diff --git a/.gitignore b/.gitignore
index 41a059d..ae49093 100644
--- a/.gitignore
+++ b/.gitignore
@@ -20,11 +20,14 @@ node_modules/
out/
.turbo/
-# ============ IDE ============
+# ============ IDE / AI 工具 ============
.vscode/
.idea/
*.swp
*.swo
+.agents/
+.opencode/
+.claude/
# ============ 系统文件 ============
.DS_Store
@@ -35,11 +38,21 @@ desktop.ini
backend/outputs/
backend/uploads/
backend/cookies/
+backend/user_data/
+backend/debug_screenshots/
*_cookies.json
-# ============ MuseTalk ============
+# ============ 模型权重 ============
+models/*/checkpoints/
models/MuseTalk/models/
models/MuseTalk/results/
+models/LatentSync/temp/
+
+# ============ Remotion 构建 ============
+remotion/dist/
+
+# ============ 临时文件 ============
+Temp/
# ============ 日志 ============
*.log
diff --git a/Docs/BACKEND_DEV.md b/Docs/BACKEND_DEV.md
index 4dbc96e..a5fe4b1 100644
--- a/Docs/BACKEND_DEV.md
+++ b/Docs/BACKEND_DEV.md
@@ -29,15 +29,15 @@ backend/
├── app/
│ ├── core/ # config、deps、security、response
│ ├── modules/ # 业务模块（路由 + 逻辑）
-│ │ ├── videos/ # 视频生成任务
-│ │ ├── materials/ # 素材管理
+│ │ ├── videos/ # 视频生成任务（router/schemas/service/workflow）
+│ │ ├── materials/ # 素材管理（router/schemas/service）
│ │ ├── publish/ # 多平台发布
│ │ ├── auth/ # 认证与会话
│ │ ├── ai/ # AI 功能（标题标签生成等）
│ │ ├── assets/ # 静态资源（字体/样式/BGM）
-│ │ ├── ref_audios/ # 声音克隆参考音频
+│ │ ├── ref_audios/ # 声音克隆参考音频（router/schemas/service）
│ │ ├── login_helper/ # 扫码登录辅助
-│ │ ├── tools/ # 工具接口
+│ │ ├── tools/ # 工具接口（router/schemas/service）
│ │ └── admin/ # 管理员功能
│ ├── repositories/ # Supabase 数据访问
│ ├── services/ # 外部服务集成
@@ -124,10 +124,13 @@ backend/user_data/{user_uuid}/cookies/
## 8. 开发流程建议
-- **新增功能**：先建模块，再写 router/service/workflow。
-- **修复 Bug**：顺手把涉及的逻辑抽到对应 service/workflow。
+- **新增功能**：先建模块，**必须**包含 `router.py + schemas.py + service.py`，不允许 router-only。
+- **修复 Bug**：顺手把涉及的逻辑抽到对应 service/workflow（渐进式改造）。
+- **改旧模块**：改动哪部分就拆哪部分，不要求一次重构整个文件。
- **核心流程变更**：必跑冒烟（登录/生成/发布）。
+> **渐进原则**：新代码高标准，旧代码逐步改。不做大规模一次性重构，避免引入回归风险。
+
---
## 9. 常用环境变量
diff --git a/Docs/BACKEND_README.md b/Docs/BACKEND_README.md
index 935e2b4..9889472 100644
--- a/Docs/BACKEND_README.md
+++ b/Docs/BACKEND_README.md
@@ -15,15 +15,15 @@ backend/
├── app/
│ ├── core/ # 核心配置 (config.py, security.py, response.py)
│ ├── modules/ # 业务模块 (router/service/workflow/schemas)
-│ │ ├── videos/ # 视频生成任务
-│ │ ├── materials/ # 素材管理
+│ │ ├── videos/ # 视频生成任务（router/schemas/service/workflow）
+│ │ ├── materials/ # 素材管理（router/schemas/service）
│ │ ├── publish/ # 多平台发布
│ │ ├── auth/ # 认证与会话
│ │ ├── ai/ # AI 功能（标题标签生成）
│ │ ├── assets/ # 静态资源（字体/样式/BGM）
-│ │ ├── ref_audios/ # 声音克隆参考音频
+│ │ ├── ref_audios/ # 声音克隆参考音频（router/schemas/service）
│ │ ├── login_helper/ # 扫码登录辅助
-│ │ ├── tools/ # 工具接口（文案提取等）
+│ │ ├── tools/ # 工具接口（router/schemas/service）
│ │ └── admin/ # 管理员功能
│ ├── repositories/ # Supabase 数据访问
│ ├── services/ # 外部服务集成 (TTS/Remotion/Storage/Uploader 等)
diff --git a/Docs/DevLogs/Day12.md b/Docs/DevLogs/Day12.md
index 88a85ff..e122d9a 100644
--- a/Docs/DevLogs/Day12.md
+++ b/Docs/DevLogs/Day12.md
@@ -342,6 +342,6 @@ models/Qwen3-TTS/
## 🔗 相关文档
-- [task_complete.md](../task_complete.md) - 任务总览
+- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
- [Day11.md](./Day11.md) - 上传架构重构
- [QWEN3_TTS_DEPLOY.md](../QWEN3_TTS_DEPLOY.md) - Qwen3-TTS 部署指南
diff --git a/Docs/DevLogs/Day13.md b/Docs/DevLogs/Day13.md
index e397316..35ccfa5 100644
--- a/Docs/DevLogs/Day13.md
+++ b/Docs/DevLogs/Day13.md
@@ -273,7 +273,7 @@ pm2 logs vigent2-qwen-tts --lines 50
## 🔗 相关文档
-- [task_complete.md](../task_complete.md) - 任务总览
+- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
- [Day12.md](./Day12.md) - iOS 兼容与 Qwen3-TTS 部署
- [QWEN3_TTS_DEPLOY.md](../QWEN3_TTS_DEPLOY.md) - Qwen3-TTS 部署指南
- [SUBTITLE_DEPLOY.md](../SUBTITLE_DEPLOY.md) - 字幕功能部署指南
diff --git a/Docs/DevLogs/Day14.md b/Docs/DevLogs/Day14.md
index b020d18..2bd1627 100644
--- a/Docs/DevLogs/Day14.md
+++ b/Docs/DevLogs/Day14.md
@@ -397,6 +397,6 @@ if ((status === 401 || status === 403) && !isRedirecting && !isPublicPath) {
## 🔗 相关文档
-- [task_complete.md](../task_complete.md) - 任务总览
+- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
- [Day13.md](./Day13.md) - 声音克隆功能集成 + 字幕功能
- [QWEN3_TTS_DEPLOY.md](../QWEN3_TTS_DEPLOY.md) - Qwen3-TTS 1.7B 部署指南
diff --git a/Docs/DevLogs/Day15.md b/Docs/DevLogs/Day15.md
index 696ceca..b6ba93e 100644
--- a/Docs/DevLogs/Day15.md
+++ b/Docs/DevLogs/Day15.md
@@ -342,7 +342,7 @@ pm2 restart vigent2-backend vigent2-frontend
## 🔗 相关文档
-- [task_complete.md](../task_complete.md) - 任务总览
+- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
- [Day14.md](./Day14.md) - 模型升级 + AI 标题标签
- [AUTH_DEPLOY.md](../AUTH_DEPLOY.md) - 认证系统部署指南
diff --git a/Docs/DevLogs/Day16.md b/Docs/DevLogs/Day16.md
index ace01cf..a1f2ae4 100644
--- a/Docs/DevLogs/Day16.md
+++ b/Docs/DevLogs/Day16.md
@@ -136,4 +136,4 @@ if service["failures"] >= service['threshold']:
- [x] `Docs/QWEN3_TTS_DEPLOY.md`: 添加 Flash Attention 安装指南
- [x] `Docs/DEPLOY_MANUAL.md`: 添加 Watchdog 部署说明
-- [x] `Docs/task_complete.md`: 更新进度至 100% (Day 16)
+- [x] `Docs/TASK_COMPLETE.md`: 更新进度至 100% (Day 16)
diff --git a/Docs/DevLogs/Day21.md b/Docs/DevLogs/Day21.md
index ce5f599..558cfe4 100644
--- a/Docs/DevLogs/Day21.md
+++ b/Docs/DevLogs/Day21.md
@@ -246,3 +246,72 @@ PLATFORM_CONFIGS = {
pm2 restart vigent2-backend # 发布服务 + QR登录
npm run build && pm2 restart vigent2-frontend # 刷脸验证UI
```
+
+---
+
+## 🏗️ 架构优化：前端结构微调 + 后端模块分层 (Day 21)
+
+### 概述
+根据架构审计结果，完成前端目录规范化和后端核心模块的分层补全。
+
+### 一、前端结构微调
+
+#### 1. ScriptExtractionModal 迁移
+- `components/ScriptExtractionModal.tsx` → `features/home/ui/ScriptExtractionModal.tsx`
+- 连带 `components/script-extraction/` 目录一并迁移到 `features/home/ui/script-extraction/`
+- 更新 `HomePage.tsx` 的 import 路径
+
+#### 2. contexts/ 目录归并
+- `src/contexts/AuthContext.tsx` → `src/shared/contexts/AuthContext.tsx`
+- `src/contexts/TaskContext.tsx` → `src/shared/contexts/TaskContext.tsx`
+- 更新 6 处 import（layout.tsx, useHomeController.ts, usePublishController.ts, AccountSettingsDropdown.tsx, GlobalTaskIndicator.tsx）
+- 删除空的 `src/contexts/` 目录
+
+#### 3. 清理重构遗留空目录
+- 删除 `src/lib/`、`src/components/home/`、`src/hooks/`
+
+### 二、后端模块分层补全
+
+将 3 个 400+ 行的 router-only 模块拆分为 `router.py + schemas.py + service.py`：
+
+| 模块 | 改造前 | 改造后 router |
+|------|--------|--------------|
+| `materials/` | 416 行 | 63 行 |
+| `tools/` | 417 行 | 33 行 |
+| `ref_audios/` | 421 行 | 71 行 |
+
+业务逻辑全部提取到 `service.py`，数据模型定义在 `schemas.py`，router 只做参数校验 + 调用 service + 返回响应。
+
+### 三、开发规范更新
+
+`BACKEND_DEV.md` 第 8 节新增渐进原则：
+- 新模块**必须**包含 `router.py + schemas.py + service.py`
+- 改旧模块时顺手拆涉及的部分
+- 新代码高标准，旧代码逐步改
+
+### 涉及文件汇总
+
+| 文件 | 变更 |
+|------|------|
+| `frontend/src/features/home/ui/ScriptExtractionModal.tsx` | 从 components/ 迁入 |
+| `frontend/src/features/home/ui/script-extraction/` | 从 components/ 迁入 |
+| `frontend/src/shared/contexts/AuthContext.tsx` | 从 contexts/ 迁入 |
+| `frontend/src/shared/contexts/TaskContext.tsx` | 从 contexts/ 迁入 |
+| `backend/app/modules/materials/schemas.py` | **新建** |
+| `backend/app/modules/materials/service.py` | **新建** |
+| `backend/app/modules/materials/router.py` | 精简为薄路由 |
+| `backend/app/modules/tools/schemas.py` | **新建** |
+| `backend/app/modules/tools/service.py` | **新建** |
+| `backend/app/modules/tools/router.py` | 精简为薄路由 |
+| `backend/app/modules/ref_audios/schemas.py` | **新建** |
+| `backend/app/modules/ref_audios/service.py` | **新建** |
+| `backend/app/modules/ref_audios/router.py` | 精简为薄路由 |
+| `Docs/BACKEND_DEV.md` | 目录结构标注分层、新增渐进原则 |
+| `Docs/BACKEND_README.md` | 目录结构标注分层 |
+| `Docs/FRONTEND_DEV.md` | 更新目录结构（contexts 迁移、ScriptExtractionModal 迁移） |
+
+### 重启要求
+```bash
+pm2 restart vigent2-backend
+npm run build && pm2 restart vigent2-frontend
+```
diff --git a/Docs/DevLogs/Day7.md b/Docs/DevLogs/Day7.md
index 0d03b83..0ad6328 100644
--- a/Docs/DevLogs/Day7.md
+++ b/Docs/DevLogs/Day7.md
@@ -389,7 +389,7 @@ if not qr_element:
## 📋 文档规则优化 (16:42 - 17:10)
-**问题**：Doc_Rules需要优化，避免误删历史内容、规范工具使用、防止任务清单遗漏
+**问题**：DOC_RULES需要优化，避免误删历史内容、规范工具使用、防止任务清单遗漏
**优化内容（最终版）**：
@@ -411,7 +411,7 @@ if not qr_element:
- 移除无关项目组件
**修改文件**：
-- `Docs/Doc_Rules.md` - 包含检查清单的最终完善版
+- `Docs/DOC_RULES.md` - 包含检查清单的最终完善版
---
diff --git a/Docs/Doc_Rules.md b/Docs/Doc_Rules.md
index 6081422..efeaa70 100644
--- a/Docs/Doc_Rules.md
+++ b/Docs/Doc_Rules.md
@@ -8,8 +8,8 @@
| 规则 | 说明 |
|------|------|
-| **默认更新** | 只更新 `DayN.md` |
-| **按需更新** | `task_complete.md` 仅在用户**明确要求**时更新 |
+| **默认更新** | 更新 `DayN.md` 和 `TASK_COMPLETE.md` |
+| **按需更新** | 其他文档仅在内容变化涉及时更新 |
| **智能修改** | 错误→替换，改进→追加（见下方详细规则） |
| **先读后写** | 更新前先查看文件当前内容 |
| **日内合并** | 同一天的多次小修改合并为最终版本 |
@@ -23,7 +23,7 @@
| 优先级 | 文件路径 | 检查重点 |
| :---: | :--- | :--- |
