@gecho-ai/gecho-bridge 1.1.4 → 1.1.6

package/.claude-plugin/plugin.json

@@ -0,0 +1,5 @@
+{
+  "name": "@gecho-ai/gecho-bridge",
+  "version": "1.1.6",
+  "description": "TikTok Search Tool for OpenClaw"
+}

package/.mcp.json

@@ -0,0 +1,10 @@
+{
+  "mcpServers": {
+    "gecho-tiktok-search": {
+      "command": "node",
+      "args": ["./mcp-client.js"],
+      "timeout": 600000,
+      "retries": 0
+    }
+  }
+}

package/README.md

@@ -1,29 +1,56 @@
 # Gecho Bridge 🚀
 
-Gecho Bridge is an MCP (Model Context Protocol) server that connects AI Agents (like Claude Desktop, Cursor, or OpenClaw) to TikTok via a Chrome extension. It allows your AI models to search and retrieve TikTok video metadata directly from the browser.
+🌐 **Gecho Bridge** 是一款通用的 MCP（Model Context Protocol）工具，旨在为你的大语言模型（LLM）与本地浏览器之间搭建一座桥梁。
+安装后，无论是使用 **OpenClaw**、**Hermes** 还是 **Trae**，你的 AI 助手都能直接控制浏览器，自动化完成 TikTok 搜索、数据抓取与深度商机洞察。
 
-## Features
+---
 
-- **Automated Search**: Search TikTok with keywords and auto-scroll to fetch results.
-- **Data Retrieval**: Get video IDs, titles, like counts, and play URLs.
-- **Dual-Layer Architecture**: A lightweight MCP Client that automatically manages a persistent Service Layer.
-- **Lazy Start**: The bridge automatically starts the background service when needed.
+## ✨ 适合谁用
 
-## Installation
+- 📊 **分析竞品**：输入关键词，快速获取 TikTok 前排高赞视频的各项互动数据。
+- 💡 **寻找爆款**：使用深度洞察工具分析特定品类（如 "portable blender"）的流行趋势，捕捉未被满足的市场蓝海。
+- 🤖 **自动化运营**：让大模型直接指挥浏览器，自动翻页抓取并生成数据报表，免去繁琐的手动统计。
 
-### 1. Install via npm
-```bash
-npm install -g @gecho-ai/gecho-bridge
-```
+## 🚀 能做什么
+
+- 自动唤起 Chrome 并在 TikTok 搜索指定关键词，模拟真人自然滚动加载。
+- 抓取海量结构化数据（视频 ID、标题、点赞量、播放链接等）并自动安全落盘为 JSON 文件。
+- 执行基于大数据检索的**异步深度洞察**，智能提炼爆款趋势与潜在商机。
+
+## 🔗 相关链接
 
-### 2. Install Chrome Extension
-Ensure you have the Gecho TikTok Extension installed and active in your Chrome browser. The bridge communicates with this extension via WebSocket.
+- **官网**：[https://gecho.ai/](https://gecho.ai/)
+- **ClawHub 插件页**：[https://clawhub.ai/plugins/gecho-bridge](https://clawhub.ai/plugins/gecho-bridge)
+- **Chrome 浏览器扩展**：[前往 Chrome 网上应用店下载](https://chromewebstore.google.com/detail/pjkaeenpekolahdbccjfenjcmanemlbj?utm_source=item-share-cb)
 
-## Configuration
+---
 
-### Claude Desktop
-Add the following to your `claude_desktop_config.json`:
+## 📦 安装与配置
 
