kb_pipeline/processors/download.py

@@ -62,11 +62,18 @@ class DownloadProcessor(BaseProcessor):
             return self._record_failure(str(e))
 
         try:
-            # Fetch metadata
-            metadata = await adapter.fetch_metadata(
-                input_data.content_id,
-                input_data.content_type
-            )
+            # Fetch metadata (pass source_url for zhihu answers)
+            if input_data.platform == "zhihu":
+                metadata = await adapter.fetch_metadata(
+                    input_data.content_id,
+                    input_data.content_type,
+                    source_url=input_data.source_url
+                )
+            else:
+                metadata = await adapter.fetch_metadata(
+                    input_data.content_id,
+                    input_data.content_type
+                )
 
             # Save metadata
             metadata_filename = adapter.get_output_filename(
@@ -85,10 +92,17 @@ class DownloadProcessor(BaseProcessor):
             # Fetch content (for text-based content)
             content_file = ""
             if input_data.content_type in ["article", "answer", "zhuanlan"]:
-                content = await adapter.fetch_content(
-                    input_data.content_id,
-                    input_data.content_type
-                )
+                if input_data.platform == "zhihu":
+                    content = await adapter.fetch_content(
+                        input_data.content_id,
+                        input_data.content_type,
+                        source_url=input_data.source_url
+                    )
+                else:
+                    content = await adapter.fetch_content(
+                        input_data.content_id,
+                        input_data.content_type
+                    )
                 content_filename = adapter.get_output_filename(
                     input_data.content_id,
                     input_data.content_type,
@@ -98,6 +112,18 @@ class DownloadProcessor(BaseProcessor):
                 self._save_content(content, content_path)
                 content_file = str(content_path)
 
+            # Download video for ASR (Whisper needs video file)
+            if input_data.content_type == "video" and input_data.platform == "bilibili":
+                download_result = await adapter.download_video(
+                    input_data.content_id,
+                    content_dir
+                )
+                if download_result["success"]:
+                    content_file = download_result["filepath"]
+                    logger.info(f"Video downloaded for ASR: {content_file}")
+                else:
+                    logger.warning(f"Video download failed: {download_result['message']}")
+
             # Record success
             result = DownloadOutput(
                 success=True,