v3.4.22

fix bug #298

astrbot/core/__init__.py

@@ -11,7 +11,8 @@ from astrbot.core.config import AstrBotConfig
 os.makedirs("data", exist_ok=True)
 
 astrbot_config = AstrBotConfig()
-html_renderer = HtmlRenderer()
+t2i_base_url = astrbot_config.get('t2i_endpoint', 'https://t2i.soulter.top/text2img')
+html_renderer = HtmlRenderer(t2i_base_url)
 logger = LogManager.GetLogger(log_name='astrbot')
 
 if os.environ.get('TESTING', ""):

astrbot/core/config/default.py

@@ -2,7 +2,7 @@
 如需修改配置，请在 `data/cmd_config.json` 中修改或者在管理面板中可视化修改。
 """
 
-VERSION = "3.4.21"
+VERSION = "3.4.22"
 DB_PATH = "data/data_v3.db"
 
 # 默认配置
@@ -29,7 +29,6 @@ DEFAULT_CONFIG = {
             "enable": False,
             "only_llm_result": True,
             "interval": "1.5,3.5",
-            "seg_prompt": "",
             "regex": ".*?[。？！~…]+|.+$"
         },
         "no_permission_reply": True,
@@ -64,8 +63,7 @@ DEFAULT_CONFIG = {
             "method": "possibility_reply",
             "possibility_reply": 0.1,
             "prompt": "",
-        },
-        "put_history_to_prompt": True,
+        }
     },
     "content_safety": {
         "internal_keywords": {"enable": True, "extra_keywords": []},
@@ -220,11 +218,6 @@ CONFIG_METADATA_2 = {
                                 "type": "string",
                                 "hint": "每一段回复的间隔时间，格式为 `最小时间,最大时间`。如 `0.75,2.5`",
                             },
-                            "seg_prompt": {
-                                "description": "分段提示词辅助",
-                                "type": "string",
-                                "hint": "此项为空时表达不启用这个方法。此方法会调用一次LLM请求。让 LLM 在某一句话中插入一个可以用正则表达式分隔的标记，来实现LLM基于情感分段。如: `请基于情感对以下文本进行分段, 并在两段之间添加`<seg>`以便我用正则匹配。`    然后将下面的正则表达式更换为`.+?<seg>`。",
-                            },
                             "regex": {
                                 "description": "正则表达式",
                                 "type": "string",
@@ -252,7 +245,7 @@ CONFIG_METADATA_2 = {
                         "type": "list",
                         "items": {"type": "string"},
                         "obvious_hint": True,
-                        "hint": "AstrBot 只处理所填写的 ID 发来的消息事件。为空时不启用白名单过滤。可以使用 /sid 指令获取在某个平台上的会话 ID。也可在 AstrBot 日志内获取会话 ID，当一条消息没通过白名单时，会输出 INFO 级别的日志。会话 ID 类似 aiocqhttp:GroupMessage:547540978",
+                        "hint": "AstrBot 只处理所填写的 ID 发来的消息事件。为空时不启用白名单过滤。可以使用 /sid 指令获取在某个平台上的会话 ID。也可在 AstrBot 日志内获取会话 ID，当一条消息没通过白名单时，会输出 INFO 级别的日志。会话 ID 类似 aiocqhttp:GroupMessage:547540978。管理员可使用 /wl 添加白名单",
                     },
                     "id_whitelist_log": {
                         "description": "打印白名单日志",
@@ -763,12 +756,6 @@ CONFIG_METADATA_2 = {
                                 "hint": "提示词。当提示词为空时，如果触发回复，则向 LLM 请求的是触发的消息的内容；否则是提示词。此项可以和定时回复（暂未实现）配合使用。",
                             },
                         },
-                    },
-                    "put_history_to_prompt": {
-                        "description": "将群聊历史记录作为 prompt",
-                        "type": "bool",
-                        "obvious_hint": True,
-                        "hint": "需要先启用 group_icl_enable。此功能会将群聊历史记录放到 prompt 再请求。如果关闭，则是放在 system_prompt。如果开启了主动回复，建议启用，模型能够更好地完成回复任务。",
                     }
                 },
             },