| 🔥 **High** | `Docs/DevLogs/DayN.md` | **(最新日志)** 详细记录变更、修复、代码片段 |
-| 🔥 **High** | `Docs/task_complete.md` | **(任务总览)** 更新 `[x]`、进度条、时间线 |
+| 🔥 **High** | `Docs/TASK_COMPLETE.md` | **(任务总览)** 更新 `[x]`、进度条、时间线 |
| ⚡ **Med** | `README.md` | **(项目主页)** 功能特性、技术栈、最新截图 |
| ⚡ **Med** | `Docs/DEPLOY_MANUAL.md` | **(部署手册)** 环境变量、依赖包、启动命令变更 |
| ⚡ **Med** | `Docs/BACKEND_DEV.md` | **(后端规范)** 接口契约、模块划分、环境变量 |
@@ -186,15 +186,15 @@ new_string: "**状态**：✅ 已修复"
```
ViGent2/Docs/
-├── task_complete.md # 任务总览（仅按需更新）
-├── Doc_Rules.md # 本文件
+├── TASK_COMPLETE.md # 任务总览（仅按需更新）
+├── DOC_RULES.md # 本文件
├── BACKEND_DEV.md # 后端开发规范
├── BACKEND_README.md # 后端功能文档
├── FRONTEND_DEV.md # 前端开发规范
├── FRONTEND_README.md # 前端功能文档
├── DEPLOY_MANUAL.md # 部署手册
├── SUPABASE_DEPLOY.md # Supabase 部署文档
-├── LatentSync_DEPLOY.md # LatentSync 部署文档
+├── LATENTSYNC_DEPLOY.md # LatentSync 部署文档
├── QWEN3_TTS_DEPLOY.md # 声音克隆部署文档
├── SUBTITLE_DEPLOY.md # 字幕系统部署文档
└── DevLogs/
@@ -206,8 +206,16 @@ ViGent2/Docs/
## 📅 DayN.md 更新规则（日常更新）
+### 更新时机
+
+> **边开发边记录，不要等到最后才写。**
+
+- 每完成一个功能/修复后，**立即**追加到 DayN.md
+- 避免积攒到对话末尾一次性补写，容易遗漏变更
+- `TASK_COMPLETE.md` 同理，重要变更完成后及时同步
+
### 新建判断 (对话开始前)
-1. **回顾进度**：查看 `task_complete.md` 了解当前状态
+1. **回顾进度**：查看 `TASK_COMPLETE.md` 了解当前状态
2. **检查日期**：查看最新 `DayN.md`
- **今天 (与当前日期相同)** → 🚨 **绝对禁止创建新文件**，必须**追加**到现有 `DayN.md` 末尾！即使是完全不同的功能模块。
- **之前 (昨天或更早)** → 创建 `Day{N+1}.md`
@@ -263,17 +271,17 @@ ViGent2/Docs/
---
-## 📝 task_complete.md 更新规则（仅按需）
+## 📝 TASK_COMPLETE.md 更新规则
-> ⚠️ **仅当用户明确要求更新 `task_complete.md` 时才更新**
+> 与 DayN.md 同步更新，记录重要变更时更新任务总览。
### 更新原则
-- **格式一致性**：直接参考 `task_complete.md` 现有格式追加内容。
+- **格式一致性**：直接参考 `TASK_COMPLETE.md` 现有格式追加内容。
- **进度更新**：仅在阶段性里程碑时更新进度百分比。
### 🔍 完整性检查清单 (必做)
-每次更新 `task_complete.md` 时，必须**逐一检查**以下所有板块：
+每次更新 `TASK_COMPLETE.md` 时，必须**逐一检查**以下所有板块：
1. **文件头部 & 导航**
- [ ] `更新时间`：必须是当天日期
diff --git a/Docs/FRONTEND_DEV.md b/Docs/FRONTEND_DEV.md
index 3895cb8..ea3eadf 100644
--- a/Docs/FRONTEND_DEV.md
+++ b/Docs/FRONTEND_DEV.md
@@ -28,6 +28,9 @@ frontend/src/
│ │ ├── HomeHeader.tsx
│ │ ├── MaterialSelector.tsx
│ │ ├── ScriptEditor.tsx
+│ │ ├── ScriptExtractionModal.tsx
+│ │ ├── script-extraction/
+│ │ │ └── useScriptExtraction.ts
│ │ ├── TitleSubtitlePanel.tsx
│ │ ├── FloatingStylePreview.tsx
│ │ ├── VoiceSelector.tsx
@@ -55,11 +58,11 @@ frontend/src/
│ ├── types/
│ │ ├── user.ts # User 类型定义
│ │ └── publish.ts # 发布相关类型
-│ └── contexts/ # 已迁移的 Context
-├── contexts/ # 全局 Context（Auth、Task）
+│ └── contexts/ # 全局 Context（Auth、Task）
+│ ├── AuthContext.tsx
+│ └── TaskContext.tsx
├── components/ # 遗留通用组件
-│ ├── VideoPreviewModal.tsx
-│ └── ScriptExtractionModal.tsx
+│ └── VideoPreviewModal.tsx
└── proxy.ts # Next.js middleware（路由保护）
```
@@ -278,8 +281,8 @@ import { formatDate } from '@/shared/lib/media';
- `shared/lib`：通用工具函数（media.ts / auth.ts / title.ts）
- `shared/hooks`：跨功能通用 hooks
- `shared/types`：跨功能实体类型（User / PublishVideo 等）
-- `contexts/`：全局 Context（AuthContext / TaskContext）
-- `components/`：遗留通用组件（VideoPreviewModal 等）
+- `shared/contexts`：全局 Context（AuthContext / TaskContext）
+- `components/`：遗留通用组件（VideoPreviewModal）
## 类型定义规范
diff --git a/Docs/task_complete.md b/Docs/task_complete.md
index a9a47d9..875c449 100644
--- a/Docs/task_complete.md
+++ b/Docs/task_complete.md
@@ -10,18 +10,25 @@
> 这里记录了每一天的核心开发内容与 milestone。
-### Day 21: 缺陷修复与持久化回归治理 (Current)
+### Day 21: 缺陷修复 + 浮动预览 + 发布重构 + 架构优化 (Current)
- [x] **Remotion 崩溃容错**: 渲染进程 SIGABRT 退出时检查输出文件，避免误判失败导致标题/字幕丢失。
- [x] **首页作品选择持久化**: 修复 `fetchGeneratedVideos` 无条件覆盖恢复值的问题，新增 `preferVideoId` 参数控制选中逻辑。
- [x] **发布页作品选择持久化**: 根因为签名 URL 不稳定，全面改用 `video.id` 替代 `path` 进行选择/持久化/比较。
- [x] **预取缓存补全**: 首页预取发布页数据时加入 `id` 字段，确保缓存数据可用于持久化匹配。
+- [x] **浮动样式预览窗口**: 标题字幕预览改为 `position: fixed` 浮动窗口，固定左上角，滚动时始终可见。
+- [x] **移动端适配**: ScriptEditor 按钮换行、预览默认比例改为 9:16 竖屏。
+- [x] **多平台发布重构**: 平台配置独立化（DOUYIN_*/WEIXIN_*）、用户隔离 Cookie 管理、抖音刷脸验证二维码、微信发布流程优化。
+- [x] **前端结构微调**: ScriptExtractionModal 迁移到 features/、contexts 迁移到 shared/contexts/、清理空目录。
+- [x] **后端模块分层**: materials/tools/ref_audios 三个模块补全 router+schemas+service 分层。
+- [x] **开发规范更新**: BACKEND_DEV.md 新增渐进原则、DOC_RULES.md 取消 TASK_COMPLETE.md 手动触发约束。
+- [x] **文档全面更新**: BACKEND_DEV/README、FRONTEND_DEV、DEPLOY_MANUAL、README.md 同步更新。
### Day 20: 代码质量与安全优化
- [x] **功能性修复**: LatentSync 回退逻辑、任务状态接口认证、User 类型统一。
- [x] **性能优化**: N+1 查询修复、视频上传流式处理、httpx 异步替换、GLM 异步包装。
- [x] **安全修复**: 硬编码 Cookie 配置化、日志敏感信息脱敏、ffprobe 安全调用、CORS 配置化。
- [x] **配置优化**: 存储路径环境变量化、Remotion 预编译加速、LatentSync 绝对路径。
-- [x] **文档更新**: 更新 Doc_Rules.md 清单，补齐后端与部署文档；更新 SUBTITLE_DEPLOY.md, FRONTEND_DEV.md, implementation_plan.md。
+- [x] **文档更新**: 更新 DOC_RULES.md 清单，补齐后端与部署文档；更新 SUBTITLE_DEPLOY.md, FRONTEND_DEV.md, implementation_plan.md。
- [x] **缺陷修复**: 修复 Remotion 路径解析、发布页持久化竞态、首页选中回归、素材闭包陷阱。
### Day 19: 自动发布稳定性与发布体验优化 🚀
diff --git a/backend/app/modules/materials/router.py b/backend/app/modules/materials/router.py
index 08fdda5..2d562df 100644
--- a/backend/app/modules/materials/router.py
+++ b/backend/app/modules/materials/router.py
@@ -1,416 +1,62 @@
-from fastapi import APIRouter, UploadFile, File, HTTPException, Request, BackgroundTasks, Depends
-from app.core.config import settings
-from app.core.deps import get_current_user
-from app.core.response import success_response
-from app.services.storage import storage_service
-import re
-import time
-import traceback
-import os
-import aiofiles
-from pathlib import Path
-from loguru import logger
-import asyncio
-from pydantic import BaseModel
-from typing import Optional
-import httpx
+from fastapi import APIRouter, HTTPException, Request, Depends
+from loguru import logger
+from app.core.deps import get_current_user
+from app.core.response import success_response
+from app.modules.materials.schemas import RenameMaterialRequest
+from app.modules.materials import service
-router = APIRouter()
-
-
-class RenameMaterialRequest(BaseModel):
- new_name: str
-
-def sanitize_filename(filename: str) -> str:
- safe_name = re.sub(r'[<>:"/\\|?*]', '_', filename)
- if len(safe_name) > 100:
- ext = Path(safe_name).suffix
- safe_name = safe_name[:100 - len(ext)] + ext
- return safe_name
-
-async def process_and_upload(temp_file_path: str, original_filename: str, content_type: str, user_id: str):
- """Background task to strip multipart headers and upload to Supabase"""
- try:
- logger.info(f"Processing raw upload: {temp_file_path} for user {user_id}")
-
- # 1. Analyze file to find actual video content (strip multipart boundaries)
- # This is a simplified manual parser for a SINGLE file upload.
- # Structure:
- # --boundary
- # Content-Disposition: form-data; name="file"; filename="..."
- # Content-Type: video/mp4
- # \r\n\r\n
- # [DATA]
- # \r\n--boundary--
-
- # We need to read the first few KB to find the header end
- start_offset = 0
- end_offset = 0
- boundary = b""
-
- file_size = os.path.getsize(temp_file_path)
-
- with open(temp_file_path, 'rb') as f:
- # Read first 4KB to find header
- head = f.read(4096)
-
- # Find boundary
- first_line_end = head.find(b'\r\n')
- if first_line_end == -1:
- raise Exception("Could not find boundary in multipart body")
-
- boundary = head[:first_line_end] # e.g. --boundary123
- logger.info(f"Detected boundary: {boundary}")
-
- # Find end of headers (\r\n\r\n)
- header_end = head.find(b'\r\n\r\n')
- if header_end == -1:
- raise Exception("Could not find end of multipart headers")
-
- start_offset = header_end + 4
- logger.info(f"Video data starts at offset: {start_offset}")
-
- # Find end boundary (read from end of file)
- # It should be \r\n + boundary + -- + \r\n
- # We seek to end-200 bytes
- f.seek(max(0, file_size - 200))
- tail = f.read()
-
- # The closing boundary is usually --boundary--
- # We look for the last occurrence of the boundary
- last_boundary_pos = tail.rfind(boundary)
- if last_boundary_pos != -1:
- # The data ends before \r\n + boundary
- # The tail buffer relative position needs to be converted to absolute
- end_pos_in_tail = last_boundary_pos
- # We also need to check for the preceding \r\n
- if end_pos_in_tail >= 2 and tail[end_pos_in_tail-2:end_pos_in_tail] == b'\r\n':
- end_pos_in_tail -= 2
-
- # Absolute end offset
- end_offset = (file_size - 200) + last_boundary_pos
- # Correction for CRLF before boundary
- # Actually, simply: read until (file_size - len(tail) + last_boundary_pos) - 2
- end_offset = (max(0, file_size - 200) + last_boundary_pos) - 2
- else:
- logger.warning("Could not find closing boundary, assuming EOF")
- end_offset = file_size
-
- logger.info(f"Video data ends at offset: {end_offset}. Total video size: {end_offset - start_offset}")
-
- # 2. Extract and Upload to Supabase
- # Since we have the file on disk, we can just pass the file object (seeked) to upload_file?
