kb_pipeline/processors/download.py

@@ -215,7 +215,21 @@ class DownloadProcessor(BaseProcessor):
 
         # Bilibili video duration
         if "metadata" in metadata and "duration" in metadata["metadata"]:
-            return metadata["metadata"]["duration"]
+            duration = metadata["metadata"]["duration"]
+            # Handle formatted duration string (e.g., "12:34" or "01:23:45")
+            if isinstance(duration, str):
+                if not duration.strip():
+                    return None
+                parts = duration.split(':')
+                try:
+                    if len(parts) == 2:
+                        return int(parts[0]) * 60 + int(parts[1])
+                    elif len(parts) == 3:
+                        return int(parts[0]) * 3600 + int(parts[1]) * 60 + int(parts[2])
+                except (ValueError, IndexError):
+                    return None
+            elif isinstance(duration, (int, float)):
+                return int(duration)
 
         return None