wx频道增加群语音聊天功能

channel/wechat/wechat_channel.py

@@ -23,10 +23,14 @@ import time
 
 
 thread_pool = ThreadPoolExecutor(max_workers=8)
+
+
 def thread_pool_callback(worker):
     worker_exception = worker.exception()
     if worker_exception:
-        logger.exception("Worker return exception: {}".format(worker_exception))
+        logger.exception(
+            "Worker return exception: {}".format(worker_exception))
+
 
 @itchat.msg_register(TEXT)
 def handler_single_msg(msg):
@@ -46,20 +50,27 @@ def handler_single_voice(msg):
     return None
 
 
+@itchat.msg_register(VOICE, isGroupChat=True)
+def handler_group_voice(msg):
+    WechatChannel().handle_group_voice(msg)
+    return None
+
+
 class WechatChannel(Channel):
     def __init__(self):
         pass
 
     def startup(self):
 
-        itchat.instance.receivingRetryCount = 600 # 修改断线超时时间
+        itchat.instance.receivingRetryCount = 600  # 修改断线超时时间
         # login by scan QRCode
         hotReload = conf().get('hot_reload', False)
         try:
             itchat.auto_login(enableCmdQR=2, hotReload=hotReload)
         except Exception as e:
             if hotReload:
-                logger.error("Hot reload failed, try to login without hot reload")
+                logger.error(
+                    "Hot reload failed, try to login without hot reload")
                 itchat.logout()
                 os.remove("itchat.pkl")
                 itchat.auto_login(enableCmdQR=2, hotReload=hotReload)
@@ -85,21 +96,23 @@ class WechatChannel(Channel):
         from_user_id = msg['FromUserName']
         other_user_id = msg['User']['UserName']
         if from_user_id == other_user_id:
-            context = Context(ContextType.VOICE,msg['FileName'])
-            context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id}
-            thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback)
-
+            context = Context(ContextType.VOICE, msg['FileName'])
+            context.kwargs = {'isgroup': False, 'msg': msg,
+                              'receiver': other_user_id, 'session_id': other_user_id}
+            thread_pool.submit(self.handle, context).add_done_callback(
+                thread_pool_callback)
 
     @time_checker
     def handle_text(self, msg):
-        logger.debug("[WX]receive text msg: " + json.dumps(msg, ensure_ascii=False))
+        logger.debug("[WX]receive text msg: " +
+                     json.dumps(msg, ensure_ascii=False))
         content = msg['Text']
         from_user_id = msg['FromUserName']
         to_user_id = msg['ToUserName']              # 接收人id
         other_user_id = msg['User']['UserName']     # 对手方id
         create_time = msg['CreateTime']             # 消息时间
         match_prefix = check_prefix(content, conf().get('single_chat_prefix'))
-        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:    #跳过1分钟前的历史消息
+        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:  # 跳过1分钟前的历史消息
             logger.debug("[WX]history message skipped")
             return
         if "」\n- - - - - - - - - - - - - - -" in content:
@@ -110,9 +123,11 @@ class WechatChannel(Channel):
         elif match_prefix is None:
             return
         context = Context()
-        context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id}
+        context.kwargs = {'isgroup': False, 'msg': msg,
+                          'receiver': other_user_id, 'session_id': other_user_id}
 
-        img_match_prefix = check_prefix(content, conf().get('image_create_prefix'))
+        img_match_prefix = check_prefix(
+            content, conf().get('image_create_prefix'))
         if img_match_prefix:
             content = content.replace(img_match_prefix, '', 1).strip()
             context.type = ContextType.IMAGE_CREATE
@@ -120,15 +135,17 @@ class WechatChannel(Channel):
             context.type = ContextType.TEXT
 
         context.content = content
-        thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback)
+        thread_pool.submit(self.handle, context).add_done_callback(
+            thread_pool_callback)
 