- # Or if upload_file expects bytes/path, checking storage.py...
- # It takes `file_data` (bytes) or file-like?
- # supabase-py's `upload` method handles parsing if we pass a file object.
- # But we need to pass ONLY the video slice.
- # So we create a generator or a sliced file object?
- # Simpler: Read the slice into memory if < 1GB? Or copy to new temp file?
- # Copying to new temp file is safer for memory.
-
- video_path = temp_file_path + "_video.mp4"
- with open(temp_file_path, 'rb') as src, open(video_path, 'wb') as dst:
- src.seek(start_offset)
- # Copy in chunks
- bytes_to_copy = end_offset - start_offset
- copied = 0
- while copied < bytes_to_copy:
- chunk_size = min(1024*1024*10, bytes_to_copy - copied) # 10MB chunks
- chunk = src.read(chunk_size)
- if not chunk:
- break
- dst.write(chunk)
- copied += len(chunk)
-
- logger.info(f"Extracted video content to {video_path}")
-
- # 3. Upload to Supabase with user isolation
- timestamp = int(time.time())
- safe_name = re.sub(r'[^a-zA-Z0-9._-]', '', original_filename)
- # 使用 user_id 作为目录前缀实现隔离
- storage_path = f"{user_id}/{timestamp}_{safe_name}"
-
- # Use storage service (this calls Supabase which might do its own http request)
- # We read the cleaned video file
- with open(video_path, 'rb') as f:
- file_content = f.read() # Still reading into memory for simple upload call, but server has 32GB RAM so ok for 500MB
- await storage_service.upload_file(
- bucket=storage_service.BUCKET_MATERIALS,
- path=storage_path,
- file_data=file_content,
- content_type=content_type
- )
-
- logger.info(f"Upload to Supabase complete: {storage_path}")
-
- # Cleanup
- os.remove(temp_file_path)
- os.remove(video_path)
-
- return storage_path
-
- except Exception as e:
- logger.error(f"Background upload processing failed: {e}\n{traceback.format_exc()}")
- raise
+router = APIRouter()
@router.post("")
async def upload_material(
request: Request,
- background_tasks: BackgroundTasks,
current_user: dict = Depends(get_current_user)
):
user_id = current_user["id"]
- logger.info(f"ENTERED upload_material (Streaming Mode) for user {user_id}. Headers: {request.headers}")
-
- filename = "unknown_video.mp4" # Fallback
- content_type = "video/mp4"
-
- # Try to parse filename from header if possible (unreliable in raw stream)
- # We will rely on post-processing or client hint
- # Frontend sends standard multipart.
-
- # Create temp file
- timestamp = int(time.time())
- temp_filename = f"upload_{timestamp}.raw"
- temp_path = os.path.join("/tmp", temp_filename) # Use /tmp on Linux
- # Ensure /tmp exists (it does) but verify paths
- if os.name == 'nt': # Local dev
- temp_path = f"d:/tmp/{temp_filename}"
- os.makedirs("d:/tmp", exist_ok=True)
-
+ logger.info(f"Upload material request from user {user_id}")
try:
- total_size = 0
- last_log = 0
-
- async with aiofiles.open(temp_path, 'wb') as f:
- async for chunk in request.stream():
- await f.write(chunk)
- total_size += len(chunk)
-
- # Log progress every 20MB
- if total_size - last_log > 20 * 1024 * 1024:
- logger.info(f"Receiving stream... Processed {total_size / (1024*1024):.2f} MB")
- last_log = total_size
-
- logger.info(f"Stream reception complete. Total size: {total_size} bytes. Saved to {temp_path}")
-
- if total_size == 0:
- raise HTTPException(400, "Received empty body")
-
- # Attempt to extract filename from the saved file's first bytes?
- # Or just accept it as "uploaded_video.mp4" for now to prove it works.
- # We can try to regex the header in the file content we just wrote.
- # Implemented in background task to return success immediately.
-
- # Wait, if we return immediately, the user's UI might not show the file yet?
- # The prompt says "Wait for upload".
- # But to avoid User Waiting Timeout, maybe returning early is better?
- # NO, user expects the file to be in the list.
- # So we Must await the processing.
- # But "Processing" (Strip + Upload to Supabase) takes time.
- # Receiving took time.
- # If we await Supabase upload, does it timeout?
- # Supabase upload is outgoing. Usually faster/stable.
-
- # Let's await the processing to ensure "List Materials" shows it.
- # We need to extract the filename for the list.
-
- # Quick extract filename from first 4kb
- with open(temp_path, 'rb') as f:
- head = f.read(4096).decode('utf-8', errors='ignore')
- match = re.search(r'filename="([^"]+)"', head)
- if match:
- filename = match.group(1)
- logger.info(f"Extracted filename from body: {filename}")
-
- # Run processing sync (in await)
- storage_path = await process_and_upload(temp_path, filename, content_type, user_id)
-
- # Get signed URL (it exists now)
- signed_url = await storage_service.get_signed_url(
- bucket=storage_service.BUCKET_MATERIALS,
- path=storage_path
- )
-
- size_mb = total_size / (1024 * 1024) # Approximate (includes headers)
-
- # 从 storage_path 提取显示名
- display_name = storage_path.split('/')[-1] # 去掉 user_id 前缀
- if '_' in display_name:
- parts = display_name.split('_', 1)
- if parts[0].isdigit():
- display_name = parts[1]
-
- return success_response({
- "id": storage_path,
- "name": display_name,
- "path": signed_url,
- "size_mb": size_mb,
- "type": "video"
- })
-
+ result = await service.upload_material(request, user_id)
+ return success_response(result)
+ except ValueError as e:
+ raise HTTPException(400, str(e))
except Exception as e:
- error_msg = f"Streaming upload failed: {str(e)}"
- detail_msg = f"Exception: {repr(e)}\nArgs: {e.args}\n{traceback.format_exc()}"
- logger.error(error_msg + "\n" + detail_msg)
-
- # Write to debug file
- try:
- with open("debug_upload.log", "a") as logf:
- logf.write(f"\n--- Error at {time.ctime()} ---\n")
- logf.write(detail_msg)
- logf.write("\n-----------------------------\n")
- except:
- pass
-
- if os.path.exists(temp_path):
- try:
- os.remove(temp_path)
- except:
- pass
- raise HTTPException(500, f"Upload failed. Check server logs. Error: {str(e)}")
+ raise HTTPException(500, f"Upload failed. Error: {str(e)}")
@router.get("")
async def list_materials(current_user: dict = Depends(get_current_user)):
user_id = current_user["id"]
- try:
- # 只列出当前用户目录下的文件
- files_obj = await storage_service.list_files(
- bucket=storage_service.BUCKET_MATERIALS,
- path=user_id
- )
- semaphore = asyncio.Semaphore(8)
-
- async def build_item(f):
- name = f.get('name')
- if not name or name == '.emptyFolderPlaceholder':
- return None
- display_name = name
- if '_' in name:
- parts = name.split('_', 1)
- if parts[0].isdigit():
- display_name = parts[1]
- full_path = f"{user_id}/{name}"
- async with semaphore:
- signed_url = await storage_service.get_signed_url(
- bucket=storage_service.BUCKET_MATERIALS,
- path=full_path
- )
- metadata = f.get('metadata', {})
- size = metadata.get('size', 0)
- created_at_str = f.get('created_at', '')
- created_at = 0
- if created_at_str:
- from datetime import datetime
- try:
- dt = datetime.fromisoformat(created_at_str.replace('Z', '+00:00'))
- created_at = int(dt.timestamp())
- except Exception:
- pass
- return {
- "id": full_path,
- "name": display_name,
- "path": signed_url,
- "size_mb": size / (1024 * 1024),
- "type": "video",
- "created_at": created_at
- }
-
- tasks = [build_item(f) for f in files_obj]
- results = await asyncio.gather(*tasks, return_exceptions=True)
-
- materials = []
- for item in results:
- if not item:
- continue
- if isinstance(item, Exception):
- logger.warning(f"Material signed url build failed: {item}")
- continue
- materials.append(item)
- materials.sort(key=lambda x: x['id'], reverse=True)
- return success_response({"materials": materials})
- except Exception as e:
- logger.error(f"List materials failed: {e}")
- return success_response({"materials": []}, message="获取素材失败")
+ materials = await service.list_materials(user_id)
+ return success_response({"materials": materials})
-@router.delete("/{material_id:path}")
-async def delete_material(material_id: str, current_user: dict = Depends(get_current_user)):
+@router.delete("/{material_id:path}")
+async def delete_material(material_id: str, current_user: dict = Depends(get_current_user)):
user_id = current_user["id"]
- # 验证 material_id 属于当前用户
- if not material_id.startswith(f"{user_id}/"):
- raise HTTPException(403, "无权删除此素材")
try:
- await storage_service.delete_file(
- bucket=storage_service.BUCKET_MATERIALS,
- path=material_id
- )
- return success_response(message="素材已删除")
- except Exception as e:
- raise HTTPException(500, f"删除失败: {str(e)}")
-
-
-@router.put("/{material_id:path}")
-async def rename_material(
- material_id: str,
- payload: RenameMaterialRequest,
- current_user: dict = Depends(get_current_user)
-):
- user_id = current_user["id"]
- if not material_id.startswith(f"{user_id}/"):
- raise HTTPException(403, "无权重命名此素材")
-
- new_name_raw = payload.new_name.strip() if payload.new_name else ""
- if not new_name_raw:
- raise HTTPException(400, "新名称不能为空")
-
- old_name = material_id.split("/", 1)[1]
- old_ext = Path(old_name).suffix
- base_name = Path(new_name_raw).stem if Path(new_name_raw).suffix else new_name_raw
- safe_base = sanitize_filename(base_name).strip()
- if not safe_base:
- raise HTTPException(400, "新名称无效")
-
- new_filename = f"{safe_base}{old_ext}"
-
- prefix = None
- if "_" in old_name:
- maybe_prefix, _ = old_name.split("_", 1)
- if maybe_prefix.isdigit():
- prefix = maybe_prefix
- if prefix:
- new_filename = f"{prefix}_{new_filename}"
-
- new_path = f"{user_id}/{new_filename}"
- try:
- if new_path != material_id:
- await storage_service.move_file(
- bucket=storage_service.BUCKET_MATERIALS,
- from_path=material_id,
- to_path=new_path
- )
-
- signed_url = await storage_service.get_signed_url(
- bucket=storage_service.BUCKET_MATERIALS,
- path=new_path
- )
-
- display_name = new_filename
- if "_" in new_filename:
- parts = new_filename.split("_", 1)
- if parts[0].isdigit():
- display_name = parts[1]
-
- return success_response({
- "id": new_path,
- "name": display_name,
- "path": signed_url,
- }, message="重命名成功")
- except Exception as e:
- raise HTTPException(500, f"重命名失败: {str(e)}")
-
+ await service.delete_material(material_id, user_id)
+ return success_response(message="素材已删除")
+ except PermissionError as e:
+ raise HTTPException(403, str(e))
+ except Exception as e:
+ raise HTTPException(500, f"删除失败: {str(e)}")
+@router.put("/{material_id:path}")
+async def rename_material(
+ material_id: str,
+ payload: RenameMaterialRequest,
+ current_user: dict = Depends(get_current_user)
+):
+ user_id = current_user["id"]
+ try:
+ result = await service.rename_material(material_id, payload.new_name, user_id)
+ return success_response(result, message="重命名成功")
+ except PermissionError as e:
+ raise HTTPException(403, str(e))
+ except ValueError as e:
+ raise HTTPException(400, str(e))
+ except Exception as e:
+ raise HTTPException(500, f"重命名失败: {str(e)}")
diff --git a/backend/app/modules/materials/schemas.py b/backend/app/modules/materials/schemas.py
new file mode 100644
index 0000000..6e681f8
--- /dev/null
+++ b/backend/app/modules/materials/schemas.py
@@ -0,0 +1,14 @@
+from pydantic import BaseModel
+
+
+class RenameMaterialRequest(BaseModel):
