
        default=sys.stdin
    )
    args = argparser.parse_args()

    csv_writer = csv.writer(sys.stdout)
    csv_writer.writerow((
        'bucket_owner',
        'bucket',
        'timestamp',
        'remote_ip',
        'requester',
        'request_id',
        'operation',
        's3_key',
        'request_uri',
        'status_code',
        'error_code',
        'bytes_sent',
        'object_size',
        'total_time',
        'turn_around_time',
        'referrer',
        'user_agent',
        'version_id',
    ))
    csv_writer.writerows(s3logparse.parse_to_tuples(args.infile.readlines()))

if __name__ == '__main__':
    main()