├── LICENSE
├── README.md
├── gtalk_export.py
└── hangouts.py


/LICENSE:
--------------------------------------------------------------------------------
 1 | The MIT License (MIT)
 2 | 
 3 | Copyright (c) 2015 coandco
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | gtalk_export
 2 | ============
 3 | 
 4 | * Author: Clint Olson (with JSON-parsing code from [Jay2K1](http://blog.jay2k1.com/))
 5 | * License: MIT
 6 | * Meaning: Use everywhere, keep copyright, it'd be swell if you'd link back here.
 7 |  
 8 | ## Usage
 9 | _Export Google Talk/Hangouts chats to logfiles_
10 | 
11 | Uses a modified version of [Jay2K1's Takeouts parser](http://hangoutparser.jay2k1.com/) (for Hangouts chats) alongside a custom mbox parser (for older Google Talk chats made before mid-2013) to produce a single set of unified logfiles.
12 | 
13 | To use it, follow these steps:
14 | 
15 | 1. Export your Google Hangouts data using [Google Takeout](https://www.google.com/settings/takeout).  You'll be using the "Hangouts.json" file from the archive this gives you.
16 | 2. [Enable IMAP](https://support.google.com/mail/troubleshooter/1668960?hl=en#ts=1665018) on your GMail account.
17 | 3. Check the box to make Chats show up in IMAP, as detailed [here](http://readwrite.com/2011/09/16/google_liberates_gmail_chat_logs_via_imap)
18 | 4. Download your GMail IMAP chats folder ([Gmail]/Chats) using a desktop email client (script tested with Thunderbird).
19 | 5. Get the files that contain your chats. This script supports both the mbox format (one file, many "emails") and the Maildir format (one file per "email"):
20 |   - If using mbox, you can simply copy the mbox file directly from your profile directory (it may be located at `[thunderbird_profile]/ImapMail/imap.gmail.com/[Gmail].sbd/Chats`). Or you can use Thunderbird's [ImportExportTools](https://addons.mozilla.org/en-us/thunderbird/addon/importexporttools/) addon to assist in obtaining the file required.
21 |   - To use Maildir, you must enable the Maildir backend for Thunderbird. It's suggested to backup your emails first & enable maildir at the local level if you regularly use Thunderbird. Maildir can be enabled in the settings 3 different ways:
22 |     - Options - Advanced - Advanced Configuration - Message Store Type for new accounts
23 |     - Account Settings - Server Settings - Message Storage - Message Store Type
24 |     - Account Settings - Local Folders - Message Storage - Message Store Type
25 | 6. Check out this repository to a directory.
26 | 7. Run this command: `python gtalk_export.py -p <path/to/mbox_file_or_maildir_directory> -j <path/to/json_file> -n <your name> -e <your email> ` **If using mbox, add `-m` to the end of the command**
27 |  
28 | The program needs your name and email so that it knows who "you" are, and by extension who the other party is -- some of the mbox-format chats just list participants with no indication of which one is the account being parsed.  Running the command will generate a large number of .txt files in the current working directory (one for each contact you conversed with).
29 | 


--------------------------------------------------------------------------------
/gtalk_export.py:
--------------------------------------------------------------------------------
  1 | import os
  2 | import mailbox
  3 | import re
  4 | import time
  5 | import sys
  6 | import xml.dom.minidom
  7 | import HTMLParser
  8 | import argparse
  9 | import hangouts
 10 | from email.utils import parsedate
 11 | import quopri
 12 | 
 13 | def extract_date_mbox(email):
 14 |     date = email.get('Date')
 15 |     return parsedate(date)
 16 | 
 17 | def filename_sanitize(input):
 18 |     return re.sub("([^a-zA-Z0-9._-])", "_", input)
 19 | 
 20 | def make_filename_json(member_array, name, email):
 21 |     outstr = ''
 22 |     for i in member_array:
 23 |         if member_array[i] not in (name, email):
 24 |             if outstr != '':
 25 |                 outstr += "_"
 26 |             outstr += member_array[i];
 27 |     #Need to limit total filename size to 255
 28 |     return outstr[:250] + ".txt"
 29 | 
 30 | def msg_to_logline_json(message):
 31 |     return "%s <%s> %s\n" % (message['datetime'],  message['sender'], message['message'])
 32 | 
 33 | def write_to_file(filename, lines):
 34 |     '''Write a set of lines to a specified file.