+ new_name: str
+
+
+class MaterialItem(BaseModel):
+ id: str
+ name: str
+ path: str
+ size_mb: float
+ type: str = "video"
+ created_at: int = 0
diff --git a/backend/app/modules/materials/service.py b/backend/app/modules/materials/service.py
new file mode 100644
index 0000000..8180caa
--- /dev/null
+++ b/backend/app/modules/materials/service.py
@@ -0,0 +1,296 @@
+import re
+import os
+import time
+import asyncio
+import traceback
+import aiofiles
+from pathlib import Path
+from loguru import logger
+
+from app.services.storage import storage_service
+
+
+def sanitize_filename(filename: str) -> str:
+ safe_name = re.sub(r'[<>:"/\\|?*]', '_', filename)
+ if len(safe_name) > 100:
+ ext = Path(safe_name).suffix
+ safe_name = safe_name[:100 - len(ext)] + ext
+ return safe_name
+
+
+def _extract_display_name(storage_name: str) -> str:
+ """从存储文件名中提取显示名（去掉时间戳前缀）"""
+ if '_' in storage_name:
+ parts = storage_name.split('_', 1)
+ if parts[0].isdigit():
+ return parts[1]
+ return storage_name
+
+
+async def _process_and_upload(temp_file_path: str, original_filename: str, content_type: str, user_id: str) -> str:
+ """Strip multipart headers and upload to Supabase, return storage_path"""
+ try:
+ logger.info(f"Processing raw upload: {temp_file_path} for user {user_id}")
+
+ file_size = os.path.getsize(temp_file_path)
+
+ with open(temp_file_path, 'rb') as f:
+ head = f.read(4096)
+
+ first_line_end = head.find(b'\r\n')
+ if first_line_end == -1:
+ raise Exception("Could not find boundary in multipart body")
+
+ boundary = head[:first_line_end]
+ logger.info(f"Detected boundary: {boundary}")
+
+ header_end = head.find(b'\r\n\r\n')
+ if header_end == -1:
+ raise Exception("Could not find end of multipart headers")
+
+ start_offset = header_end + 4
+ logger.info(f"Video data starts at offset: {start_offset}")
+
+ f.seek(max(0, file_size - 200))
+ tail = f.read()
+
+ last_boundary_pos = tail.rfind(boundary)
+ if last_boundary_pos != -1:
+ end_offset = (max(0, file_size - 200) + last_boundary_pos) - 2
+ else:
+ logger.warning("Could not find closing boundary, assuming EOF")
+ end_offset = file_size
+
+ logger.info(f"Video data ends at offset: {end_offset}. Total video size: {end_offset - start_offset}")
+
+ video_path = temp_file_path + "_video.mp4"
+ with open(temp_file_path, 'rb') as src, open(video_path, 'wb') as dst:
+ src.seek(start_offset)
+ bytes_to_copy = end_offset - start_offset
+ copied = 0
+ while copied < bytes_to_copy:
+ chunk_size = min(1024 * 1024 * 10, bytes_to_copy - copied)
+ chunk = src.read(chunk_size)
+ if not chunk:
+ break
+ dst.write(chunk)
+ copied += len(chunk)
+
+ logger.info(f"Extracted video content to {video_path}")
+
+ timestamp = int(time.time())
+ safe_name = re.sub(r'[^a-zA-Z0-9._-]', '', original_filename)
+ storage_path = f"{user_id}/{timestamp}_{safe_name}"
+
+ with open(video_path, 'rb') as f:
+ file_content = f.read()
+ await storage_service.upload_file(
+ bucket=storage_service.BUCKET_MATERIALS,
+ path=storage_path,
+ file_data=file_content,
+ content_type=content_type
+ )
+
+ logger.info(f"Upload to Supabase complete: {storage_path}")
+
+ os.remove(temp_file_path)
+ os.remove(video_path)
+
+ return storage_path
+
+ except Exception as e:
+ logger.error(f"Background upload processing failed: {e}\n{traceback.format_exc()}")
+ raise
+
+
+async def upload_material(request, user_id: str) -> dict:
+ """接收流式上传并存储到 Supabase，返回素材信息"""
+ filename = "unknown_video.mp4"
+ content_type = "video/mp4"
+
+ timestamp = int(time.time())
+ temp_filename = f"upload_{timestamp}.raw"
+ temp_path = os.path.join("/tmp", temp_filename)
+ if os.name == 'nt':
+ temp_path = f"d:/tmp/{temp_filename}"
+ os.makedirs("d:/tmp", exist_ok=True)
+
+ try:
+ total_size = 0
+ last_log = 0
+
+ async with aiofiles.open(temp_path, 'wb') as f:
+ async for chunk in request.stream():
+ await f.write(chunk)
+ total_size += len(chunk)
+
+ if total_size - last_log > 20 * 1024 * 1024:
+ logger.info(f"Receiving stream... Processed {total_size / (1024*1024):.2f} MB")
+ last_log = total_size
+
+ logger.info(f"Stream reception complete. Total size: {total_size} bytes. Saved to {temp_path}")
+
+ if total_size == 0:
+ raise ValueError("Received empty body")
+
+ with open(temp_path, 'rb') as f:
+ head = f.read(4096).decode('utf-8', errors='ignore')
+ match = re.search(r'filename="([^"]+)"', head)
+ if match:
+ filename = match.group(1)
+ logger.info(f"Extracted filename from body: {filename}")
+
+ storage_path = await _process_and_upload(temp_path, filename, content_type, user_id)
+
+ signed_url = await storage_service.get_signed_url(
+ bucket=storage_service.BUCKET_MATERIALS,
+ path=storage_path
+ )
+
+ size_mb = total_size / (1024 * 1024)
+ display_name = _extract_display_name(storage_path.split('/')[-1])
+
+ return {
+ "id": storage_path,
+ "name": display_name,
+ "path": signed_url,
+ "size_mb": size_mb,
+ "type": "video"
+ }
+
+ except Exception as e:
+ error_msg = f"Streaming upload failed: {str(e)}"
+ detail_msg = f"Exception: {repr(e)}\nArgs: {e.args}\n{traceback.format_exc()}"
+ logger.error(error_msg + "\n" + detail_msg)
+
+ try:
+ with open("debug_upload.log", "a") as logf:
+ logf.write(f"\n--- Error at {time.ctime()} ---\n")
+ logf.write(detail_msg)
+ logf.write("\n-----------------------------\n")
+ except:
+ pass
+
+ if os.path.exists(temp_path):
+ try:
+ os.remove(temp_path)
+ except:
+ pass
+ raise
+
+
+async def list_materials(user_id: str) -> list[dict]:
+ """列出用户的所有素材"""
+ try:
+ files_obj = await storage_service.list_files(
+ bucket=storage_service.BUCKET_MATERIALS,
+ path=user_id
+ )
+ semaphore = asyncio.Semaphore(8)
+
+ async def build_item(f):
+ name = f.get('name')
+ if not name or name == '.emptyFolderPlaceholder':
+ return None
+ display_name = _extract_display_name(name)
+ full_path = f"{user_id}/{name}"
+ async with semaphore:
+ signed_url = await storage_service.get_signed_url(
+ bucket=storage_service.BUCKET_MATERIALS,
+ path=full_path
+ )
+ metadata = f.get('metadata', {})
+ size = metadata.get('size', 0)
+ created_at_str = f.get('created_at', '')
+ created_at = 0
+ if created_at_str:
+ from datetime import datetime
+ try:
+ dt = datetime.fromisoformat(created_at_str.replace('Z', '+00:00'))
+ created_at = int(dt.timestamp())
+ except Exception:
+ pass
+ return {
+ "id": full_path,
+ "name": display_name,
+ "path": signed_url,
+ "size_mb": size / (1024 * 1024),
+ "type": "video",
+ "created_at": created_at
+ }
+
+ tasks = [build_item(f) for f in files_obj]
+ results = await asyncio.gather(*tasks, return_exceptions=True)
+
+ materials = []
+ for item in results:
+ if not item:
+ continue
+ if isinstance(item, Exception):
+ logger.warning(f"Material signed url build failed: {item}")
+ continue
+ materials.append(item)
+ materials.sort(key=lambda x: x['id'], reverse=True)
+ return materials
+ except Exception as e:
+ logger.error(f"List materials failed: {e}")
+ return []
+
+
+async def delete_material(material_id: str, user_id: str) -> None:
+ """删除素材"""
+ if not material_id.startswith(f"{user_id}/"):
+ raise PermissionError("无权删除此素材")
+ await storage_service.delete_file(
+ bucket=storage_service.BUCKET_MATERIALS,
+ path=material_id
+ )
+
+
+async def rename_material(material_id: str, new_name_raw: str, user_id: str) -> dict:
+ """重命名素材，返回更新后的素材信息"""
+ if not material_id.startswith(f"{user_id}/"):
+ raise PermissionError("无权重命名此素材")
+
+ new_name_raw = new_name_raw.strip() if new_name_raw else ""
+ if not new_name_raw:
+ raise ValueError("新名称不能为空")
+
+ old_name = material_id.split("/", 1)[1]
+ old_ext = Path(old_name).suffix
+ base_name = Path(new_name_raw).stem if Path(new_name_raw).suffix else new_name_raw
+ safe_base = sanitize_filename(base_name).strip()
+ if not safe_base:
+ raise ValueError("新名称无效")
+
+ new_filename = f"{safe_base}{old_ext}"
+
+ prefix = None
+ if "_" in old_name:
+ maybe_prefix, _ = old_name.split("_", 1)
+ if maybe_prefix.isdigit():
+ prefix = maybe_prefix
+ if prefix:
+ new_filename = f"{prefix}_{new_filename}"
+
+ new_path = f"{user_id}/{new_filename}"
+
+ if new_path != material_id:
+ await storage_service.move_file(
+ bucket=storage_service.BUCKET_MATERIALS,
+ from_path=material_id,
+ to_path=new_path
+ )
+
+ signed_url = await storage_service.get_signed_url(
+ bucket=storage_service.BUCKET_MATERIALS,
+ path=new_path
+ )
+
+ display_name = _extract_display_name(new_filename)
+
+ return {
+ "id": new_path,
+ "name": display_name,
+ "path": signed_url,
+ }
diff --git a/backend/app/modules/ref_audios/router.py b/backend/app/modules/ref_audios/router.py
index 8f57129..c564d35 100644
--- a/backend/app/modules/ref_audios/router.py
+++ b/backend/app/modules/ref_audios/router.py
@@ -1,83 +1,14 @@
-"""
-参考音频管理 API
-支持上传/列表/删除参考音频，用于 Qwen3-TTS 声音克隆
-"""
+"""参考音频管理 API"""
from fastapi import APIRouter, UploadFile, File, Form, HTTPException, Depends
-from pydantic import BaseModel
-from typing import List, Optional
-from pathlib import Path
from loguru import logger
-import time
-import json
-import subprocess
-import tempfile
-import os
-import re
from app.core.deps import get_current_user
-from app.services.storage import storage_service
from app.core.response import success_response
+from app.modules.ref_audios.schemas import RenameRequest
+from app.modules.ref_audios import service
router = APIRouter()
-# 支持的音频格式
-ALLOWED_AUDIO_EXTENSIONS = {'.wav', '.mp3', '.m4a', '.webm', '.ogg', '.flac', '.aac'}
-
-# 参考音频 bucket
-BUCKET_REF_AUDIOS = "ref-audios"
-
-
-class RefAudioResponse(BaseModel):
- id: str
- name: str
- path: str # signed URL for playback
- ref_text: str
- duration_sec: float
- created_at: int
-
-
-class RefAudioListResponse(BaseModel):
- items: List[RefAudioResponse]
-
-
-def sanitize_filename(filename: str) -> str:
- """清理文件名，移除特殊字符"""
- safe_name = re.sub(r'[<>:"/\\|?*\s]', '_', filename)
- if len(safe_name) > 50:
- ext = Path(safe_name).suffix
- safe_name = safe_name[:50 - len(ext)] + ext
- return safe_name
-
-
-def get_audio_duration(file_path: str) -> float:
- """获取音频时长 (秒)"""
- try:
- result = subprocess.run(
- ['ffprobe', '-v', 'quiet', '-show_entries', 'format=duration',
- '-of', 'csv=p=0', file_path],
- capture_output=True, text=True, timeout=10
- )
- return float(result.stdout.strip())
- except Exception as e:
- logger.warning(f"获取音频时长失败: {e}")
- return 0.0
-
-
-def convert_to_wav(input_path: str, output_path: str) -> bool:
- """将音频转换为 WAV 格式 (16kHz, mono)"""
- try:
- subprocess.run([
- 'ffmpeg', '-y', '-i', input_path,
- '-ar', '16000', # 16kHz 采样率
- '-ac', '1', # 单声道
- '-acodec', 'pcm_s16le', # 16-bit PCM
- output_path
- ], capture_output=True, timeout=60, check=True)
- return True
- except Exception as e:
- logger.error(f"音频转换失败: {e}")
- return False
-
@router.post("")
async def upload_ref_audio(
@@ -85,156 +16,12 @@ async def upload_ref_audio(
ref_text: str = Form(...),
user: dict = Depends(get_current_user)
):
- """
- 上传参考音频
-
- - file: 音频文件 (支持 wav, mp3, m4a, webm 等)
- - ref_text: 参考音频的转写文字 (必填)
- """
- user_id = user["id"]
-
- if not file.filename:
- raise HTTPException(status_code=400, detail="文件名无效")
- filename = file.filename
