gistfile1.py

def has_nothing_to_do_with_n(text):
    if type(text) == unicode:
        text = text.encode('utf-8')
    reason = False
    if len(text) < 5:
        reason = 'too short'
    elif text[2:].startswith(('\xc3','.','!','@','_','-','~','\xe9\x9f\xbf')):
        reason = 'not for n'
    elif len(text.split('@')) > 5:
        reason = '#ff'

    if reason:
        logging.debug("IGNORE: %s: %r", reason, text)
        return True
    return False