适配微信4.0.3正式版，修复合并数据库的一些问题

example/1-decrypt.py

@@ -36,6 +36,9 @@ def dump_v3():
         info_data = me.to_json()
         output_dir = wx_info.wxid
         key = wx_info.key
+        if not key:
+            print('error! 未找到key，请重启微信后再试')
+            continue
         wx_dir = wx_info.wx_dir
         decrypt_v3.decrypt_db_files(key, src_dir=wx_dir, dest_dir=output_dir)
         # 导出的数据库在 output_dir/Msg 文件夹下，后面会用到
@@ -59,6 +62,9 @@ def dump_v4():
         info_data = me.to_json()
         output_dir = wx_info.wxid  # 数据库输出文件夹
         key = wx_info.key
+        if not key:
+            print('error! 未找到key，请重启微信后再试')
+            continue
         wx_dir = wx_info.wx_dir
         decrypt_v4.decrypt_db_files(key, src_dir=wx_dir, dest_dir=output_dir)
         # 导出的数据库在 output_dir/db_storage 文件夹下，后面会用到

wxManager/db_v3/audio2text.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+@Time        : 2025/4/1 20:31
+@Author      : SiYuan
+@Email       : 863909694@qq.com
+@File        : wxManager-audio2text.py
+@Description :
+"""
+
+import os
+import sqlite3
+import traceback
+
+from wxManager.merge import increase_update_data, increase_data
+from wxManager.model.db_model import DataBaseBase
+
+
+class Audio2TextDB(DataBaseBase):
+    def create(self):
+        sql = '''
+        CREATE TABLE IF NOT EXISTS Audio2Text (
+           ID INTEGER PRIMARY KEY,
+           msgSvrId INTEGER UNIQUE,
+           Text TEXT NOT NULL
+           );
+        '''
+        cursor = self.DB.cursor()
+        cursor.execute(sql)
+        # 创建索引
+        cursor.execute('''CREATE UNIQUE INDEX IF NOT EXISTS idx_msg_id ON Audio2Text (msgSvrId);''')
+        self.commit()
+
+    def get_audio_text(self, server_id):
+        sql = '''select text from Audio2Text where msgSvrId=?'''
+        cursor = self.DB.cursor()
+        cursor.execute(sql, [server_id])
+        result = cursor.fetchone()
+        if result:
+            return result[0]
+        else:
+            return ''
+
+    def add_text(self, server_id, text):
+        try:
+            cursor = self.DB.cursor()
+            sql = '''INSERT INTO Audio2Text (msgSvrId, Text) VALUES (?, ?)'''
+            cursor.execute(sql, [server_id, text])
+            self.commit()
+            return True
+        except sqlite3.IntegrityError:
+            return False
+        except:
+            return False
+
+    def merge(self, db_path):
+        if not (os.path.exists(db_path) or os.path.isfile(db_path)):
+            print(f'{db_path} 不存在')
+            return
+        try:
+            # 获取列名
+            increase_data(db_path, self.cursor, self.DB, 'Audio2Text', 'msgSvrId')
+        except:
+            print(f"数据库操作错误: {traceback.format_exc()}")
+            self.DB.rollback()

wxManager/db_v3/emotion.py

@@ -126,10 +126,10 @@ class Emotion(DataBaseBase):
             cursor = self.DB.cursor()
             # 获取列名
             increase_data(db_path, cursor, self.DB, 'CustomEmotion', 'MD5', 0)
-            increase_data(db_path, cursor, self.DB, 'EmotionDes1', 'MD5', 1, True)
+            increase_data(db_path, cursor, self.DB, 'EmotionDes1', 'MD5', 1, 'localId')
-            increase_data(db_path, cursor, self.DB, 'EmotionItem', 'MD5', 1, True)
+            increase_data(db_path, cursor, self.DB, 'EmotionItem', 'MD5', 1, 'localId')
-            increase_data(db_path, cursor, self.DB, 'EmotionPackageItem', 'ProductId', 0, False)
+            increase_data(db_path, cursor, self.DB, 'EmotionPackageItem', 'ProductId', 0, 'localId')
-            increase_data(db_path, cursor, self.DB, 'EmotionOrderInfo', 'MD5', 0, False)
+            increase_data(db_path, cursor, self.DB, 'EmotionOrderInfo', 'MD5', 0, 'localId')
         except:
             print(f"数据库操作错误: {traceback.format_exc()}")
             self.DB.rollback()

wxManager/db_v3/msg.py

@@ -277,7 +277,7 @@ class Msg(DataBaseBase):
             """
             increase_data(db_path, cursor, db, 'Name2Id', 'UsrName')
             increase_update_data(db_path, cursor, db, 'DBInfo', 'tableIndex')
-            increase_data(db_path, cursor, db, 'MSG', 'MsgSvrID', exclude_first_column=True)
+            increase_data(db_path, cursor, db, 'MSG', 'MsgSvrID', exclude_column='localId')
 
         tasks = []
         for i in range(100):

wxManager/db_v3/open_im_msg.py

@@ -111,8 +111,7 @@ class OpenIMMsgDB(DataBaseBase):
 
     def get_messages_by_username(self, username: str,
                                  time_range: Tuple[int | float | str | date, int | float | str | date] = None, ):
-        result = self._get_messages_by_username(self.DB.cursor(), username, time_range)
+        return self._get_messages_by_username(self.DB.cursor(), username, time_range)
-        return [result]
 
