A specialized content extraction tool for Xiaohongshu that converts notes and media into structured Markdown and JSON data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install xiaohongshu-scraper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install xiaohongshu-scraper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Xiaohongshu Scraper?
The Xiaohongshu Scraper is a powerful utility designed to harvest and organize content from the popular social media platform Little Red Book. Built for users of Openclaw Skills, this tool streamlines the process of capturing note text, high-resolution images, and engagement metadata. It bridges the gap between social media browsing and data archival by transforming web content into structured Markdown documents and JSON files, making it an essential asset for content creators and researchers.
By leveraging advanced automation, this skill simplifies the complex task of social media scraping. It includes a dedicated API service and a command-line interface, allowing for both manual extraction and automated workflows. Whether you are building a personal knowledge base or conducting market analysis, this integration within the Openclaw Skills ecosystem ensures your data is clean, organized, and ready for use.
Xiaohongshu Scraper Use Cases
- Archiving Xiaohongshu notes for offline research and personal knowledge management.
- Extracting text and images from competitors to analyze digital marketing trends.
- Automatically converting image-heavy tutorials into searchable Markdown documentation via OCR.
- Batch downloading high-quality media assets for creative inspiration and mood boarding.
- Powering automated content analysis workflows within the broader Openclaw Skills environment.
How Xiaohongshu Scraper Works
- The user initializes the local API service which manages the connection to the content source.
- One or more Xiaohongshu URLs (including shortened xhslink.com links) are provided to the scraper.
- The skill fetches detailed metadata including titles, descriptions, tags, and engagement metrics like like-counts.
- Visual media is downloaded locally while maintaining high resolution.
- On macOS systems, the integrated Vision framework performs OCR on the images to extract embedded text.
- The skill synthesizes all gathered data into a structured directory containing JSON, Markdown, and media files.
Xiaohongshu Scraper Setup
To begin using this tool within your Openclaw Skills workflow, first ensure Python 3.12+ is installed. Start the background API service:
cd /path/to/xiaohongshu-scraper/scripts
./xhs-api-service.sh start
Once the service is active, you can scrape a note by running the following command:
python xhs_scraper.py "YOUR_XHS_URL" --output ./my_data
You can also interact with the service directly via CURL for programmatic integration.
Xiaohongshu Scraper Data Schema & Taxonomy
This skill organizes data into a structured folder named after the Note ID. This structure is designed for easy integration with other Openclaw Skills:
| Component | File Path | Content |
|---|---|---|
| Structured Data | note.json |
Full metadata including author info, tags, and stats. |
| Human Readable | note.md |
A formatted Markdown version of the note text. |
| Media Assets | images/ |
A folder containing all downloaded JPEG/PNG files. |
| OCR Results | ocr/ |
Individual Markdown files containing text recognized from each image. |
The note.json file includes a comprehensive schema covering author.nickname, interact.liked_count, and publish_time.
Xiaohongshu Scraper Advanced Features
- Native macOS OCR: Utilizes the Vision framework for high-speed, accurate text extraction from images.
- Batch Processing: Support for multiple URLs in a single command for high-volume data collection.
- Metadata-Only Mode: Use the
--info-onlyflag to quickly gather stats without downloading large media files. - REST API Integration: A local server provides a documentation endpoint at port 5556 for custom developer hooks.
- Short Link Resolution: Automatically resolves shortened xhslink.com URLs into standard web links for processing within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Patent Assistant
An AI-powered assistant designed to transform technical ideas into structured patent disclosure documents and perform comprehensive global patent searches.
NVIDIA FLUX Image Generation
A high-performance AI tool for generating and editing images using NVIDIA FLUX models via simple CLI commands.
Self-Improvement Skill
A structured logging and memory system that enables AI agents to capture errors, corrections, and best practices for continuous autonomous improvement.
Revenue Calculator
A powerful projection tool for estimating monthly and annual revenue for AI agents and marketplace strategies.
Z.AI Web Search API Skill
An AI-powered web search skill optimized for Chinese-language content and LLM-ready structured data.
Polymarket US Prediction Markets
Access real-time prediction market data and execute trades on Polymarket US using Openclaw Skills.
Featured*