 35 | 
 36 |     @param filename: path to file
 37 |     @type filename: string
 38 |     @param lines: array of log lines (strings) to write
 39 |     @type lines: [string, string, ...]
 40 |     
 41 |     '''
 42 |     with open(filename, "a") as myfile:
 43 |             myfile.write("".join(lines))
 44 | 
 45 | def parse_mailbox(mailbox_path, my_name, my_email, timestamp_format, use_mbox):
 46 |     if not use_mbox:
 47 |         mailbox_path = os.path.join(mailbox_path,"")
 48 |         if not os.path.isdir(mailbox_path + 'new'):
 49 |             os.mkdir(mailbox_path + 'new')
 50 |         if not os.path.isdir(mailbox_path + 'tmp'):
 51 |             os.mkdir(mailbox_path + 'tmp')
 52 | 
 53 |     if use_mbox:
 54 |         mbox = mailbox.mbox(mailbox_path)
 55 |     else:
 56 |         mbox = mailbox.Maildir(mailbox_path, None)
 57 |     sorted_mails = sorted(mbox, key=extract_date_mbox)
 58 | 
 59 |     # Sometimes thunderbird will produce mbox files with duplicate messages.
 60 |     # Keep track of all seen Message-ID's to prevent writing out duplicate
 61 |     # lines to the logs.
 62 |     seen_ids = set()
 63 | 
 64 |     for message in sorted_mails:
 65 |         messageobj = []
 66 | 
 67 |         # Very rarely (happened to me with only 1 message out of 25,000),
 68 |         # Thunderbird/GMail will produce a malformed message with a payload,
 69 |         # but no metadata. Just skip these, but print a warning so the user
 70 |         # can ensure that this is not happening too often.
 71 |         if len(message.keys()) == 0:
 72 |             print("Warning: Skipping malformed message")
 73 |             continue
 74 | 
 75 |         # Skip duplicates
 76 |         if message['Message-ID'] in seen_ids:
 77 |             continue
 78 |         seen_ids.add(message['Message-ID'])
 79 | 
 80 |         name = re.sub("Chat with ", "", message['subject'])
 81 | 
 82 |         payload = message.get_payload()
 83 |         if type(payload) is str:
 84 |             # We're in one of the new hybrid-style single-use messages
 85 | 
 86 |             # Some (but not all) of these messages use quoted-printable
 87 |             # encoding (which uses = as an escape character).
 88 |             # The remainder are encoded with 7bit ASCII, which must not
 89 |             # be decoded, because treating = as an escape causes havoc.
 90 |             if message['Content-Transfer-Encoding'] == 'quoted-printable':
 91 |                 payload = quopri.decodestring(payload)
 92 |                 payload = payload.decode('utf-8')
 93 |             payload = payload.strip()
 94 |             to_name = re.sub(" <[^>]*>", "", message.get('To'))
 95 |             from_name = re.sub(" <[^>]*>", "", message.get('From'))
 96 |             if not name:
 97 |                 name = to_name if to_name != my_name else from_name
 98 |             rawtimestr = message.get('Date')
 99 |             timestamp = time.strftime(timestamp_format, parsedate(rawtimestr))
100 |             
101 |             pars = HTMLParser.HTMLParser()
102 |             outline = "%s <%s> %s\n" % (timestamp, from_name, pars.unescape(payload))
103 |             messageobj.append(outline.encode('utf-8'))
104 |         else:
105 |             #We're in an old Google Talk Jabber conversation message
106 | 
107 |             payload = payload[0].as_string()
108 |             # Seemingly all of these messages use quoted-printable encoding,
109 |             # even though 'Content-Transfer-Encoding' is never set.
