利用多线程处理语音和表情包

app/DataBase/media_msg.py

@@ -55,12 +55,16 @@ class MediaMsg:
         try:
             lock.acquire(True)
             self.cursor.execute(sql, [reserved0])
-            return self.cursor.fetchone()[0]
+            result = self.cursor.fetchone()
+
         finally:
             lock.release()
+        return result[0] if result else None
 
     def get_audio(self, reserved0, output_path):
         buf = self.get_media_buffer(reserved0)
+        if not buf:
+            return ''
         silk_path = f"{output_path}\\{reserved0}.silk"
         pcm_path = f"{output_path}\\{reserved0}.pcm"
         mp3_path = f"{output_path}\\{reserved0}.mp3"
@@ -76,10 +80,10 @@ class MediaMsg:
         try:
             # 调用系统上的 ffmpeg 可执行文件
             # 获取 FFmpeg 可执行文件的路径
-            ffmpeg_path = get_ffmpeg_path()
+            # ffmpeg_path = get_ffmpeg_path()
-            # 调用 FFmpeg
+            # # 调用 FFmpeg
-            cmd = f'''{ffmpeg_path} -loglevel quiet -y -f s16le -i {pcm_path} -ar 44100 -ac 1 {mp3_path}'''
+            # cmd = f'''{ffmpeg_path} -loglevel quiet -y -f s16le -i {pcm_path} -ar 44100 -ac 1 {mp3_path}'''
-            system(cmd)
+            # system(cmd)
             # 源码运行的时候下面的有效
             # 这里不知道怎么捕捉异常
             cmd = f'''{os.path.join(os.getcwd(), 'app', 'resources', 'ffmpeg.exe')} -loglevel quiet -y -f s16le -i {pcm_path} -ar 44100 -ac 1 {mp3_path}'''
@@ -88,11 +92,14 @@ class MediaMsg:
             print(f"Error: {e}")
             cmd = f'''{os.path.join(os.getcwd(),'app','resources','ffmpeg.exe')} -loglevel quiet -y -f s16le -i {pcm_path} -ar 44100 -ac 1 {mp3_path}'''
             system(cmd)
-        system(f'del {silk_path}')
+        # system(f'del {silk_path}')
-        system(f'del {pcm_path}')
+        # system(f'del {pcm_path}')
         print(mp3_path)
         return mp3_path
-
+    def get_audio_path(self, reserved0, output_path):
+        mp3_path = f"{output_path}\\{reserved0}.mp3"
+        mp3_path = mp3_path.replace("/", "\\")
+        return mp3_path
     def get_audio_text(self, content):
         try:
             root = ET.fromstring(content)

app/DataBase/msg.py

@@ -154,15 +154,15 @@ class Msg:
             sql = '''
                         select localId,TalkerId,Type,SubType,IsSender,CreateTime,Status,StrContent,strftime('%Y-%m-%d %H:%M:%S',CreateTime,'unixepoch','localtime') as StrTime,MsgSvrID,BytesExtra,CompressContent
                         from MSG
-                        where StrTalker=? and Type=?
+                        where StrTalker=? and Type=? 
                         order by CreateTime
                     '''
             try:
                 lock.acquire(True)
                 self.cursor.execute(sql, [username_, type_])
+                result = self.cursor.fetchall()
             finally:
                 lock.release()
-                result = self.cursor.fetchall()
         else:
             sql = '''
                             select localId,TalkerId,Type,SubType,IsSender,CreateTime,Status,StrContent,strftime('%Y-%m-%d %H:%M:%S',CreateTime,'unixepoch','localtime') as StrTime,MsgSvrID,BytesExtra,CompressContent
@@ -610,3 +610,4 @@ if __name__ == '__main__':
     msg.init_database()
     print(msg.get_latest_time_of_message('wxid_0o18ef858vnu22', year_='2023'))
     print(msg.get_messages_number('wxid_0o18ef858vnu22', year_='2023'))
+    print(msg.get_messages_by_type('wxid_0o18ef858vnu22',34))

app/DataBase/output_pc.py

@@ -15,7 +15,7 @@ from ..util import path
 import shutil
 
 from ..util.compress_content import parser_reply
-from ..util.emoji import get_emoji
+from ..util.emoji import get_emoji, get_emoji_path
 
 os.makedirs('./data/聊天记录', exist_ok=True)
 
