更新

2026-02-03 13:46:52 +08:00
parent eb3ed23326
commit cb10da52fc
18 changed files with 1018 additions and 657 deletions
--- a/backend/app/api/tools.py
+++ b/backend/app/api/tools.py
@@ -38,11 +38,13 @@ async def extract_script_tool(
        temp_dir.mkdir(parents=True, exist_ok=True)

        # 1. 获取/保存文件
+        loop = asyncio.get_event_loop()
+        
        if file:
            safe_filename = Path(file.filename).name.replace(" ", "_")
            temp_path = temp_dir / f"tool_extract_{timestamp}_{safe_filename}"
-            with open(temp_path, "wb") as buffer:
-                shutil.copyfileobj(file.file, buffer)
+            # 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:
            # URL 下载逻辑
@@ -55,8 +57,8 @@ async def extract_script_tool(
            
            logger.info(f"Tool downloading URL: {url}")
            
-            # 先尝试 yt-dlp
-            try:
+            # 封装 yt-dlp 下载函数 (Blocking)
+            def _download_yt_dlp():
                import yt_dlp
                logger.info("Attempting download with yt-dlp...")
                
@@ -80,8 +82,12 @@ async def extract_script_tool(
                        id = info.get('id')
                        downloaded_file = str(temp_dir / f"tool_download_{timestamp}_{id}.{ext}")
                    
-                    temp_path = Path(downloaded_file)
-                    logger.info(f"yt-dlp downloaded to: {temp_path}")
+                    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...")
@@ -107,46 +113,48 @@ async def extract_script_tool(
        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) 传给 Whisper
-        # 这一步既能验证文件有效性（ffmpeg会报错），又能避免 PyAV 音频解码 bug
+        # 1.5 安全转换: 强制转为 WAV (16k)
        import subprocess
        audio_path = temp_dir / f"extract_audio_{timestamp}.wav"
-        try:
-            # ffmpeg -i input -vn -acodec pcm_s16le -ar 16000 -ac 1 output.wav -y
-            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 以便出错时打印
-            subprocess.run(convert_cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-            logger.info(f"Converted to WAV: {audio_path}")
-            
-            # 使用转换后的文件
-            target_path = audio_path
-            
-        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}")
-            
-            # 尝试判断是不是 HTML
-            head = b""
+        
+        def _convert_audio():
            try:
-                with open(temp_path, 'rb') as f:
-                    head = f.read(100)
-            except: 
-                pass
-                
-            if b'<!DOCTYPE html' in head or b'<html' in head:
+                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'<!DOCTYPE html' in head or b'<html' in head:
+                    raise ValueError("HTML_DETECTED")
+                raise ValueError("CONVERT_FAILED")
+
+        # 执行转换 (Run in Executor)
+        try:
+            await loop.run_in_executor(None, _convert_audio)
+            logger.info(f"Converted to WAV: {audio_path}")
+            target_path = audio_path
+        except ValueError as ve:
+            if str(ve) == "HTML_DETECTED":
                 raise HTTPException(400, "下载的文件是网页而非视频，请重试或手动上传。")
-            
-            raise HTTPException(400, "下载的文件已损坏或格式无法识别。")
+            else:
+                 raise HTTPException(400, "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(target_path))