astrbot/core/pipeline/process_stage/method/llm_request.py

@@ -129,6 +129,9 @@ class LLMRequestSubStage(Stage):
                     req.prompt += extra_prompt
                     async for _ in self.process(event, _nested=True):
                         yield
+                else:
+                    if llm_response.completion_text:
+                        event.set_result(MessageEventResult().message(llm_response.completion_text))
 
         except BaseException as e:
             logger.error(traceback.format_exc())

astrbot/core/pipeline/result_decorate/stage.py

@@ -30,7 +30,6 @@ class ResultDecorateStage:
         # 分段回复
         self.enable_segmented_reply = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
         self.only_llm_result = ctx.astrbot_config['platform_settings']['segmented_reply']['only_llm_result']
-        self.seg_prompt = ctx.astrbot_config['platform_settings']['segmented_reply']['seg_prompt']
         self.regex = ctx.astrbot_config['platform_settings']['segmented_reply']['regex']
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
@@ -57,19 +56,6 @@ class ResultDecorateStage:
                     new_chain = []
                     for comp in result.chain:
                         if isinstance(comp, Plain):
-                            
-                            if self.seg_prompt:
-                                try:
-                                    llm_resp = await self.ctx.plugin_manager.context.get_using_provider().text_chat(
-                                        prompt=f"{self.seg_prompt}\n{comp.text}",
-                                    )
-                                    comp.text = llm_resp.completion_text
-                                except BaseException as e:
-                                    traceback.print_exc()
-                                    logger.warning("使用 LLM 分段回复失败。将不分段回复。： " + str(e))
-                                    new_chain.append(comp)
-                                    continue
-                            
                             split_response = re.findall(self.regex, comp.text)
                             if not split_response:
                                 new_chain.append(comp)

astrbot/core/provider/sources/gemini_source.py

@@ -181,9 +181,9 @@ class ProviderGoogleGenAI(Provider):
             llm_response = await self._query(payloads, func_tool)
         except Exception as e:
             if "maximum context length" in str(e):
-                retry_cnt = 10
+                retry_cnt = 20
                 while retry_cnt > 0:
-                    logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。")
+                    logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
                     try:
                         await self.pop_record(context_query)
                         llm_response = await self._query(payloads, func_tool)
@@ -231,6 +231,9 @@ class ProviderGoogleGenAI(Provider):
                     image_data = await self.encode_image_bs64(image_path)
                 else:
                     image_data = await self.encode_image_bs64(image_url)
+                if not image_data:
+                    logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                    continue
                 user_content["content"].append({"type": "image_url", "image_url": {"url": image_data}})
             return user_content
         else:

astrbot/core/provider/sources/openai_source.py

@@ -80,12 +80,14 @@ class ProviderOpenAIOfficial(Provider):
             raise Exception("API 返回的 completion 为空。")
         choice = completion.choices[0]
         
+        llm_response = LLMResponse("assistant")
+                
         if choice.message.content:
             # text completion
             completion_text = str(choice.message.content).strip()
-
-            return LLMResponse("assistant", completion_text, raw_completion=completion)
-        elif choice.message.tool_calls:
+            llm_response.completion_text = completion_text
+        
+        if choice.message.tool_calls:
             # tools call (function calling)
             args_ls = []
             func_name_ls = []
@@ -95,10 +97,15 @@ class ProviderOpenAIOfficial(Provider):
                         args = json.loads(tool_call.function.arguments)
                         args_ls.append(args)
                         func_name_ls.append(tool_call.function.name)
-            return LLMResponse(role="tool", tools_call_args=args_ls, tools_call_name=func_name_ls, raw_completion=completion)
-        else:
+            llm_response.role = "tool"
+            llm_response.tools_call_args = args_ls
+            llm_response.tools_call_name = func_name_ls
+
+        if not llm_response.completion_text and not llm_response.tools_call_args:
             logger.error(f"API 返回的 completion 无法解析：{completion}。")
-            raise Exception("Internal Error")
+            raise Exception(f"API 返回的 completion 无法解析：{completion}。")
+        
+        return llm_response
 