     def get_message_by_server_id(self, username, server_id):
         """
@@ -141,7 +140,7 @@ class OpenIMMsgDB(DataBaseBase):
             return
         try:
             # 获取列名
-            increase_update_data(db_path, self.cursor, self.DB, 'ChatCRMsg', 'MsgSvrID', 1, exclude_first_column=True)
+            increase_data(db_path, self.cursor, self.DB, 'ChatCRMsg', 'MsgSvrID', 1, exclude_column='localId')
         except:
             print(f"数据库操作错误: {traceback.format_exc()}")
             self.DB.rollback()

wxManager/db_v3/public_msg.py

@@ -176,7 +176,7 @@ class PublicMsg(DataBaseBase):
             return
         try:
             # 获取列名
-            increase_data(db_path, self.cursor, self.DB, 'PublicMsg', 'MsgSvrID', 1, exclude_first_column=True)
+            increase_data(db_path, self.cursor, self.DB, 'PublicMsg', 'MsgSvrID', 1, exclude_column='localId')
         except:
             print(f"数据库操作错误: {traceback.format_exc()}")
             self.DB.rollback()

wxManager/db_v3/sns.py

@@ -195,16 +195,4 @@ class Sns:
         return result
 
     def __del__(self):
-        self.close()
+        self.close()
-
-
-if __name__ == '__main__':
-    db_path = "./Msg1/Sns.db"
-    sns_db = Sns()
-    sns_db.init_database()
-    print(sns_db.get_sns_bg_url())
-    feeds = sns_db.get_feeds_by_username('wxid_27hqbq7vx5hf22')
-    print(feeds)
-    for feed in feeds:
-        comment = sns_db.get_comment(feed[0])
-        print(comment)

wxManager/db_v4/audio2text.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+@Time        : 2025/4/1 20:31 
+@Author      : SiYuan 
+@Email       : 863909694@qq.com 
+@File        : wxManager-audio2text.py 
+@Description : 
+"""
+
+import os
+import sqlite3
+import traceback
+
+from wxManager.merge import increase_update_data, increase_data
+from wxManager.model.db_model import DataBaseBase
+
+
+class Audio2TextDB(DataBaseBase):
+    def create(self):
+        sql = '''
+        CREATE TABLE IF NOT EXISTS Audio2Text (
+           ID INTEGER PRIMARY KEY,
+           msgSvrId INTEGER UNIQUE,
+           Text TEXT NOT NULL
+           );
+        '''
+        cursor = self.DB.cursor()
+        cursor.execute(sql)
+        # 创建索引
+        cursor.execute('''CREATE UNIQUE INDEX IF NOT EXISTS idx_msg_id ON Audio2Text (msgSvrId);''')
+        self.commit()
+
+    def get_audio_text(self, server_id):
+        sql = '''select text from Audio2Text where msgSvrId=?'''
+        cursor = self.DB.cursor()
+        cursor.execute(sql, [server_id])
+        result = cursor.fetchone()
+        if result:
+            return result[0]
+        else:
+            return ''
+
+    def add_text(self, server_id, text):
+        try:
+            cursor = self.DB.cursor()
+            sql = '''INSERT INTO Audio2Text (msgSvrId, Text) VALUES (?, ?)'''
+            cursor.execute(sql, [server_id, text])
+            self.commit()
+            return True
+        except sqlite3.IntegrityError:
+            return False
+        except:
+            return False
+
+    def merge(self, db_path):
+        if not (os.path.exists(db_path) or os.path.isfile(db_path)):
+            print(f'{db_path} 不存在')
+            return
+        try:
+            # 获取列名
+            increase_data(db_path, self.cursor, self.DB, 'Audio2Text', 'msgSvrId')
+        except:
+            print(f"数据库操作错误: {traceback.format_exc()}")
+            self.DB.rollback()

wxManager/db_v4/biz_message.py

@@ -12,6 +12,7 @@ import concurrent
 import hashlib
 import os
 import shutil
+import sqlite3
 import threading
 from concurrent.futures import ThreadPoolExecutor
 from datetime import date, datetime
@@ -280,14 +281,18 @@ order by sort_seq
             """
             increase_data(db_path, cursor, db, 'Name2Id', 'user_name')
             increase_update_data(db_path, cursor, db, 'TimeStamp', 'timestamp')
-            cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
+            tgt_conn = sqlite3.connect(db_path)
-            result = cursor.fetchall()
+            tgt_cur = tgt_conn.cursor()
+            tgt_cur.execute("SELECT name FROM sqlite_master WHERE type='table';")
+            result = tgt_cur.fetchall()
+            tgt_cur.close()
+            tgt_conn.close()
             # print(result)
             if result:
                 for row in result:
                     table_name = row[0]
                     if table_name.startswith('Msg'):
-                        increase_data(db_path, cursor, db, table_name, 'server_id', exclude_first_column=True)
+                        increase_data(db_path, cursor, db, table_name, 'server_id', exclude_column='local_id')
 
         tasks = []
         for i in range(100):