     @time_checker
     def handle_group(self, msg):
-        logger.debug("[WX]receive group msg: " + json.dumps(msg, ensure_ascii=False))
+        logger.debug("[WX]receive group msg: " +
+                     json.dumps(msg, ensure_ascii=False))
         group_name = msg['User'].get('NickName', None)
         group_id = msg['User'].get('UserName', None)
         create_time = msg['CreateTime']             # 消息时间
-        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:    #跳过1分钟前的历史消息
+        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:  # 跳过1分钟前的历史消息
             logger.debug("[WX]history group message skipped")
             return
         if not group_name:
@@ -146,12 +163,14 @@ class WechatChannel(Channel):
             return ""
         config = conf()
         match_prefix = (msg['IsAt'] and not config.get("group_at_off", False)) or check_prefix(origin_content, config.get('group_chat_prefix')) \
-                       or check_contain(origin_content, config.get('group_chat_keyword'))
+            or check_contain(origin_content, config.get('group_chat_keyword'))
         if ('ALL_GROUP' in config.get('group_name_white_list') or group_name in config.get('group_name_white_list') or check_contain(group_name, config.get('group_name_keyword_white_list'))) and match_prefix:
             context = Context()
-            context.kwargs = { 'isgroup': True, 'msg': msg, 'receiver': group_id}
-            
-            img_match_prefix = check_prefix(content, conf().get('image_create_prefix'))
+            context.kwargs = {'isgroup': True,
+                              'msg': msg, 'receiver': group_id}
+
+            img_match_prefix = check_prefix(
+                content, conf().get('image_create_prefix'))
             if img_match_prefix:
                 content = content.replace(img_match_prefix, '', 1).strip()
                 context.type = ContextType.IMAGE_CREATE
@@ -167,10 +186,24 @@ class WechatChannel(Channel):
             else:
                 context['session_id'] = msg['ActualUserName']
 
-            thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback)
+            thread_pool.submit(self.handle, context).add_done_callback(
+                thread_pool_callback)
+
+    def handle_group_voice(self, msg):
+        if conf().get('speech_recognition') != True:
+            return
+        logger.debug("[WX]receive group voice msg: " + msg['FileName'])
+        group_name = msg['User'].get('NickName', None)
+        group_id = msg['User'].get('UserName', None)
+        from_user_id = msg['ActualUserName']
+        context = Context(ContextType.VOICE, msg['FileName'])
+        context.kwargs = {'isgroup': True, 'msg': msg,
+                          'receiver': group_id, 'session_id': from_user_id}
+        thread_pool.submit(self.handle, context).add_done_callback(
+            thread_pool_callback)
 
     # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息
-    def send(self, reply : Reply, receiver):
+    def send(self, reply: Reply, receiver):
         if reply.type == ReplyType.TEXT:
             itchat.send(reply.content, toUserName=receiver)
             logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver))
@@ -179,8 +212,9 @@ class WechatChannel(Channel):
             logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver))
         elif reply.type == ReplyType.VOICE:
             itchat.send_file(reply.content, toUserName=receiver)
-            logger.info('[WX] sendFile={}, receiver={}'.format(reply.content, receiver))
-        elif reply.type == ReplyType.IMAGE_URL: # 从网络下载图片
+            logger.info('[WX] sendFile={}, receiver={}'.format(
+                reply.content, receiver))
+        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
             img_url = reply.content
             pic_res = requests.get(img_url, stream=True)
             image_storage = io.BytesIO()
@@ -188,8 +222,9 @@ class WechatChannel(Channel):
                 image_storage.write(block)
             image_storage.seek(0)
             itchat.send_image(image_storage, toUserName=receiver)
-            logger.info('[WX] sendImage url={}, receiver={}'.format(img_url,receiver))
-        elif reply.type == ReplyType.IMAGE: # 从文件读取图片
+            logger.info('[WX] sendImage url={}, receiver={}'.format(
+                img_url, receiver))
+        elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
             image_storage = reply.content
             image_storage.seek(0)
             itchat.send_image(image_storage, toUserName=receiver)
@@ -200,12 +235,14 @@ class WechatChannel(Channel):
         reply = Reply()
 