110 |             payload = quopri.decodestring(payload)
111 |             payload = payload.decode('utf-8')
112 |             # The emails have a couple of chaff lines before the XML starts
113 |             payload = re.sub(r'^[^<]*<', "<", payload)
114 | 
115 |             chatxml = xml.dom.minidom.parseString(payload.encode('utf-8'))
116 |             
117 |             for messagexml in chatxml.getElementsByTagName("cli:message"):
118 |                 speaker = messagexml.getAttribute("from")
119 |                 rawtimestr = messagexml.getElementsByTagName("time")[0].getAttribute("ms")
120 |                 timefloat = float(rawtimestr[:-3] + "." + rawtimestr[-3:])
121 |                 timestamp = time.strftime(timestamp_format,time.localtime(timefloat))
122 |                 try:
123 |                     content = messagexml.getElementsByTagName("cli:body")[0].firstChild.data
124 |                 except AttributeError:
125 |                     # No 'data' element means that it's an empty message
126 |                     content = ""
127 |                 except IndexError:
128 |                     # No "cli:body" elements means that it's a non-message event,
129 |                     # like a time-gap or user-unavailable message
130 |                     continue
131 |                 outline = "%s <%s> %s\n" % (timestamp, speaker, content)
132 |                 messageobj.append(outline.encode('utf-8'))
133 | 
134 |         write_to_file("%s.txt" % filename_sanitize(name)[:250], messageobj)
135 | 
136 | def parse_json(json_path, name, email, timestamp_format):
137 |     with open(json_path, "r") as myfile:
138 |         mydata=myfile.read()
139 | 
140 |     conversations = hangouts.hangoutsToArray(mydata, timestamp_format)
141 | 
142 |     print("JSON file first pass completed.  Writing to logfiles...")
143 | 
144 |     for conversation in conversations:
145 |         filename = filename_sanitize(make_filename_json(conversation['members'],
146 |                                                         name, email))
147 |         messageobj = []
148 |         for message in conversation['messages']:
149 |             messageobj.append(msg_to_logline_json(message).encode("UTF-8"))
150 |         write_to_file(filename, messageobj)
151 | 
152 | parser = argparse.ArgumentParser(prog="gtalk_export")
153 | parser.add_argument("-p", "--mailbox-path",
154 |                     required=False,
155 |                     default=None,
156 |                     help="The location of the IMAP Maildir or mbox to parse")
157 | parser.add_argument("-j", "--json-path",
158 |                     required=False,
159 |                     default=None,
160 |                     help="The location of the Takeouts JSON to parse")
161 | parser.add_argument("-n", "--name",
162 |                     required=True,
163 |                     help="The chat participant name whose files are being parsed")
164 | parser.add_argument("-e", "--email",
165 |                     required=True,
166 |                     help="The chat participant email whose files are being parsed")
167 | parser.add_argument("-t", "--timestamp-format",
168 |                     required=False,
169 |                     default='%Y-%m-%d %H:%M:%S',
170 |                     help="Timestamp format to display in output logs")
171 | parser.add_argument("-m", "--mbox",
172 |                     action='store_true',
173 |                     help="Use mbox instead of Maildir")                    
174 |                     
175 | 
176 | args = parser.parse_args()
177 | 
178 | if args.mailbox_path is None and args.json_path is None:
179 |     sys.exit("No mbox or JSON provided -- nothing to do!")
180 | 
181 | if args.mailbox_path:
182 |     print("Processing mailbox at %s" % args.mailbox_path)
183 |     parse_mailbox(args.mailbox_path, args.name, args.email, args.timestamp_format, args.mbox)
184 |     print("Finished processing mailbox")
185 | 
186 | if args.json_path:
187 |     print("Processing json file at %s" % args.json_path)
188 |     parse_json(args.json_path, args.name, args.email, args.timestamp_format)
189 |     print("Finished processing json file")
190 | 
191 | print("GTalk/Hangouts export completed!")
