群聊显示具体的发送人。

pywxdump/__init__.py

@@ -7,7 +7,7 @@
 # -------------------------------------------------------------------------------
 from .wx_info import BiasAddr,read_info, get_wechat_db,encrypt,batch_decrypt,decrypt
 from .wx_info import  merge_copy_db, merge_msg_db, merge_media_msg_db
-from .analyzer.db_parsing import read_img_dat, read_emoji, decompress_CompressContent, read_audio_buf, read_audio, parse_xml_string
+from .analyzer.db_parsing import read_img_dat, read_emoji, decompress_CompressContent, read_audio_buf, read_audio, parse_xml_string,read_BytesExtra
 from .ui import app_show_chat, get_user_list, export
 
 import os,json

pywxdump/analyzer/__init__.py

@@ -5,4 +5,4 @@
 # Author:       xaoyaoo
 # Date:         2023/09/27
 # -------------------------------------------------------------------------------
-from .db_parsing import read_img_dat, read_emoji, decompress_CompressContent, read_audio_buf, read_audio, parse_xml_string
+from .db_parsing import read_img_dat, read_emoji, decompress_CompressContent, read_audio_buf, read_audio, parse_xml_string,read_BytesExtra

pywxdump/analyzer/db_parsing.py

@@ -153,11 +153,13 @@ def decompress_CompressContent(data):
     """
     if data is None or not isinstance(data, bytes):
         return None
-
+    try:
         dst = lz4.block.decompress(data, uncompressed_size=len(data) << 8)
-    dst.decode().replace('\x00', '')  # 已经解码完成后，还含有0x00的部分，要删掉，要不后面ET识别的时候会报错
+        dst.decode().replace(b'\x00', '')  # 已经解码完成后，还含有0x00的部分，要删掉，要不后面ET识别的时候会报错
-    uncompressed_data = dst.encode('utf-8', errors='ignore')
+        uncompressed_data = dst.decode('utf-8', errors='ignore')
         return uncompressed_data
+    except Exception as e:
+        return data.decode('utf-8', errors='ignore')
 
 
 def read_audio_buf(buf_data, is_play=False, is_wave=False, rate=24000):
@@ -257,13 +259,13 @@ def read_BytesExtra(BytesExtra):
 
 
 if __name__ == '__main__':
-    DB = sqlite3.connect(r"D:\_code\py_code\test\a2023\b0821wxdb\merge_wfwx_db\kkWxMsg\MSG_all.db")
+    DB = sqlite3.connect(r"D:\_code\py_code\test\a2023\b0821wxdb\merge_wfwx_db\hwfWxMsg\MSG_all.db")
     cursor = DB.cursor()
-    sql = "select MsgSvrID,BytesExtra from MSG where BytesExtra is not null and StrTalker='24724392255@chatroom' order by CreateTime desc limit 10"
+    sql = "select MsgSvrID,CompressContent from MSG where MSG.MsgSvrID=5379391128928795712"
     DBdata = cursor.execute(sql).fetchall()
     for i in DBdata:
-        MsgSvrID, BytesExtra = i
+        MsgSvrID, CompressContent = i
-        data = read_BytesExtra(BytesExtra)
+        data = decompress_CompressContent(CompressContent)
         # 提取特定键的信息
         print(MsgSvrID,"\n",data)
         print("-" * 64)

pywxdump/ui/templates/chat.html

@@ -22,7 +22,7 @@
                     {% if msg.is_sender == 1 %}
                     <div style="background-color: #f3e9c1;">
 
-                        <label style="color:#A13A50">[发][{{msg.type_name}}] {{msg.CreateTime}}</label><br>
+                        <label style="color:#A13A50">[{{msg.talker}}][{{msg.type_name}}] {{msg.CreateTime}}</label><br>
 
                         {% if msg.type_name == '语音' %}
                         <audio controls>
@@ -39,7 +39,7 @@
                     </div>
                     {% else %}
                     <div style="background-color: #d3eed3">
-                        <label style="color:#f54f71">[收][{{msg.type_name}}] {{msg.CreateTime}}</label><br>
+                        <label style="color:#f54f71">[{{msg.talker}}][{{msg.type_name}}] {{msg.CreateTime}}</label><br>
 
                         {% if msg.type_name == '语音' %}
                         <audio controls>

pywxdump/ui/view_chat.py

@@ -6,12 +6,13 @@
 # Date:         2023/11/10
 # -------------------------------------------------------------------------------
 import base64
+import re
 import sqlite3
 import os
 import json
 import time
 import hashlib
-from pywxdump.analyzer import read_img_dat, decompress_CompressContent, read_audio, parse_xml_string
+from pywxdump.analyzer import read_img_dat, decompress_CompressContent, read_audio, parse_xml_string, read_BytesExtra
 
 from flask import Flask, request, render_template, g, Blueprint
 
@@ -24,26 +25,31 @@ def get_md5(s):
 
 def get_user_list(MSG_ALL_db_path, MicroMsg_db_path):
     users = []
+
     # 连接 MSG_ALL.db 数据库，并执行查询
     db1 = sqlite3.connect(MSG_ALL_db_path)
     cursor1 = db1.cursor()
     cursor1.execute("SELECT StrTalker, COUNT(*) AS ChatCount FROM MSG GROUP BY StrTalker ORDER BY ChatCount DESC")
     result = cursor1.fetchall()
 