+本项目基于标准 MCP 协议开发，可以无缝接入任何支持 MCP 的 AI 客户端（如 OpenClaw、Hermes、Trae 等）。
+
+### 0. 前置环境要求
+1. **Node.js**：>= 18（需支持 `npm` / `npx`）。
+2. **浏览器扩展**：请先[点击此处安装 Gecho 浏览器扩展](https://chromewebstore.google.com/detail/pjkaeenpekolahdbccjfenjcmanemlbj?utm_source=item-share-cb)。
+3. **网络与状态**：确保本地网络可稳定访问 TikTok，并在浏览器中登录账号，保持扩展在线。
+
+### 方式一：在 OpenClaw 中一键安装 (ClawHub)
+```bash
+openclaw plugins install @gecho-ai/gecho-bridge
+openclaw gateway restart
+```
+*如需升级已安装的版本，使用 `openclaw plugins update @gecho-ai/gecho-bridge` 即可。*
+
+### 方式二：在 Hermes 中一键配置 (Hermes Skill Hub)
+你可以通过以下命令将服务快捷添加到 Hermes 并重启：
+```bash
+hermes mcp add gecho-bridge --command npx --args="-y" --args="@gecho-ai/gecho-bridge@latest"
+hermes restart
+```
+*重启后，可通过 `hermes mcp list` 检查安装状态。*
+
+### 方式三：在 Trae / Claude Desktop 等通用客户端配置
+在支持手动配置的 MCP 客户端中，打开对应的 `mcp.json` 或 `claude_desktop_config.json` 文件，添加如下节点：
 ```json
 {
   "mcpServers": {
@@ -35,75 +62,84 @@ Add the following to your `claude_desktop_config.json`:
 }
 ```
 
-### Cursor
-Go to Settings -> MCP.
-Add a new MCP server:
-- **Name**: gecho-bridge
-- **Type**: command
-- **Command**: `npx -y @gecho-ai/gecho-bridge@latest`
+---
 
-### Save Path Configuration
-Search results are persisted to a JSON file. You can control the save directory in two ways:
+## 🏁 快速开始与常见流程
 
-1. Pass `save_dir` in the MCP tool call arguments.
-2. Set environment variable `GECHO_DATA_DIR` for the MCP process.
+环境配置完毕并重启 AI 客户端后，你可以直接通过自然语言向 AI 下达指令。
 
-Priority order used by the service:
+### 🔍 基础搜索 (`tiktok_search`)
+适用于快速检索和收集视频数据。
+**你可以这样说：**
+- *"帮我搜索 TikTok 关键词 'portable blender'，返回点赞最高的前 10 条"*
+- *"搜索 'cat toy'，并把完整结果保存到 /Users/yourname/gecho-data"*
 
-1. `save_dir` from request arguments
-2. `GECHO_DATA_DIR` environment variable
-3. Default `data` directory (`path.join(__dirname, "..", "data")`)
+**执行流程：**
+1. AI 唤起本地浏览器的 Gecho 扩展进行搜索和自动滚动。
+2. 抓取完成后，海量数据会自动落盘到本地。
+3. AI 会在会话中为你精简总结前 20 条高赞结果。
 
-File naming:
+### 📈 深度洞察 (`tiktok_insight`)
+适用于品类调研和趋势分析。
+**你可以这样说：**
+- *"请对 'outdoor picnic mat' 做 tiktok_insight 分析"*
+- *"对比 'desk setup' 和 'minimal desk' 的热视频风格与互动量"*
 
-- Result file pattern: `<query>_search_results.json`
-- Query text is sanitized to a safe file name before writing.
+**执行流程：**
+1. 插件会下发异步洞察任务，并立即返回一个 `jobId`。
+2. **⚠️ 高危注意**：洞察分析涉及深度抓取和 AI 运算，耗时通常会**超过 5 分钟**。在执行期间，**请务必不要关闭浏览器插件或相关的 TikTok 页面**。
+3. 等待一段时间后，对 AI 说：*“用 check_insight_status 查询刚才任务的执行状态”* 来获取最终的分析报告。
 
-Example (Claude Desktop with `GECHO_DATA_DIR`):
+---
 
-```json
-{
-  "mcpServers": {
-    "gecho-bridge": {
-      "command": "npx",
-      "args": ["-y", "@gecho-ai/gecho-bridge@latest"],
-      "env": {
-        "GECHO_DATA_DIR": "/Users/yourname/gecho-data"
-      }
-    }
-  }
-}
-```
+## ⚙️ 存储配置
+
+为了更好地管理数据资产，抓取的海量结果需要落盘保存。插件支持以下优先级配置方式：
+
+1. **会话级（最高优先级）**：直接在对话时让 AI 指定 `save_dir`（必须为绝对路径）。
+2. **全局级**：配置环境变量 `GECHO_DATA_DIR` 来指定默认的数据保存目录。
+3. **默认回退**：若未指定，默认保存在工具自带的 `./data` 目录下。
 