192 | 


--------------------------------------------------------------------------------
/hangouts.py:
--------------------------------------------------------------------------------
  1 | import re
  2 | import json
  3 | import time
  4 | 
  5 | # This code was inspired by Jay2K1's Hangouts parser.  You can see the 
  6 | # blogpost for the original at:
  7 | # http://blog.jay2k1.com/2014/11/10/how-to-export-and-backup-your-google-hangouts-chat-history/
  8 | # He also runs a webservice for parsing Google Hangouts JSON files at:
  9 | # http://hangoutparser.jay2k1.com/
 10 | 
 11 | def replaceSmileys(string):
 12 |     # replaces UTF-8 graphical emoticons by their ASCII equivalents
 13 |     # list of emoji codes taken from https://aprescott.com/posts/hangouts-emoji
 14 |     patterns = [
 15 |         u'\U0001F41D',         # -<@% ?       honeybee
 16 |         u'\U0001F435',         # :(|) ?       monkey face
 17 |         u'\U0001F437',         # :(:) ?       pig face
 18 |         u'\U0001F473',         # (]:{ ?       man with turban
 19 |         u'\U0001F494',         # <\3 </3      ?       broken heart
 20 |         u'\U0001F49C',         # <3   ?       purple heart
 21 |         u'\U0001F4A9',         # ~@~  ?       pile of poo
 22 |         u'\U0001F600',         # :D :-D       ?       grinning face
 23 |         u'\U0001F601',         # ^_^  ?       grinning face with smiling eyes
 24 |         u'\U0001F602',         # XD
 25 |         u'\U0001F603',         # :) :-) =)    ?       smiling face with open mouth
 26 |         u'\U0001F604',         # =D   ?       smiling face with open mouth and smiling eyes
 27 |         u'\U0001F605',         # ^_^;;        ?       smiling face with open mouth and cold sweat
 28 |         u'\U0001F607',         # O:) O:-) O=) ?       smiling face with halo
 29 |         u'\U0001F608',         # }:) }:-) }=) ?       smiling face with horns
 30 |         u'\U0001F609',         # ;) ;-)       ?       winking face
 31 |         u'\U0001F60E',         # B) B-)       ?       smiling face with sunglasses
 32 |         u'\U0001F610',         # :-| :| =|    ?       neutral face
 33 |         u'\U0001F611',         # -_-  ?       expressionless face
 34 |         u'\U0001F613',         # o_o; ?       face with cold sweat
 35 |         u'\U0001F614',         # u_u  ?       pensive face
 36 |         u'\U0001F615',         # :\ :/ :-\ :-/ =\ =/  ?       confused face
 37 |         u'\U0001F616',         # :S :-S :s :-s        ?       confounded face
 38 |         u'\U0001F617',         # :* :-*       ?       kissing face
 39 |         u'\U0001F618',         # ;* ;-*       ?       face throwing a kiss
 40 |         u'\U0001F61B',         # :P :-P =P :p :-p =p  ?       face with stuck-out tongue
 41 |         u'\U0001F61C',         # ;P ;-P ;p ;-p        ?       face with stuck-out tongue and winking eye
 42 |         u'\U0001F61E',         # :( :-( =(    ?       disappointed face
 43 |         u'\U0001F621',         # >.< >:( >:-( >=(     ?       pouting face
 44 |         u'\U0001F622',         # T_T :'( ;_; ='(      ?       crying face
 45 |         u'\U0001F623',         # >_<  ?       persevering face
 46 |         u'\U0001F626',         # D:   ?       frowning face with open mouth
 47 |         u'\U0001F62E',         # o.o :o :-o =o        ?       face with open mouth
 48 |         u'\U0001F632',         # O.O :O :-O =O        ?       astonished face
 49 |         u'\U0001F634',         # O.O :O :-O =O        ?       astonished face
 50 |         u'\U0001F635',         # x_x X-O X-o X( X-(   ?       dizzy face
 51 |         u'\U0001F638',         # :X) :3 (=^..^=) (=^.^=) =^_^=        ?       grinning cat face with smiling eyes
 52 |         u'\U0001F64C'          # Dunno, but it needs to be replaced for ASCII
 53 |     ]
 54 |     replacements = [
 55 |         '-<@%',
 56 |         ':(|)',
 57 |         ':(:)',
 58 |         '(]:{',
 59 |         '</3',
 60 |         '<3',
 61 |         '~@~',
 62 |         ':D',
 63 |         '^_^',
 64 |         'XD',
 65 |         ':)',
 66 |         '=D',
 67 |         '^_^;;',
 68 |         'O:)',
 69 |         '}:)',
 70 |         ';)',
 71 |         'B-)',
 72 |         ':|',
 73 |         '-_-',
 74 |         'o_o;',
 75 |         'u_u',
 76 |         ':/',
 77 |         ':S',
 78 |         ':*',
 79 |         ';*',
 80 |         ':P',
 81 |         ';P',
 82 |         ':(',
 83 |         '>.<',
 84 |         ":'(",
 85 |         '>_<',
 86 |         'D:',
 87 |         ':o',
 88 |         ':O',
 89 |         '-_-Zzz',
 90 |         'x_x',
 91 |         ':3',
 92 |         '_'
 93 |     ]
 94 | 
 95 |     for index in range(len(patterns)):
 96 |         string = re.sub(patterns[index], replacements[index], string)
 97 |     return string
 98 | 
 99 | def hangoutsToArray(json_input, timestamp_format):
100 |     # set the desired timestamp format here
101 |     # the default is '%Y-%m-%d %H:%M:%S' which is YYYY-MM-DD HH:mm:ss.