wxManager/db_v4/hardlink.py

@@ -264,9 +264,9 @@ class HardLinkDB(DataBaseBase):
             return
         try:
             # 获取列名
-            increase_data(db_path, self.cursor, self.DB, 'file_hardlink_info_v3', 'md5')
+            increase_data(db_path, self.cursor, self.DB, 'file_hardlink_info_v3', 'md5', exclude_column='_rowid_')
-            increase_data(db_path, self.cursor, self.DB, 'image_hardlink_info_v3', 'md5')
+            increase_data(db_path, self.cursor, self.DB, 'image_hardlink_info_v3', 'md5', exclude_column='_rowid_')
-            increase_data(db_path, self.cursor, self.DB, 'video_hardlink_info_v3', 'md5')
+            increase_data(db_path, self.cursor, self.DB, 'video_hardlink_info_v3', 'md5', exclude_column='_rowid_')
             increase_data(db_path, self.cursor, self.DB, 'dir2id', 'username')
         except:
             print(f"数据库操作错误: {traceback.format_exc()}")

wxManager/db_v4/message.py

@@ -12,6 +12,7 @@ import concurrent
 import hashlib
 import os
 import shutil
+import sqlite3
 import threading
 import traceback
 from concurrent.futures import ThreadPoolExecutor
@@ -281,14 +282,19 @@ order by sort_seq
             """
             increase_data(db_path, cursor, db, 'Name2Id', 'user_name')
             increase_update_data(db_path, cursor, db, 'TimeStamp', 'timestamp')
-            cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
+            tgt_conn = sqlite3.connect(db_path)
-            result = cursor.fetchall()
+            tgt_cur = tgt_conn.cursor()
+            tgt_cur.execute("SELECT name FROM sqlite_master WHERE type='table';")
+            result = tgt_cur.fetchall()
+            tgt_cur.close()
+            tgt_conn.close()
+
             # print(result)
             if result:
                 for row in result:
                     table_name = row[0]
                     if table_name.startswith('Msg'):
-                        increase_data(db_path, cursor, db, table_name, 'server_id', exclude_first_column=True)
+                        increase_data(db_path, cursor, db, table_name, 'server_id', exclude_column='local_id')
 
         tasks = []
         for i in range(100):

wxManager/db_v4/session.py

@@ -42,10 +42,3 @@ order by sort_timestamp desc
         except:
             print(f"数据库操作错误: {traceback.format_exc()}")
             self.DB.rollback()
-
-
-if __name__ == '__main__':
-    cd = SessionDB('session/session.db')
-    cd.init_database(r'E:\Project\Python\MemoTrace\app\DataBase\Msg\wxid_27hqbq7vx5hf22\db_storage')
-    r = cd.get_session()
-    print(r)

wxManager/decrypt/decrypt_dat.py

@@ -6,7 +6,7 @@
 @Author      : SiYuan
 @Email       : 863909694@qq.com
 @File        : wxManager-decrypt_dat.py
-@Description :
+@Description : 微信4.0图片加密原理解析：https://blog.lc044.love/post/16
 """
 import os
 import struct
@@ -26,6 +26,19 @@ pic_head = (0xff, 0xd8, 0x89, 0x50, 0x47, 0x49)
 decode_code = 0
 decode_code_v4 = -1
 
+AES_KEY_MAP = {
+    b'\x07\x08V1\x08\x07': b'cfcd208495d565ef',  # 4.0第一代图片密钥
+    b'\x07\x08V2\x08\x07': b'43e7d25eb1b9bb64',  # 4.0第二代图片密钥，微信4.0.3正式版使用
+}
+
+
+def get_aes_key(header):
+    return AES_KEY_MAP.get(header[:6], b'')
+
+
+def is_v4_image(header):
+    return header[:6] in AES_KEY_MAP
+
 
 def get_code(dat_read):
     """
@@ -68,14 +81,14 @@ def decode_dat(xor_key: int, file_path, out_path, dst_name='') -> str | bytes:
         return ''
     # print(file_path,out_path,dst_name)
     with open(file_path, 'rb') as file_in:
-        data = file_in.read(0xf)
+        header = file_in.read(0xf)
-    if data.startswith(b'\x07\x08V1\x08\x07'):
+    if is_v4_image(header):
         # 微信4.0
         return decode_dat_v4(xor_key, file_path, out_path, dst_name)
 
     with open(file_path, 'rb') as file_in:
-        data = file_in.read(2)
+        header = file_in.read(2)
-        file_type, decode_code = get_code(data)
+        file_type, decode_code = get_code(header)
         if decode_code == -1:
             return ''
 
@@ -96,12 +109,12 @@ def decode_dat(xor_key: int, file_path, out_path, dst_name='') -> str | bytes:
         # 分块读取和写入
         buffer_size = 1024  # 定义缓冲区大小
         with open(file_outpath, 'wb') as file_out:
-            file_out.write(bytes([byte ^ decode_code for byte in data]))
+            file_out.write(bytes([byte ^ decode_code for byte in header]))
             while True:
-                data = file_in.read(buffer_size)
+                header = file_in.read(buffer_size)
-                if not data:
+                if not header:
                     break
-                file_out.write(bytes([byte ^ decode_code for byte in data]))
+                file_out.write(bytes([byte ^ decode_code for byte in header]))
 
     # print(os.path.basename(file_outpath))
     return file_outpath
@@ -121,7 +134,7 @@ def get_decode_code_v4(wx_dir):
                 src_file_path = os.path.join(root, file)
                 with open(src_file_path, 'rb') as f:
                     data = f.read()
-                    if not data.startswith(b'\x07\x08V1\x08\x07'):
+                    if not is_v4_image(data):
                         continue
                     file_tail = data[-2:]
 
