Extract email from a file, make them unique and sort them.

email_cleaner.py

import re, sys
 
email_pattern = re.compile('([\w\-\.]+@(\w[\w\-]+\.)+[\w\-]+)')

email_list = [] 

for line in sys.stdin:
    # there are several matches per line
    for match in email_pattern.findall(line):
	email = match[0].lower()
        if email not in email_list:
            email_list.append(email)

email_list.sort()

for email in email_list:
    print email