102 |     #timestamp_format = '%Y-%m-%d %H:%M:%S'
103 | 
104 |     # decode JSON
105 |     decoded = json.loads(json_input)
106 |     # extract useful part
107 |     rawconvos = decoded['conversations']
108 |     #print "%r" % rawconvos
109 |     retval = []
110 |     # loop through conversations
111 |     for i in range(len(rawconvos)):
112 |         #print "i is %d" % i
113 |         #print "attempting in_conv: %s" % rawconvos[i]['conversation_state']['conversation']
114 |         # first, get metadata
115 |         retval.append({})
116 |         convo = rawconvos[i]
117 |         #print "%r" % convo
118 |         in_conv = rawconvos[i]['conversation']['conversation']
119 |         in_event = rawconvos[i]['events']
120 |         pdata = in_conv['participant_data']
121 |         retval[i]['type'] = in_conv['type']
122 |         retval[i]['msgcount'] = len(in_event)
123 |         retval[i]['name'] = in_conv['name'] if 'name' in in_conv.keys() else ""
124 |         # conversation participants
125 |         for j in range(len(pdata)):
126 |             id = pdata[j]['id']['chat_id']
127 |             # use "unknown_<chat_id>" as name if they don't have a fallback_name
128 |             name = pdata[j]['fallback_name'] if 'fallback_name' in pdata[j].keys() else "unknown_%s" % id
129 |             if not 'members' in retval[i].keys():
130 |                 retval[i]['members'] = {}
131 |             retval[i]['members'][id] = name
132 | 
133 |         # loop through messages/events
134 |         messages = []
135 |         for k in range(len(in_event)):
136 |             messages.append({})
137 |             messages[k]['timestamp'] = in_event[k]['timestamp']
138 |             messages[k]['datetime'] = time.strftime(timestamp_format,time.localtime(int(messages[k]['timestamp'][0:10])))
139 |             messages[k]['sender_id'] = in_event[k]['sender_id']['chat_id']
140 |             messages[k]['sender'] = retval[i]['members'][messages[k]['sender_id']] if messages[k]['sender_id'] in retval[i]['members'].keys() else "unknown_%s" % id
141 |             messages[k]['event_type'] = in_event[k]['event_type']
142 | 
143 |             if messages[k]['event_type'] == 'RENAME_CONVERSATION':
144 |                 newname = in_event[k]['conversation_rename']['new_name']
145 |                 oldname = in_event[k]['conversation_rename']['old_name']
146 |                 messages[k]['message'] = "changed conversation name %s%s" % \
147 |                                          (("from '%s'" % oldname) if oldname else "", 
148 |                                           ("to '%s'" % newname) if newname else "")
149 |             elif messages[k]['event_type'] == 'HANGOUT_EVENT':
150 |                 if in_event[k]['hangout_event']['event_type'] == 'START_HANGOUT':
151 |                     messages[k]['message'] = 'started a video chat'
152 |                 elif in_event[k]['hangout_event']['event_type'] == 'END_HANGOUT':
153 |                     messages[k]['message'] = 'ended a video chat'
154 |                 else:
155 |                     messages[k]['message'] = in_event[k]['hangout_event']['event_type']
156 |             elif messages[k]['event_type'] == 'REGULAR_CHAT_MESSAGE':
157 |                 messages[k]['message'] = ""
158 |                 msg = ""
159 |                 msghtml = ""
160 |                 # join message segments together
161 |                 if 'segment' in in_event[k]['chat_message']['message_content'].keys():
162 |                     for event in in_event[k]['chat_message']['message_content']['segment']:
163 |                         if not 'text' in event.keys():
164 |                             continue
165 |                         if event['type'] == 'TEXT':
166 |                             msg += event['text']
167 |                             msghtml += re.sub("\n", "<br>", event['text'])
168 |                         elif event['type'] == 'LINK':
169 |                             msg += event['text']
170 |                             msghtml += '<a href="%s" target="_blank">%s</a>' % (event['link_data']['link_target'], event['text'])