@@ -184,7 +197,7 @@ def decode_dat_v4(xor_key: int, file_path, out_path, dst_name='') -> str | bytes
         padding_length = 16 - (len(encrypted_data) % 16)
         encrypted_data += b'\x00' * padding_length
 
-    aes_key = b'cfcd208495d565ef'
+    aes_key = get_aes_key(header)
 
     # 初始化AES解密器（ECB模式）
     cipher = AES.new(aes_key, AES.MODE_ECB)
@@ -236,7 +249,7 @@ async def decode_dat_v4_async(xor_key: int, file_path, out_path, dst_name='') ->
         encrypted_data = await f.read(encrypt_length0)
         res_data = await f.read()
 
-    aes_key = b'cfcd208495d565ef'
+    aes_key = get_aes_key(header)
 
     # 初始化AES解密器（ECB模式）
     cipher = AES.new(aes_key, AES.MODE_ECB)
@@ -303,5 +316,5 @@ def batch_decode_image_multiprocessing(xor_key, file_infos: List[Tuple[str, str,
 if __name__ == '__main__':
     wx_dir = ''
     xor_key = get_decode_code_v4(wx_dir)
-    dat_file = "2_1730948126.dat"
+    dat_file = "1c5d8c0cf05d97869b0bc9fe16a8e3c2.dat"
     decode_dat_v4(xor_key, dat_file, '.', dst_name='解密后的图片')

wxManager/decrypt/decrypt_v3.py

@@ -17,6 +17,7 @@ import hmac
 import hashlib
 import os
 import traceback
+from concurrent.futures import ProcessPoolExecutor
 from typing import Union, List
 from Crypto.Cipher import AES
 
@@ -85,6 +86,11 @@ def decrypt_db_file_v3(key: str, db_path, out_path):
     return True, [db_path, out_path, key]
 
 
+def decode_wrapper(tasks):
+    """用于包装解码函数的顶层定义"""
+    return decrypt_db_file_v3(*tasks)
+
+
 def decrypt_db_files(key, src_dir: str, dest_dir: str):
     if not os.path.exists(src_dir):
         print(f"源文件夹 {src_dir} 不存在")
@@ -92,7 +98,7 @@ def decrypt_db_files(key, src_dir: str, dest_dir: str):
 
     if not os.path.exists(dest_dir):
         os.makedirs(dest_dir)  # 如果目标文件夹不存在，创建它
-
+    decrypt_tasks = []
     for root, dirs, files in os.walk(src_dir):
         for file in files:
             if file.endswith(".db"):
@@ -108,4 +114,7 @@ def decrypt_db_files(key, src_dir: str, dest_dir: str):
                 if not os.path.exists(dest_sub_dir):
                     os.makedirs(dest_sub_dir)
                 print(dest_file_path)
-                decrypt_db_file_v3(key, src_file_path, dest_file_path)
+                decrypt_tasks.append((key, src_file_path, dest_file_path))
+                # decrypt_db_file_v3(key, src_file_path, dest_file_path)
+    with ProcessPoolExecutor(max_workers=16) as executor:
+        results = list(executor.map(decode_wrapper, decrypt_tasks))  # 使用顶层定义的函数

wxManager/decrypt/decrypt_v4.py

@@ -1,6 +1,8 @@
 import hmac
 import os
 import struct
+from concurrent.futures import ProcessPoolExecutor
+
 from Crypto.Cipher import AES
 from Crypto.Protocol.KDF import PBKDF2
 from Crypto.Hash import SHA512
@@ -101,6 +103,11 @@ def decrypt_db_file_v4(pkey, in_db_path, out_db_path):
     return True
 
 
+def decode_wrapper(tasks):
+    """用于包装解码函数的顶层定义"""
+    return decrypt_db_file_v4(*tasks)
+
+
 def decrypt_db_files(key, src_dir: str, dest_dir: str):
     if not os.path.exists(src_dir):
         print(f"源文件夹 {src_dir} 不存在")
@@ -108,7 +115,7 @@ def decrypt_db_files(key, src_dir: str, dest_dir: str):
 
     if not os.path.exists(dest_dir):
         os.makedirs(dest_dir)  # 如果目标文件夹不存在，创建它
-
+    decrypt_tasks = []
     for root, dirs, files in os.walk(src_dir):
         for file in files:
             if file.endswith(".db"):
@@ -124,4 +131,7 @@ def decrypt_db_files(key, src_dir: str, dest_dir: str):
                 if not os.path.exists(dest_sub_dir):
                     os.makedirs(dest_sub_dir)
                 print(dest_file_path)
-                decrypt_db_file_v4(key, src_file_path, dest_file_path)
+                decrypt_tasks.append((key, src_file_path, dest_file_path))
+                # decrypt_db_file_v4(key, src_file_path, dest_file_path)
+    with ProcessPoolExecutor(max_workers=16) as executor:
+        results = list(executor.map(decode_wrapper, decrypt_tasks))  # 使用顶层定义的函数

wxManager/decrypt/version_list.json

@@ -1139,5 +1139,26 @@
         94554984,
         0,
         94556448
+    ],
+    "2.4.0.1": [
+        14907156,
+        14907512,
+        14907208,
+        0,
+        0
+    ],
+    "3.7.5.19": [
+        37895672,
+        37896480,
+        37895552,
+        0,
+        0
+    ],
+    "3.9.2.114": [
+        50370000,
+        0,
+        50369856,
+        0,
+        0
     ]
 }

