openclaw-skills/skills/obsidian-kb/add_video.py

#!/usr/bin/env python3
"""手动添加B站视频到obsidian-kb收件箱"""

import sys
import os
import urllib.request
from urllib.request import Request, urlopen

# 添加路径以便导入模块
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), 'src'))

from sources.bilibili import BilibiliAdapter
from models import Content, ContentStatus
from storage import Storage
from shortlink_resolver import (
    ShortLinkResolver,
    PlaywrightResolver,
    detect_and_format
)

def resolve_short_url(url: str, try_playwright: bool = False) -> str:
    """
    解析短链接（如 b23.tv）到完整URL，或接受BV号

    Args:
        url: 可能是短链接的URL、完整URL或BV号
        try_playwright: 是否尝试使用Playwright解析短链接

    Returns:
        str: 完整URL或BV号，如果失败返回None
    """
    # 如果已经是完整URL，直接返回
    if 'bilibili.com/video/' in url:
        return url

    # 如果是BV号，直接返回（bilibili.py 的 extract_content 会处理）
    if url.upper().startswith('BV'):
        return url

    # 如果是短链接，尝试解析
    resolver = ShortLinkResolver()

    if resolver.is_bilibili_short_link(url):
        print(f"  ⚠️  检测到短链接 {url}")

        # 尝试使用Playwright解析（如果启用）
        if try_playwright:
            print(f"  🔄 尝试使用浏览器解析...")
            playwright_resolver = PlaywrightResolver(headless=True)

            try:
                resolved_url = playwright_resolver.resolve_bilibili_short(url)
                if resolved_url:
                    print(f"  ✅ 解析成功: {resolved_url}")
                    return resolved_url
                else:
                    print(f"  ❌ 浏览器解析失败")
            except Exception as e:
                print(f"  ❌ Playwright不可用或解析失败: {e}")

        # 显示用户引导
        print("")
        print(resolver.format_short_link_help(url))
        print("")
        return None

    # 默认返回原URL
    return url

def add_video_to_inbox(url: str, try_playwright: bool = False) -> str:
    """
    添加B站视频到收件箱

    Args:
        url: B站视频URL
        try_playwright: 是否尝试使用Playwright解析短链接

    Returns:
        str: Content ID
    """
    print(f"📥 正在处理视频: {url}")

    # 解析短链接
    resolved_url = resolve_short_url(url, try_playwright=try_playwright)
    if resolved_url is None:
        return None

    # 创建适配器
    adapter = BilibiliAdapter()

    # 提取视频元数据
    print("  → 获取视频信息...")
    content = adapter.extract_content(resolved_url)
    if not content:
        print("  ❌ 无法提取视频信息")
        return None

    print(f"  → 标题: {content.title}")
    print(f"  → UP主: {content.author}")
    print(f"  → 时长: {content.duration}秒")

    # 获取字幕
    print("  → 获取字幕...")
    transcript = adapter.get_transcript(content)
    if transcript:
        content.transcript = transcript
        print(f"  ✓ 字幕已获取 ({len(transcript)} 字符)")
    else:
        print("  ⚠️  无法获取字幕")

    # 设置状态为已确认（准备处理）
    content.status = ContentStatus.CONFIRMED

    # 保存到收件箱
    print("  → 保存到收件箱...")
    storage = Storage()
    storage.save_content(content)

    print(f"\n✅ 视频已添加到收件箱!")
    print(f"   Content ID: {content.id}")
    print(f"\n💡 使用以下命令处理:")
    print(f"   python3 src/cli.py process {content.id}")
    print(f"   或者:")
    print(f"   python3 src/cli.py process all")

    return content.id

if __name__ == '__main__':
    if len(sys.argv) < 2:
        print("用法: python3 add_video.py <B站视频URL>")
        print("示例:")
        print("  python3 add_video.py https://www.bilibili.com/video/BV1xx411c7mD")
        print("  python3 add_video.py BV1xx411c7mD")
        print("  python3 add_video.py https://b23.tv/oLBZZfK")
        print("\n选项:")
        print("  --playwright  尝试使用浏览器解析短链接")
        sys.exit(1)

    url = sys.argv[1]
    try_playwright = '--playwright' in sys.argv
    if try_playwright and url == '--playwright' and len(sys.argv) > 2:
        url = sys.argv[2]

    add_video_to_inbox(url, try_playwright=try_playwright)