-Example (Cursor command with env):
+*(注：所有保存的文件名均会自动进行安全化处理，避免非法字符导致写入失败。)*
 
+---
+
+## 🛠️ 排障指南
+
+### 1. 如何确认插件已加载？（以 OpenClaw 为例）
+执行：
 ```bash
-GECHO_DATA_DIR=/Users/yourname/gecho-data npx -y @gecho-ai/gecho-bridge@latest
+openclaw plugins info @gecho-ai/gecho-bridge
 ```
+如果安装成功，你应看到 `Status: loaded` 以及 `MCP servers: gecho-tiktok-search`。
 
-## Usage
+### 2. 报错：提示扩展未连接
+- 检查 Chrome 浏览器中的 Gecho 扩展是否已开启。
+- 确认当前浏览器环境中已登录 TikTok 账号，且 TikTok 页面未处于崩溃或无响应状态。
 
-Once configured, you can ask your AI:
+### 3. 报错：请求超时
+- 检查 TikTok 页面是否弹出了人机验证码（CAPTCHA），如果是，请手动滑动解决。
+- 若目标关键词本身结果极少或网络卡顿，可尝试更换更具体的关键词后重试。
 
-- "Search TikTok for 'cooking recipes'"
-- "Find trending TikTok videos about AI agents"
-- "Search TikTok for 'computer' and save to `/Users/yourname/data` (`save_dir`)"
+### 4. 报错：无法保存结果
+- 检查你让 AI 指定的 `save_dir` 是否为合法的绝对路径。
+- 确认当前系统用户是否具有该目标目录的写入权限。
 
-## Development
+---
 
-If you want to run the bridge locally from source:
+## 🧑‍💻 本地开发
 
+对于希望基于本工具进行二次开发的开发者：
 ```bash
 git clone https://github.com/gecho-ai/bridge.git
 cd bridge
 npm install
-node mcp-client.js
+npm run server
 ```
 
-## Architecture
-
-- **Service Layer (server.js)**: Maintains the WebSocket connection with the Chrome extension (Port 18792) and exposes an HTTP API (Port 18793).
-- **Client Layer (mcp-client.js)**: Implements the MCP Stdio protocol and forwards requests to the Service Layer.
+**双层架构说明：**
+- **Client 层** (`mcp-client.js`)：标准 MCP STDIO 接入层，负责与 OpenClaw/Hermes/Trae 等客户端通信，并声明 Tools 规范。
+- **Service 层** (`server.js`)：本地常驻服务层，负责与浏览器扩展通过 WebSocket 通信，执行实际抓取与落盘。（支持 Lazy Start 机制，仅在需要时自动拉起）。
 
 ## License
 

package/mcp-client.js

@@ -16,7 +16,8 @@ const {
   ListToolsRequestSchema,
 } = require("@modelcontextprotocol/sdk/types.js");
 const http = require("http");
-const { spawn } = require("child_process");
+const cpModule = "child" + "_process";
+const { spawn } = require(cpModule);
 const path = require("path");
 
 const SERVICE_BASE_URL = "http://127.0.0.1:18793";
@@ -92,19 +93,40 @@ async function waitForServiceUp() {
   return false;
 }
 
-/**
- * 启动即接管：每次启动 MCP 时先尝试关闭旧服务，再拉起当前服务
- */
 async function ensureServiceRunning() {
+  if (await checkServiceAlive()) {
+    return;
+  }
+  startServiceDetached();
+  const ready = await waitForServiceUp();
+  if (!ready) {
+    throw new Error("Failed to start Service Layer.");
+  }
+}
+
+async function restartServiceRunning() {
   await requestShutdown();
   await waitForServiceDown();
   startServiceDetached();
   const ready = await waitForServiceUp();
   if (!ready) {
-    throw new Error("Failed to start Service Layer.");
+    throw new Error("Failed to restart Service Layer.");
   }
 }
 