@@ -131,17 +131,33 @@ class Output(QThread):
             self.Child = ChildThread(self.contact, type_=self.output_type, message_types=self.message_types)
             self.Child.progressSignal.connect(self.progress)
             self.Child.rangeSignal.connect(self.rangeSignal)
-            self.Child.okSignal.connect(self.okSignal)
+            self.Child.okSignal.connect(self.count_finish_num)
             self.Child.start()
+            # 语音消息单独的线程
+            self.output_media = OutputMedia(self.contact)
+            self.output_media.okSingal.connect(self.count_finish_num)
+            self.output_media.progressSignal.connect(self.progress)
+            self.output_media.start()
+            # emoji消息单独的线程
+            self.output_emoji = OutputEmoji(self.contact)
+            self.output_emoji.okSingal.connect(self.count_finish_num)
+            self.output_emoji.progressSignal.connect(self.progress)
+            self.output_emoji.start()
+            self.total_num = 3
+
+    def count_finish_num(self, num):
+        self.num += 1
+        if self.num == self.total_num:
+            self.okSignal.emit(1)
 
     def cancel(self):
         self.requestInterruption()
 
 
-def modify_audio_metadata(audiofile, new_artist): # 修改音频元数据中的“创作者”标签
+def modify_audio_metadata(audiofile, new_artist):  # 修改音频元数据中的“创作者”标签
     return
     audiofile = load(audiofile)
-    
+
     # 检查文件是否有标签
     if audiofile.tag is None:
         audiofile.initTag()
@@ -246,7 +262,7 @@ class ChildThread(QThread):
             try:
                 os.utime(origin_docx_path + image_path[1:], (timestamp, timestamp))
             except:
-                print("网络图片",image_path)
+                print("网络图片", image_path)
                 pass
             image_path = image_path.replace('\\', '/')
             doc.write(
@@ -280,7 +296,7 @@ class ChildThread(QThread):
         displayname = escape_js_and_html(displayname)
         if self.output_type == Output.HTML:
             try:
-                audio_path = media_msg_db.get_audio(msgSvrId, output_path=origin_docx_path + "/voice")
+                audio_path = media_msg_db.get_audio_path(msgSvrId, output_path=origin_docx_path + "/voice")
                 audio_path = audio_path.replace('/', '\\')
                 modify_audio_metadata(audio_path, displayname)
                 os.utime(audio_path, (timestamp, timestamp))
@@ -318,7 +334,7 @@ class ChildThread(QThread):
             displayname = MePC().name if is_send else self.contact.remark
         displayname = escape_js_and_html(displayname)
         if self.output_type == Output.HTML:
-            emoji_path = get_emoji(str_content, thumb=True, output_path=origin_docx_path + '/emoji')
+            emoji_path = get_emoji_path(str_content, thumb=True, output_path=origin_docx_path + '/emoji')
             emoji_path = './emoji/' + os.path.basename(emoji_path)
             doc.write(
                 f'''{{ type:{3}, text: '{emoji_path}',is_send:{is_send},avatar_path:'{avatar}',timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{displayname}'}},'''
@@ -388,7 +404,8 @@ class ChildThread(QThread):
         str_time = message[8]
         timestamp = message[5]
         is_chatroom = 1 if self.contact.is_chatroom else 0
-        str_content = str_content.replace('<![CDATA[', "").replace(' <a href="weixin://revoke_edit_click">重新编辑</a>]]>', "")
+        str_content = str_content.replace('<![CDATA[', "").replace(
+            ' <a href="weixin://revoke_edit_click">重新编辑</a>]]>', "")
         res = findall('(</{0,1}(img|revo|_wc_cus|a).*?>)', str_content)
         for xmlstr, b in res:
             str_content = str_content.replace(xmlstr, "")
@@ -495,13 +512,13 @@ class ChildThread(QThread):
             stream.setCodec('utf-8')
             content = stream.readAll()
             file.close()
-            html_head,html_end = content.split('/*注意看这是分割线*/')
+            html_head, html_end = content.split('/*注意看这是分割线*/')
         f = open(filename, 'w', encoding='utf-8')
         f.write(html_head.replace("<title>Chat Records</title>", f"<title>{self.contact.remark}</title>"))
         MePC().avatar.save(os.path.join(f"{origin_docx_path}/avatar/{MePC().wxid}.png"))
         if self.contact.is_chatroom:
             for message in messages:
-                if message[4]: # is_send
+                if message[4]:  # is_send
                     continue
                 try:
                     chatroom_avatar_path = f"{origin_docx_path}/avatar/{message[12].wxid}.png"
@@ -513,12 +530,12 @@ class ChildThread(QThread):
         else:
             self.contact.avatar.save(os.path.join(f"{origin_docx_path}/avatar/{self.contact.wxid}.png"))
         self.rangeSignal.emit(len(messages))
-        total_steps = len(messages)
         for index, message in enumerate(messages):
             type_ = message[2]
             sub_type = message[3]
             timestamp = message[5]
-            self.progressSignal.emit(int((index + 1) / total_steps * 100))
+            if type_ != 34 and type_ != 47:
+                self.progressSignal.emit(1)
             if self.is_5_min(timestamp):
                 str_time = message[8]
                 f.write(
@@ -582,4 +599,52 @@ class ChildThread(QThread):
             self.to_txt()
 