171 |                         elif event['type'] == 'LINE_BREAK':
172 |                             msg += event['text']
173 |                             msghtml += re.sub("\n", "<br>", event['text'])
174 |                 # handle attachments
175 |                 elif 'attachment' in in_event[k]['chat_message']['message_content'].keys():
176 |                     # loop through attachments
177 |                     for att in in_event[k]['chat_message']['message_content']['attachment']:
178 |                         # echo "<pre>";print_r($att);echo "</pre>";
179 |                         if att['embed_item']['type'][0] == 'PLUS_PHOTO':
180 |                             imgurl = att['embed_item']['plus_photo']['url']
181 |                             msg += imgurl
182 |                             msghtml += '<a href="%s" target="_blank"><img src="%s" alt="attached image" style="max-width:%s"></a>' % (imgurl, imgurl, "100%")
183 |                 # replace unicode emoticon characters by smileys
184 |                 messages[k]['message'] = replaceSmileys(msg)
185 |                 if msg != msghtml:
186 |                     messages[k]['message_html'] = replaceSmileys(msghtml)
187 |             elif messages[k]['event_type'] == 'ADD_USER':
188 |                 newuserid = in_event[k]['membership_change']['participant_id'][0]['chat_id']
189 |                 newusername = retval[i]['members'][newuserid] if newuserid in retval[i]['members'].keys() else 'unknown_%s' % newuserid
190 |                 messages[k]['message'] = "added user '%s' to conversation" % newusername
191 |             elif messages[k]['event_type'] == 'REMOVE_USER':
192 |                 newuserid = in_event[k]['membership_change']['participant_id'][0]['chat_id']
193 |                 newusername = retval[i]['members'][newuserid] if newuserid in retval[i]['members'].keys() else 'unknown_%s' % newuserid
194 |                 messages[k]['message'] = "removed user '%s' from conversation" % newusername
195 |             elif messages[k]['event_type'] == 'SMS':
196 |                 messages[k]['message'] = ""
197 |                 # join message segments together
198 |                 if 'segment' in in_event[k]['chat_message']['message_content'].keys():
199 |                     for l in range(len(in_event[k]['chat_message']['message_content']['segment'])):
200 |                         if not 'text' in in_event[k]['chat_message']['message_content']['segment'][l].keys():
201 |                             continue
202 |                         messages[k]['message'] += in_event[k]['chat_message']['message_content']['segment'][l]['text']
203 |                 # replace unicode emoticon characters by smileys
204 |                 messages[k]['message'] = replaceSmileys(messages[k]['message'])
205 |             elif messages[k]['event_type'] == 'OTR_MODIFICATION':
206 |                 messages[k]['message'] = 'unknown OTR_MODIFICATION'
207 |             elif messages[k]['event_type'] == 'VOICEMAIL':
208 |                 messages[k]['message'] = "new voicemail:\n"
209 |                 # join message segments together
210 |                 if 'segment' in in_event[k]['chat_message']['message_content'].keys():
211 |                     for l in range(len(in_event[k]['chat_message']['message_content']['segment'])):
212 |                         if not 'text' in in_event[k]['chat_message']['message_content']['segment'][l].keys():
213 |                             continue
214 |                         messages[k]['message'] += in_event[k]['chat_message']['message_content']['segment'][l]['text']
215 |                 # replace unicode emoticon characters by smileys
216 |                 messages[k]['message'] = replaceSmileys(messages[k]['message'])
217 |         # sort messages by timestamp because for some reason they're cluttered
218 |         messages.sort(cmp=lambda a,b: int(a['timestamp']) - int(b['timestamp']))
219 |         # add the messages array to the conversation array
220 |         retval[i]['messages'] = messages
221 |     return retval
222 | 


--------------------------------------------------------------------------------