-
- # 验证文件扩展名
- ext = Path(filename).suffix.lower()
- if ext not in ALLOWED_AUDIO_EXTENSIONS:
- raise HTTPException(
- status_code=400,
- detail=f"不支持的音频格式: {ext}。支持的格式: {', '.join(ALLOWED_AUDIO_EXTENSIONS)}"
- )
-
- # 验证 ref_text
- if not ref_text or len(ref_text.strip()) < 2:
- raise HTTPException(status_code=400, detail="参考文字不能为空")
-
+ """上传参考音频"""
try:
- # 创建临时文件
- with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp_input:
- content = await file.read()
- tmp_input.write(content)
- tmp_input_path = tmp_input.name
-
- # 转换为 WAV 格式
- tmp_wav_path = tmp_input_path + ".wav"
- if ext != '.wav':
- if not convert_to_wav(tmp_input_path, tmp_wav_path):
- raise HTTPException(status_code=500, detail="音频格式转换失败")
- else:
- # 即使是 wav 也要标准化格式
- convert_to_wav(tmp_input_path, tmp_wav_path)
-
- # 获取音频时长
- duration = get_audio_duration(tmp_wav_path)
- if duration < 1.0:
- raise HTTPException(status_code=400, detail="音频时长过短，至少需要 1 秒")
- if duration > 60.0:
- raise HTTPException(status_code=400, detail="音频时长过长，最多 60 秒")
-
-
- # 3. 处理重名逻辑 (Friendly Display Name)
- original_name = filename
-
- # 获取用户现有的所有参考音频列表 (为了检查文件名冲突)
- # 注意: 这种列表方式在文件极多时性能一般，但考虑到单用户参考音频数量有限，目前可行
- existing_files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
- existing_names = set()
-
- # 预加载所有现有的 display name
- # 这里需要并发请求 metadata 可能会慢，优化: 仅检查 metadata 文件并解析
- # 简易方案: 仅在 metadata 中读取 original_filename
- # 但 list_files 返回的是 name，我们需要 metadata
- # 考虑到性能，这里使用一种妥协方案：
- # 我们不做全量检查，而是简单的检查：如果用户上传 myvoice.wav
- # 我们看看有没有 (timestamp)_myvoice.wav 这种其实并不能准确判断 display name 是否冲突
- #
- # 正确做法: 应该有个数据库表存 metadata。但目前是无数据库设计。
- #
- # 改用简单方案:
- # 既然我们无法快速获取所有 display name，
- # 我们暂时只处理 "在新上传时，original_filename 保持原样"
- # 但用户希望 "如果在列表中看到重复的，自动加(1)"
- #
- # 鉴于无数据库架构的限制，要在上传时知道"已有的 display name" 成本太高(需遍历下载所有json)。
- #
- # 💡 替代方案:
- # 我们不检查旧的。我们只保证**存储**唯一。
- # 对于用户提到的 "新上传的文件名后加个数字" -> 这通常是指 "另存为" 的逻辑。
- # 既然用户现在的痛点是 "显示了时间戳太丑"，而我已经去掉了时间戳显示。
- # 那么如果用户上传两个 "TEST.wav"，列表里就会有两个 "TEST.wav" (但时间不同)。
- # 这其实是可以接受的。
- #
- # 但如果用户强求 "自动重命名":
- # 我们可以在这里做一个轻量级的 "同名检测"：
- # 检查有没有 *_{original_name} 的文件存在。
- # 如果 storage 里已经有 123_abc.wav, 456_abc.wav
- # 我们可以认为 abc.wav 已经存在。
-
- dup_count = 0
- search_suffix = f"_{original_name}" # 比如 _test.wav
-
- for f in existing_files:
- fname = f.get('name', '')
- if fname.endswith(search_suffix):
- dup_count += 1
-
- final_display_name = original_name
- if dup_count > 0:
- name_stem = Path(original_name).stem
- name_ext = Path(original_name).suffix
- final_display_name = f"{name_stem}({dup_count}){name_ext}"
-
- # 生成存储路径 (唯一ID)
- timestamp = int(time.time())
- safe_name = sanitize_filename(Path(filename).stem)
- storage_path = f"{user_id}/{timestamp}_{safe_name}.wav"
-
- # 上传 WAV 文件到 Supabase
- with open(tmp_wav_path, 'rb') as f:
- wav_data = f.read()
-
- await storage_service.upload_file(
- bucket=BUCKET_REF_AUDIOS,
- path=storage_path,
- file_data=wav_data,
- content_type="audio/wav"
- )
-
- # 上传元数据 JSON
- metadata = {
- "ref_text": ref_text.strip(),
- "original_filename": final_display_name, # 这里的名字如果有重复会自动加(1)
- "duration_sec": duration,
- "created_at": timestamp
- }
- metadata_path = f"{user_id}/{timestamp}_{safe_name}.json"
- await storage_service.upload_file(
- bucket=BUCKET_REF_AUDIOS,
- path=metadata_path,
- file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
- content_type="application/json"
- )
-
- # 获取签名 URL
- signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
-
- # 清理临时文件
- os.unlink(tmp_input_path)
- if os.path.exists(tmp_wav_path):
- os.unlink(tmp_wav_path)
-
- return success_response(RefAudioResponse(
- id=storage_path,
- name=filename,
- path=signed_url,
- ref_text=ref_text.strip(),
- duration_sec=duration,
- created_at=timestamp
- ).model_dump())
-
- except HTTPException:
- raise
+ result = await service.upload_ref_audio(file, ref_text, user["id"])
+ return success_response(result)
+ except ValueError as e:
+ raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
logger.error(f"上传参考音频失败: {e}")
raise HTTPException(status_code=500, detail=f"上传失败: {str(e)}")
@@ -243,81 +30,9 @@ async def upload_ref_audio(
@router.get("")
async def list_ref_audios(user: dict = Depends(get_current_user)):
"""列出当前用户的所有参考音频"""
- user_id = user["id"]
-
try:
- # 列出用户目录下的文件
- files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
-
- # 过滤出 .wav 文件
- wav_files = [f for f in files if f.get("name", "").endswith(".wav")]
-
- if not wav_files:
- return success_response(RefAudioListResponse(items=[]).model_dump())
-
- # 并发获取所有 metadata 和签名 URL
- async def fetch_audio_info(f):
- """获取单个音频的信息（metadata + signed URL）"""
- name = f.get("name", "")
- storage_path = f"{user_id}/{name}"
- metadata_name = name.replace(".wav", ".json")
- metadata_path = f"{user_id}/{metadata_name}"
-
- ref_text = ""
- duration_sec = 0.0
- created_at = 0
- original_filename = ""
-
- try:
- # 获取 metadata 内容
- metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
- import httpx
- async with httpx.AsyncClient(timeout=5.0) as client:
- resp = await client.get(metadata_url)
- if resp.status_code == 200:
- metadata = resp.json()
- ref_text = metadata.get("ref_text", "")
- duration_sec = metadata.get("duration_sec", 0.0)
- created_at = metadata.get("created_at", 0)
- original_filename = metadata.get("original_filename", "")
- except Exception as e:
- logger.debug(f"读取 metadata 失败: {e}")
- # 从文件名提取时间戳
- try:
- created_at = int(name.split("_")[0])
- except:
- pass
-
- # 获取音频签名 URL
- signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
-
- # 优先显示原始文件名 (去掉时间戳前缀)
- display_name = original_filename if original_filename else name
- # 如果原始文件名丢失，尝试从现有文件名中通过正则去掉时间戳
- if not display_name or display_name == name:
- # 匹配 "1234567890_filename.wav"
- match = re.match(r'^\d+_(.+)$', name)
- if match:
- display_name = match.group(1)
-
- return RefAudioResponse(
- id=storage_path,
- name=display_name,
- path=signed_url,
- ref_text=ref_text,
- duration_sec=duration_sec,
- created_at=created_at
- )
-
- # 使用 asyncio.gather 并发获取所有音频信息
- import asyncio
- items = await asyncio.gather(*[fetch_audio_info(f) for f in wav_files])
-
- # 按创建时间倒序排列
- items = sorted(items, key=lambda x: x.created_at, reverse=True)
-
- return success_response(RefAudioListResponse(items=items).model_dump())
-
+ result = await service.list_ref_audios(user["id"])
+ return success_response(result)
except Exception as e:
logger.error(f"列出参考音频失败: {e}")
raise HTTPException(status_code=500, detail=f"获取列表失败: {str(e)}")
@@ -326,96 +41,30 @@ async def list_ref_audios(user: dict = Depends(get_current_user)):
@router.delete("/{audio_id:path}")
async def delete_ref_audio(audio_id: str, user: dict = Depends(get_current_user)):
"""删除参考音频"""
- user_id = user["id"]
-
- # 安全检查：确保只能删除自己的文件
- if not audio_id.startswith(f"{user_id}/"):
- raise HTTPException(status_code=403, detail="无权删除此文件")
-
try:
- # 删除 WAV 文件
- await storage_service.delete_file(BUCKET_REF_AUDIOS, audio_id)
-
- # 删除 metadata JSON
- metadata_path = audio_id.replace(".wav", ".json")
- try:
- await storage_service.delete_file(BUCKET_REF_AUDIOS, metadata_path)
- except:
- pass # metadata 可能不存在
-
+ await service.delete_ref_audio(audio_id, user["id"])
return success_response(message="删除成功")
-
+ except PermissionError as e:
+ raise HTTPException(status_code=403, detail=str(e))
except Exception as e:
logger.error(f"删除参考音频失败: {e}")
raise HTTPException(status_code=500, detail=f"删除失败: {str(e)}")
-class RenameRequest(BaseModel):
- new_name: str
-
-
@router.put("/{audio_id:path}")
async def rename_ref_audio(
audio_id: str,
request: RenameRequest,
user: dict = Depends(get_current_user)
):
- """重命名参考音频 (修改 metadata 中的 display name)"""
- user_id = user["id"]
-
- # 安全检查
- if not audio_id.startswith(f"{user_id}/"):
- raise HTTPException(status_code=403, detail="无权修改此文件")
-
- new_name = request.new_name.strip()
- if not new_name:
- raise HTTPException(status_code=400, detail="新名称不能为空")
-
- # 确保新名称有后缀 (保留原后缀或添加 .wav)
- if not Path(new_name).suffix:
- new_name += ".wav"
-
+ """重命名参考音频"""
try:
- # 1. 下载现有的 metadata
- metadata_path = audio_id.replace(".wav", ".json")
- try:
- # 获取已有的 JSON
- import httpx
- metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
- if not metadata_url:
- # 如果 json 不存在，则需要新建一个基础的
- raise Exception("Metadata not found")
-
- async with httpx.AsyncClient() as client:
- resp = await client.get(metadata_url)
- if resp.status_code == 200:
- metadata = resp.json()
- else:
- raise Exception(f"Failed to fetch metadata: {resp.status_code}")
-
- except Exception as e:
- logger.warning(f"无法读取元数据: {e}, 将创建新的元数据")
- # 兜底：如果读取失败，构建最小元数据
- metadata = {
- "ref_text": "", # 可能丢失
- "duration_sec": 0.0,
- "created_at": int(time.time()),
- "original_filename": new_name
- }
-
- # 2. 更新 original_filename
- metadata["original_filename"] = new_name
-
- # 3. 覆盖上传 metadata
- await storage_service.upload_file(
- bucket=BUCKET_REF_AUDIOS,
- path=metadata_path,
- file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
- content_type="application/json"
- )
-
- return success_response({"name": new_name}, message="重命名成功")
-
+ result = await service.rename_ref_audio(audio_id, request.new_name, user["id"])
+ return success_response(result, message="重命名成功")
+ except PermissionError as e:
+ raise HTTPException(status_code=403, detail=str(e))
+ except ValueError as e:
+ raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
logger.error(f"重命名失败: {e}")
raise HTTPException(status_code=500, detail=f"重命名失败: {str(e)}")
diff --git a/backend/app/modules/ref_audios/schemas.py b/backend/app/modules/ref_audios/schemas.py
new file mode 100644
index 0000000..1099183
--- /dev/null
+++ b/backend/app/modules/ref_audios/schemas.py
@@ -0,0 +1,19 @@
+from pydantic import BaseModel
+from typing import List
+
+
+class RefAudioResponse(BaseModel):
+ id: str
+ name: str
+ path: str
+ ref_text: str
+ duration_sec: float
+ created_at: int
+
+
+class RefAudioListResponse(BaseModel):
+ items: List[RefAudioResponse]
+
+
+class RenameRequest(BaseModel):
+ new_name: str
diff --git a/backend/app/modules/ref_audios/service.py b/backend/app/modules/ref_audios/service.py
new file mode 100644
index 0000000..55a7a75
--- /dev/null
+++ b/backend/app/modules/ref_audios/service.py
@@ -0,0 +1,269 @@
+import re
+import os
+import time
+import json
+import asyncio
+import subprocess
+import tempfile
+from pathlib import Path
+from typing import Optional
+
+import httpx
+from loguru import logger
+
+from app.services.storage import storage_service
+from app.modules.ref_audios.schemas import RefAudioResponse, RefAudioListResponse
+
+ALLOWED_AUDIO_EXTENSIONS = {'.wav', '.mp3', '.m4a', '.webm', '.ogg', '.flac', '.aac'}
+BUCKET_REF_AUDIOS = "ref-audios"
+
+
+def sanitize_filename(filename: str) -> str:
+ """清理文件名，移除特殊字符"""
+ safe_name = re.sub(r'[<>:"/\\|?*\s]', '_', filename)
+ if len(safe_name) > 50:
+ ext = Path(safe_name).suffix
+ safe_name = safe_name[:50 - len(ext)] + ext
+ return safe_name
+
+
+def _get_audio_duration(file_path: str) -> float:
+ """获取音频时长 (秒)"""
+ try:
+ result = subprocess.run(
+ ['ffprobe', '-v', 'quiet', '-show_entries', 'format=duration',
+ '-of', 'csv=p=0', file_path],