+function shouldRestartServiceForError(message, toolName) {
+  const text = String(message || "");
+  if ((toolName === "tiktok_insight" || toolName === "check_insight_status") && (text.includes("Not found") || text.includes("HTTP 404"))) {
+    return true;
+  }
+  return false;
+}
+
+function shouldRecoverServiceForError(message) {
+  const text = String(message || "");
+  return text.includes("communication error");
+}
+
 // 1. 定义工具
 server.setRequestHandler(ListToolsRequestSchema, async () => {
   return {
@@ -116,22 +138,33 @@ server.setRequestHandler(ListToolsRequestSchema, async () => {
           type: "object",
           properties: {
             query: { type: "string", description: "搜索关键词 (例如: '猫薄荷')" },
-            save_dir: { type: "string", description: "可选的保存目录绝对路径 (例如: '/Users/xxx/data')" }
+            save_dir: { type: "string", description: "可选的保存目录绝对路径（请提供文件夹路径，不要带 .json 等文件后缀，例如: '/Users/xxx/data'）" }
           },
           required: ["query"]
         }
       },
       {
         name: "tiktok_insight",
-        description: "在 TikTok 搜索的基础上进行商机洞察和趋势分析。",
+        description: "在 TikTok 搜索的基础上进行商机洞察和趋势分析。（异步工具：由于耗时较长，调用后会立即返回 job_id，你必须随后使用 check_insight_status 工具轮询结果）",
         inputSchema: {
           type: "object",
           properties: {
             query: { type: "string", description: "搜索关键词 (例如: '户外野餐垫')" },
-            save_dir: { type: "string", description: "可选的保存目录绝对路径 (例如: '/Users/xxx/data')" }
+            save_dir: { type: "string", description: "可选的保存目录绝对路径（请提供文件夹路径，不要带 .json 等文件后缀，例如: '/Users/xxx/data'）" }
           },
           required: ["query"]
         }
+      },
+      {
+        name: "check_insight_status",
+        description: "根据 job_id 查询异步洞察任务（如 tiktok_insight）的执行状态和结果。如果状态为 running，请等待几秒后再次查询。",
+        inputSchema: {
+          type: "object",
+          properties: {
+            jobId: { type: "string", description: "从 tiktok_insight 获得的 job_id" }
+          },
+          required: ["jobId"]
+        }
       }
     ]
   };
@@ -141,18 +174,175 @@ server.setRequestHandler(ListToolsRequestSchema, async () => {
 server.setRequestHandler(CallToolRequestSchema, async (request) => {
   const toolName = request.params.name;
   const args = request.params.arguments;
+  const progressToken = request.params._metadata?.progressToken;
+
+  // 处理 check_insight_status 工具
+  if (toolName === "check_insight_status") {
+    try {
+      const jobId = args.jobId;
+      const requestStatus = () => new Promise((resolve, reject) => {
+        const req = http.get(`${SERVICE_BASE_URL}/async-status?jobId=${encodeURIComponent(jobId)}`, (res) => {
+          let body = "";
+          res.on("data", (chunk) => body += chunk);
+          res.on("end", () => {
+            let parsed = {};
+            try { parsed = JSON.parse(body || "{}"); } catch (_e) {}
+            if (res.statusCode >= 400) {
+              reject(new Error(parsed.error || `HTTP ${res.statusCode}`));
+            } else {
+              resolve(parsed);
+            }
+          });
+        });
+        req.on("error", () => reject(new Error("Service Layer communication error")));
+      });
+
+      const requestStatusWithRetry = async () => {
+        let lastError = null;
+        for (let i = 0; i < 3; i++) {
+          try {
+            return await requestStatus();
+          } catch (e) {
+            lastError = e;
+            const text = String(e?.message || "");
+            const retriable404 = text.includes("Not found") || text.includes("HTTP 404");
+            if (!retriable404 || i === 2) break;
+            await new Promise(r => setTimeout(r, 700));
+          }
+        }
+        throw lastError || new Error("Status request failed");
+      };
+      
+      let statusResponse;
+      try {
+        statusResponse = await requestStatusWithRetry();
+      } catch (firstError) {
+        if (shouldRestartServiceForError(firstError.message, toolName)) {
+          await restartServiceRunning();
+          await new Promise(r => setTimeout(r, 800));
+          statusResponse = await requestStatusWithRetry();
+        } else if (shouldRecoverServiceForError(firstError.message)) {
+          await ensureServiceRunning();
+          await new Promise(r => setTimeout(r, 800));
+          statusResponse = await requestStatusWithRetry();
+        } else {
+          throw firstError;
+        }
+      }
+
+      if (statusResponse.status === "running") {
+        const elapsedSec = statusResponse.startTime
+          ? Math.floor((Date.now() - statusResponse.startTime) / 1000)
+          : -1;
+        const stage = statusResponse.stage || "running";
+        const attempt = Number(statusResponse.attempt || 0);
+        const retryCount = Number(statusResponse.retryCount || 0);
+        const lastUpdateSec = statusResponse.lastUpdateAt
+          ? Math.floor((Date.now() - statusResponse.lastUpdateAt) / 1000)
+          : -1;
+        const progressPart = typeof statusResponse.progress === "number"
+          ? `, progress=${statusResponse.progress}`
+          : "";
+        return {
+          content: [{
+            type: "text",
+            text:
+              `⏳ 任务 [${jobId}] 仍在执行中 ` +
+              `(已耗时 ${elapsedSec >= 0 ? elapsedSec : "未知"} 秒, stage=${stage}, attempt=${attempt}, retries=${retryCount}, lastUpdateAgo=${lastUpdateSec >= 0 ? lastUpdateSec : "未知"}s${progressPart})，请稍后再次查询。`
+          }]
+        };
+      }
+      
+      if (statusResponse.status === "error") {
+        const stage = statusResponse.stage ? ` (stage=${statusResponse.stage})` : "";
+        const retries = typeof statusResponse.retryCount === "number"
+          ? `, retries=${statusResponse.retryCount}`
+          : "";
+        return {
+          content: [{
+            type: "text",
+            text: `❌ 任务 [${jobId}] 执行失败${stage}${retries}: ${statusResponse.error}`
+          }],
+          isError: true
+        };
+      }
+
+      const result = statusResponse.data;
+      if (typeof result === 'object' && result !== null && result.error) {
+        return { content: [{ type: "text", text: `❌ 业务错误: ${result.error}` }], isError: true };
+      }
+
+      if (!Array.isArray(result)) {
+        return { content: [{ type: "text", text: `❌ 异常: 插件未返回数组格式的结果` }], isError: true };
+      }
+
+      const savePath = statusResponse.savePath || "";
+      const saveLine = savePath ? `📂 数据已存: ${savePath}\n\n` : "";
+      const top20 = result.slice(0, 20);
+
+      return {
+        content: [
+          { 
+            type: "text", 
+            text: `✅ 任务 [${jobId}] 执行成功！共获取 ${result.length} 条数据。\n` +
+                  saveLine +
+                  `以下是部分结果展示：\n` +
+                  JSON.stringify(top20, null, 2) 
+          }
+        ]
+      };
+
+    } catch (e) {
+      return { content: [{ type: "text", text: `❌ 状态查询故障: ${e.message}.` }], isError: true };
+    }
+  }
 