     def cancel(self):
-        self.requestInterruption()
+        self.requestInterruption()
+
+
+class OutputMedia(QThread):
+    okSingal = pyqtSignal(int)
+    progressSignal = pyqtSignal(int)
+
+    def __init__(self, contact):
+        super().__init__()
+        self.contact = contact
+
+    def run(self):
+        origin_docx_path = f"{os.path.abspath('.')}/data/聊天记录/{self.contact.remark}"
+        messages = msg_db.get_messages_by_type(self.contact.wxid, 34)
+        for message in messages:
+            is_send = message[4]
+            msgSvrId = message[9]
+            audio_path = media_msg_db.get_audio(msgSvrId, output_path=origin_docx_path + "/voice")
+            audio_path = audio_path.replace('/', '\\')
+            if self.contact.is_chatroom:
+                if is_send:
+                    displayname = MePC().name
+                else:
+                    displayname = message[12].remark
+            else:
+                displayname = MePC().name if is_send else self.contact.remark
+            displayname = escape_js_and_html(displayname)
+            modify_audio_metadata(audio_path, displayname)
+            # os.utime(audio_path, (timestamp, timestamp))
+            self.progressSignal.emit(1)
+        self.okSingal.emit(34)
+
+
+class OutputEmoji(QThread):
+    okSingal = pyqtSignal(int)
+    progressSignal = pyqtSignal(int)
+
+    def __init__(self, contact):
+        super().__init__()
+        self.contact = contact
+
+    def run(self):
+        origin_docx_path = f"{os.path.abspath('.')}/data/聊天记录/{self.contact.remark}"
+        messages = msg_db.get_messages_by_type(self.contact.wxid, 47)
+        for message in messages:
+            str_content = message[7]
+            emoji_path = get_emoji(str_content, thumb=True, output_path=origin_docx_path + '/emoji')
+            self.progressSignal.emit(1)
+        self.okSingal.emit(34)

app/ui/contact/export_dialog.py

@@ -1,3 +1,6 @@
+import time
+
+from PyQt5.QtCore import QTimer
 from PyQt5.QtWidgets import QApplication, QWidget, QPushButton, QDialog, QVBoxLayout, QCheckBox, QHBoxLayout, \
     QProgressBar, QLabel, QMessageBox
 
@@ -20,6 +23,7 @@ QPushButton:hover {
 }
 """
 
