Xiaohongshu CN

小红书分析 - 热门笔记发现、关键词监控、趋势分析（Instagram 中国版）

Security Scan

The skill is a coherent how-to for scraping/analysing Xiaohongshu, but its runtime instructions recommend reverse engineering, packet-capture, and running third‑party scraping code — actions that carry legal, privacy, and supply‑chain risks and should be vetted before use.

Purpose & Capability

The name/description (Xiaohongshu analysis) match the content: instructions for discovering popular notes, keyword monitoring and trend analysis. It does not request unrelated credentials or system access.

Instruction Scope

SKILL.md explicitly recommends cloning and running third‑party scraping projects, performing '小程序抓包' (packet capture/intercepting mobile app traffic), and reverse engineering the API. Those instructions expand scope beyond safe, read-only guidance: they can collect sensitive data, may violate terms of service or law, and instruct the user to run unvetted code and network interception tools.

Install Mechanism

The skill is instruction-only (no install). However it instructs the operator to git clone and run external GitHub projects. That delegates installation/execution to third‑party code (supply‑chain risk). The skill itself does not fetch or embed code, but following its steps involves installing arbitrary external packages.

Credentials

The skill declares no required environment variables, credentials, or config paths. It does not request broad secrets or system access in its metadata. Note: practical use of recommended techniques (e.g., intercepting mobile traffic or running scrapers) may implicitly require device/proxy credentials, but those are not requested by the skill itself.

Persistence & Privilege

No install spec and no persistence requested. always is false and the skill does not attempt to modify other skills or system settings. It is agent-invocable in the normal way.

What to consider before installing

This skill is essentially a how-to for scraping Xiaohongshu (a site without a public API). Before using it: 1) Understand legal and ToS risks — packet capture, reverse engineering, or aggressive scraping can violate laws or the platform's rules. 2) Do not blindly run cloned repositories: review the GitHub code, check community reputation, and run in an isolated environment (VM/container) with least privilege. 3) Prefer official or paid data providers where available, respect robots.txt and rate limits, and avoid collecting personal/private data. 4) If you must use packet‑capture or proxy tools, ensure you have lawful authorization and are not intercepting other users' traffic. 5) The skill itself does not execute anything until you follow its instructions — treat those external commands as higher-risk operations and vet them accordingly.

小红书分析

热门笔记发现、关键词监控、趋势分析。

功能

• 📕 热门笔记发现
• 🔍 关键词搜索
• 📊 趋势分析
• 👥 博主分析

⚠️ 重要提示

小红书没有公开 API，需要以下方式之一：

1. 网页爬虫

# 使用现有爬虫项目
git clone https://github.com/Big-Buffer/XiaohongshuSpider
cd XiaohongshuSpider
pip install -r requirements.txt
python main.py

2. 小程序抓包

# 参考
# https://github.com/lonngxiang/xiaohongshu-spider

3. 手动查询

直接访问小红书网页版：

• 热门: https://www.xiaohongshu.com/explore
• 搜索: https://www.xiaohongshu.com/search_result

热门分类

分类	关键词
美妆	护肤、彩妆、测评
穿搭	OOTD、日常穿搭
美食	探店、食谱
旅行	攻略、打卡
家居	装修、好物

使用场景

1. 内容创作

• 发现热门话题
• 学习爆款标题
• 分析竞品笔记

2. 市场研究

• 了解用户偏好
• 追踪品牌声量
• 发现新品趋势

3. 营销推广

• 找到 KOL
• 分析投放效果
• 优化内容策略

数据字段

字段	说明
note_id	笔记 ID
title	标题
desc	描述
author	作者
likes	点赞数
comments	评论数
shares	分享数
tags	标签

与其他平台对比

平台	对应美国平台	特点
小红书	Instagram/Pinterest	图文+短视频
抖音	TikTok	短视频
B站	YouTube	长视频
知乎	Quora	问答

注意事项

1. 合规爬虫: 遵守 robots.txt
2. 频率限制: 不要过于频繁请求
3. 账号风险: 频繁爬虫可能导致封号
4. 数据用途: 仅用于个人研究

推荐工具

• XiaohongshuSpider - Python 爬虫
• xiaohongshu-spider - Selenium + Fiddler
• Nanji - 数据分析平台

---

版本: 1.0.0 注意: 小红书 API 需要逆向工程