A specialized Python crawler designed to transform WeChat Official Account articles into clean Markdown files with locally preserved images.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wechat-article-spider
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 wechat-article-spider 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 WeChat Article Spider?
WeChat Article Spider is an essential utility for developers and researchers who need to archive content from the WeChat ecosystem. As part of the Openclaw Skills library, this tool automates the process of fetching remote article data, parsing complex HTML structures, and downloading all embedded media to a local environment. It solves the problem of content volatility by providing a reliable way to save high-quality WeChat posts for offline reading or integration into personal knowledge management systems.
By converting dynamic WeChat pages into static Markdown, the tool ensures that the content remains accessible even if the original post is deleted. It handles the nuances of WeChat image hosting by re-linking downloaded images to local relative paths, making the resulting documents fully portable and ready for tools like Obsidian, Notion, or static site generators.
WeChat Article Spider Use Cases
- Archiving high-quality technical articles from WeChat for offline personal knowledge bases.
- Migrating WeChat Official Account content to personal blogs or documentation sites.
- Researching and collecting media assets from specific WeChat publications.
- Preserving critical information from public accounts that may face content expiration.
How WeChat Article Spider Works
- The user provides the script with a public WeChat article URL and an optional output directory.
- The spider utilizes the requests library to fetch the raw HTML content of the page.
- BeautifulSoup4 and lxml parse the document to extract the core article text and identify all image sources.
- The tool automatically downloads every image found in the article, saving them to a local subdirectory.
- It generates unique hash-based filenames for images to prevent naming conflicts.
- A Markdown file is generated where all original image URLs are replaced with local relative file paths.
WeChat Article Spider Setup
To get started with this tool from the Openclaw Skills repository, follow these steps:
# Navigate to the scripts directory
cd wechat-article-dl/scripts
# Install the necessary Python dependencies
pip install -r requirements.txt
# Run the spider by providing an article URL
python main.py https://mp.weixin.qq.com/s/example_id
WeChat Article Spider Data Schema & Taxonomy
The WeChat Article Spider organizes data in a clean, hierarchical structure:
| File/Folder | Description |
|---|---|
output/ |
The root directory for the exported content. |
Article_Title.md |
The final Markdown document with processed text and image links. |
images/ |
A subdirectory containing all downloaded media files. |
img_xxx.jpg |
Individual image files named using MD5 hashes for uniqueness. |
WeChat Article Spider Advanced Features
- Custom output path support allows for organized bulk downloads into specific folders.
- Automated image deduplication using hash-based naming conventions.
- Relative path referencing ensures that the generated Markdown remains functional when moved between different systems.
- Lightweight architecture designed to be integrated into larger Openclaw Skills automation workflows.
SKILL.md
Loading
Related Openclaw Skills
Content Scheduler
A smart content planning and rotation system designed to prevent format fatigue and optimize engagement through data-driven tracking.
EdrawMax AI Diagram Generator
A professional AI-driven skill that transforms natural language descriptions into high-quality visual diagrams and source code.
Blackbox CLI
A sophisticated multi-model coding agent that executes tasks across several LLMs and utilizes an internal judge to select the highest quality code implementation.
Kimi API Workflow Integration
A professional-grade integration skill for building, debugging, and optimizing Kimi API workflows with a focus on reliability and operational safety.
Yelp
A comprehensive tool for searching Yelp businesses, analyzing review trends, and auditing listing quality through official APIs and public data.
Content Monetization Assistant
An AI-powered strategist that helps creators assess content value, select monetization channels, and build actionable revenue models.
Featured*
