update readme

README.md

@@ -11,12 +11,19 @@
 
 #### Get Necessary Data:
 + Get /data/data/com.tencent.mm/MicroMsg/long-long-name/EnMicroMsg.db from root filesystem, possible ways are:
-	+ `adb root`, `adb pull /xxx/xxx.db`
+	+ `adb root`, `adb pull /data/data/com.tencent.mm/MicroMsg/long-long-name/EnMicroMsg.db`
 	+ Use your rooted file system manager app
-+ Get WeChat user resource directory from user filesystem, for example: sdcard:/tencent/MicroMsg/long-long-name. (could be different)
++ Get WeChat user resource directory from user filesystem, possibly at: /mnt/sdcard/tencent/MicroMsg/long-long-name:
+	+ adb pull /mnt/sdcard/tencent/MicroMsg/long-long-name
 + Get Wechat uin, possible ways are:
 	+ Login to [web-based wechat](https://wx.qq.com); get wxuin=1234567 from `document.cookie`
-	+ Get ``default_uin`` from /data/data/com.tencent.mm/shared_prefs/system_config_prefs.xml.
+	+
+```
+adb pull /data/data/com.tencent.mm/shared_prefs/system_config_prefs.xml
+grep 'default_uin' system_config_prefs.xml | grep -o 'value="[0-9]*' | cut -c 8-
+```
+
+
 + Get phone IMEI, possible ways are:
 	+ Call `*#06#` on your phone
 	+ Find IMEI in system settings
@@ -37,9 +44,8 @@
 ```
 
 ### TODO
-+ Parse uncommon message types
-+ Separate messages into multiple html files
 + Group message
++ Change max size for custom emoji
 + Fix smiley spacing in html
 + Show name of emoji in text output
 + Search by uid/username..

lib/msg.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: msg.py
-# Date: Mon Dec 22 23:04:02 2014 +0800
+# Date: Wed Dec 24 22:00:42 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 from datetime import datetime
@@ -51,7 +51,7 @@ class WeChatMsg(object):
                     label = poiname
             except:
                 pass
-            return label + " ({},{})".format(loc['x'], loc['y'])
+            return "LOCATION:" + label + " ({},{})".format(loc['x'], loc['y'])
         elif self.type == TYPE_VOIP:
             return "REQUEST VIDEO CHAT"
         elif self.type == TYPE_LINK:

lib/msgslice.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: msgslice.py
-# Date: Mon Dec 22 23:56:55 2014 +0800
+# Date: Wed Dec 24 22:06:41 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 class MessageSlicerByTime(object):
@@ -52,7 +52,7 @@ class MessageSlicerBySize(object):
                     now = [m]
                     continue
             now.append(m)
-        if len(now) > self.size / 2:
+        if len(now) > self.size / 2 or len(ret) == 0:
             ret.append(now)
         else:
             ret[-1].extend(now)

lib/smiley.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: smiley.py
-# Date: Mon Dec 22 16:50:15 2014 +0800
+# Date: Wed Dec 24 22:16:33 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import os
@@ -13,7 +13,8 @@ UNICODE_SMILEY_FILE = os.path.join(LIB_PATH, 'static', 'unicode-smiley.json')
 TENCENT_SMILEY_FILE = os.path.join(LIB_PATH, 'static', 'tencent-smiley.json')
 TENCENT_EXTRASMILEY_FILE = os.path.join(LIB_PATH,
                                        'static', 'tencent-smiley-extra.json')
-UNICODE_SMILEY_RE = re.compile(u'[\U00010000-\U0010ffff]|[\u2600-\u2764]|\u2122|\u00a9|\u00ae')
+UNICODE_SMILEY_RE = re.compile(
+    u'[\U00010000-\U0010ffff]|[\u2600-\u2764]|\u2122|\u00a9|\u00ae|[\ue000-\ue5ff]')
 
 class SmileyProvider(object):
     def __init__(self, html_replace=True):
@@ -36,9 +37,13 @@ class SmileyProvider(object):
         # 1f35c -> "\ue340"
         #self.unicode_smiley_code = gUnicodeCodeMap
 
-        # u'\U0001f35c' -> "e340"
+        # u'\U0001f35c' -> "e340"   # for iphone
+        # u'\ue415' -> 'e415'       # for android
+        unicode_smiley_dict = json.load(open(UNICODE_SMILEY_FILE))
         self.unicode_smiley = {unichr(int(k, 16)): hex(ord(v))[2:] for k, v in
-                                  json.load(open(UNICODE_SMILEY_FILE)).iteritems()}
+                                unicode_smiley_dict.iteritems()}
+        self.unicode_smiley.update({v: hex(ord(v))[2:] for _, v in
+                                unicode_smiley_dict.iteritems()})
         self.used_smiley_id = set()
 
 
@@ -75,6 +80,6 @@ class SmileyProvider(object):
 
 if __name__ == '__main__':
     smiley = SmileyProvider()
-    msg = u"[挥手]哈哈呵呵ｈｉｈｉ\U0001f684\u2728\u0001 /::<"
+    msg = u"[挥手]哈哈呵呵ｈｉｈｉ\U0001f684\u2728\u0001 /::<\ue415"
     msg = smiley.replace_smileycode(msg)
     print msg

lib/static/gen_smiley_css.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: gen_smiley_css.py
-# Date: Mon Dec 22 21:44:00 2014 +0800
+# Date: Wed Dec 24 22:20:08 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import os
@@ -13,7 +13,7 @@ OUTPUT_FILE = os.path.join(DIR_PATH, 'smiley.css')
 
 HEAD = """.smiley {
     padding: 1px;
-    background-position: 0px -2px;
+    background-position: -1px -1px;
     background-repeat: no-repeat;
     width: 20px;
     height: 20px;

lib/static/smileys/down2.sh

@@ -1,16 +1,16 @@
 #!/bin/bash -e
 # File: down2.sh
-# Date: Sun Dec 14 01:18:45 2014 +0800
+# Date: Wed Dec 24 22:31:37 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 # This script is used to download unicode emoji
 
-emojis=$(cat ../../emojiname.py | grep -o '\\ue[^"]*' | cut -c 3-)
+emojis=$(cat ../unicode-smiley.json | grep -o '\\ue[^"]*' | cut -c 3-)
 for i in $emojis; do
 	size=$(wc -c "$i.png" 2>/dev/null | cut -f 1 -d ' ')
 	if [[ -n "$size" && $size -ge 0 ]]; then
 		echo "File $i Already There!"
 	else
-		wget http://www.easyapns.com/emoji/$i.png
+		wget http://www.easyapns.com/emoji/$i.png &
 	fi
 done