#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
B站视频提取脚本
提取视频信息、统计数据、字幕并生成Markdown笔记
"""

import sys
import os
import json
import re
from datetime import datetime

# 添加skills路径
sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'skills', 'obsidian-kb'))

from src.extractors.bilibili_extractor import BilibiliExtractor
from src.config import get_config


def format_number(num):
    """格式化数字"""
    if num >= 100000000:
        return f"{num / 100000000:.1f}亿"
    elif num >= 10000:
        return f"{num / 10000:.1f}万"
    else:
        return f"{num:,}"


def generate_markdown(result, bvid):
    """生成Markdown笔记"""
    metadata = result['metadata']
    stats = result['stats']
    description = result['description']
    subtitle = result['subtitle']

    # 获取当前时间
    now = datetime.now().strftime('%Y-%m-%d %H:%M:%S')

    md = f"""# {metadata['title']}

> **来源**: [B站](https://www.bilibili.com/video/{bvid})
> **作者**: {metadata['author']}
> **发布时间**: {metadata['pubtime']}
> **提取时间**: {now}
> **时长**: {metadata['duration']}

## 📊 统计数据

| 指标 | 数量 |
|------|------|
| 👀 播放 | {format_number(stats['view'])} |
| 💬 弹幕 | {format_number(stats['danmaku'])} |
| 📝 评论 | {format_number(stats['reply'])} |
| ⭐ 收藏 | {format_number(stats['favorite'])} |
| 🪙 投币 | {format_number(stats['coin'])} |
| 🔗 分享 | {format_number(stats['share'])} |
| 👍 点赞 | {format_number(stats['like'])} |

## 📝 视频简介

{description if description else '(暂无简介)'}

## 📌 标签

{metadata['tags'] if metadata['tags'] else '(无标签)'}

## 🎬 字幕

{subtitle if subtitle else '(无字幕)'}

---

**元数据**:
- BV号: `{metadata['bvid']}`
- AV号: `{metadata['aid']}`
- UP主ID: `{metadata['mid']}`
"""

    return md


def main():
    """主函数"""
    # BV号
    bvid = "BV1N5foBjE5K"  # 从 https://b23.tv/btMGoOi 解析得到

    print(f"开始提取B站视频: {bvid}")
    print("=" * 60)

    # 获取配置
    try:
        config = get_config()
    except Exception as e:
        print(f"⚠️  获取配置失败，使用默认配置: {e}")
        config = None

    # 创建提取器
    extractor = BilibiliExtractor(config=config)

    # 提取视频信息
    try:
        result = extractor.extract(bvid)

        print("\n✅ 提取成功！\n")
        print("=" * 60)
        print("基本信息:")
        print("=" * 60)
        print(f"标题: {result['metadata']['title']}")
        print(f"作者: {result['metadata']['author']}")
        print(f"时长: {result['metadata']['duration']}")
        print(f"发布: {result['metadata']['pubtime']}")

        print("\n" + "=" * 60)
        print("统计数据:")
        print("=" * 60)
        print(f"播放: {format_number(result['stats']['view'])}")
        print(f"弹幕: {format_number(result['stats']['danmaku'])}")
        print(f"评论: {format_number(result['stats']['reply'])}")
        print(f"收藏: {format_number(result['stats']['favorite'])}")
        print(f"投币: {format_number(result['stats']['coin'])}")
        print(f"点赞: {format_number(result['stats']['like'])}")

        # 生成 Markdown 笔记
        md_content = generate_markdown(result, bvid)

        # 确保 notes 目录存在
        notes_dir = "/home/admin/.openclaw/workspace/notes"
        os.makedirs(notes_dir, exist_ok=True)

        # 生成文件名（使用BV号作为文件名）
        filename = f"{bvid}.md"
        filepath = os.path.join(notes_dir, filename)

        # 写入文件
        with open(filepath, 'w', encoding='utf-8') as f:
            f.write(md_content)

        print("\n" + "=" * 60)
        print(f"✅ Markdown笔记已生成: {filepath}")
        print("=" * 60)

        # 返回笔记内容
        return md_content

    except Exception as e:
        print(f"\n❌ 提取失败: {e}")
        import traceback
        traceback.print_exc()
        return None


if __name__ == '__main__':
    main()