OpenClaw Agent
61dad2414d
新增参数: - --pending: 链接解析 - --metadata: 元数据提取 - --content: 内容下载 - --ocr: OCR处理 - --analyze: 深度分析 - --extract_platform: 提取平台名称 - --link_file, --meta_file, --text_file, --source: 输入文件路径
389 lines
15 KiB
Python
389 lines
15 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
KB Workflow - Knowledge Base Workflow Orchestrator
|
|
|
|
知识库工作流辅助工具函数。
|
|
|
|
此模块提供查重、文件操作、Git 管理等工具函数，
|
|
供主代理在执行 SKILL.md 中定义的 workflow 时调用。
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import json
|
|
import argparse
|
|
import subprocess
|
|
import shutil
|
|
import re
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
from typing import Dict, List, Optional, Any
|
|
|
|
# ==================== 工具函数 ====================
|
|
|
|
def extract_platform(filename: str) -> str:
|
|
"""从文件名提取平台（第一个下划线之前）"""
|
|
match = re.match(r'^([a-zA-Z0-9]+)_(.+)$', filename)
|
|
if match:
|
|
return match.group(1)
|
|
return "unknown"
|
|
|
|
|
|
def extract_base_name(filename: str) -> str:
|
|
"""从文件名提取基础名称（去掉扩展名）"""
|
|
return Path(filename).stem
|
|
|
|
|
|
def get_knowledge_base_path() -> Path:
|
|
"""获取知识库根目录"""
|
|
base_path_str = os.environ.get('KB_BASE_PATH', '')
|
|
if base_path_str:
|
|
return Path(base_path_str).expanduser()
|
|
return Path.home() / "work" / "knowledge-base"
|
|
|
|
|
|
def ensure_directories(base_path: Path = None) -> Dict[str, Path]:
|
|
"""确保目录存在"""
|
|
if base_path is None:
|
|
base_path = get_knowledge_base_path()
|
|
|
|
dirs = {
|
|
"base": base_path,
|
|
"pending": base_path / "pending",
|
|
"metadata": base_path / "metadata",
|
|
"content": base_path / "content",
|
|
"content_downloads": base_path / "content" / "downloads",
|
|
"content_subtitles": base_path / "content" / "subtitles",
|
|
"analyzed": base_path / "analyzed",
|
|
"archive": base_path / "archive",
|
|
"archive_subscriptions": base_path / "archive" / "subscriptions",
|
|
}
|
|
|
|
for name, dir_path in dirs.items():
|
|
if isinstance(dir_path, Path):
|
|
dir_path.mkdir(parents=True, exist_ok=True)
|
|
|
|
return dirs
|
|
|
|
|
|
def check_duplicate(base_path: Path = None, url: str = None, platform: str = None, content_id: str = None) -> Dict[str, Any]:
|
|
"""查重检查"""
|
|
if base_path is None:
|
|
base_path = get_knowledge_base_path()
|
|
|
|
metadata_dir = base_path / "metadata"
|
|
archive_dir = base_path / "archive"
|
|
|
|
# TODO 直接使用url在知识库中查询metadata中的origin_url项
|
|
|
|
result = {"duplicate": False, "status": None, "files": []}
|
|
|
|
return result
|
|
|
|
|
|
def archive_and_git(
|
|
analyzed_file: str,
|
|
base_path: Path = None,
|
|
git_root: Path = None,
|
|
git_user: str = None,
|
|
git_email: str = None,
|
|
git_remote: str = None
|
|
) -> Dict[str, Any]:
|
|
"""归档并提交Git"""
|
|
if base_path is None:
|
|
base_path = get_knowledge_base_path()
|
|
if git_root is None:
|
|
git_root = base_path / "archive"
|
|
if git_user is None:
|
|
git_user = os.environ.get('KB_GIT_USER', '')
|
|
if git_email is None:
|
|
git_email = os.environ.get('KB_GIT_EMAIL', '')
|
|
if git_remote is None:
|
|
git_remote = os.environ.get('KB_GIT_REMOTE', '')
|
|
|
|
result = {
|
|
"success": False,
|
|
"archive_path": "",
|
|
"git_commit": False,
|
|
"git_push": None,
|
|
"error": None
|
|
}
|
|
|
|
try:
|
|
# 1. 创建归档目录
|
|
date_str = datetime.now().strftime('%Y-%m-%d')
|
|
date_dir = base_path / "archive" / date_str
|
