From 60b0eaec938f5e0608be6a49481a6b6f3c30d6e1 Mon Sep 17 00:00:00 2001
From: starmen1265 <starmen1265@163.com>
Date: Mon, 16 Mar 2026 00:04:56 +0800
Subject: [PATCH] feat(download): add video download capability for videos
 without official subtitles

- When content_type is video and no official subtitle available:
  - Download video using yt-dlp
  - Extract audio for Whisper fallback
- Update content_file with actual video path

This enables the pipeline to handle videos that don't have
official Bilibili subtitles.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 kb_pipeline/processors/download.py | 44 ++++++++++++++++++++++++------
 1 file changed, 35 insertions(+), 9 deletions(-)

diff --git a/kb_pipeline/processors/download.py b/kb_pipeline/processors/download.py
index b0171c6..82241c8 100644
--- a/kb_pipeline/processors/download.py
+++ b/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,