A powerful automation tool for batch scraping WeChat Official Account history and exporting content into clean Markdown or HTML formats.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wechat-article-scraper-pro
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-scraper-pro 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 Scraper?
The WeChat Article Scraper is a specialized utility designed for content creators, operations professionals, and researchers who need to archive or migrate WeChat content. It streamlines the process of fetching historical articles from official accounts, ensuring that text, images, and vital metadata are preserved in local storage. By leveraging this tool within the ecosystem of Openclaw Skills, users can transform restricted platform content into versatile, SEO-friendly formats.
This skill addresses the common challenge of content fragmentation by providing a structured way to download and reorganize WeChat data. Whether you are building a personal knowledge base or performing competitive analysis, it offers a reliable bridge between the WeChat ecosystem and professional documentation workflows.
WeChat Article Scraper Use Cases
- Archiving entire historical catalogs of WeChat Official Accounts for offline reading.
- Converting WeChat articles into Markdown for migration to personal blogs or static site generators.
- Extracting engagement metrics like read counts, likes, and 'looking' stats for data analytics.
- Batch downloading high-quality image assets from published articles for design inspiration or reposting.
- Monitoring specific accounts for new content without manual browsing.
How WeChat Article Scraper Works
- The user initiates the skill and completes a micro-payment verification via the integrated SkillPay interface.
- The user provides the URL of the target WeChat Official Account homepage.
- The scraper crawls the account feed based on the specified range (either all history or the most recent N articles).
- The system parses the HTML content, extracts metadata (titles, tags, dates), and downloads associated media files.
- Content is automatically deduplicated against the local SQLite database to prevent redundant processing.
- The processed data is formatted into the user's choice of Markdown, HTML, or plain text for final export.
WeChat Article Scraper Setup
To get started with this component of Openclaw Skills, ensure you have Python 3.8+ installed and follow these steps:
# Install the necessary Python dependencies
pip install flask requests beautifulsoup4 pandas
# Navigate to the scripts directory and launch the service
python scripts/app.py
Once the server is running, access the user interface at http://localhost:5002.
WeChat Article Scraper Data Schema & Taxonomy
The skill manages data using a structured local approach to ensure security and speed. The following schema defines how information is organized:
| Data Type | Description |
|---|---|
| SQLite Database | Stores article metadata, engagement stats (read counts, likes), and crawl history for deduplication. |
| Markdown/HTML | The primary output files containing the formatted article content. |
| Image Assets | Locally stored image files extracted from the articles, organized by article ID. |
| Metadata Taxonomy | Includes Author, Publish Time, Cover Image URL, Tags, and Article Category. |
WeChat Article Scraper Advanced Features
- Integrated SkillPay interface for seamless, low-cost per-use micro-transactions (0.001 USDT).
- Automatic image localization to prevent broken links in exported Markdown files.
- Smart deduplication logic to efficiently update existing archives without re-scraping the entire history.
- Multi-format export support including structured JSON for data analysis or raw text for LLM training.
- Local data persistence using SQLite, ensuring your scraped data remains private and accessible without internet connectivity.
SKILL.md
Loading
Related Openclaw Skills
Code Archaeology
A systematic analysis methodology for dissecting legacy codebases to extract business logic, technical debt, and actionable modernization roadmaps.
Uploader
A streamlined utility to upload local media and documents to the Astron Claw Bridge and retrieve secure, public download links.
Fictional Companion Forge
Fictional Companion Forge reconstructs fictional personas into emotionally immersive, voice-faithful Openclaw Skills companion agents.
EdgeOne HTML Deployer
Deploy HTML or text content to a public URL instantly without requiring an account or API keys.
WeryAI Video Lips Change
A specialized AI tool for synchronizing the lip movements of an existing video to a separate, high-quality audio source via public URLs.
WeChat MP to Notion
A specialized tool to bridge the gap between WeChat public account content and Notion by converting articles into structured, readable blocks.
Featured*