|
date_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
# 2. 复制分析报告
|
|
src_file = Path(analyzed_file)
|
|
archive_file = date_dir / src_file.name
|
|
shutil.copy(src_file, archive_file)
|
|
result["archive_path"] = str(archive_file)
|
|
|
|
# 3. 复制元数据
|
|
meta_file = base_path / "metadata" / f"{src_file.stem}.meta.json"
|
|
if meta_file.exists():
|
|
shutil.copy(meta_file, date_dir / meta_file.name)
|
|
|
|
# 4. Git 操作
|
|
git_dir = git_root / ".git"
|
|
if not git_dir.exists():
|
|
subprocess.run(['git', 'init'], cwd=str(git_root), capture_output=True)
|
|
if git_user:
|
|
subprocess.run(['git', 'config', 'user.name', git_user], cwd=str(git_root))
|
|
if git_email:
|
|
subprocess.run(['git', 'config', 'user.email', git_email], cwd=str(git_root))
|
|
|
|
if (git_root / ".git").exists():
|
|
subprocess.run(['git', 'add', '.'], cwd=str(git_root), capture_output=True)
|
|
commit_msg = f"Archive: {src_file.name} - {datetime.now().isoformat()}"
|
|
commit_result = subprocess.run(
|
|
['git', 'commit', '-m', commit_msg],
|
|
cwd=str(git_root), capture_output=True, text=True
|
|
)
|
|
result["git_commit"] = commit_result.returncode == 0
|
|
|
|
if git_remote and commit_result.returncode == 0:
|
|
push_result = subprocess.run(
|
|
['git', 'push', 'origin', 'master'],
|
|
cwd=str(git_root), capture_output=True, text=True, timeout=60
|
|
)
|
|
result["git_push"] = {"success": push_result.returncode == 0}
|
|
|
|
result["success"] = True
|
|
|
|
except Exception as e:
|
|
result["error"] = str(e)
|
|
|
|
return result
|
|
|
|
|
|
def generate_summary(url: str, stages: List[Dict], final_file: str, archive_result: Dict = None) -> str:
|
|
"""生成处理完成汇报"""
|
|
# 提取视频标题（如果有）
|
|
title_match = re.search(r'com/video/([^?]+)', url)
|
|
title = title_match.group(1) if title_match else "未知"
|
|
|
|
summary = f"""
|
|
✅ **处理完成！**
|
|
|
|
**视频:** {title}
|
|
|
|
**处理阶段:**
|
|
"""
|
|
for stage in stages:
|
|
stage_name = stage.get('stage', 'unknown')
|
|
emoji = "✓" if stage.get('success') else "○"
|
|
summary += f"{emoji} {stage_name}\n"
|
|
|
|
if final_file:
|
|
summary += f"\n**最终文件:** `{final_file}`"
|
|
|
|
if archive_result:
|
|
if archive_result.get('git_commit'):
|
|
summary += f"\n**Git:** 已提交"
|
|
if archive_result.get('git_push', {}).get('success'):
|
|
summary += " ✓"
|
|
elif archive_result.get('git_push'):
|
|
summary += " ✗"
|
|
|
|
return summary
|
|
|
|
|
|
# ==================== CLI ====================
|
|
|
|
def main():
|
|
"""CLI入口 - 用于命令行测试"""
|
|
parser = argparse.ArgumentParser(
|
|
description='KB Workflow - Knowledge Base Workflow Orchestrator',
|
|
formatter_class=argparse.RawDescriptionHelpFormatter,
|
|
epilog="""
|
|
使用示例:
|
|
# 查重
|
|
python kb_workflow.py --check --url "https://www.bilibili.com/video/BVxxx"
|
|
|
|
# 提取平台
|
|
python kb_workflow.py --extract_platform "bilibili_BVxxx.link.json"
|
|
|
|
# 链接解析
|
|
python kb_workflow.py --pending --url "https://www.bilibili.com/video/BVxxx"
|
|
|
|
# 元数据提取
|
|
python kb_workflow.py --metadata --link_file "pending/bilibili_BVxxx.link.json"
|
|
|
|
# 内容下载
|
|
python kb_workflow.py --content --meta_file "metadata/bilibili_BVxxx.meta.json"
|
|
|
|
# OCR处理
|
|
python kb_workflow.py --ocr --source "content/subtitles/bilibili_BVxxx.srt"
|
|
|
|
# 深度分析
|
|
python kb_workflow.py --analyze --meta_file "metadata/bilibili_BVxxx.meta.json" --text_file "content/bilibili_BVxxx.txt"
