tarfile_pax_headers.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import argparse
import tarfile
import json


def get_tar_metadata(file_name):
    tar = tarfile.open(file_name, encoding="iso8859-1")
    metadata = [ { "filename": x.name, "headers": x.pax_headers }  for x in tar.getmembers() ]
    return metadata

  
if __name__ == "__main__":
    parser = argparse.ArgumentParser("Extract tar filenames and metadata from the PAX headers")
    parser.add_argument("-f",
                        "--file",
                        type=str,
                        help="tar file to read",
                        required=True)

    args = parser.parse_args()
    metadata = get_tar_metadata(args.file)
    
    print(json.dumps(metadata, indent=2, separators=(',', ': ')))