+ capture_output=True, text=True, timeout=10
+ )
+ return float(result.stdout.strip())
+ except Exception as e:
+ logger.warning(f"获取音频时长失败: {e}")
+ return 0.0
+
+
+def _convert_to_wav(input_path: str, output_path: str) -> bool:
+ """将音频转换为 WAV 格式 (16kHz, mono)"""
+ try:
+ subprocess.run([
+ 'ffmpeg', '-y', '-i', input_path,
+ '-ar', '16000',
+ '-ac', '1',
+ '-acodec', 'pcm_s16le',
+ output_path
+ ], capture_output=True, timeout=60, check=True)
+ return True
+ except Exception as e:
+ logger.error(f"音频转换失败: {e}")
+ return False
+
+
+async def upload_ref_audio(file, ref_text: str, user_id: str) -> dict:
+ """上传参考音频：转码、获取时长、存储到 Supabase"""
+ if not file.filename:
+ raise ValueError("文件名无效")
+ filename = file.filename
+
+ ext = Path(filename).suffix.lower()
+ if ext not in ALLOWED_AUDIO_EXTENSIONS:
+ raise ValueError(f"不支持的音频格式: {ext}。支持的格式: {', '.join(ALLOWED_AUDIO_EXTENSIONS)}")
+
+ if not ref_text or len(ref_text.strip()) < 2:
+ raise ValueError("参考文字不能为空")
+
+ # 创建临时文件
+ with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp_input:
+ content = await file.read()
+ tmp_input.write(content)
+ tmp_input_path = tmp_input.name
+
+ try:
+ # 转换为 WAV 格式
+ tmp_wav_path = tmp_input_path + ".wav"
+ if not _convert_to_wav(tmp_input_path, tmp_wav_path):
+ raise RuntimeError("音频格式转换失败")
+
+ # 获取音频时长
+ duration = _get_audio_duration(tmp_wav_path)
+ if duration < 1.0:
+ raise ValueError("音频时长过短，至少需要 1 秒")
+ if duration > 60.0:
+ raise ValueError("音频时长过长，最多 60 秒")
+
+ # 检查重名
+ existing_files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
+ dup_count = 0
+ search_suffix = f"_{filename}"
+ for f in existing_files:
+ fname = f.get('name', '')
+ if fname.endswith(search_suffix):
+ dup_count += 1
+
+ final_display_name = filename
+ if dup_count > 0:
+ name_stem = Path(filename).stem
+ name_ext = Path(filename).suffix
+ final_display_name = f"{name_stem}({dup_count}){name_ext}"
+
+ # 生成存储路径
+ timestamp = int(time.time())
+ safe_name = sanitize_filename(Path(filename).stem)
+ storage_path = f"{user_id}/{timestamp}_{safe_name}.wav"
+
+ # 上传 WAV 文件
+ with open(tmp_wav_path, 'rb') as f:
+ wav_data = f.read()
+
+ await storage_service.upload_file(
+ bucket=BUCKET_REF_AUDIOS,
+ path=storage_path,
+ file_data=wav_data,
+ content_type="audio/wav"
+ )
+
+ # 上传元数据 JSON
+ metadata = {
+ "ref_text": ref_text.strip(),
+ "original_filename": final_display_name,
+ "duration_sec": duration,
+ "created_at": timestamp
+ }
+ metadata_path = f"{user_id}/{timestamp}_{safe_name}.json"
+ await storage_service.upload_file(
+ bucket=BUCKET_REF_AUDIOS,
+ path=metadata_path,
+ file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
+ content_type="application/json"
+ )
+
+ # 获取签名 URL
+ signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
+
+ return RefAudioResponse(
+ id=storage_path,
+ name=filename,
+ path=signed_url,
+ ref_text=ref_text.strip(),
+ duration_sec=duration,
+ created_at=timestamp
+ ).model_dump()
+
+ finally:
+ os.unlink(tmp_input_path)
+ if os.path.exists(tmp_input_path + ".wav"):
+ os.unlink(tmp_input_path + ".wav")
+
+
+async def list_ref_audios(user_id: str) -> dict:
+ """列出用户的所有参考音频"""
+ files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
+ wav_files = [f for f in files if f.get("name", "").endswith(".wav")]
+
+ if not wav_files:
+ return RefAudioListResponse(items=[]).model_dump()
+
+ async def fetch_audio_info(f):
+ name = f.get("name", "")
+ storage_path = f"{user_id}/{name}"
+ metadata_name = name.replace(".wav", ".json")
+ metadata_path = f"{user_id}/{metadata_name}"
+
+ ref_text = ""
+ duration_sec = 0.0
+ created_at = 0
+ original_filename = ""
+
+ try:
+ metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
+ async with httpx.AsyncClient(timeout=5.0) as client:
+ resp = await client.get(metadata_url)
+ if resp.status_code == 200:
+ metadata = resp.json()
+ ref_text = metadata.get("ref_text", "")
+ duration_sec = metadata.get("duration_sec", 0.0)
+ created_at = metadata.get("created_at", 0)
+ original_filename = metadata.get("original_filename", "")
+ except Exception as e:
+ logger.debug(f"读取 metadata 失败: {e}")
+ try:
+ created_at = int(name.split("_")[0])
+ except:
+ pass
+
+ signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
+
+ display_name = original_filename if original_filename else name
+ if not display_name or display_name == name:
+ match = re.match(r'^\d+_(.+)$', name)
+ if match:
+ display_name = match.group(1)
+
+ return RefAudioResponse(
+ id=storage_path,
+ name=display_name,
+ path=signed_url,
+ ref_text=ref_text,
+ duration_sec=duration_sec,
+ created_at=created_at
+ )
+
+ items = await asyncio.gather(*[fetch_audio_info(f) for f in wav_files])
+ items = sorted(items, key=lambda x: x.created_at, reverse=True)
+
+ return RefAudioListResponse(items=items).model_dump()
+
+
+async def delete_ref_audio(audio_id: str, user_id: str) -> None:
+ """删除参考音频及其元数据"""
+ if not audio_id.startswith(f"{user_id}/"):
+ raise PermissionError("无权删除此文件")
+
+ await storage_service.delete_file(BUCKET_REF_AUDIOS, audio_id)
+
+ metadata_path = audio_id.replace(".wav", ".json")
+ try:
+ await storage_service.delete_file(BUCKET_REF_AUDIOS, metadata_path)
+ except:
+ pass
+
+
+async def rename_ref_audio(audio_id: str, new_name: str, user_id: str) -> dict:
+ """重命名参考音频（修改 metadata 中的 display name）"""
+ if not audio_id.startswith(f"{user_id}/"):
+ raise PermissionError("无权修改此文件")
+
+ new_name = new_name.strip()
+ if not new_name:
+ raise ValueError("新名称不能为空")
+
+ if not Path(new_name).suffix:
+ new_name += ".wav"
+
+ # 下载现有 metadata
+ metadata_path = audio_id.replace(".wav", ".json")
+ try:
+ metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
+ async with httpx.AsyncClient() as client:
+ resp = await client.get(metadata_url)
+ if resp.status_code == 200:
+ metadata = resp.json()
+ else:
+ raise Exception(f"Failed to fetch metadata: {resp.status_code}")
+ except Exception as e:
+ logger.warning(f"无法读取元数据: {e}, 将创建新的元数据")
+ metadata = {
+ "ref_text": "",
+ "duration_sec": 0.0,
+ "created_at": int(time.time()),
+ "original_filename": new_name
+ }
+
+ # 更新并覆盖上传
+ metadata["original_filename"] = new_name
+ await storage_service.upload_file(
+ bucket=BUCKET_REF_AUDIOS,
+ path=metadata_path,
+ file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
+ content_type="application/json"
+ )
+
+ return {"name": new_name}
diff --git a/backend/app/modules/tools/router.py b/backend/app/modules/tools/router.py
index 59d3de8..c45293e 100644
--- a/backend/app/modules/tools/router.py
+++ b/backend/app/modules/tools/router.py
@@ -1,417 +1,32 @@
from fastapi import APIRouter, UploadFile, File, Form, HTTPException
-from typing import Optional, Any, cast
-import asyncio
-import shutil
-import os
-import time
-from pathlib import Path
-from loguru import logger
+from typing import Optional
import traceback
-import re
-import json
-import requests
-from urllib.parse import unquote
+from loguru import logger
-from app.services.whisper_service import whisper_service
-from app.services.glm_service import glm_service
from app.core.response import success_response
+from app.modules.tools import service
router = APIRouter()
+
@router.post("/extract-script")
async def extract_script_tool(
file: Optional[UploadFile] = File(None),
url: Optional[str] = Form(None),
rewrite: bool = Form(True)
):
- """
- 独立文案提取工具
- 支持上传视频/音频 OR 输入视频链接 -> 提取文字 -> (可选) AI洗稿
- """
- if not file and not url:
- raise HTTPException(400, "必须提供文件或视频链接")
-
- temp_path = None
+ """独立文案提取工具"""
try:
- timestamp = int(time.time())
- temp_dir = Path("/tmp")
- if os.name == 'nt':
- temp_dir = Path("d:/tmp")
- temp_dir.mkdir(parents=True, exist_ok=True)
-
- # 1. 获取/保存文件
- loop = asyncio.get_event_loop()
-
- if file:
- filename = file.filename
- if not filename:
- raise HTTPException(400, "文件名无效")
- safe_filename = Path(filename).name.replace(" ", "_")
- temp_path = temp_dir / f"tool_extract_{timestamp}_{safe_filename}"
- # 文件 I/O 放入线程池
- await loop.run_in_executor(None, lambda: shutil.copyfileobj(file.file, open(temp_path, "wb")))
- logger.info(f"Tool processing upload file: {temp_path}")
- else:
- if not url:
- raise HTTPException(400, "必须提供视频链接")
- url_value: str = url
- # URL 下载逻辑
- # 自动提取文案中的链接 (支持 Douyin/Bilibili 等分享文案)
- url_match = re.search(r'https?://[^\s]+', url_value)
- if url_match:
- extracted_url = url_match.group(0)
- logger.info(f"Extracted URL from text: {extracted_url}")
- url_value = extracted_url
-
- logger.info(f"Tool downloading URL: {url_value}")
-
- # 封装 yt-dlp 下载函数 (Blocking)
- def _download_yt_dlp():
- import yt_dlp
- logger.info("Attempting download with yt-dlp...")
-
- ydl_opts = {
- 'format': 'bestaudio/best',
- 'outtmpl': str(temp_dir / f"tool_download_{timestamp}_%(id)s.%(ext)s"),
- 'quiet': True,
- 'no_warnings': True,
- 'http_headers': {
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
- 'Referer': 'https://www.douyin.com/',
- }
- }
-
- with yt_dlp.YoutubeDL() as ydl_raw:
- ydl: Any = ydl_raw
- ydl.params.update(ydl_opts)
- info = ydl.extract_info(url_value, download=True)
- if 'requested_downloads' in info:
- downloaded_file = info['requested_downloads'][0]['filepath']
- else:
- ext = info.get('ext', 'mp4')
- id = info.get('id')
- downloaded_file = str(temp_dir / f"tool_download_{timestamp}_{id}.{ext}")
-
- return Path(downloaded_file)
-
- # 先尝试 yt-dlp (Run in Executor)
- try:
- temp_path = await loop.run_in_executor(None, _download_yt_dlp)
- logger.info(f"yt-dlp downloaded to: {temp_path}")
-
- except Exception as e:
- logger.warning(f"yt-dlp download failed: {e}. Trying manual Douyin fallback...")
-
- # 失败则尝试手动解析 (Douyin Fallback)
- if "douyin" in url_value:
- manual_path = await download_douyin_manual(url_value, temp_dir, timestamp)
- if manual_path:
- temp_path = manual_path
- logger.info(f"Manual Douyin fallback successful: {temp_path}")
- else:
- raise HTTPException(400, f"视频下载失败。yt-dlp 报错: {str(e)}")
- elif "bilibili" in url_value:
- manual_path = await download_bilibili_manual(url_value, temp_dir, timestamp)
- if manual_path:
- temp_path = manual_path
- logger.info(f"Manual Bilibili fallback successful: {temp_path}")
- else:
- raise HTTPException(400, f"视频下载失败。yt-dlp 报错: {str(e)}")
- else:
- raise HTTPException(400, f"视频下载失败: {str(e)}")
-
- if not temp_path or not temp_path.exists():
- raise HTTPException(400, "文件获取失败")
-
- # 1.5 安全转换: 强制转为 WAV (16k)
- import subprocess
- audio_path = temp_dir / f"extract_audio_{timestamp}.wav"
-
- def _convert_audio():
- try:
- convert_cmd = [
- 'ffmpeg',
- '-i', str(temp_path),
- '-vn', # 忽略视频
- '-acodec', 'pcm_s16le',
- '-ar', '16000', # Whisper 推荐采样率
- '-ac', '1', # 单声道
- '-y', # 覆盖
- str(audio_path)
- ]
- # 捕获 stderr
- subprocess.run(convert_cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
- return True
- except subprocess.CalledProcessError as e:
- error_log = e.stderr.decode('utf-8', errors='ignore') if e.stderr else str(e)
- logger.error(f"FFmpeg check/convert failed: {error_log}")
- # 检查是否为 HTML
- head = b""
- try:
- with open(temp_path, 'rb') as f:
- head = f.read(100)
- except: pass
- if b' 0:
- logger.info("Rewriting script...")