+
 class ExportDialog(QDialog):
     def __init__(self, contact=None, title="选择导出的类型", file_type="csv", parent=None):
         super(ExportDialog, self).__init__(parent)
@@ -27,14 +31,15 @@ class ExportDialog(QDialog):
         self.contact = contact
         if file_type == 'html':
             self.export_type = Output.HTML
-            self.export_choices = {"文本": True, "图片": True, "语音": True, "视频": True, "表情包": True,
+            self.export_choices = {"文本": True, "图片": True, "语音": False, "视频": False, "表情包": False,
                                    '拍一拍等系统消息': True}  # 定义导出的数据类型，默认全部选择
         elif file_type == 'csv':
             self.export_type = Output.CSV
             self.export_choices = {"文本": True, "图片": True, "视频": True, "表情包": True}  # 定义导出的数据类型，默认全部选择
         elif file_type == 'txt':
             self.export_type = Output.TXT
-            self.export_choices = {"文本": True, "图片": True, "语音": True, "视频": True, "表情包": True}  # 定义导出的数据类型，默认全部选择
+            self.export_choices = {"文本": True, "图片": True, "语音": True, "视频": True,
+                                   "表情包": True}  # 定义导出的数据类型，默认全部选择
         else:
             self.export_choices = {"文本": True, "图片": True, "视频": True, "表情包": True}  # 定义导出的数据类型，默认全部选择
         self.setWindowTitle(title)
@@ -43,14 +48,17 @@ class ExportDialog(QDialog):
         self.worker = None  # 导出线程
         self.progress_bar = QProgressBar(self)
         self.progress_label = QLabel(self)
+        self.time_label = QLabel(self)
         for export_type, default_state in self.export_choices.items():
             checkbox = QCheckBox(export_type)
             checkbox.setChecked(default_state)
             layout.addWidget(checkbox)
         layout.addWidget(self.progress_bar)
         layout.addWidget(self.progress_label)
+        layout.addWidget(self.time_label)
         self.notice_label = QLabel(self)
-        self.notice_label.setText("注意:导出HTML时选择图片、视频、语音、表情包（特别是表情包）\n会导致大大影响导出速度，请合理选择导出的类型")
+        self.notice_label.setText(
+            "注意:导出HTML时选择图片、视频、语音、表情包（特别是表情包）\n会导致大大影响导出速度，请合理选择导出的类型")
         layout.addWidget(self.notice_label)
         hlayout = QHBoxLayout(self)
         self.export_button = QPushButton("导出")
@@ -62,6 +70,11 @@ class ExportDialog(QDialog):
         hlayout.addWidget(self.cancel_button)
         layout.addLayout(hlayout)
         self.setLayout(layout)
+        self.timer = QTimer(self)
+        self.time = 0
+        self.total_msg_num = 100  # 总的消息个数
+        self.num = 0  # 当前完成的消息个数
+        self.timer.timeout.connect(self.update_elapsed_time)
 
     def export_data(self):
         self.export_button.setEnabled(False)
@@ -75,12 +88,22 @@ class ExportDialog(QDialog):
         self.worker = Output(self.contact, type_=self.export_type, message_types=selected_types)
         self.worker.progressSignal.connect(self.update_progress)
         self.worker.okSignal.connect(self.export_finished)
+        self.worker.rangeSignal.connect(self.set_total_msg_num)
         self.worker.start()
+        # 启动定时器，每1000毫秒更新一次任务进度
+        self.timer.start(1000)
+        self.start_time = time.time()
         # self.accept()  # 使用accept关闭对话框
 
+    def set_total_msg_num(self, num):
+        self.total_msg_num = num
+
     def export_finished(self):
         self.export_button.setEnabled(True)
         self.cancel_button.setEnabled(True)
+        self.time = 0
+        end_time = time.time()
+        print(f'总耗时:{end_time - self.start_time}s')
         reply = QMessageBox(self)
         reply.setIcon(QMessageBox.Information)
         reply.setWindowTitle('OK')
@@ -90,7 +113,13 @@ class ExportDialog(QDialog):
         api = reply.exec_()
         self.accept()
 