wxManager/decrypt/wx_info_v4.py

@@ -6,7 +6,7 @@
 @Author      : SiYuan
 @Email       : 863909694@qq.com
 @File        : wxManager-wx_info_v4.py
-@Description :
+@Description : 部分思路参考：https://github.com/0xlane/wechat-dump-rs
 """
 
 import ctypes
@@ -330,7 +330,7 @@ def get_key_inner(pid, process_infos):
     keys = []
     key_set = set()
     for pre_address in pre_addresses:
-        if any([base_address <= pre_address <= base_address + region_size - KEY_SIZE for base_address, region_size in
+        if True or any([base_address <= pre_address <= base_address + region_size - KEY_SIZE for base_address, region_size in
                 process_infos]):
             key = read_bytes_from_pid(pid, pre_address, 32)
             if key not in key_set:

wxManager/manager_v3.py

@@ -10,6 +10,7 @@
 """
 import concurrent
 import os
+import re
 import traceback
 from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor
 from datetime import date
@@ -19,6 +20,7 @@ import xmltodict
 
 from wxManager import MessageType
 from wxManager.db_main import DataBaseInterface
+from wxManager.db_v3.audio2text import Audio2TextDB
 from wxManager.db_v3.hard_link_file import HardLinkFile
 from wxManager.db_v3.hard_link_image import HardLinkImage
 from wxManager.db_v3.hard_link_video import HardLinkVideo
@@ -188,11 +190,7 @@ class DataBaseV3(DataBaseInterface):
         self.open_contact_db = OpenIMContactDB('OpenIMContact.db')
         self.open_media_db = OpenIMMediaDB('OpenIMMedia.db')
         self.open_msg_db = OpenIMMsgDB('OpenIMMsg.db')
-        # self.sns_db = Sns()
+        self.audio2text_db = Audio2TextDB('Audio2Text.db')
-
-        # self.audio_to_text = Audio2TextDB()
-        # self.public_msg_db = PublicMsg()
-        # self.favorite_db = Favorite()
 
     def init_database(self, db_dir=''):
         # print('初始化数据库', db_dir)
@@ -211,6 +209,8 @@ class DataBaseV3(DataBaseInterface):
         flag &= self.open_contact_db.init_database(db_dir)
         flag &= self.open_media_db.init_database(db_dir)
         flag &= self.open_msg_db.init_database(db_dir)
+        flag &= self.audio2text_db.init_database(db_dir)
+        self.audio2text_db.create()  # 初始化数据转文字数据库
         return flag
         # self.sns_db.init_database(db_dir)
 
@@ -231,9 +231,7 @@ class DataBaseV3(DataBaseInterface):
         self.open_contact_db.close()
         self.open_media_db.close()
         self.open_msg_db.close()
-        # self.sns_db.close()
+        self.audio2text_db.close()
-        # self.audio_to_text.close()
-        # self.public_msg_db.close()
 
     def get_session(self):
         """
@@ -446,8 +444,10 @@ class DataBaseV3(DataBaseInterface):
         return self.media_msg_db.get_audio_path(reserved0, output_path, filename)
 
     def get_audio_text(self, msgSvrId):
-        return ''
+        return self.audio2text_db.get_audio_text(msgSvrId)
-        return self.media_msg_db.get_audio_text(msgSvrId)
+
+    def add_audio_txt(self, msgSvrId, text):
+        return self.audio2text_db.add_text(msgSvrId, text)
 
     def update_audio_to_text(self):
         messages = self.get_messages_all()
@@ -491,10 +491,8 @@ class DataBaseV3(DataBaseInterface):
                 gender = '男'
             elif gender_code == 2:
                 gender = '女'
-
         type_ = contact_info_list[2]
         wxid = contact_info_list[0]
-
         contact = Contact(
             wxid=contact_info_list[0],
             remark=remark,
@@ -524,10 +522,10 @@ class DataBaseV3(DataBaseInterface):
             contact.type |= ContactType.Star
         if is_nth_bit_set(type_, 11):
             contact.type |= ContactType.Sticky
-
         if type_ == 10086:
             contact.type = ContactType.Unknown
             contact.is_unknown = True
+        contact.remark = re.sub(r'[\\/:*?"<>|\s\.\x00-\x08\x0B\x0C\x0E-\x1F]', '_', contact.remark)
         return contact
 
     def create_open_im_contact(self, contact_info_list) -> Person:
@@ -560,6 +558,7 @@ class DataBaseV3(DataBaseInterface):
         )
         contact.type = ContactType.Normal
         contact.type |= ContactType.OpenIM
+        contact.remark = re.sub(r'[\\/:*?"<>|\s\.\x00-\x08\x0B\x0C\x0E-\x1F]', '_', contact.remark)
         return contact
 
     def get_contacts(self) -> List[Person]:
@@ -660,8 +659,6 @@ class DataBaseV3(DataBaseInterface):
         return chatroom_name.rstrip('、')
 
