Parse senders email information from eml files

eml_sender_email_extractor.py

import argparse
import os
from email import policy
from email.parser import BytesParser
from pathlib import Path


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('eml_directory_path')
    parser.add_argument('output_file')
    args = parser.parse_args()

    if not os.path.isdir(args.eml_directory_path):
        raise IOError('EML directory not found. Please check given directory path')
    eml_directory_path = Path(args.eml_directory_path)
    senders = set()

    for eml_file_path in eml_directory_path.rglob("*.eml"):
        with open(eml_file_path, 'rb') as eml_file:
            msg = BytesParser(policy=policy.default).parse(eml_file, headersonly=True)
            senders.add(msg['From'])

    # write all senders addresses
    with open(args.output_file, 'w') as sender_file:
        for sender in senders:
            sender_file.write(sender)
            sender_file.write('\n')


if __name__ == '__main__':
    main()