     async def text_chat(
         self,
@@ -135,15 +142,16 @@ class ProviderOpenAIOfficial(Provider):
             # 尝试删除所有 image
             new_contexts = await self._remove_image_from_context(context_query)
             payloads['messages'] = new_contexts
+            context_query = new_contexts
             llm_response = await self._query(payloads, func_tool)
         except Exception as e:
             if "maximum context length" in str(e):
                 # 重试 10 次
-                retry_cnt = 10
+                retry_cnt = 20
                 while retry_cnt > 0:
-                    logger.warning("上下文长度超过限制。尝试弹出最早的记录然后重试。")
+                    logger.warning(f"上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
                     try:
-                        await self.pop_record(session_id)
+                        await self.pop_record(context_query)
                         llm_response = await self._query(payloads, func_tool)
                         break
                     except Exception as e:
@@ -235,6 +243,9 @@ class ProviderOpenAIOfficial(Provider):
                     image_data = await self.encode_image_bs64(image_path)
                 else:
                     image_data = await self.encode_image_bs64(image_url)
+                if not image_data:
+                    logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                    continue
                 user_content["content"].append({"type": "image_url", "image_url": {"url": image_data}})
             return user_content
         else:

astrbot/core/utils/dify_api_client.py

@@ -35,19 +35,30 @@ class DifyAPIClient:
                 text = await resp.text()
                 raise Exception(f"chat_messages 请求失败：{resp.status}. {text}")
             
+            buffer = ""
             while True:
-                data = await resp.content.read(8192) # 防止数据过大导致高水位报错
-                if not data:
+                # 保持原有的8192字节限制，防止数据过大导致高水位报错
+                chunk = await resp.content.read(8192)
+                if not chunk:
                     break
-                if not data.strip():
-                    continue
-                elif data.startswith(b"data:"):
-                    try:
-                        json_ = json.loads(data[5:])
-                        yield json_
-                    except BaseException:
-                        pass
                     
+                buffer += chunk.decode('utf-8')
+                blocks = buffer.split('\n\n')
+                
+                # 处理完整的数据块
+                for block in blocks[:-1]:
+                    if block.strip() and block.startswith('data:'):
+                        try:
+                            json_str = block[5:]  # 移除 "data:" 前缀
+                            json_obj = json.loads(json_str)
+                            yield json_obj
+                        except json.JSONDecodeError as e:
+                            logger.error(f"JSON解析错误: {str(e)}")
+                            logger.error(f"原始数据块: {json_str}")
+                
+                # 保留最后一个可能不完整的块
+                buffer = blocks[-1] if blocks else ""
+
     async def workflow_run(
         self,
         inputs: Dict,
@@ -66,20 +77,32 @@ class DifyAPIClient:
         ) as resp:
             if resp.status != 200:
                 text = await resp.text()
-                raise Exception(f"chat_messages 请求失败：{resp.status}. {text}")
+                raise Exception(f"workflow_run 请求失败：{resp.status}. {text}")
+            
+            buffer = ""
             while True:
-                data = await resp.content.read(8192) # 防止数据过大导致高水位报错
-                if not data:
+                # 保持原有的8192字节限制，防止数据过大导致高水位报错
+                chunk = await resp.content.read(8192)
+                if not chunk:
                     break
-                if not data.strip():
-                    continue
-                elif data.startswith(b"data:"):
-                    try:
-                        json_ = json.loads(data[5:])
-                        yield json_
-                    except BaseException:
-                        pass
                     
+                buffer += chunk.decode('utf-8')
+                blocks = buffer.split('\n\n')
+                
+                # 处理完整的数据块
+                for block in blocks[:-1]:
+                    if block.strip() and block.startswith('data:'):
+                        try:
+                            json_str = block[5:]  # 移除 "data:" 前缀
+                            json_obj = json.loads(json_str)
+                            yield json_obj
+                        except json.JSONDecodeError as e:
+                            logger.error(f"JSON解析错误: {str(e)}")
+                            logger.error(f"原始数据块: {json_str}")
+                
+                # 保留最后一个可能不完整的块
+                buffer = blocks[-1] if blocks else ""
+
     async def file_upload(
         self,
         file_path: str,