+    dict_user_count = {}
+    # 将结果转换为字典
     for row in result:
-        # 获取用户名、昵称、备注和聊天记录数量
+        dict_user_count[row[0]] = row[1]
+
     db2 = sqlite3.connect(MicroMsg_db_path)
     cursor2 = db2.cursor()
-        cursor2.execute("SELECT UserName, NickName, Remark FROM Contact WHERE UserName=?", (row[0],))
+    cursor2.execute("SELECT UserName, NickName, Remark FROM Contact;")
-        result2 = cursor2.fetchone()
+    result2 = cursor2.fetchall()
-        if result2:
+    for row in result2:
-            username, nickname, remark = result2
+        username, nickname, remark = row
-            chat_count = row[1]
-
         # 拼接四列数据为元组
-            row_data = {"username": username, "nickname": nickname, "remark": remark, "chat_count": chat_count,
+        row_data = {"username": username, "nickname": nickname, "remark": remark,
+                    "chat_count": dict_user_count.get(username, 0),
                     "isChatRoom": username.startswith("@chatroom")}
         users.append(row_data)
+
+    users.sort(key=lambda x: x["chat_count"], reverse=True)  # 按照聊天记录数量排序
     cursor2.close()
     db2.close()
     cursor1.close()
@@ -94,7 +100,7 @@ def load_base64_img_data(start_time, end_time, username_md5, FileStorage_path):
 
 
 def load_chat_records(selected_talker, start_index, page_size, user_list, MSG_ALL_db_path, MediaMSG_all_db_path,
-                      FileStorage_path):
+                      FileStorage_path, USER_LIST):
     username = user_list.get("username", "")
     username_md5 = get_md5(username)
     type_name_dict = {
@@ -116,7 +122,7 @@ def load_chat_records(selected_talker, start_index, page_size, user_list, MSG_AL
     cursor1 = db1.cursor()
 
     cursor1.execute(
-        "SELECT localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType,CreateTime,MsgSvrID,DisplayContent,CompressContent FROM MSG WHERE StrTalker=? ORDER BY CreateTime ASC LIMIT ?,?",
+        "SELECT localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType,CreateTime,MsgSvrID,DisplayContent,CompressContent,BytesExtra FROM MSG WHERE StrTalker=? ORDER BY CreateTime ASC LIMIT ?,?",
         (selected_talker, start_index, page_size))
     result1 = cursor1.fetchall()
 
@@ -127,7 +133,7 @@ def load_chat_records(selected_talker, start_index, page_size, user_list, MSG_AL
 
     data = []
     for row in result1:
-        localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType, CreateTime, MsgSvrID, DisplayContent, CompressContent = row
+        localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType, CreateTime, MsgSvrID, DisplayContent, CompressContent, BytesExtra = row
         CreateTime = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(CreateTime))
 
         type_name = type_name_dict.get(Type, {}).get(SubType, "未知")
@@ -172,8 +178,28 @@ def load_chat_records(selected_talker, start_index, page_size, user_list, MSG_AL
 
         else:
             content["msg"] = StrContent
+        talker = "未知"
+        if IsSender == 1:
+            talker = "我"
+        else:
+            if StrTalker.endswith("@chatroom"):
+                bytes_extra = read_BytesExtra(BytesExtra)
+                if bytes_extra:
+                    try:
+                        matched_string = bytes_extra['3'][0]['2'].decode('utf-8', errors='ignore')
+                        talker_dicts = list(filter(lambda x: x["username"] == matched_string, USER_LIST))
+                        if len(talker_dicts) > 0:
+                            talker_dict = talker_dicts[0]
+                            room_username = talker_dict.get("username", "")
+                            room_nickname = talker_dict.get("nickname", "")
+                            room_remark = talker_dict.get("remark", "")
+                            talker = room_remark if room_remark else room_nickname if room_nickname else room_username
+                        else:
+                            talker = matched_string
+                    except:
+                        pass
 
-        row_data = {"MsgSvrID": MsgSvrID, "type_name": type_name, "is_sender": IsSender,
+        row_data = {"MsgSvrID": MsgSvrID, "type_name": type_name, "is_sender": IsSender, "talker": talker,
                     "content": content, "CreateTime": CreateTime}
         data.append(row_data)
     return data
@@ -221,7 +247,9 @@ app_show_chat.debug = False
 @app_show_chat.route('/')
 def index():
     g.USER_LIST = get_user_list(g.MSG_ALL_db_path, g.MicroMsg_db_path)
-    return render_template("index.html", users=g.USER_LIST)
+    # 只去前面500个有聊天记录的用户
+    USER_LIST = g.USER_LIST[:500]
+    return render_template("index.html", users=USER_LIST)
 
 
 # 获取聊天记录
@@ -240,7 +268,7 @@ def get_chat_data():
         page_size = limit
 
         data = load_chat_records(username, start_index, page_size, user, g.MSG_ALL_db_path, g.MediaMSG_all_db_path,
-                                 g.FileStorage_path)
+                                 g.FileStorage_path, g.USER_LIST)
         return render_template("chat.html", msgs=data)
     else:
         return "error"

pywxdump/wx_info/get_wx_info.py

@@ -194,7 +194,6 @@ def get_key(db_path, addr_len):
                 continue
             if verify_key(key_bytes, MicroMsg_path):
                 return key_bytes.hex()
-
     return "None"
 
 
@@ -326,7 +325,6 @@ def get_wechat_db(require_list: Union[List[str], str] = "all", msg_dir: str = No
                     print(f"        {path.replace(user, '')}")
         print("-" * 32)
         print(f"[+] 共 {len(user_dirs)} 个微信账号")
-
     return user_dirs