Script to tally the domains of emails contained in the Ashley Madison email file

email_domains.py

# write domain counts to file after every 1,000,000 emails read
increment_to_save = 1000000

def write_to_file(file_name, domains):
    # sort the domains by count
    from operator import itemgetter
    domains = sorted(domains, key=itemgetter('count'))

    # write the domains to the results file
    results_file = open(file_name, "w")
    domains = reversed(domains)
    for domain in domains:
        results_file.write(domain["domain"] + "," + str(domain["count"]) + "\n")
    results_file.close()


emails_file = open("emails_dump.txt", "r")

# storage for domain counts
domains = list()

email_number = 1
for email in emails_file:
    # if not @ symbol in email, go onto next email
    if(email.find("@") != -1):
        # get the email's domain
        email_domain = email.split("@")[-1].rstrip('\n')
        # go through the existing domains checking for the email's domain
        domain_exists = False
        for domain in domains:
            if domain["domain"] == email_domain:
                domain["count"] += 1
                domain_exists = True
                break
        # if the domain doesn't already exist in the counts, then add it     
        if not domain_exists:
            new_domain = {"domain": "", "count": 1}
            new_domain["domain"] = email_domain
            domains.append(new_domain)
        # for every 1 million email addresses read, write the current domain counts to a file
        if ((email_number % increment_to_save) == 0) and (email_number > 0):
            write_to_file("domain_counts_" + str(int(email_number/increment_to_save)) + ".csv", domains)
    email_number+=1
emails_file.close()

# write the final domain counts to a file
write_to_file("final_domain_counts.csv", domains)