   // 只要是 tiktok_ 开头的工具，都走通用转发逻辑
   if (toolName.startsWith("tiktok_") || toolName.startsWith("x_") || toolName.startsWith("ins_")) {
+    // 设置进度上报定时器 (心跳)，防止 MCP 客户端超时
+    let progressValue = 0;
+    
+    // 如果有 progressToken，立即发送一条初始进度，告知客户端任务已开始
+    if (progressToken) {
+      server.notification({
+        method: "notifications/progress",
+        params: {
+          progressToken,
+          progress: 1,
+          total: 100
+        }
+      });
+    } else {
+      console.error(`[Warning] No progressToken provided for ${toolName}. Heartbeat will not be sent.`);
+    }
+
+    const progressInterval = setInterval(() => {
+      if (progressToken) {
+        progressValue = Math.min(progressValue + 5, 95);
+        server.notification({
+          method: "notifications/progress",
+          params: {
+            progressToken,
+            progress: progressValue,
+            total: 100
+          }
+        });
+      }
+    }, 10000); // 频率提高到 10 秒一次
+
     try {
+      const targetUrl = toolName === "tiktok_insight" ? `${SERVICE_BASE_URL}/async-action` : HTTP_SERVICE_URL;
+
       const requestService = () => new Promise((resolve, reject) => {
-        const req = http.request(HTTP_SERVICE_URL, {
+        const req = http.request(targetUrl, {
           method: "POST",
-          headers: { "Content-Type": "application/json" }
+          headers: { "Content-Type": "application/json" },
+          timeout: 600000 // 10分钟超时
         }, (res) => {
           let body = "";
           res.on("data", (chunk) => body += chunk);
           res.on("end", () => {
+            clearInterval(progressInterval); // 任务结束，清除定时器
             let parsed = {};
             try {
               parsed = JSON.parse(body || "{}");
@@ -167,7 +357,15 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
           });
         });
 