astrbot/core/utils/t2i/network_strategy.py

@@ -14,11 +14,22 @@ class NetworkRenderStrategy(RenderStrategy):
             base_url = ASTRBOT_T2I_DEFAULT_ENDPOINT
         self.BASE_RENDER_URL = base_url
         self.TEMPLATE_PATH = os.path.join(os.path.dirname(__file__), "template")
+        
+        if self.BASE_RENDER_URL.endswith("/"):
+            self.BASE_RENDER_URL = self.BASE_RENDER_URL[:-1]
+        if not self.BASE_RENDER_URL.endswith("text2img"):
+            self.BASE_RENDER_URL += "/text2img"
 
     def set_endpoint(self, base_url: str):
         if not base_url:
             base_url = ASTRBOT_T2I_DEFAULT_ENDPOINT
         self.BASE_RENDER_URL = base_url
+        
+        if self.BASE_RENDER_URL.endswith("/"):
+            self.BASE_RENDER_URL = self.BASE_RENDER_URL[:-1]
+        if not self.BASE_RENDER_URL.endswith("text2img"):
+            self.BASE_RENDER_URL += "/text2img"
+
 
     async def render_custom_template(self, tmpl_str: str, tmpl_data: dict, return_url: bool=True) -> str:
         '''使用自定义文转图模板'''

changelogs/v3.4.22.md

@@ -0,0 +1,12 @@
+# What's Changed
+
+1. fix: 400 Bad Request: The browser (or proxy) sent a request that this server could not understand. #396
+2. remove: 移除了 put_history_to_prompt。当主动回复时，将群聊记录将自动放入prompt，当未主动回复但是开启群聊增强时，群聊记录将放入system prompt
+3. fix: 插件错误信息点击关闭没反应 #394
+4. fix: 自部署文转图不生效 #352
+5. fix: Google Search 报 429 错误时，放宽 Exception 至其他搜索引擎 #405
+6. fix: 使用 Google Gemini （OpenAI 兼容）的部分情况下联网搜索等函数调用工具没被调用 #342
+7. fix: 修复尝试弹出最早的记录失效的问题
+8. fix: 移除了分段回复llm提示词辅助
+9. perf: 当图片数据为空时不加入上下文 #379
+10. 修复 dify 返回的结果带有多行数据时的 json 解析异常导致返回值为空的问题 #298 by @zhaolj

dashboard/src/views/ExtensionPage.vue

@@ -25,18 +25,22 @@ import { max } from 'date-fns';
                 <v-icon>mdi-alert-circle</v-icon>
               </v-btn>
             </template>
-            <v-card>
-              <v-card-title class="headline">错误信息</v-card-title>
-              <v-card-text>{{ extension_data.message }}
-                <br>
-                <small>详情请检查控制台</small>
-              </v-card-text>
 
-              <v-card-actions>
-                <v-spacer></v-spacer>
-                <v-btn color="primary" text>关闭</v-btn>
-              </v-card-actions>
-            </v-card>
+            <template v-slot:default="{ isActive }">
+              <v-card>
+                <v-card-title class="headline">错误信息</v-card-title>
+                <v-card-text>{{ extension_data.message }}
+                  <br>
+                  <small>详情请检查控制台</small>
+                </v-card-text>
+
+                <v-card-actions>
+                  <v-spacer></v-spacer>
+                  <v-btn color="primary" text @click="isActive.value = false">关闭</v-btn>
+                </v-card-actions>
+              </v-card>
+            </template>
+
           </v-dialog>
         </div>
       </div>
@@ -48,7 +52,8 @@ import { max } from 'date-fns';
           <span style="font-weight: bold;">By @{{ extension.author }}</span>
           <span> | 插件有 {{ extension.handlers.length }} 个行为</span>
           <p style="margin-top: 8px;">{{ extension.desc }}</p>
-          <a style="font-size: 12px; cursor: pointer; text-decoration: underline; color: #555;" @click="reloadPlugin(extension.name)">重载插件</a>
+          <a style="font-size: 12px; cursor: pointer; text-decoration: underline; color: #555;"
+            @click="reloadPlugin(extension.name)">重载插件</a>
         </div>
         <div class="d-flex align-center gap-2 " style="overflow-x: auto;">
           <v-btn v-if="!extension.reserved" class="text-none mr-2" size="small" text="Read" variant="flat" border
@@ -381,7 +386,7 @@ export default {
       if (this.upload_file !== null) {
         this.toast("正在从文件安装插件", "primary");
         const formData = new FormData();
-        formData.append('file', this.upload_file[0]);
+        formData.append('file', this.upload_file);
         axios.post('/api/plugin/install-upload', formData, {
           headers: {
             'Content-Type': 'multipart/form-data'

packages/astrbot/long_term_memory.py

@@ -33,7 +33,7 @@ class LongTermMemory:
         self.ar_possibility = self.active_reply["possibility_reply"]
         self.ar_prompt = self.active_reply.get("prompt", "")
         
