feat: 支持嵌套格式元数据（kb-bilibili-metadata 输出）

skills/kb-deep-analyzer/deep_analyzer.py

@@ -751,6 +751,70 @@ def load_json(file_path: str) -> Dict:
         return json.load(f)
 
 
+def normalize_metadata(metadata: Dict) -> Dict:
+    """
+    标准化元数据格式，支持嵌套和平面两种结构
+
+    支持以下输入格式:
+    1. 扁平结构: {"title": "xxx", "author": "yyy", "duration": 619}
+    2. 嵌套结构: {"data": {"metadata": {"title": "xxx", "author": "yyy", "duration": "10:19"}}}
+
+    输出: 扁平结构，duration 转换为秒数
+    """
+    if not metadata:
+        return {}
+
+    # 如果已经包含 title 字段，认为是扁平结构
+    if 'title' in metadata:
+        # 处理 duration 格式（可能是 "10:19" 字符串或数字）
+        duration = metadata.get('duration', 0)
+        if isinstance(duration, str) and ':' in duration:
+            parts = duration.split(':')
+            try:
+                seconds = int(parts[0]) * 60 + int(parts[1])
+                metadata['duration'] = seconds
+            except (ValueError, IndexError):
+                pass
+        return metadata
+
+    # 如果是嵌套结构，提取 data.metadata
+    data = metadata.get('data', {})
+    meta = data.get('metadata', {})
+
+    # 提取扁平化字段
+    normalized = {
+        'title': meta.get('title', metadata.get('title', '未知')),
+        'author': meta.get('author', metadata.get('author', '')),
+        'bvid': meta.get('bvid', metadata.get('bvid', '')),
+        'aid': meta.get('aid', metadata.get('aid', 0)),
+        'pubtime': meta.get('pubtime', metadata.get('pubtime', '')),
+        'platform': meta.get('platform', 'unknown'),
+        'url': meta.get('url', ''),
+    }
+
+    # 处理 duration
+    duration = meta.get('duration', 0)
+    if isinstance(duration, str):
+        if ':' in duration:
+            # "10:19" 格式
+            parts = duration.split(':')
+            try:
+                normalized['duration'] = int(parts[0]) * 60 + int(parts[1])
+            except (ValueError, IndexError):
+                normalized['duration'] = 0
+        else:
+            try:
+                normalized['duration'] = int(duration)
+            except ValueError:
+                normalized['duration'] = 0
+    elif isinstance(duration, (int, float)):
+        normalized['duration'] = int(duration)
+    else:
+        normalized['duration'] = 0
+
+    return normalized
+
+
 def format_duration(seconds: int) -> str:
     """格式化时长"""
     h = seconds // 3600
@@ -827,7 +891,8 @@ def main():
 
     # 加载数据
     print(f"[Main] 加载元数据: {args.metadata}")
-    metadata = load_json(args.metadata)
+    raw_metadata = load_json(args.metadata)
+    metadata = normalize_metadata(raw_metadata)
 
     print(f"[Main] 加载内容: {args.content}")
     content = load_json(args.content)