Process SendGrid suppressions into SparkPost compatible format. Allows diffing of email CSVs to exclude previously bounced addresses.

suppressions.py

#!/usr/local/bin/python3
import csv
import argparse
from os import path


def combine_suppressions(outfilename='suppressions.csv'):
    suppressions = set()
    suppression_map = {
        'suppression_blocks.csv': 2,
        'suppression_bounces.csv': 2,
        'suppression_invalid_emails.csv': 1,
        'suppression_spam_reports.csv': 1
    }

    for filename, email_index in suppression_map.items():
        print('Processing %s...' % filename)
        with open(filename, 'r') as file:
            reader = csv.reader(file)
            for row in reader:
                suppressions.add(row[email_index])

    with open(outfilename, 'w') as outfile:
        writer = csv.writer(outfile, quoting=csv.QUOTE_ALL, lineterminator='\n')
        # write header for SparkPost
        writer.writerow(('recipient', 'transactional', 'non_transactional'))
        for email in suppressions:
            writer.writerow((email, 'true', 'true'))

def diff(emails_filename, verbose=False, suppressions_filename='suppressions.csv', suppression_index=0, email_index=1):
    suppressions = set()
    with open(suppressions_filename, 'r') as suppressions_file:
        suppressions_reader = csv.reader(suppressions_file)
        # skip header
        next(suppressions_reader)
        for row in suppressions_reader:
            suppressions.add((row[suppression_index]))

    with open('clean-%s' % path.basename(emails_filename), 'w') as emails_clean_file, open(emails_filename, 'r') as emails_file:
        writer = csv.writer(emails_clean_file, quoting=csv.QUOTE_ALL, lineterminator='\n')
        emails_reader = csv.reader(emails_file)
        # write header
        writer.writerow(next(emails_reader))
        removed = 0
        for row in emails_reader:
            if (row[email_index]) not in suppressions:
                writer.writerow(row)
            else:
                if verbose:
                    print('Removing %s' % row[email_index])
                removed += 1
        print('Removed %s emails and wrote output to %s' % (removed, emails_clean_file.name))


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Process suppressions and diff with sending list.')
    parser.add_argument('--verbose', action='store_true', help='Print more.', default=False)
    parser.add_argument('--diff', action='store_true', help='Diff Mode: Removes emails to be suppressed from the given CSV. Creates a new file called clean-*.csv in the working directory.')
    parser.add_argument('--emails', type=str, dest='emails_filename', default='emails.csv', help='Email CSV filename for diff mode.')
    parser.add_argument('--combine', action='store_true', help='Combine Mode: Combines the SendGrid suppression CSVs to a single CSV in SparkPost-compatible format.')

    args = parser.parse_args()

    if not args.diff and not args.combine:
        parser.print_help()

    if args.diff:
        diff(args.emails_filename, verbose=args.verbose)

    if args.combine:
        combine_suppressions()