-        self.put_history_to_prompt = self.config["put_history_to_prompt"]
+        # self.put_history_to_prompt = self.config["put_history_to_prompt"]
         
     async def remove_session(self, event: AstrMessageEvent) -> int:
         cnt = 0
@@ -110,11 +110,11 @@ class LongTermMemory:
         
         chats_str = '\n---\n'.join(self.session_chats[event.unified_msg_origin])
         
-        if self.put_history_to_prompt:
+        if self.enable_active_reply:
             prompt = req.prompt
             req.prompt = f"You are now in a chatroom. The chat history is as follows:\n{chats_str}"
             req.prompt += f"\nNow, a new message is coming: `{prompt}`. Please react to it. Only output your response and do not output any other information."
-            req.contexts = [] # 清空上下文，当使用了群聊增强，所有聊天记录都在一个prompt中。
+            req.contexts = [] # 清空上下文，当使用了主动回复，所有聊天记录都在一个prompt中。
         else:
             req.system_prompt += "You are now in a chatroom. The chat history is as follows: \n"
             req.system_prompt += chats_str

packages/astrbot/main.py

@@ -80,6 +80,7 @@ AstrBot 指令:
 /persona: 人格情景(op)
 /tool ls: 函数工具
 /key: API Key(op)
+/websearch: 网页搜索
 
 [其他]
 /set <变量名> <值>: 为会话定义变量。适用于 Dify 工作流输入。
@@ -227,6 +228,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("wl")
     async def wl(self, event: AstrMessageEvent, sid: str):
+        '''添加白名单。wl <sid>'''
         self.context.get_config()['platform_settings']['id_whitelist'].append(sid)
         self.context.get_config().save_config()
         event.set_result(MessageEventResult().message("添加白名单成功。"))
@@ -234,6 +236,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("dwl")
     async def dwl(self, event: AstrMessageEvent, sid: str):
+        '''删除白名单。dwl <sid>'''
         try:
             self.context.get_config()['platform_settings']['id_whitelist'].remove(sid)
             self.context.get_config().save_config()
@@ -274,7 +277,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("reset")
     async def reset(self, message: AstrMessageEvent):
-        
+        '''重置 LLM 会话'''
         if not self.context.get_using_provider():
             message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
             return
@@ -298,7 +301,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
 
     @filter.command("model")
     async def model_ls(self, message: AstrMessageEvent, idx_or_name: Union[int, str] = None):
-                
+        '''查看或者切换模型'''
         if not self.context.get_using_provider():
             message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
             return

packages/web_searcher/engines/__init__.py

@@ -1,9 +1,30 @@
 import random
-from .config import HEADERS, USER_AGENTS
 from bs4 import BeautifulSoup
 from aiohttp import ClientSession
 from dataclasses import dataclass
 from typing import List
+import urllib.parse
+
+HEADERS = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0',
+    'Accept': '*/*', 
+    'Connection': 'keep-alive', 
+    'Accept-Language': 'en-GB,en;q=0.5'
+}
+
+USER_AGENT_BING = 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0'
+USER_AGENTS = [
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1.2 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1 Safari/537.36',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0'
+]
 