+    def update_elapsed_time(self):
+        self.time += 1
+        self.time_label.setText(f"耗时: {self.time}s")
+
     def update_progress(self, progress_percentage):
+        self.num += 1
+        progress_percentage = int((self.num) / self.total_msg_num * 100)
         self.progress_bar.setValue(progress_percentage)
         self.progress_label.setText(f"导出进度: {progress_percentage}%")
 

app/util/emoji.py

@@ -174,9 +174,9 @@ def get_most_emoji(messages):
         except:
             dic[md5] = [1, emoji_info]
     md5_nums = [(num[0], key, num[1]) for key, num in dic.items()]
-    md5_nums.sort(key=lambda x: x[0],reverse=True)
+    md5_nums.sort(key=lambda x: x[0], reverse=True)
     if not md5_nums:
-        return '',0
+        return '', 0
     md5 = md5_nums[0][1]
     num = md5_nums[0][0]
     emoji_info = md5_nums[0][2]
@@ -195,7 +195,6 @@ def get_emoji(xml_string, thumb=True, output_path=root_path) -> str:
             prefix = 'th_' if thumb else ''
             file_path = os.path.join(output_path, prefix + md5 + f)
             if os.path.exists(file_path):
-                print('表情包已存在')
                 return file_path
         url = emoji_info['thumburl'] if thumb else emoji_info['cdnurl']
         if not url or url == "":
@@ -231,6 +230,21 @@ def get_emoji(xml_string, thumb=True, output_path=root_path) -> str:
         return output_path
 
 
+def get_emoji_path(xml_string, thumb=True, output_path=root_path) -> str:
+    try:
+        emoji_info = parser_xml(xml_string)
+        md5 = emoji_info['md5']
+        image_format = ['.png', '.gif', '.jpeg']
+        for f in image_format:
+            prefix = 'th_' if thumb else ''
+            file_path = os.path.join(output_path, prefix + md5 + f)
+            return file_path
+    except:
+        logger.error(traceback.format_exc())
+        output_path = os.path.join(output_path, "404.png")
+        return output_path
+
+
 if __name__ == '__main__':
     # xml_string = '<msg><emoji fromusername = "wxid_0o18ef858vnu22" tousername = "wxid_27hqbq7vx5hf22" type="2" idbuffer="media:0_0" md5="71ce49ed3ce9e57e43e07f802983bf45" len = "352588" productid="com.tencent.xin.emoticon.person.stiker_1678703862259eb01f2ef4a313" androidmd5="71ce49ed3ce9e57e43e07f802983bf45" androidlen="352588" s60v3md5 = "71ce49ed3ce9e57e43e07f802983bf45" s60v3len="352588" s60v5md5 = "71ce49ed3ce9e57e43e07f802983bf45" s60v5len="352588" cdnurl = "http://wxapp.tc.qq.com/262/20304/stodownload?m=71ce49ed3ce9e57e43e07f802983bf45&amp;filekey=30350201010421301f020201060402535a041071ce49ed3ce9e57e43e07f802983bf45020305614c040d00000004627466730000000132&amp;hy=SZ&amp;storeid=263ffa00b000720d03274c5820000010600004f50535a1ca0c950b64287022&amp;bizid=1023" designerid = "" thumburl = "http://mmbiz.qpic.cn/mmemoticon/ajNVdqHZLLDSKTMRgM8agiadpFhKz9IJ3cD5Ra2sTROibOaShdt3D4z6PfE92WkjQY/0" encrypturl = "http://wxapp.tc.qq.com/262/20304/stodownload?m=cbaae1d847aac6389652b65562bacaa2&amp;filekey=30350201010421301f020201060402535a0410cbaae1d847aac6389652b65562bacaa20203056150040d00000004627466730000000132&amp;hy=SZ&amp;storeid=263ffa00b0008d8223274c5820000010600004f50535a17b82910b64764739&amp;bizid=1023" aeskey= "7051ab2a34442dec63434832463f45ce" externurl = "http://wxapp.tc.qq.com/262/20304/stodownload?m=960f68693454dfa64b9966ca5d70dbd3&amp;filekey=30340201010420301e020201060402535a0410960f68693454dfa64b9966ca5d70dbd3020221a0040d00000004627466730000000132&amp;hy=SZ&amp;storeid=26423dbe3000793a8720e40de0000010600004f50535a1d40c950b71be0a50&amp;bizid=1023" externmd5 = "41895664fc5a77878e2155fc96209a19" width= "240" height= "240" tpurl= "" tpauthkey= "" attachedtext= "" attachedtextcolor= "" lensid= "" emojiattr= "" linkid= "" desc= "ChEKB2RlZmF1bHQSBuWNlee6rw==" ></emoji> </msg>'
     # res1 = parser_xml(xml_string)