You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
93 lines
2.8 KiB
Python
93 lines
2.8 KiB
Python
#!/usr/bin/python
|
|
|
|
import os, argparse, hashlib, email, email.header, email.utils, glob
|
|
|
|
parser = argparse.ArgumentParser(description='Parses emails into an SQLite database and an attachment folder.')
|
|
|
|
parser.add_argument('-p', dest='pattern', action='store', default='*',
|
|
help='glob pattern (including path) that has to be matched for a file to be parsed')
|
|
|
|
parser.add_argument('-I', '--ignore-invalid', dest='ignore_invalid', action='store_true',
|
|
help='process invalid e-mail files anyway, for example when missing message-id headers')
|
|
|
|
args = parser.parse_args()
|
|
options = vars(args)
|
|
|
|
def getheader(header_text, default="ascii"):
|
|
headers = email.header.decode_header(header_text)
|
|
try:
|
|
header_sections = [unicode(text, charset or default) for text, charset in headers]
|
|
except UnicodeDecodeError:
|
|
header_sections = [unicode(text, 'windows-1252') for text, charset in headers]
|
|
except LookupError:
|
|
return u""
|
|
|
|
return u"".join(header_sections)
|
|
|
|
def find_submessages(message):
|
|
if message.is_multipart():
|
|
return [find_submessages(part) for part in message.get_payload()]
|
|
else:
|
|
return message
|
|
|
|
def flatten(x):
|
|
# http://kogs-www.informatik.uni-hamburg.de/~meine/python_tricks
|
|
result = []
|
|
for el in x:
|
|
if hasattr(el, "__iter__") and not isinstance(el, basestring):
|
|
result.extend(flatten(el))
|
|
else:
|
|
result.append(el)
|
|
return result
|
|
|
|
def get_charset(part):
|
|
charset = None
|
|
|
|
if part.get_content_charset():
|
|
charset = part.get_content_charset()
|
|
elif part.get_charset():
|
|
charset = part.get_charset()
|
|
|
|
if charset is None or charset == "default" or charset.startswith("us-ascii"):
|
|
return "ascii"
|
|
else:
|
|
return charset
|
|
|
|
# Select all files matching the given pattern
|
|
file_list = glob.glob(options['pattern'])
|
|
|
|
finished = 0
|
|
|
|
for email_file in file_list:
|
|
# To save time when updating a database, let's first check whether the filename is already present in the database as a hash.
|
|
# There is no need to check for the format here, since if the filename is not a valid hash, it simply won't match anything.
|
|
|
|
message = email.message_from_file(open(email_file, 'r'))
|
|
|
|
if message['message-id'] is None:
|
|
if options['ignore_invalid'] == True:
|
|
message_id = ""
|
|
print "WARNING: %s does not contain a valid message-id header. Empty message-id assumed." % email_file
|
|
else:
|
|
print "%s is not a valid e-mail file." % email_file
|
|
finished += 1
|
|
continue
|
|
else:
|
|
message_id = message['message-id']
|
|
|
|
if 'subject' not in message or message['subject'] is None:
|
|
subject = ""
|
|
else:
|
|
subject = message['subject']
|
|
|
|
sha1_hash = hashlib.sha1("%s/%s/%s/%s" % (message['from'], message['to'], message_id, subject)).hexdigest()
|
|
|
|
new_path = "%s/%s.eml" % (os.path.dirname(email_file), sha1_hash)
|
|
|
|
os.rename(email_file, new_path)
|
|
print "%s -> %s" % (email_file, new_path)
|
|
|
|
finished += 1
|
|
|
|
print "Renamed %d files." % finished
|