A powerful utility to extract WeChat Official Account articles and transform them into clean, portable Markdown files with local image support.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jeffli-wechat-article
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 jeffli-wechat-article 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 tool within the Openclaw Skills ecosystem designed to bridge the gap between WeChat's closed ecosystem and your personal knowledge management system. It automates the process of fetching article content, cleaning up HTML noise, and converting the layout into standard Markdown formatting.
By leveraging advanced browser automation, this skill ensures that complex WeChat layouts are preserved while giving users the flexibility to download images locally or maintain remote links. It is an essential component for researchers, content creators, and developers who need to archive or repurpose content from WeChat Official Accounts into developer-friendly formats.
WeChat Article Scraper Use Cases
- Archiving WeChat Official Account articles for long-term personal storage.
- Converting WeChat content into Markdown for seamless import into tools like Obsidian, Notion, or Hugo.
- Automating content research by extracting text and images from specific WeChat URLs.
- Creating local backups of high-value technical or news articles to prevent data loss from link expiration.
How WeChat Article Scraper Works
- The user provides a WeChat article URL to the Openclaw Skills execution environment.
- The scraper initializes a browser instance (using camoufox) to bypass basic anti-scraping measures and render the article.
- The skill parses the HTML content using BeautifulSoup4 to identify the core article body, title, and media elements.
- Markdownify processes the cleaned HTML to generate a structured Markdown file.
- If enabled, the system downloads all embedded images into a local directory and updates the Markdown links to point to these local assets.
- The final output is organized into a dedicated folder named after the article title for easy navigation.
WeChat Article Scraper Setup
To get started with this skill, navigate to your workspace and run the main script. Ensure you have the necessary dependencies installed.
# Navigate to the skill directory
cd ~/.openclaw/workspace/skills/wechat-article
# Execute the scraper
python3 scripts/main.py "YOUR_WECHAT_URL" -o ~/.openclaw/workspace/output
Dependencies:
- camoufox
- markdownify
- beautifulsoup4
- httpx
- aiohttp
WeChat Article Scraper Data Schema & Taxonomy
The skill follows a strict directory structure to keep your extracted content organized within the Openclaw Skills workspace:
| Level | Component | Description |
|---|---|---|
| Root | output/ |
The base directory for all exports |
| Folder | [Article Title]/ |
A unique folder created for each article |
| File | [Article Title].md |
The converted Markdown content |
| Sub-folder | images/ |
Stores all .jpg, .png, or .webp files locally |
WeChat Article Scraper Advanced Features
- Headless Toggle: Use the
--no-headlessflag to manually resolve captchas or verification pages when WeChat's anti-bot measures are triggered. - Image Management: Toggle between local image hosting and remote URLs with the
--no-imagesflag to save disk space. - Force Overwrite: Use the
--forceparameter to re-scrape and update existing files if content has changed. - MCP Server Integration: Includes a dedicated
mcp_server.pyfor integration with Model Context Protocol compatible agents. - Debug Logging: Enable verbose output with the
-vflag for troubleshooting complex rendering issues.
SKILL.md
Loading
Related Openclaw Skills
Income Tracker
A comprehensive financial management tool for freelancers and creators to track multi-source income with automated currency conversion and visual analytics.
Research Agent
A sophisticated AI research specialist that transforms vague inquiries into comprehensive, source-backed analysis reports and comparison matrices.
Content Scrubber
A deterministic redaction engine that prevents private infrastructure details from leaking into public messaging channels.
China Image Generator (china-image-gen)
A specialized image generation skill that leverages the SiliconFlow API to provide high-performance AI art creation within China without needing a VPN.
Web Search (Serper API)
A real-time web search skill for AI agents that leverages the Serper API to provide Google Search results without regional access restrictions.
Helium
A comprehensive integration for managing Helium's decentralized wireless networks, LoRaWAN devices, and data processing flows.
Featured*
