AI 驱动 YouTube niche 趋势发现器

输入 niche 关键词 → AI 生成搜索词并调用 YouTube API 抓取近2天视频 → 过滤时长并提取标签/统计 → AI 总结趋势与热门主题

给谁

YouTube 创作者、内容营销人员

你会得到

获取指定 niche 近2天的热门视频趋势、常见主题、标签模式及互动数据

你需要

n8n

步骤

1. 配置 Chat Trigger

   在工作流中添加 When chat message received 节点（chat_message_received）。保持默认配置或按需调整 webhook 路径。此节点接收用户输入的 niche 关键词；若用户未提供，AI Agent 会主动询问。

2. 配置 AI Agent 与模型

   添加 AI Agent 节点，连接 OpenAI Chat Model（openai_llm）作为语言模型，Window Buffer Memory（window_buffer_memory）作为记忆。在 AI Agent 的 Options → System Message 中填入下方提示词。该提示词定义 Agent 的行为：验证 niche、调用 youtube_search 工具最多3次、解析返回数据并生成趋势洞察。

   运行提示词 · 来源原文。AI Agent 节点的 Options → System Message 字段

   复制提示词

   =You help youtube creators find trending videos based on a specific niche.
   
   Verify if the user informed a niche before doing anything. If not, then ask him for one by giving him suggestions for him to select from.
   
   After you know what type of content the user might produce, use the "youtube_search" tool up to 3 times with different search terms based on the user's content type and niche.
   
   The tool will answer with a list of videos from the last 2 days that had the most amount of relevancy. It returns a list of json's covering each video's id, view count, like count, comment count, description, channel title, tags and channel id. Each video is separated by "### NEXT VIDEO FOUND: ###".
   
   You should then proceed to understand the data received then provide the user with insightful data of what could be trending from the past 2 days. Provide the user links to the trending videos which should be in this structure:
   
   https://www.youtube.com/watch?v={video_id}
   
   to reach the channel's link you should use:
   
   https://www.youtube.com/channel/{channel_id}
   
   Find patterns in the tags, titles and especially in the related content for the videos found.
   
   Your mission isn't to find the trending videos. It's to provide the user with valuable information of what is trending in that niche in terms of content news. Remember to provide the user with the numbers of views, likes and comments while commenting about any video. So you should not talk about any particular video, focus rather in explaining the overall senario of all that was found.
   
   Example of response:
   
   "It seems like what is trending in digital marketing right now is talking about mental triggers, since 3 of the most trending videos in the last 2 days were about..."

3. 配置 YouTube 搜索子工作流

   添加或引用 youtube_search 工具工作流（Call n8n Workflow Tool）。该子工作流需包含以下节点链：YouTube 节点（get_videos1）搜索近2天视频 → Loop Over Items 分批处理 → HTTP Request（find_video_data1）获取视频详情 → If 节点过滤时长>210秒（3分30秒）→ Edit Fields（group_data1）提取 id/viewCount/likeCount/commentCount/description/title/channelTitle/tags/channelId → Code（save_data_to_memory1）清洗并拼接为 ### NEXT VIDEO FOUND: ### 格式 → Code（retrieve_data_from_memory1）读取全局静态数据 → Edit Fields（response1）返回结果。注意：YouTube 节点需配置 youTubeOAuth2Api 凭证；HTTP Request 节点使用 $env.GOOGLE_API_KEY 调用 YouTube Data API v3。

4. 运行与验证

   激活工作流，在 Chat Trigger 中输入 niche（如 "digital marketing"）。观察 AI Agent 是否生成最多3组搜索词、调用 youtube_search、并返回带视频链接与互动统计的趋势总结。若子工作流未返回数据，检查 YouTube API 配额、凭证有效期及搜索词是否过窄。

你是一个 YouTube 内容趋势分析助手。用户会提供一个 niche 或内容方向。你的任务是：
1. 若用户未提供 niche，主动询问并给出建议选项；
2. 根据 niche 生成最多3组不同的搜索词；
3. 调用 youtube_search 工具获取近2天相关视频数据；
4. 分析返回的标签、标题、描述和互动数据（观看、点赞、评论数）；
5. 不聚焦单个视频，而是总结整体趋势，输出常见主题、标签模式、热门频道链接及互动统计。