Email addresses clean up - remove nonsense from a long list of emails

email_clean_up.py

""" Remove nonsense from a long list of emails
[email protected]
"""

raw_emails_file = './email_addresses.txt'
clean_email_file = './clean_email_addresses.txt'

raw_emails =  open(raw_emails_file, 'r').readlines()
clean_emails = open(clean_email_file, 'w')


valid_counter = 0

for raw_email in raw_emails:

    # skip empty/invalid lines
    if not '@' in raw_email:
        continue

    # if < > found then save the valid part
    if '<' in raw_email:
        left_pos = raw_email.find('<')
        right_pos = raw_email.find('>')
        raw_email = raw_email[left_pos+1 : right_pos]

    # if no special case found, remove nonsense and save
    valid_address = raw_email.replace(' ', '')
    valid_address = valid_address.replace(',', '')
    valid_address = valid_address.lower()

    # write valid address to new line
    if valid_address.endswith('\n'):
        clean_emails.write(valid_address)
    else:
        clean_emails.write(valid_address + '\n')

    print(valid_address)
    valid_counter += 1

clean_emails.close()

print(f'a total of {valid_counter} valid emails saved to {clean_email_file}')