Outlook Mac `olm` archive contact extractor

contacts-extractor.py

#!/usr/bin/env python

import re
import sys
import xml.etree.ElementTree as ET
from collections import Counter
from zipfile import ZipFile

messageRe = re.compile('.*message_[0-9]{5}\.xml')

full_email_list = []
parsedEmails = 0
name = False
debug = False
blacklist = ['reply',
             'noreply',
             'no-reply',
             'registration',
             'chime',
             'support@',
             '-beta',
             '.calendar',
             'carlsonwagonlit.com',
             'mailbox',
             'account',
             'marketing@',
             'help@',
             'sales']

with ZipFile('OutlookArchive.olm', 'r') as zipObj:
   # Get list of files names in zip
   fileList = zipObj.namelist()
   # Iterate over the list of file names in given list & print them
   for file in fileList:
       # keep only email related files
       if (messageRe.match(file)):
        message = zipObj.read(file)
        root = None
        try:
            root = ET.fromstring(message)
        except:
            print('"{0}" couldn\'t parsed'.format(file))
            print('Unexpected error:', sys.exc_info()[0])
        finally:
            for item in root.iter('emailAddress'):
                if 'OPFContactEmailAddressAddress' in item.attrib:
                    if any(to_check in item.attrib['OPFContactEmailAddressAddress'].lower() for to_check in blacklist):
                        continue
                    if 'OPFContactEmailAddressName' in item.attrib and name:
                        to_append = item.attrib['OPFContactEmailAddressName']+' <'+item.attrib['OPFContactEmailAddressAddress'].lower()+'>'
                    else:
                        to_append = item.attrib['OPFContactEmailAddressAddress'].lower()
                    full_email_list.append(to_append)
            parsedEmails += 1
            if parsedEmails == 100 and debug:
                exit()

print('Parsed emails: {0}'.format(parsedEmails))

counts = Counter(full_email_list)
counts = dict(sorted(counts.items(), key=lambda x: x[1], reverse=True))
print(counts)

with open('extract.csv', 'wb') as f:
    for key in counts.keys():
        f.write('{0},{1}\n'.format(key, counts[key]).encode('utf8'))

# make every email unique
email_list = list(set(full_email_list))

with open('extract.txt', 'wb') as f:
    f.write('\n'.join(email_list).encode('utf8'))

print('extraction completed')