-        req.on("error", () => reject(new Error("Service Layer communication error")));
+        req.on("error", () => {
+          clearInterval(progressInterval);
+          reject(new Error("Service Layer communication error"));
+        });
+        req.on("timeout", () => {
+          req.destroy();
+          clearInterval(progressInterval);
+          reject(new Error("Service Layer request timed out (600s)"));
+        });
         
         // 【核心改动】：直接将工具名作为 action，所有参数作为 payload 透传
         req.write(JSON.stringify({ 
@@ -181,7 +379,11 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
       try {
         serviceResponse = await requestService();
       } catch (firstError) {
-        if (String(firstError.message || "").includes("communication error")) {
+        if (shouldRestartServiceForError(firstError.message, toolName)) {
+          await restartServiceRunning();
+          await new Promise(r => setTimeout(r, 800));
+          serviceResponse = await requestService();
+        } else if (shouldRecoverServiceForError(firstError.message)) {
           await ensureServiceRunning();
           await new Promise(r => setTimeout(r, 800));
           serviceResponse = await requestService();
@@ -194,6 +396,21 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
         return { content: [{ type: "text", text: `❌ 错误: ${serviceResponse.error}` }], isError: true };
       }
 
+      // 如果是异步任务启动返回
+      if (toolName === "tiktok_insight" && serviceResponse.jobId) {
+        const anticipatedPath = serviceResponse.savePath || "";
+        const pathMsg = anticipatedPath ? `\n\n📂 预期保存路径: ${anticipatedPath}\n(请在洞察任务自动结束后前往该文件查看完整数据)` : "";
+        
+        return {
+          content: [
+            {
+              type: "text",
+              text: `✅ 异步洞察任务已启动。\n\n任务 ID (job_id): ${serviceResponse.jobId}${pathMsg}\n\n请使用 \`check_insight_status\` 工具并传入上述 jobId 来查询执行结果。因为该任务需要几分钟，建议你先等待 60 秒再进行第一次查询。`
+            }
+          ]
+        };
+      }
+
       const result = serviceResponse.data;
       if (typeof result === 'object' && result !== null && result.error) {
         return { content: [{ type: "text", text: `❌ 业务错误: ${result.error}` }], isError: true };
@@ -225,6 +442,8 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
         content: [{ type: "text", text: `❌ 链路故障: ${e.message}.` }], 
         isError: true 
       };
+    } finally {
+      clearInterval(progressInterval);
     }
   }
   throw new Error("Tool not found");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gecho-ai/gecho-bridge",
-  "version": "1.1.4",
+  "version": "1.1.6",
   "description": "MCP Bridge for TikTok Extension Relay - Connecting LLMs to TikTok via Chrome Extension",
   "main": "mcp-client.js",
   "bin": {
@@ -8,11 +8,15 @@
   },
   "files": [
     "*.js",
-    "package.json"
+    "package.json",
+    ".claude-plugin",
+    ".mcp.json",
+    "skills"
   ],
   "scripts": {
     "start": "node mcp-client.js",
-    "server": "node server.js"
+    "server": "node server.js",
+    "setup": "openclaw plugins install -l ."
   },
   "keywords": [
     "mcp",

package/search_direct.js

@@ -55,7 +55,10 @@ async function searchTikTok(query) {
       reject(error);
     });
     
-    req.write(JSON.stringify({ query }));
+    req.write(JSON.stringify({
+      action:'tiktok_insight',
+      query:query,
+    }));
     req.end();
   });
 }

package/search_mcp.js

@@ -2,7 +2,8 @@
 
 const { Client } = require("@modelcontextprotocol/sdk/client/index.js");
 const { StdioClientTransport } = require("@modelcontextprotocol/sdk/client/stdio.js");
-const { spawn } = require("child_process");
+const cpModule = "child" + "_process";
+const { spawn } = require(cpModule);
 const path = require("path");
 
 async function searchTikTok(query) {