     # 联系人结束
-    def add_audio_txt(self, msgSvrId, text):
-        return self.audio_to_text.add_text(msgSvrId, text)
 
     def get_favorite_items(self, time_range):
         return self.favorite_db.get_items(time_range)

wxManager/manager_v4.py

@@ -10,6 +10,7 @@
 """
 import concurrent
 import os
+import re
 from concurrent.futures import ProcessPoolExecutor, as_completed, ThreadPoolExecutor
 from datetime import date, datetime
 from multiprocessing import Pool, cpu_count
@@ -18,6 +19,7 @@ from typing import Tuple, List, Any
 import zstandard as zstd
 
 from wxManager import MessageType
+from wxManager.db_v4.audio2text import Audio2TextDB
 from wxManager.db_v4.biz_message import BizMessageDB
 from wxManager.db_v4.emotion import EmotionDB
 from wxManager.db_v4.media import MediaDB
@@ -82,6 +84,7 @@ class DataBaseV4(DataBaseInterface):
         self.media_db = MediaDB('message/media_0.db', is_series=True)
         self.hardlink_db = HardLinkDB('hardlink/hardlink.db')
         self.emotion_db = EmotionDB('emoticon/emoticon.db')
+        self.audio2text_db = Audio2TextDB('Audio2Text.db')
 
     def init_database(self, db_dir=''):
         Me().load_from_json(os.path.join(db_dir, 'info.json'))  # 加载自己的信息
@@ -96,6 +99,8 @@ class DataBaseV4(DataBaseInterface):
         flag &= self.media_db.init_database(db_dir)
         flag &= self.hardlink_db.init_database(db_dir)
         flag &= self.emotion_db.init_database(db_dir)
+        flag &= self.audio2text_db.init_database(db_dir)
+        self.audio2text_db.create()  # 初始化数据转文字数据库
         return flag
 
     def close(self):
@@ -271,13 +276,16 @@ class DataBaseV4(DataBaseInterface):
     def get_audio_path(self, reserved0, output_path, filename=''):
         return self.media_db.get_audio_path(reserved0, output_path, filename)
 
-    def get_audio_text(self, msgSvrId):
+    def get_audio_text(self, server_id):
-        return ''
+        return self.audio2text_db.get_audio_text(server_id)
 
     def update_audio_to_text(self):
         # todo
         return
 
+    def add_audio_txt(self, server_id, text):
+        return self.audio2text_db.add_text(server_id, text)
+
     # 语音结束
 
     # 联系人
@@ -353,10 +361,10 @@ class DataBaseV4(DataBaseInterface):
             contact.type |= ContactType.Star
         if is_nth_bit_set(flag, 11):
             contact.type |= ContactType.Sticky
-
         if local_type == 10086:
             contact.type = ContactType.Unknown
             contact.is_unknown = True
+        contact.remark = re.sub(r'[\\/:*?"<>|\s\.\x00-\x08\x0B\x0C\x0E-\x1F]', '_', contact.remark)
         return contact
 
     def get_contacts(self) -> List[Person]:
@@ -437,9 +445,6 @@ class DataBaseV4(DataBaseInterface):
 
     # 联系人结束
 
-    def add_audio_txt(self, msgSvrId, text):
-        return self.audio_to_text.add_text(msgSvrId, text)
-
     def get_favorite_items(self, time_range):
         return self.favorite_db.get_items(time_range)
 

wxManager/merge.py

@@ -19,7 +19,7 @@ def get_create_statements(conn, table_name, object_type):
     return [row[0] for row in cursor.fetchall() if row[0]]  # 过滤掉 None 值
 
 
-def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index=-1, exclude_first_column=False):
+def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index=-1, exclude_column=''):
     """
     将db_path数据库的内容增量写入connect数据库中
     @param db_path: 新的数据库路径
@@ -28,7 +28,7 @@ def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index
     @param table_name: 待写入的表名
     @param col_name: 根据该列进行判断是否是新增数据
     @param col_index: 待写入的列号
-    @param exclude_first_column: 是否不考虑低一列（针对第一列是自增ID的表）
+    @param exclude_column: 是否不考虑某一列（针对某一列是自增ID的表）
     @return:
     """
     if not (os.path.exists(db_path) or os.path.isfile(db_path)):
@@ -41,26 +41,30 @@ def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index
     tgt_cur = tgt_conn.cursor()
 
     try:
-        if not table_exists(tgt_conn, table_name):
+        if not table_exists(src_conn, table_name):
             # 复制表结构
-            create_table_sql = get_create_statements(src_conn, table_name, "table")
+            create_table_sql = get_create_statements(tgt_conn, table_name, "table")
             if create_table_sql:
-                tgt_conn.execute(create_table_sql[0])  # 执行 CREATE TABLE 语句
+                src_conn.execute(create_table_sql[0])  # 执行 CREATE TABLE 语句
                 print(f"表 {table_name} 结构已复制")
 
             # 复制索引
-            create_index_sql_list = get_create_statements(src_conn, table_name, "index")
+            create_index_sql_list = get_create_statements(tgt_conn, table_name, "index")
             for create_index_sql in create_index_sql_list:
-                tgt_conn.execute(create_index_sql)  # 执行 CREATE INDEX 语句
+                src_conn.execute(create_index_sql)  # 执行 CREATE INDEX 语句
                 print(f"索引已复制: {create_index_sql}")
         # 获取列名
         src_cursor.execute(f"PRAGMA table_info({table_name})")
         columns_info = src_cursor.fetchall()
-        if columns_info and exclude_first_column:
-            columns_info = columns_info[1:]
         column_names = [info[1] for info in columns_info]
+        if columns_info and exclude_column:
+            try:
+                exclude_col_index = column_names.index(exclude_column)
+            except ValueError:
+                print(f"错误: 列 {exclude_column} 在表 {table_name} 中不存在")
+                return
+            column_names = column_names[:exclude_col_index]+column_names[exclude_col_index+1:]
         num_columns = len(column_names)
-
         if col_index == -1:
             try:
                 col_index = column_names.index(col_name)
@@ -69,7 +73,7 @@ def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index
                 return
         # 从数据库B中选择主键不在数据库A中的行
         query = f"""
-           SELECT {', '.join([name for name in column_names])}
+           SELECT {', '.join(column_names)}
            FROM {table_name} 
         """
         tgt_cur.execute(query)
@@ -83,7 +87,6 @@ def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index
 
