Find email addresses in some text (e.g. html) file

findadds.py

import re

with open('cic.html', 'r') as f:
    raw = f.read()

    r = r"[a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_`{|}~-]+)*@(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?"

    add = re.findall(r, raw)

unique = sorted(set(add))

print '; '.join(unique)