         logger.debug('[WX] ready to handle context: {}'.format(context))
-        
+
         # reply的构建步骤
-        e_context = PluginManager().emit_event(EventContext(Event.ON_HANDLE_CONTEXT, {'channel' : self, 'context': context, 'reply': reply}))
+        e_context = PluginManager().emit_event(EventContext(Event.ON_HANDLE_CONTEXT, {
+            'channel': self, 'context': context, 'reply': reply}))
         reply = e_context['reply']
         if not e_context.is_pass():
-            logger.debug('[WX] ready to handle context: type={}, content={}'.format(context.type, context.content))
+            logger.debug('[WX] ready to handle context: type={}, content={}'.format(
+                context.type, context.content))
             if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE:
                 reply = super().build_reply_content(context.content, context)
             elif context.type == ContextType.VOICE:
@@ -214,8 +251,24 @@ class WechatChannel(Channel):
                 msg.download(file_name)
                 reply = super().build_voice_to_text(file_name)
                 if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO:
-                    context.content = reply.content # 语音转文字后，将文字内容作为新的context
+                    context.content = reply.content  # 语音转文字后，将文字内容作为新的context
                     context.type = ContextType.TEXT
+                    if (context["isgroup"] == True):
+                        # 校验关键字
+                        match_prefix = self.check_prefix(context.content, conf().get('group_chat_prefix')) \
+                            or self.check_contain(context.content, conf().get('group_chat_keyword'))
+                        # Wechaty判断is_at为True，返回的内容是过滤掉@之后的内容；而is_at为False，则会返回完整的内容
+                        if match_prefix is not None:
+                            # 故判断如果匹配到自定义前缀，则返回过滤掉前缀+空格后的内容，用于实现类似自定义+前缀触发生成AI图片的功能
+                            prefixes = conf().get('group_chat_prefix')
+                            for prefix in prefixes:
+                                if context.content.startswith(prefix):
+                                    context.content = context.content.replace(prefix, '', 1).strip()
+                                    break
+                        else:
+                            logger.info("[WX]receive voice check prefix: " + 'False')
+                            return
+                            
                     reply = super().build_reply_content(context.content, context)
                     if reply.type == ReplyType.TEXT:
                         if conf().get('voice_reply_voice'):
@@ -225,16 +278,19 @@ class WechatChannel(Channel):
                 return
 
         logger.debug('[WX] ready to decorate reply: {}'.format(reply))
-        
+
         # reply的包装步骤
         if reply and reply.type:
-            e_context = PluginManager().emit_event(EventContext(Event.ON_DECORATE_REPLY, {'channel' : self, 'context': context, 'reply': reply}))
-            reply=e_context['reply']
+            e_context = PluginManager().emit_event(EventContext(Event.ON_DECORATE_REPLY, {
+                'channel': self, 'context': context, 'reply': reply}))
+            reply = e_context['reply']
             if not e_context.is_pass() and reply and reply.type:
                 if reply.type == ReplyType.TEXT:
                     reply_text = reply.content
                     if context['isgroup']:
-                        reply_text = '@' +  context['msg']['ActualNickName'] + ' ' + reply_text.strip()
+                        reply_text = '@' + \
+                            context['msg']['ActualNickName'] + \
+                            ' ' + reply_text.strip()
                         reply_text = conf().get("group_chat_reply_prefix", "")+reply_text
                     else:
                         reply_text = conf().get("single_chat_reply_prefix", "")+reply_text
@@ -244,15 +300,18 @@ class WechatChannel(Channel):
                 elif reply.type == ReplyType.IMAGE_URL or reply.type == ReplyType.VOICE or reply.type == ReplyType.IMAGE:
                     pass
                 else:
-                    logger.error('[WX] unknown reply type: {}'.format(reply.type))
+                    logger.error(
+                        '[WX] unknown reply type: {}'.format(reply.type))
                     return
 
-        # reply的发送步骤   
+        # reply的发送步骤
         if reply and reply.type:
-            e_context = PluginManager().emit_event(EventContext(Event.ON_SEND_REPLY, {'channel' : self, 'context': context, 'reply': reply}))
-            reply=e_context['reply']
+            e_context = PluginManager().emit_event(EventContext(Event.ON_SEND_REPLY, {
+                'channel': self, 'context': context, 'reply': reply}))
+            reply = e_context['reply']
             if not e_context.is_pass() and reply and reply.type:
-                logger.debug('[WX] ready to send reply: {} to {}'.format(reply, context['receiver']))
+                logger.debug('[WX] ready to send reply: {} to {}'.format(
+                    reply, context['receiver']))
                 self.send(reply, context['receiver'])