A specialized tool for scraping WeChat Official Account articles and converting them into clean, structured Markdown files.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wechat-articles-skill
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-articles-skill 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 Articles Scraper?
The WeChat Articles skill is a powerful automation utility designed for the Openclaw Skills ecosystem. It addresses the common challenge of archiving and repurposing content from the WeChat Official Accounts platform (mp.weixin.qq.com), which is typically difficult to export.
By leveraging browser automation, this skill extracts high-fidelity content—including metadata like titles, authors, and publishing times—and transforms the raw HTML into a readable Markdown format. This ensures that developers and researchers can maintain a local, searchable database of important articles without the clutter of web styles.
WeChat Articles Scraper Use Cases
- Archiving WeChat Official Account articles for offline reading or personal knowledge bases.
- Migrating content from WeChat to personal blogs or documentation sites.
- Automating research by batch-converting multiple WeChat links into manageable Markdown files.
- Extracting images and text from protected web layouts for better accessibility.
How WeChat Articles Scraper Works
- URL Reception: The agent receives a valid WeChat article link (mp.weixin.qq.com) from the user.
- Headless Interaction: It launches a Playwright-powered headless browser to navigate to the link and waits for all dynamic elements to load.
- Element Extraction: Using specific CSS selectors (like #js_content and #activity-name), it pulls the core article data.
- Markdown Transformation: The skill processes the HTML, stripping away unnecessary styling while preserving the structural integrity of the text and media.
- File Persistence: The resulting Markdown is saved to the local file system using the article's title as the filename.
WeChat Articles Scraper Setup
To use this skill within the Openclaw Skills framework, ensure you have Playwright and Python 3 installed. You can execute the scraper directly via the CLI:
python3 ~/.nvm/versions/node/v24.14.0/lib/node_modules/openclaw/skills/wechat-articles/scripts/fetch_article.py "<WECHAT_URL>" [--output <directory>]
WeChat Articles Scraper Data Schema & Taxonomy
The skill generates a structured Markdown file with comprehensive Frontmatter and a dedicated assets folder:
| Field | Description |
|---|---|
| Title | The original article heading extracted from #activity-name |
| Author | The WeChat Official Account name |
| URL | The source link for reference |
| Fetched | ISO timestamp of the scraping event |
| Images | Saved locally in an images/ subdirectory with relative path linking |
Example File Structure:
Article-Title.mdimages/(contains downloaded JPG/PNG assets)
WeChat Articles Scraper Advanced Features
- Automated Image Handling: Downloads and re-links all article images to a local folder by default.
- Headless Browser Simulation: Uses a 30-second timeout to ensure even heavy articles with lazy-loaded images are fully captured.
- Custom Output Paths: Supports the
--outputflag for organized data storage within different project directories. - Image Suppression: Use the
--no-imagesparameter for text-only extractions to save bandwidth and storage.
SKILL.md
Loading
Related Openclaw Skills
Feishu Rate Limit Skill
A sophisticated rate-limiting strategy for Feishu/Lark APIs that prevents 429 errors through dynamic interval adjustment and intelligent retry logic.
Extract Design
A sophisticated design extraction engine that captures the visual DNA and atmospheric mood of websites for AI-driven frontend development.
Beike
A professional real estate assistant designed to optimize property operations, client consultations, and transaction conversions on the Beike platform.
Audible Skill
An automated data extraction skill for organizing Audible public library content, membership details, and support documentation.
1Person Pro
A comprehensive AI assistant platform for multi-agent orchestration and autonomous workflow execution.
58 Tongcheng Local Service Optimizer
An expert AI assistant specialized in optimizing local service exposure, information publishing, and lead conversion on the 58 Tongcheng platform.
Featured*