- rewritten = await glm_service.rewrite_script(script)
- else:
- logger.warning("No script extracted, skipping rewrite")
-
- return success_response({
- "original_script": script,
- "rewritten_script": rewritten
- })
-
- except HTTPException as he:
- raise he
+ result = await service.extract_script(file=file, url=url, rewrite=rewrite)
+ return success_response(result)
+ except ValueError as e:
+ raise HTTPException(400, str(e))
+ except HTTPException:
+ raise
except Exception as e:
logger.error(f"Tool extract failed: {e}")
logger.error(traceback.format_exc())
-
- # Friendly error message
msg = str(e)
if "Fresh cookies" in msg:
msg = "下载失败：目标平台开启了反爬验证，请过段时间重试或直接上传视频文件。"
-
raise HTTPException(500, f"提取失败: {msg}")
- finally:
- # 清理临时文件
- if temp_path and temp_path.exists():
- try:
- os.remove(temp_path)
- logger.info(f"Cleaned up temp file: {temp_path}")
- except Exception as e:
- logger.warning(f"Failed to cleanup temp file {temp_path}: {e}")
-
-
-async def download_douyin_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
- """
- 手动下载抖音视频 (Fallback logic - Ported from SuperIPAgent/douyinDownloader)
- 使用特定的 User Profile URL 和硬编码 Cookie 绕过反爬
- """
- import httpx
-
- logger.info(f"[SuperIPAgent] Starting download for: {url}")
-
- try:
- # 1. 提取 Modal ID (支持短链跳转)
- headers = {
- "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
- }
-
- # 如果是短链或重定向 - 使用异步 httpx
- async with httpx.AsyncClient(follow_redirects=True, timeout=10.0) as client:
- resp = await client.get(url, headers=headers)
- final_url = str(resp.url)
-
- logger.info(f"[SuperIPAgent] Final URL: {final_url}")
-
- modal_id = None
- match = re.search(r'/video/(\d+)', final_url)
- if match:
- modal_id = match.group(1)
-
- if not modal_id:
- logger.error("[SuperIPAgent] Could not extract modal_id")
- return None
-
- logger.info(f"[SuperIPAgent] Extracted modal_id: {modal_id}")
-
- # 2. 构造特定请求 URL (Copy from SuperIPAgent)
- # 使用特定用户的 Profile 页 + modal_id 参数，配合特定 Cookie
- target_url = f"https://www.douyin.com/user/MS4wLjABAAAAN_s_hups7LD0N4qnrM3o2gI0vuG3pozNaEolz2_py3cHTTrpVr1Z4dukFD9SOlwY?from_tab_name=main&modal_id={modal_id}"
-
- # 3. 使用配置的 Cookie (从环境变量 DOUYIN_COOKIE 读取)
- from app.core.config import settings
- if not settings.DOUYIN_COOKIE:
- logger.warning("[SuperIPAgent] DOUYIN_COOKIE 未配置，视频下载可能失败")
-
- headers_with_cookie = {
- "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
- "cookie": settings.DOUYIN_COOKIE,
- "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
- }
-
- logger.info(f"[SuperIPAgent] Requesting page with Cookie...")
-
- async with httpx.AsyncClient(timeout=10.0) as client:
- response = await client.get(target_url, headers=headers_with_cookie)
-
- # 4. 解析 RENDER_DATA
- content_match = re.findall(r'', response.text)
- if not content_match:
- # 尝试解码后再查找？或者结构变了
- # 再尝试找 SSR_HYDRATED_DATA
- if "SSR_HYDRATED_DATA" in response.text:
- content_match = re.findall(r'', response.text)
-
- if not content_match:
- logger.error(f"[SuperIPAgent] Could not find RENDER_DATA in page (len={len(response.text)})")
- return None
-
- content = unquote(content_match[0])
- try:
- data = json.loads(content)
- except:
- logger.error("[SuperIPAgent] JSON decode failed")
- return None
-
- # 5. 提取视频流
- video_url = None
- try:
- # 路径通常是: app -> videoDetail -> video -> bitRateList -> playAddr -> src
- if "app" in data and "videoDetail" in data["app"]:
- info = data["app"]["videoDetail"]["video"]
- if "bitRateList" in info and info["bitRateList"]:
- video_url = info["bitRateList"][0]["playAddr"][0]["src"]
- elif "playAddr" in info and info["playAddr"]:
- video_url = info["playAddr"][0]["src"]
- except Exception as e:
- logger.error(f"[SuperIPAgent] Path extraction failed: {e}")
-
- if not video_url:
- logger.error("[SuperIPAgent] No video_url found")
- return None
-
- if video_url.startswith("//"):
- video_url = "https:" + video_url
-
- logger.info(f"[SuperIPAgent] Found video URL: {video_url[:50]}...")
-
- # 6. 下载 (带 Header) - 使用异步 httpx
- temp_path = temp_dir / f"douyin_manual_{timestamp}.mp4"
- download_headers = {
- 'Referer': 'https://www.douyin.com/',
- 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
- }
-
- async with httpx.AsyncClient(timeout=60.0) as client:
- async with client.stream("GET", video_url, headers=download_headers) as dl_resp:
- if dl_resp.status_code == 200:
- with open(temp_path, 'wb') as f:
- async for chunk in dl_resp.aiter_bytes(chunk_size=8192):
- f.write(chunk)
-
- logger.info(f"[SuperIPAgent] Downloaded successfully: {temp_path}")
- return temp_path
- else:
- logger.error(f"[SuperIPAgent] Download failed: {dl_resp.status_code}")
- return None
-
- except Exception as e:
- logger.error(f"[SuperIPAgent] Logic failed: {e}")
- return None
-
-async def download_bilibili_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
- """
- 手动下载 Bilibili 视频 (Fallback logic - Playwright Version)
- B站通常音视频分离，这里只提取音频即可（因为只需要文案）
- """
- from playwright.async_api import async_playwright
-
- logger.info(f"[Playwright] Starting Bilibili download for: {url}")
-
- playwright = None
- browser = None
- try:
- playwright = await async_playwright().start()
- # Launch browser (ensure chromium is installed: playwright install chromium)
- browser = await playwright.chromium.launch(headless=True, args=['--no-sandbox', '--disable-setuid-sandbox'])
-
- # Mobile User Agent often gives single stream?
- # But Bilibili mobile web is tricky. Desktop is fine.
- context = await browser.new_context(
- user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
- )
-
- page = await context.new_page()
-
- # Intercept audio responses?
- # Bilibili streams are usually .m4s
- # But finding the initial state is easier.
-
- logger.info("[Playwright] Navigating to Bilibili...")
- await page.goto(url, timeout=45000)
-
- # Wait for video element (triggers loading)
- try:
- await page.wait_for_selector('video', timeout=15000)
- except:
- logger.warning("[Playwright] Video selector timeout")
-
- # 1. Try extracting from __playinfo__
- # window.__playinfo__ contains dash streams
- playinfo = await page.evaluate("window.__playinfo__")
-
- audio_url = None
-
- if playinfo and "data" in playinfo and "dash" in playinfo["data"]:
- dash = playinfo["data"]["dash"]
- if "audio" in dash and dash["audio"]:
- audio_url = dash["audio"][0]["baseUrl"]
- logger.info(f"[Playwright] Found audio stream in __playinfo__: {audio_url[:50]}...")
-
- # 2. If playinfo fails, try extracting video src (sometimes it's a blob, which we can't fetch easily without interception)
- # But interception is complex. Let's try requests with Referer if we have URL.
-
- if not audio_url:
- logger.warning("[Playwright] Could not find audio in __playinfo__")
- return None
-
- # Download the audio stream
- temp_path = temp_dir / f"bilibili_audio_{timestamp}.m4s" # usually m4s
-
- try:
- api_request = context.request
- headers = {
- "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
- "Referer": "https://www.bilibili.com/"
- }
-
- logger.info(f"[Playwright] Downloading audio stream...")
- response = await api_request.get(audio_url, headers=headers)
-
- if response.status == 200:
- body = await response.body()
- with open(temp_path, 'wb') as f:
- f.write(body)
-
- logger.info(f"[Playwright] Downloaded successfully: {temp_path}")
- return temp_path
- else:
- logger.error(f"[Playwright] API Request failed: {response.status}")
- return None
-
- except Exception as e:
- logger.error(f"[Playwright] Download logic error: {e}")
- return None
-
- except Exception as e:
- logger.error(f"[Playwright] Bilibili download failed: {e}")
- return None
- finally:
- if browser:
- await browser.close()
- if playwright:
- await playwright.stop()
diff --git a/backend/app/modules/tools/schemas.py b/backend/app/modules/tools/schemas.py
new file mode 100644
index 0000000..5d93cb1
--- /dev/null
+++ b/backend/app/modules/tools/schemas.py
@@ -0,0 +1,7 @@
+from pydantic import BaseModel
+from typing import Optional
+
+
+class ExtractScriptResponse(BaseModel):
+ original_script: Optional[str] = None
+ rewritten_script: Optional[str] = None
diff --git a/backend/app/modules/tools/service.py b/backend/app/modules/tools/service.py
new file mode 100644
index 0000000..e87ba33
--- /dev/null
+++ b/backend/app/modules/tools/service.py
@@ -0,0 +1,355 @@
+import asyncio
+import os
+import re
+import json
+import time
+import shutil
+import subprocess
+import traceback
+from pathlib import Path
+from typing import Optional, Any
+from urllib.parse import unquote
+
+import httpx
+from loguru import logger
+
+from app.services.whisper_service import whisper_service
+from app.services.glm_service import glm_service
+
+
+async def extract_script(file=None, url: Optional[str] = None, rewrite: bool = True) -> dict:
+ """
+ 文案提取：上传文件或视频链接 -> Whisper 转写 -> (可选) GLM 洗稿
+ """
+ if not file and not url:
+ raise ValueError("必须提供文件或视频链接")
+
+ temp_path = None
+ try:
+ timestamp = int(time.time())
+ temp_dir = Path("/tmp")
+ if os.name == 'nt':
+ temp_dir = Path("d:/tmp")
+ temp_dir.mkdir(parents=True, exist_ok=True)
+
+ loop = asyncio.get_event_loop()
+
+ # 1. 获取/保存文件
+ if file:
+ filename = file.filename
+ if not filename:
+ raise ValueError("文件名无效")
+ safe_filename = Path(filename).name.replace(" ", "_")
+ temp_path = temp_dir / f"tool_extract_{timestamp}_{safe_filename}"
+ await loop.run_in_executor(None, lambda: shutil.copyfileobj(file.file, open(temp_path, "wb")))
+ logger.info(f"Tool processing upload file: {temp_path}")
+ else:
+ temp_path = await _download_video(url, temp_dir, timestamp)
+
+ if not temp_path or not temp_path.exists():
+ raise ValueError("文件获取失败")
+
+ # 1.5 安全转换: 强制转为 WAV (16k)
+ audio_path = temp_dir / f"extract_audio_{timestamp}.wav"
+ try:
+ await loop.run_in_executor(None, lambda: _convert_to_wav(temp_path, audio_path))
+ logger.info(f"Converted to WAV: {audio_path}")
+ except ValueError as ve:
+ if str(ve) == "HTML_DETECTED":
+ raise ValueError("下载的文件是网页而非视频，请重试或手动上传。")
+ else:
+ raise ValueError("下载的文件已损坏或格式无法识别。")
+
+ # 2. 提取文案 (Whisper)
+ script = await whisper_service.transcribe(str(audio_path))
+
+ # 3. AI 洗稿 (GLM)
+ rewritten = None
+ if rewrite and script and len(script.strip()) > 0:
+ logger.info("Rewriting script...")
+ rewritten = await glm_service.rewrite_script(script)
+
+ return {
+ "original_script": script,
+ "rewritten_script": rewritten
+ }
+
+ finally:
+ if temp_path and temp_path.exists():
+ try:
+ os.remove(temp_path)
+ logger.info(f"Cleaned up temp file: {temp_path}")
+ except Exception as e:
+ logger.warning(f"Failed to cleanup temp file {temp_path}: {e}")
+
+
+def _convert_to_wav(input_path: Path, output_path: Path) -> None:
+ """FFmpeg 转换为 16k WAV"""
+ try:
+ convert_cmd = [
+ 'ffmpeg',
+ '-i', str(input_path),
+ '-vn',
+ '-acodec', 'pcm_s16le',
+ '-ar', '16000',
+ '-ac', '1',
+ '-y',
+ str(output_path)
+ ]
+ subprocess.run(convert_cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ except subprocess.CalledProcessError as e:
+ error_log = e.stderr.decode('utf-8', errors='ignore') if e.stderr else str(e)
+ logger.error(f"FFmpeg check/convert failed: {error_log}")
+ head = b""
+ try:
+ with open(input_path, 'rb') as f:
+ head = f.read(100)
+ except:
+ pass
+ if b' Path:
+ """下载视频（yt-dlp 优先，失败回退手动解析）"""
+ url_value = url
+ url_match = re.search(r'https?://[^\s]+', url_value)
+ if url_match:
+ extracted_url = url_match.group(0)
+ logger.info(f"Extracted URL from text: {extracted_url}")
+ url_value = extracted_url
+
+ logger.info(f"Tool downloading URL: {url_value}")
+ loop = asyncio.get_event_loop()
+
+ # 先尝试 yt-dlp
+ try:
+ temp_path = await loop.run_in_executor(None, lambda: _download_yt_dlp(url_value, temp_dir, timestamp))
+ logger.info(f"yt-dlp downloaded to: {temp_path}")
+ return temp_path
+ except Exception as e:
+ logger.warning(f"yt-dlp download failed: {e}. Trying manual fallback...")
