feat(06-01): create metadata directory and move bilibili modules

- Rename kb-workflow to kb_workflow for Python package compatibility - Move bilibili_extractor.py and bilibili_metadata.py to kb_workflow/metadata/ - Create metadata/__init__.py with BilibiliExporter export Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 23:59:23 +08:00
parent 444ac22e44
commit e2edce2e29
8 changed files with 10 additions and 0 deletions
@@ -0,0 +1,149 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+KB Workflow - Knowledge Base Workflow Orchestrator
+
+知识库工作流管道入口。
+
+此模块提供 process_command() 函数作为管道入口，
+内部使用 kb_pipeline 包实现完整的内容处理流程。
+
+使用方式:
+    python kb_workflow.py process "https://www.bilibili.com/video/BVxxx"
+    python kb_workflow.py process "https://..." -o /path/to/output
+"""
+
+import argparse
+import asyncio
+import json
+import sys
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+
+def process_command(
+    url: str,
+    output_dir: Optional[str] = None,
+    skip_completed: bool = True
+) -> Dict[str, Any]:
+    """Execute full pipeline for a URL
+
+    Args:
+        url: URL to process
+        output_dir: Optional output directory for content. Defaults to
+            KB_INTERMEDIATE_PATH env var or ~/work/intermediate/analysis/
+        skip_completed: Skip already completed steps (default True)
+
+    Returns:
+        Dictionary with success status, content_dir, and results
+    """
+    # Add project root to path for kb_pipeline imports
+    project_root = Path(__file__).parent.parent
+    if str(project_root) not in sys.path:
+        sys.path.insert(0, str(project_root))
+
+    try:
+        from kb_pipeline.config import get_settings
+        from kb_pipeline.pipeline import Pipeline
+        from kb_pipeline.processors import (
+            ASRProcessor, AnalyzeProcessor, ArchiveProcessor,
+            DownloadProcessor, ParseProcessor
+        )
+        from kb_pipeline.schemas import PipelineConfig
+
+        async def run_pipeline():
+            # Determine output directory - default to intermediate_path
+            settings = get_settings()
+            out_dir = Path(output_dir) if output_dir else Path(settings.intermediate_path)
+
+            # Create processors
+            processors = [
+                ParseProcessor(),
+                DownloadProcessor(),
+                ASRProcessor(),
+                AnalyzeProcessor(),
+                ArchiveProcessor(),
+            ]
+
+            # Create pipeline config
+            config = PipelineConfig(
+                steps=["parse", "download", "asr", "analyze", "archive"],
+                output_dir=out_dir,
+                skip_completed=skip_completed,
+            )
+
+            # Create and run pipeline
+            pipeline = Pipeline(
+                processors=processors,
+                config=config,
+                output_dir=out_dir,
+            )
+
+            result = await pipeline.run(url)
+            return result
+
+        # Run async pipeline
+        result = asyncio.run(run_pipeline())
+
+        return {
+            "success": result.success,
+            "error": result.error_message,
+            "content_dir": str(result.content_dir) if result.content_dir else None,
+            "results": result.results,
+        }
+
+    except Exception as e:
+        return {
+            "success": False,
+            "error": str(e),
+            "content_dir": None,
+            "results": {},
+        }
+
+
+def main():
+    """CLI入口 - 用于命令行调用"""
+    parser = argparse.ArgumentParser(
+        description='KB Workflow - Knowledge Base Workflow Orchestrator',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog='''
+使用示例:
+  # 处理URL (通过完整管道)
+  python kb_workflow.py process "https://www.bilibili.com/video/BVxxx"
+
+  # 指定输出目录
+  python kb_workflow.py process "https://..." -o /path/to/output
+
+  # 强制重新执行（忽略已完成状态）
+  python kb_workflow.py process "https://..." --no-skip
+        '''
+    )
+
+    # Create subparsers for commands
+    subparsers = parser.add_subparsers(dest='command', help='Available commands')
+
+    # Process subcommand
+    process_parser = subparsers.add_parser('process', help='Process URL through full pipeline')
+    process_parser.add_argument('url', type=str, help='URL to process')
+    process_parser.add_argument('--output-dir', '-o', type=str, help='Output directory for content')
+    process_parser.add_argument('--skip-completed', action='store_true', default=True,
+                                help='Skip completed steps (default: True)')
+    process_parser.add_argument('--no-skip', action='store_false', dest='skip_completed',
+                                help='Re-run all steps')
+
+    args = parser.parse_args()
+
+    # Handle process subcommand
+    if args.command == 'process':
+        result = process_command(
+            url=args.url,
+            output_dir=args.output_dir,
+            skip_completed=args.skip_completed
+        )
+        print(json.dumps(result, ensure_ascii=False, indent=2))
+    else:
+        parser.print_help()
+
+
+if __name__ == '__main__':
+    main()