|
|
|
|
# 归档
|
|
python kb_workflow.py --archive "analyzed/bilibili_BVxxx.md"
|
|
"""
|
|
)
|
|
|
|
parser.add_argument('--check', action='store_true', help='查重')
|
|
parser.add_argument('--url', type=str, help='要检查的URL')
|
|
parser.add_argument('--archive', type=str, help='要归档的文件路径')
|
|
parser.add_argument('--base-path', type=str, help='知识库根目录')
|
|
parser.add_argument('--pending', action='store_true', help='执行链接解析')
|
|
parser.add_argument('--metadata', action='store_true', help='执行元数据提取')
|
|
parser.add_argument('--content', action='store_true', help='执行内容下载')
|
|
parser.add_argument('--ocr', action='store_true', help='执行OCR处理')
|
|
parser.add_argument('--analyze', action='store_true', help='执行深度分析')
|
|
parser.add_argument('--link_file', type=str, help='链接解析结果文件路径')
|
|
parser.add_argument('--meta_file', type=str, help='元数据文件路径')
|
|
parser.add_argument('--text_file', type=str, help='文字内容文件路径')
|
|
parser.add_argument('--source', type=str, help='OCR源文件路径')
|
|
parser.add_argument('--extract_platform', type=str, help='提取平台名称')
|
|
args = parser.parse_args()
|
|
|
|
# 获取知识库路径
|
|
base_path_str = os.environ.get('KB_BASE_PATH', '')
|
|
base_path = Path(base_path_str).expanduser() if base_path_str else Path.home() / "work" / "knowledge-base"
|
|
|
|
# 获取子目录路径
|
|
pending_dir = base_path / "pending"
|
|
metadata_dir = base_path / "metadata"
|
|
content_dir = base_path / "content"
|
|
content_downloads_dir = content_dir / "downloads"
|
|
content_subtitles_dir = content_dir / "subtitles"
|
|
analyzed_dir = base_path / "analyzed"
|
|
archive_dir = base_path / "archive"
|
|
|
|
if args.extract_platform:
|
|
result = extract_platform(args.extract_platform)
|
|
print(result)
|
|
return
|
|
|
|
if args.check and args.url:
|
|
result = check_duplicate(base_path, args.url)
|
|
print(json.dumps(result, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
if args.pending and args.url:
|
|
# 链接解析 - 调用 kb-link-parser
|
|
import subprocess
|
|
cmd = ['python3', 'kb-link-parser/link-parser.py', '--url', args.url]
|
|
proc = subprocess.run(cmd, capture_output=True, text=True)
|
|
if proc.returncode == 0:
|
|
data = json.loads(proc.stdout)
|
|
if data.get('success'):
|
|
platform = data.get('platform', 'unknown')
|
|
content_id = data.get('id', 'unknown')
|
|
output_file = pending_dir / f"{platform}_{content_id}.link.json"
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
json.dump(data, f, ensure_ascii=False, indent=2)
|
|
print(json.dumps({"success": True, "output_file": str(output_file)}, ensure_ascii=False, indent=2))
|
|
else:
|
|
print(proc.stdout)
|
|
else:
|
|
print(json.dumps({"success": False, "error": proc.stderr}, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
if args.metadata and args.link_file:
|
|
# 元数据提取 - 调用对应平台的元数据技能
|
|
link_file = Path(args.link_file)
|
|
with open(link_file, 'r', encoding='utf-8') as f:
|
|
link_data = json.load(f)
|
|
platform = link_data.get('platform', '')
|
|
content_id = link_data.get('id', '')
|
|
|
|
if platform == 'bilibili':
|
|
cmd = ['python3', 'kb-bilibili-metadata/bilibili_metadata.py',
|
|
'--id', content_id, '--type', 'video',
|
|
'--output', str(metadata_dir / f"{platform}_{content_id}.meta.json")]
|
|
elif platform == 'zhihu':
|
|
cmd = ['python3', 'kb-zhihu-metadata/zhihu_metadata.py', '--url', link_data.get('url', '')]