+
+ if "douyin" in url_value:
+ manual_path = await _download_douyin_manual(url_value, temp_dir, timestamp)
+ if manual_path:
+ return manual_path
+ raise ValueError(f"视频下载失败。yt-dlp 报错: {str(e)}")
+ elif "bilibili" in url_value:
+ manual_path = await _download_bilibili_manual(url_value, temp_dir, timestamp)
+ if manual_path:
+ return manual_path
+ raise ValueError(f"视频下载失败。yt-dlp 报错: {str(e)}")
+ else:
+ raise ValueError(f"视频下载失败: {str(e)}")
+
+
+def _download_yt_dlp(url_value: str, temp_dir: Path, timestamp: int) -> Path:
+ """yt-dlp 下载（阻塞调用，应在线程池中运行）"""
+ import yt_dlp
+ logger.info("Attempting download with yt-dlp...")
+
+ ydl_opts = {
+ 'format': 'bestaudio/best',
+ 'outtmpl': str(temp_dir / f"tool_download_{timestamp}_%(id)s.%(ext)s"),
+ 'quiet': True,
+ 'no_warnings': True,
+ 'http_headers': {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+ 'Referer': 'https://www.douyin.com/',
+ }
+ }
+
+ with yt_dlp.YoutubeDL() as ydl_raw:
+ ydl: Any = ydl_raw
+ ydl.params.update(ydl_opts)
+ info = ydl.extract_info(url_value, download=True)
+ if 'requested_downloads' in info:
+ downloaded_file = info['requested_downloads'][0]['filepath']
+ else:
+ ext = info.get('ext', 'mp4')
+ id = info.get('id')
+ downloaded_file = str(temp_dir / f"tool_download_{timestamp}_{id}.{ext}")
+
+ return Path(downloaded_file)
+
+
+async def _download_douyin_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
+ """手动下载抖音视频 (Fallback)"""
+ logger.info(f"[SuperIPAgent] Starting download for: {url}")
+
+ try:
+ headers = {
+ "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
+ }
+
+ async with httpx.AsyncClient(follow_redirects=True, timeout=10.0) as client:
+ resp = await client.get(url, headers=headers)
+ final_url = str(resp.url)
+
+ logger.info(f"[SuperIPAgent] Final URL: {final_url}")
+
+ modal_id = None
+ match = re.search(r'/video/(\d+)', final_url)
+ if match:
+ modal_id = match.group(1)
+
+ if not modal_id:
+ logger.error("[SuperIPAgent] Could not extract modal_id")
+ return None
+
+ logger.info(f"[SuperIPAgent] Extracted modal_id: {modal_id}")
+
+ target_url = f"https://www.douyin.com/user/MS4wLjABAAAAN_s_hups7LD0N4qnrM3o2gI0vuG3pozNaEolz2_py3cHTTrpVr1Z4dukFD9SOlwY?from_tab_name=main&modal_id={modal_id}"
+
+ from app.core.config import settings
+ if not settings.DOUYIN_COOKIE:
+ logger.warning("[SuperIPAgent] DOUYIN_COOKIE 未配置，视频下载可能失败")
+
+ headers_with_cookie = {
+ "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+ "cookie": settings.DOUYIN_COOKIE,
+ "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
+ }
+
+ logger.info(f"[SuperIPAgent] Requesting page with Cookie...")
+
+ async with httpx.AsyncClient(timeout=10.0) as client:
+ response = await client.get(target_url, headers=headers_with_cookie)
+
+ content_match = re.findall(r'', response.text)
+ if not content_match:
+ if "SSR_HYDRATED_DATA" in response.text:
+ content_match = re.findall(r'', response.text)
+
+ if not content_match:
+ logger.error(f"[SuperIPAgent] Could not find RENDER_DATA in page (len={len(response.text)})")
+ return None
+
+ content = unquote(content_match[0])
+ try:
+ data = json.loads(content)
+ except:
+ logger.error("[SuperIPAgent] JSON decode failed")
+ return None
+
+ video_url = None
+ try:
+ if "app" in data and "videoDetail" in data["app"]:
+ info = data["app"]["videoDetail"]["video"]
+ if "bitRateList" in info and info["bitRateList"]:
+ video_url = info["bitRateList"][0]["playAddr"][0]["src"]
+ elif "playAddr" in info and info["playAddr"]:
+ video_url = info["playAddr"][0]["src"]
+ except Exception as e:
+ logger.error(f"[SuperIPAgent] Path extraction failed: {e}")
+
+ if not video_url:
+ logger.error("[SuperIPAgent] No video_url found")
+ return None
+
+ if video_url.startswith("//"):
+ video_url = "https:" + video_url
+
+ logger.info(f"[SuperIPAgent] Found video URL: {video_url[:50]}...")
+
+ temp_path = temp_dir / f"douyin_manual_{timestamp}.mp4"
+ download_headers = {
+ 'Referer': 'https://www.douyin.com/',
+ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+ }
+
+ async with httpx.AsyncClient(timeout=60.0) as client:
+ async with client.stream("GET", video_url, headers=download_headers) as dl_resp:
+ if dl_resp.status_code == 200:
+ with open(temp_path, 'wb') as f:
+ async for chunk in dl_resp.aiter_bytes(chunk_size=8192):
+ f.write(chunk)
+
+ logger.info(f"[SuperIPAgent] Downloaded successfully: {temp_path}")
+ return temp_path
+ else:
+ logger.error(f"[SuperIPAgent] Download failed: {dl_resp.status_code}")
+ return None
+
+ except Exception as e:
+ logger.error(f"[SuperIPAgent] Logic failed: {e}")
+ return None
+
+
+async def _download_bilibili_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
+ """手动下载 Bilibili 视频 (Playwright Fallback)"""
+ from playwright.async_api import async_playwright
+
+ logger.info(f"[Playwright] Starting Bilibili download for: {url}")
+
+ playwright = None
+ browser = None
+ try:
+ playwright = await async_playwright().start()
+ browser = await playwright.chromium.launch(headless=True, args=['--no-sandbox', '--disable-setuid-sandbox'])
+
+ context = await browser.new_context(
+ user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+ )
+
+ page = await context.new_page()
+
+ logger.info("[Playwright] Navigating to Bilibili...")
+ await page.goto(url, timeout=45000)
+
+ try:
+ await page.wait_for_selector('video', timeout=15000)
+ except:
+ logger.warning("[Playwright] Video selector timeout")
+
+ playinfo = await page.evaluate("window.__playinfo__")
+
+ audio_url = None
+
+ if playinfo and "data" in playinfo and "dash" in playinfo["data"]:
+ dash = playinfo["data"]["dash"]
+ if "audio" in dash and dash["audio"]:
+ audio_url = dash["audio"][0]["baseUrl"]
+ logger.info(f"[Playwright] Found audio stream in __playinfo__: {audio_url[:50]}...")
+
+ if not audio_url:
+ logger.warning("[Playwright] Could not find audio in __playinfo__")
+ return None
+
+ temp_path = temp_dir / f"bilibili_audio_{timestamp}.m4s"
+
+ try:
+ api_request = context.request
+ headers = {
+ "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+ "Referer": "https://www.bilibili.com/"
+ }
+
+ logger.info(f"[Playwright] Downloading audio stream...")
+ response = await api_request.get(audio_url, headers=headers)
+
+ if response.status == 200:
+ body = await response.body()
+ with open(temp_path, 'wb') as f:
+ f.write(body)
+
+ logger.info(f"[Playwright] Downloaded successfully: {temp_path}")
+ return temp_path
+ else:
+ logger.error(f"[Playwright] API Request failed: {response.status}")
+ return None
+
+ except Exception as e:
+ logger.error(f"[Playwright] Download logic error: {e}")
+ return None
+
+ except Exception as e:
+ logger.error(f"[Playwright] Bilibili download failed: {e}")
+ return None
+ finally:
+ if browser:
+ await browser.close()
+ if playwright:
+ await playwright.stop()
diff --git a/frontend/src/app/layout.tsx b/frontend/src/app/layout.tsx
index b0db1e0..6f365fd 100644
--- a/frontend/src/app/layout.tsx
+++ b/frontend/src/app/layout.tsx
@@ -1,8 +1,8 @@
import type { Metadata, Viewport } from "next";
import { Geist, Geist_Mono } from "next/font/google";
import "./globals.css";
-import { AuthProvider } from "@/contexts/AuthContext";
-import { TaskProvider } from "@/contexts/TaskContext";
+import { AuthProvider } from "@/shared/contexts/AuthContext";
+import { TaskProvider } from "@/shared/contexts/TaskContext";
import { Toaster } from "sonner";
diff --git a/frontend/src/components/AccountSettingsDropdown.tsx b/frontend/src/components/AccountSettingsDropdown.tsx
index f834e30..3e74e5c 100644
--- a/frontend/src/components/AccountSettingsDropdown.tsx
+++ b/frontend/src/components/AccountSettingsDropdown.tsx
@@ -1,7 +1,7 @@
"use client";
import { useState, useEffect, useRef } from "react";
-import { useAuth } from "@/contexts/AuthContext";
+import { useAuth } from "@/shared/contexts/AuthContext";
import api from "@/shared/api/axios";
import { ApiResponse } from "@/shared/api/types";
diff --git a/frontend/src/components/GlobalTaskIndicator.tsx b/frontend/src/components/GlobalTaskIndicator.tsx
index 6163329..844e1ca 100644
--- a/frontend/src/components/GlobalTaskIndicator.tsx
+++ b/frontend/src/components/GlobalTaskIndicator.tsx
@@ -1,6 +1,6 @@
"use client";
-import { useTask } from "@/contexts/TaskContext";
+import { useTask } from "@/shared/contexts/TaskContext";
import Link from "next/link";
import { usePathname } from "next/navigation";
diff --git a/frontend/src/features/home/model/useHomeController.ts b/frontend/src/features/home/model/useHomeController.ts
index 7e85655..f53533a 100644
--- a/frontend/src/features/home/model/useHomeController.ts
+++ b/frontend/src/features/home/model/useHomeController.ts
@@ -11,8 +11,8 @@ import {
} from "@/shared/lib/media";
import { clampTitle } from "@/shared/lib/title";
import { useTitleInput } from "@/shared/hooks/useTitleInput";
-import { useAuth } from "@/contexts/AuthContext";
-import { useTask } from "@/contexts/TaskContext";
+import { useAuth } from "@/shared/contexts/AuthContext";
+import { useTask } from "@/shared/contexts/TaskContext";
import { toast } from "sonner";
import { usePublishPrefetch } from "@/shared/hooks/usePublishPrefetch";
import { PublishAccount } from "@/shared/types/publish";
diff --git a/frontend/src/features/home/ui/HomePage.tsx b/frontend/src/features/home/ui/HomePage.tsx
index 00e3627..de24151 100644
--- a/frontend/src/features/home/ui/HomePage.tsx
+++ b/frontend/src/features/home/ui/HomePage.tsx
@@ -3,7 +3,7 @@
import { useEffect } from "react";
import { useRouter } from "next/navigation";
import VideoPreviewModal from "@/components/VideoPreviewModal";
-import ScriptExtractionModal from "@/components/ScriptExtractionModal";
+import ScriptExtractionModal from "./ScriptExtractionModal";
import { useHomeController } from "@/features/home/model/useHomeController";
import { BgmPanel } from "@/features/home/ui/BgmPanel";
import { GenerateActionBar } from "@/features/home/ui/GenerateActionBar";
diff --git a/frontend/src/components/ScriptExtractionModal.tsx b/frontend/src/features/home/ui/ScriptExtractionModal.tsx
similarity index 100%
rename from frontend/src/components/ScriptExtractionModal.tsx
rename to frontend/src/features/home/ui/ScriptExtractionModal.tsx
diff --git a/frontend/src/components/script-extraction/useScriptExtraction.ts b/frontend/src/features/home/ui/script-extraction/useScriptExtraction.ts
similarity index 100%
rename from frontend/src/components/script-extraction/useScriptExtraction.ts
rename to frontend/src/features/home/ui/script-extraction/useScriptExtraction.ts
diff --git a/frontend/src/features/publish/model/usePublishController.ts b/frontend/src/features/publish/model/usePublishController.ts
index bf7e4e0..f6b10ab 100644
--- a/frontend/src/features/publish/model/usePublishController.ts
+++ b/frontend/src/features/publish/model/usePublishController.ts
@@ -5,8 +5,8 @@ import { ApiResponse, unwrap } from "@/shared/api/types";
import { formatDate, getApiBaseUrl, isAbsoluteUrl, resolveMediaUrl } from "@/shared/lib/media";
import { clampTitle } from "@/shared/lib/title";
import { useTitleInput } from "@/shared/hooks/useTitleInput";
-import { useAuth } from "@/contexts/AuthContext";
-import { useTask } from "@/contexts/TaskContext";
+import { useAuth } from "@/shared/contexts/AuthContext";
+import { useTask } from "@/shared/contexts/TaskContext";
import { toast } from "sonner";
import { usePublishPrefetch } from "@/shared/hooks/usePublishPrefetch";
import {
diff --git a/frontend/src/contexts/AuthContext.tsx b/frontend/src/shared/contexts/AuthContext.tsx
similarity index 100%
rename from frontend/src/contexts/AuthContext.tsx
rename to frontend/src/shared/contexts/AuthContext.tsx
diff --git a/frontend/src/contexts/TaskContext.tsx b/frontend/src/shared/contexts/TaskContext.tsx
similarity index 100%
rename from frontend/src/contexts/TaskContext.tsx
rename to frontend/src/shared/contexts/TaskContext.tsx