fix(download): handle formatted duration strings in metadata

Parse duration strings like "12:34" or "01:23:45" into seconds.
Previously only integer duration values were handled.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

kb_pipeline/platforms/bilibili.py

@@ -170,9 +170,11 @@ class BilibiliAdapter(PlatformAdapter):
             ValueError: If content_type is not supported
         """
         if content_type == "video":
-            return self._extractor.extract_video_metadata(content_id)
+            # Call async method directly to avoid nested asyncio.run()
+            return await self._extractor._extract_video_async(content_id)
         elif content_type == "article":
-            return self._extractor.extract_article_metadata(content_id)
+            # Call async method directly to avoid nested asyncio.run()
+            return await self._extractor._extract_article_async(content_id)
         else:
             raise ValueError(f"Unsupported content type: {content_type}")
 

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