#!/usr/bin/env python

"""Strip mail box of attachements and extrax junk

Usage: mailarch [options] msgfile

Options:
    -h / --help
        Print this message and exit.

msgfile is the path to the file containing the MIME message.

Usage mailarch mbox > mi2004sc.txt

python ~/play/python/mailarch.py ~/Library/Mail/Mailboxes/shortlist.mbox/mbox > /tmp/mi200YMs.txt
python ~/play/python/mailarch.py ~/Library/Mail/POP-jchatjch@mail.earthlink.net/INBOX.mbox/mbox  > /tmp/mi200YM.txt
python ~/play/python/mailarch.py ~/Library/Mail/POP-jchatjch@mail.earthlink.net/Sent\ Messages.mbox/mbox  > /tmp/mo200YM.txt

"""

import sys
import os
import getopt
import errno
import mimetypes
import email
import email.Errors
import mailbox
import formatter, time

def usage(code, msg=''):
    print >> sys.stderr, __doc__
    if msg:
        print >> sys.stderr, msg
    sys.exit(code)

def msgfactory(fp):
    try:
        return email.message_from_file(fp)
    except email.Errors.MessageParseError:
        # Don't return None since that will
        # stop the mailbox iterator
        return ''

def main():
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'hd:', ['help', 'directory='])
    except getopt.error, msg:
        usage(1, msg)

    dir = os.curdir
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-d', '--directory'):
            dir = arg

    try:
        msgfile = args[0]
    except IndexError:
        usage(1)

    fp = open(msgfile)
    # msg = email.message_from_file(fp)
    mbox = mailbox.UnixMailbox(fp, msgfactory)

    msg = mbox.next()
    print "Cleaning %s with mailarch.py on %s"%(msgfile, time.strftime("%a, %d %b %Y %H:%M:%S +0000", time.gmtime(time.time())))
    counter = 1
    while msg is not None:
        print "\n=== msg %d %s\n"%(counter, msg.get_unixfrom())
        if msg.is_multipart():
            # print msg.keys()
            if msg.has_key('From'):
                print 'From: '+msg.get('From')
            if msg.has_key('To'):
                print 'To: '+msg.get('To')               
            if msg.has_key('CC'):
                print 'CC: '+msg.get('CC')               
            if msg.has_key('Date'):
                print 'Date: '+msg.get('Date')
            if msg.has_key('Subject'):
                print 'Subject: '+msg.get('Subject')
            if msg.has_key('Reply-To'):
                print 'Reply-To: '+msg.get('Reply-To')

            haveText = False
            skipped = ' '
            for part in msg.walk():
                if part.get_content_type() == 'text/plain':
                    haveText = True
                else:
                    skipped = skipped + ' ' + part.get_content_type()
                    
            if haveText == False:
                print "!!  No test/plain !!" + skipped
            else:
                print "       ** MIME Multipart - skipped others :%s\n"%(skipped)
            
            for part in msg.walk():
                if haveText:
                    if part.get_content_type() == 'text/plain':
                        print part.get_payload()
                        something = True                                                
                else:
                    if part.get_content_maintype() == 'text':
                        print part
                        something = True
        else:
            print msg.as_string(True)
            something = True
        counter += 1
        msg = mbox.next()

    fp.close()
if __name__ == '__main__':
    main()