 
 @dataclass
@@ -38,11 +59,13 @@ class SearchEngine():
         if data:
             async with ClientSession() as session:
                 async with session.post(url, headers=headers, data=data, timeout=self.TIMEOUT) as resp:
-                    return await resp.text(encoding="utf-8")
+                    ret = await resp.text(encoding="utf-8")
+                    return ret
         else:
             async with ClientSession() as session:
                 async with session.get(url, headers=headers, timeout=self.TIMEOUT) as resp:
-                    return await resp.text(encoding="utf-8")
+                    ret = await resp.text(encoding="utf-8")
+                    return ret
                 
     
     def tidy_text(self, text: str) -> str:
@@ -53,6 +76,8 @@ class SearchEngine():
 
 
     async def search(self, query: str, num_results: int) -> List[SearchResult]:
+        query = urllib.parse.quote(query)
+        
         try:
             resp = await self._get_next_page(query)
             soup = BeautifulSoup(resp, 'html.parser')

packages/web_searcher/engines/bing.py

@@ -1,11 +1,11 @@
 from typing import List
-from .engine import SearchEngine, SearchResult
-from .config import USER_AGENT_BING
+from . import SearchEngine, SearchResult
+from . import USER_AGENT_BING
 
 class Bing(SearchEngine):
     def __init__(self) -> None:
         super().__init__()
-        self.base_url = "https://www.bing.com"
+        self.base_urls = ["https://cn.bing.com", "https://www.bing.com"]
         self.headers.update({'User-Agent': USER_AGENT_BING})
 
     def _set_selector(self, selector: str):
@@ -19,11 +19,17 @@ class Bing(SearchEngine):
         return selectors[selector]
 
     async def _get_next_page(self, query) -> str:
-        if self.page == 1:
-            await self._get_html(self.base_url)
-        url = f'{self.base_url}/search?q={query}&form=QBLH&sp=-1&lq=0&pq=hi&sc=10-2&qs=n&sk=&cvid=DE75965E2D6346D681288933984DE48F&ghsh=0&ghacc=0&ghpl='
-        return await self._get_html(url, None)
-    
+        # if self.page == 1:
+        #     await self._get_html(self.base_url)
+        for base_url in self.base_urls:
+            try:
+                url = f'{base_url}/search?q={query}'
+                return await self._get_html(url, None)
+            except Exception as _:
+                self.base_url = base_url
+                continue
+        raise Exception("Bing search failed")
+
     async def search(self, query: str, num_results: int) -> List[SearchResult]:
         results = await super().search(query, num_results)
         for result in results:

packages/web_searcher/engines/config.py

@@ -1,20 +0,0 @@
-HEADERS = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0',
-    'Accept': '*/*', 
-    'Connection': 'keep-alive', 
-    'Accept-Language': 'en-GB,en;q=0.5'
-}
-
-USER_AGENT_BING = 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0'
-USER_AGENTS = [
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1.2 Safari/537.36',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1 Safari/537.36',
-    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
-    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0'
-]

packages/web_searcher/engines/google.py

@@ -1,7 +1,7 @@
 import os
 from googlesearch import search
 
-from .engine import SearchEngine, SearchResult
+from . import SearchEngine, SearchResult
 
 from typing import List
 

packages/web_searcher/engines/sogo.py

@@ -1,8 +1,8 @@
 import random
 import re
 from bs4 import BeautifulSoup
-from .engine import SearchEngine, SearchResult
-from .config import USER_AGENTS
+from . import SearchEngine, SearchResult
+from . import USER_AGENTS
 
 from typing import List
 

packages/web_searcher/main.py

@@ -9,7 +9,7 @@ from .engines.sogo import Sogo
 from .engines.google import Google
 from readability import Document
 from bs4 import BeautifulSoup
-from .engines.config import HEADERS, USER_AGENTS
+from .engines import HEADERS, USER_AGENTS
 
 
 @star.register(name="astrbot-web-searcher", desc="让 LLM 具有网页检索能力", author="Soulter", version="1.14.514")
@@ -85,19 +85,19 @@ class Main(star.Star):
         RESULT_NUM = 5
         try:
             results = await self.google.search(query, RESULT_NUM)
-        except BaseException as e:
+        except Exception as e:
             logger.error(f"google search error: {e}, try the next one...")
         if len(results) == 0:
             logger.debug("search google failed")
             try:
                 results = await self.bing_search.search(query, RESULT_NUM)
-            except BaseException as e:
+            except Exception as e:
                 logger.error(f"bing search error: {e}, try the next one...")
         if len(results) == 0:
             logger.debug("search bing failed")
             try:
                 results = await self.sogo_search.search(query, RESULT_NUM)
-            except BaseException as e:
+            except Exception as e:
                 logger.error(f"sogo search error: {e}")
         if len(results) == 0:
             logger.debug("search sogo failed")