1 # Copyright (C) 2012 W. Trevor King <wking@drexel.edu>
3 # This file is part of pygrader.
5 # pygrader is free software: you can redistribute it and/or modify it under the
6 # terms of the GNU General Public License as published by the Free Software
7 # Foundation, either version 3 of the License, or (at your option) any later
10 # pygrader is distributed in the hope that it will be useful, but WITHOUT ANY
11 # WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
12 # A PARTICULAR PURPOSE. See the GNU General Public License for more details.
14 # You should have received a copy of the GNU General Public License along with
15 # pygrader. If not, see <http://www.gnu.org/licenses/>.
17 """Extract message parts with a given MIME type from a mailbox.
20 from __future__ import absolute_import
22 import email.utils as _email_utils
23 import hashlib as _hashlib
24 import mailbox as _mailbox
26 import os.path as _os_path
29 from . import LOG as _LOG
30 from .color import color_string as _color_string
31 from .color import standard_colors as _standard_colors
34 def message_time(message, use_color=None):
35 """Get the Unix time when ``message`` was received.
37 >>> from email.utils import formatdate
38 >>> from pgp_mime.email import encodedMIMEText
39 >>> msg = encodedMIMEText('Ping!')
40 >>> msg['Received'] = (
41 ... 'from smtp.home.net (smtp.home.net [123.456.123.456]) '
42 ... 'by smtp.mail.uu.edu (Postfix) with ESMTP id 5BA225C83EF '
43 ... 'for <wking@tremily.us>; Sun, 09 Oct 2011 11:50:46 -0400 (EDT)')
44 >>> time = message_time(msg)
48 'Sun, 09 Oct 2011 15:50:46 -0000'
50 highlight,lowlight,good,bad = _standard_colors(use_color=use_color)
51 received = message['Received'] # RFC 822
53 mid = message['Message-ID']
54 _LOG.debug(_color_string(
55 string='no Received in {}'.format(mid), color=lowlight))
57 date = received.split(';', 1)[1]
58 return _time.mktime(_email_utils.parsedate(date))
60 def extract_mime(message, mime_type=None, output='.', dry_run=False):
61 _LOG.debug('parsing {}'.format(message['Subject']))
62 time = message_time(message=message)
63 for part in message.walk():
64 fname = part.get_filename()
66 continue # don't extract parts without filenames
67 ffname = _os_path.join(output, fname) # full file name
68 ctype = part.get_content_type()
69 if mime_type is None or ctype == mime_type:
70 contents = part.get_payload(decode=True)
74 while _os_path.exists(ffname):
75 old = _hashlib.sha1(open(ffname, 'rb').read())
76 new = _hashlib.sha1(contents)
77 if old.digest() == new.digest():
81 ffname = '{}.{}'.format(base_ffname, count)
83 _LOG.debug('{} already extracted as {}'.format(fname, ffname))
85 _LOG.debug('extract {} to {}'.format(fname, ffname))
87 with open(ffname, 'wb') as f:
90 _os.utime(ffname, (time, time))