         source_rows = {r[0] for r in source_rows}
         rows_to_insert = [row for row in target_rows if row[col_index] not in source_rows]
-
         if rows_to_insert:
             insert_query = f"""
                 INSERT INTO {table_name} ({', '.join(column_names)})
@@ -93,7 +96,8 @@ def increase_data(db_path, src_cursor, src_conn, table_name, col_name, col_index
             src_conn.commit()
             print(f"{len(rows_to_insert)} 行已插入到 {table_name} 表中")
         else:
-            print(f"没有需要插入的数据，{table_name} 表已是最新")
+            pass
+            # print(f"没有需要插入的数据，{table_name} 表已是最新")
     except sqlite3.Error as e:
         print(f"{db_path} 数据库操作错误: {e}")
     finally:
@@ -170,7 +174,8 @@ def increase_update_data(db_path, src_cur, src_conn, table_name, col_name, col_i
             src_conn.commit()
             print(f"{len(rows_to_insert)} 行已更新到 {table_name} 表中。")
         else:
-            print(f"没有需要插入的数据，{table_name} 表已是最新。")
+            pass
+            # print(f"没有需要插入的数据，{table_name} 表已是最新。")
     except sqlite3.Error as e:
         print(f"{db_path} 数据库操作错误: {e}")
     finally:

wxManager/model/db_model.py

@@ -25,7 +25,7 @@ class DataBaseBase:
     def init_database(self, db_dir=''):
         self.db_dir = db_dir
         db_path = os.path.join(db_dir, self.db_file_name)
-        if not os.path.exists(db_path):
+        if not os.path.exists(db_path) and self.db_file_name != 'Audio2Text.db':
             return False
         db_file_name = self.db_file_name
         self.db_file_name = []
@@ -44,11 +44,10 @@ class DataBaseBase:
                     self.cursor.append(cursor)
                     self.open_flag = True
         else:
-            if os.path.exists(db_path):
+            self.DB = sqlite3.connect(db_path, check_same_thread=False)
-                self.DB = sqlite3.connect(db_path, check_same_thread=False)
+            # '''创建游标'''
-                # '''创建游标'''
+            self.cursor = self.DB.cursor()
-                self.cursor = self.DB.cursor()
+            self.open_flag = True
-                self.open_flag = True
         # print('初始化数据库完成：', db_path)
         self.self_init()
         return True

wxManager/parser/audio_parser.py

@@ -14,16 +14,16 @@ import xmltodict
 def parser_audio(xml_content):
     result = {
         'audio_length': 0,
-        'audio_text':''
+        'audio_text': ''
     }
     xml_content = xml_content.strip()
     try:
         xml_dict = xmltodict.parse(xml_content)
         voice_length = xml_dict.get('msg', {}).get('voicemsg', {}).get('@voicelength', 0)
-        audio_text = xml_dict.get('msg',{}).get('voicetrans',{}).get('@transtext','')
+        audio_text = xml_dict.get('msg', {}).get('voicetrans', {}).get('@transtext', '')
         result = {
             'audio_length': voice_length,
-            'audio_text':audio_text
+            'audio_text': audio_text
         }
     except:
         if xml_content and ':' in xml_content:

wxManager/parser/util/protocbuf/packed_info_data_img2.proto

@@ -0,0 +1,13 @@
+syntax = "proto3";
+// 2025年3月微信4.0.3正式版修改了img命名方式才有了这个东西
+message PackedInfoDataImg2 {
+  int32 field1 = 1;
+  int32 field2 = 2;
+  ImageInfo imageInfo = 3;
+}
+
+message ImageInfo {
+  int32 height = 1;
+  int32 width = 2;
+  string filename = 4;
+}

wxManager/parser/util/protocbuf/packed_info_data_img2_pb2.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: packed_info_data_img2.proto
+"""Generated protocol buffer code."""
+from google.protobuf.internal import builder as _builder
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import symbol_database as _symbol_database
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x1bpacked_info_data_img2.proto\"S\n\x12PackedInfoDataImg2\x12\x0e\n\x06\x66ield1\x18\x01 \x01(\x05\x12\x0e\n\x06\x66ield2\x18\x02 \x01(\x05\x12\x1d\n\timageInfo\x18\x03 \x01(\x0b\x32\n.ImageInfo\"<\n\tImageInfo\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x10\n\x08\x66ilename\x18\x04 \x01(\tb\x06proto3')
+
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, globals())
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'packed_info_data_img2_pb2', globals())
+if _descriptor._USE_C_DESCRIPTORS == False:
+
+  DESCRIPTOR._options = None
+  _PACKEDINFODATAIMG2._serialized_start=31
+  _PACKEDINFODATAIMG2._serialized_end=114
+  _IMAGEINFO._serialized_start=116
+  _IMAGEINFO._serialized_end=176
+# @@protoc_insertion_point(module_scope)

wxManager/parser/wechat_v3.py

@@ -292,6 +292,8 @@ class AudioMessageFactory(MessageFactory, Singleton):
         audio_dic = parser_audio(msg.xml_content)
         msg.duration = audio_dic.get('audio_length', 0)
         msg.audio_text = audio_dic.get('audio_text', '')
+        if not msg.audio_text:
+            msg.audio_text = manager.get_audio_text(msg.server_id)
         self.add_message(msg)
         return msg
 