|
|
else:
|
|
print(json.dumps({"success": False, "error": f"不支持的平台: {platform}"}, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
proc = subprocess.run(cmd, capture_output=True, text=True)
|
|
if proc.returncode == 0:
|
|
print(proc.stdout)
|
|
else:
|
|
print(json.dumps({"success": False, "error": proc.stderr}, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
if args.content and args.meta_file:
|
|
# 内容下载 - 调用对应平台的内容技能
|
|
meta_file = Path(args.meta_file)
|
|
with open(meta_file, 'r', encoding='utf-8') as f:
|
|
meta_data = json.load(f)
|
|
platform = extract_platform(meta_file.name)
|
|
content_id = extract_base_name(meta_file.name)
|
|
|
|
if platform == 'bilibili':
|
|
# 下载视频
|
|
cmd_video = ['python3', 'kb-bilibili-content/bilibili_content.py',
|
|
'--id', content_id, '--type', 'video', '--output', str(content_dir)]
|
|
subprocess.run(cmd_video)
|
|
# 下载字幕
|
|
cmd_subtitle = ['python3', 'kb-bilibili-content/bilibili_content.py',
|
|
'--id', content_id, '--type', 'subtitle', '--output', str(content_dir)]
|
|
subprocess.run(cmd_subtitle)
|
|
# 查找生成的文件
|
|
video_file = None
|
|
subtitle_file = None
|
|
for f in content_downloads_dir.iterdir():
|
|
if content_id in f.name:
|
|
video_file = str(f)
|
|
for f in content_subtitles_dir.iterdir():
|
|
if content_id in f.name:
|
|
subtitle_file = str(f)
|
|
print(json.dumps({"success": True, "output_file": video_file, "subtitles": subtitle_file}, ensure_ascii=False, indent=2))
|
|
else:
|
|
print(json.dumps({"success": False, "error": f"不支持的平台: {platform}"}, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
if args.ocr and args.source:
|
|
# OCR处理 - 调用 kb-ocr-processor
|
|
source_file = Path(args.source)
|
|
platform = extract_platform(source_file.name)
|
|
content_id = extract_base_name(source_file.name)
|
|
output_file = content_dir / f"{platform}_{content_id}.txt"
|
|
|
|
cmd = ['python3', 'kb-ocr-processor/ocr_processor.py',
|
|
'--input', str(source_file), '--output', str(output_file)]
|
|
proc = subprocess.run(cmd, capture_output=True, text=True)
|
|
if proc.returncode == 0:
|
|
print(json.dumps({"success": True, "output_file": str(output_file)}, ensure_ascii=False, indent=2))
|
|
else:
|
|
print(json.dumps({"success": False, "error": proc.stderr}, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
if args.analyze and args.meta_file:
|
|
# 深度分析 - 调用 kb-deep-analyzer
|
|
meta_file = Path(args.meta_file)
|
|
platform = extract_platform(meta_file.name)
|
|
content_id = extract_base_name(meta_file.name)
|
|
output_file = analyzed_dir / f"{platform}_{content_id}.md"
|
|
|
|
text_file = args.text_file if args.text_file else str(meta_file)
|
|
|
|
cmd = ['python3', 'kb-deep-analyzer/deep_analyzer.py',
|
|
'--metadata', str(meta_file), '--content', text_file, '--output', str(output_file)]
|
|
proc = subprocess.run(cmd, capture_output=True, text=True)
|
|
if proc.returncode == 0:
|
|
print(json.dumps({"success": True, "output_file": str(output_file)}, ensure_ascii=False, indent=2))
|
|
else:
|
|
print(json.dumps({"success": False, "error": proc.stderr}, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
if args.archive:
|
|
result = archive_and_git(args.archive, base_path)
|
|
print(json.dumps(result, ensure_ascii=False, indent=2))
|
|
return
|
|
|
|
parser.print_help()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|