summarize_video_story

Extract story summaries and key content from YouTube Shorts videos by analyzing titles, descriptions, themes, and narrative techniques.

Instructions

提炼 YouTube Shorts 视频的故事梗概和核心内容。基于视频标题和描述,分析视频的主题、情节和创作手法。

Input Schema

TableJSON Schema

Name	Required	Description	Default
`video_url`	Yes	YouTube Shorts 视频链接

Implementation Reference

src/server.py:575-646 (handler)

Main handler function for summarize_video_story tool. Extracts video ID, fetches video details via YouTubeClient, and formats the video information (title, channel, stats, description) into a structured text response for Claude to analyze and summarize.

async def summarize_video_story(video_url: str) -> list[TextContent]:
    """
    工具 4 的实现:提炼视频故事梗概
    
    这个工具的巧妙之处:
    1. 我们只负责获取视频的标题和描述
    2. 将这些信息返回给 Claude
    3. Claude 会自动分析并提炼故事梗概
    4. 用户看到的是 Claude 基于视频信息生成的分析
    """
    
    try:
        # 提取视频 ID
        video_id = extract_video_id(video_url)
        
        if not video_id:
            return [TextContent(
                type="text",
                text=f"❌ 无效的 YouTube 链接: {video_url}"
            )]
        
        # 获取视频详情
        client = YouTubeClient()
        videos = client.get_video_details([video_id])
        
        if not videos:
            return [TextContent(
                type="text",
                text=f"❌ 未找到视频: {video_id}"
            )]
        
        video = videos[0]
        
        # 构建视频信息文本,供 Claude 分析
        info = f"""# 视频信息

**标题**: {video.title}

**频道**: {video.channel_name}

**发布时间**: {video.published_at.strftime('%Y-%m-%d %H:%M UTC')}

**播放量**: {video.views:,}

**点赞数**: {video.likes:,}

**评论数**: {video.comments:,}

**视频链接**: {video.url}

---

## 视频描述

{video.description if video.description else '(该视频没有描述)'}

---

**请基于以上信息,分析这个视频的:**
1. 主题和核心内容
2. 可能的故事情节或创作手法
3. 为什么这个视频可能受欢迎
4. 适合什么样的观众群体
"""
        
        return [TextContent(type="text", text=info)]
    
    except Exception as e:
        return [TextContent(
            type="text",
            text=f"❌ 获取视频信息失败: {str(e)}"
        )]

src/server.py:235-251 (registration)

Tool registration in list_tools() function. Defines the tool name 'summarize_video_story', description for Claude, and the inputSchema requiring a 'video_url' parameter.

Tool(
    name="summarize_video_story",
    description=(
        "提炼 YouTube Shorts 视频的故事梗概和核心内容。"
        "基于视频标题和描述,分析视频的主题、情节和创作手法。"
    ),
    inputSchema={
        "type": "object",
        "properties": {
            "video_url": {
                "type": "string",
                "description": "YouTube Shorts 视频链接"
            }
        },
        "required": ["video_url"]
    }
),

src/server.py:344-347 (registration)
Call routing in call_tool() function. Routes tool calls with name='summarize_video_story' to the summarize_video_story handler function, passing the video_url argument.
```
elif name == "summarize_video_story":
    return await summarize_video_story(
        video_url=arguments["video_url"]
    )
```

src/server.py:104-117 (helper)

Helper function extract_video_id() used by summarize_video_story to parse YouTube URLs and extract the video ID using regex patterns for different YouTube URL formats.

def extract_video_id(url: str) -> Optional[str]:
    """从 YouTube URL 中提取视频 ID"""
    patterns = [
        r'youtube\.com/shorts/([a-zA-Z0-9_-]+)',
        r'youtube\.com/watch\?v=([a-zA-Z0-9_-]+)',
        r'youtu\.be/([a-zA-Z0-9_-]+)',
    ]
    
    for pattern in patterns:
        match = re.search(pattern, url)
        if match:
            return match.group(1)
    
    return None

Viral Shorts