Audit cardholder list produced by mep_cardholders.py

audit_identifiers.py

with open('/tmp/sylviabeach-card-images.txt') as found_images:
    urls = found_images.read().split('\n')
    identifiers = {}
    for u in urls:
        identifier = '/'.join(u.split('/')[-3:])
        identifiers[identifier] = ''


with open('/tmp/pudl0123-825298-noboxes-sorted.txt') as image_list:
    with open('/tmp/missing-identifiers.txt', 'w') as missing_list:
        missing = []
        for line in image_list:
                if line.strip() not in identifiers:
                    missing.append(line)
        missing_list.write('Found %d identifiers listed by PUDL not in data export\n' % len(missing))
        for line in missing:
            missing_list.write(line)