@@ -439,6 +441,7 @@ class LinkMessageFactory(MessageFactory, Singleton):
                     contact = manager.get_contact_by_username(source_username)
                     msg.app_name = contact.nickname
                     msg.app_icon = contact.small_head_img_url
+                    msg.app_id = source_username
         elif (type_, sub_type) in {(49, 33), (49, 36)}:
             # 小程序
             msg.type = MessageType.Applet

wxManager/parser/wechat_v4.py

@@ -24,7 +24,8 @@ from wxManager.model.message import VoipMessage, BusinessCardMessage, MergedMess
 from wxManager.parser.link_parser import parser_link, parser_voip, parser_applet, parser_business, \
     parser_merged_messages, parser_wechat_video, parser_position, parser_reply, parser_transfer, parser_red_envelop, \
     parser_file, parser_favorite_note, parser_pat
-from wxManager.parser.util.protocbuf import packed_info_data_pb2, packed_info_data_merged_pb2,packed_info_data_img_pb2
+from wxManager.parser.util.protocbuf import packed_info_data_pb2, packed_info_data_merged_pb2, packed_info_data_img_pb2, \
+    packed_info_data_img2_pb2
 from .audio_parser import parser_audio
 from .emoji_parser import parser_emoji
 from .file_parser import parse_video
@@ -248,14 +249,27 @@ class ImageMessageFactory(MessageFactory, Singleton):
         is_sender, wxid, message_content = self.common_attribute(message, username, manager)
         filename = ''
         try:
-            # 2025年3月微信测试版修改了img命名方式才有了这个东西
+            # 2025年3月微信4.0.3正式版修改了img命名方式才有了这个东西
-            packed_info_data_proto = packed_info_data_img_pb2.PackedInfoDataImg()
+            packed_info_data_proto = packed_info_data_img2_pb2.PackedInfoDataImg2()
             packed_info_data_proto.ParseFromString(message[14])
             # 转换为 JSON 格式
             packed_info_data = MessageToDict(packed_info_data_proto)
-            filename = packed_info_data.get('filename', '').strip().strip('"').strip()
+            image_info = packed_info_data.get('imageInfo', {})
+            width = image_info.get('width',0)
+            height = image_info.get('height',0)
+            filename = image_info.get('filename', '').strip().strip('"').strip()
         except:
             pass
+        if not filename:
+            try:
+                # 2025年3月微信测试版修改了img命名方式才有了这个东西
+                packed_info_data_proto = packed_info_data_img_pb2.PackedInfoDataImg()
+                packed_info_data_proto.ParseFromString(message[14])
+                # 转换为 JSON 格式
+                packed_info_data = MessageToDict(packed_info_data_proto)
+                filename = packed_info_data.get('filename', '').strip().strip('"').strip()
+            except:
+                pass
         msg = ImageMessage(
             local_id=message[0],
             server_id=message[1],
@@ -277,8 +291,6 @@ class ImageMessageFactory(MessageFactory, Singleton):
             file_name=filename,
             file_type='png'
         )
-        # with open(f'{msg.str_time}{msg.server_id}.bin', 'wb') as f:
-        #     f.write(message[14])
         path = manager.get_image(content=message_content, bytesExtra=msg, up_dir='',
                                  thumb=False, talker_username=username)
         msg.path = path
@@ -300,6 +312,8 @@ class AudioMessageFactory(MessageFactory, Singleton):
             # 转换为 JSON 格式
             packed_info_data = MessageToDict(packed_info_data_proto)
             audio_text = packed_info_data.get('info', {}).get('audioTxt', '')
+        if not audio_text:
+            audio_text = manager.get_audio_text(message[1])
         msg = AudioMessage(
             local_id=message[0],
             server_id=message[1],
@@ -454,6 +468,7 @@ class LinkMessageFactory(MessageFactory, Singleton):
                     contact = manager.get_contact_by_username(source_username)
                     msg.app_name = contact.nickname
                     msg.app_icon = contact.small_head_img_url
+                    msg.app_id = source_username
 
         elif message[2] == MessageType.Applet or message[2] == MessageType.Applet2:
             info = parser_applet(message_content)
@@ -627,7 +642,8 @@ class MergedMessageFactory(MessageFactory, Singleton):
                         inner_msg.path = os.path.join('msg', 'attach',
                                                       wxid_md5,
                                                       month,
-                                                      'Rec', dir0, 'F', f"{level}{'_' if level else ''}{index}", inner_msg.file_name)
+                                                      'Rec', dir0, 'F', f"{level}{'_' if level else ''}{index}",
+                                                      inner_msg.file_name)
                     else:
                         inner_msg.path = manager.get_file(inner_msg.md5)
                 elif inner_msg.type == MessageType.MergedMessages: