A specialized tool for converting WeChat public account articles into clean, archived Markdown files with full image and metadata support.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wechat-article-extractor
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-extractor 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 Extractor?
The WeChat Article Extractor is a technical solution designed to bypass the complex anti-scraping measures of the WeChat (mp.weixin.qq.com) ecosystem. Since WeChat often blocks standard web fetching with CAPTCHAs and environment checks, this skill leverages the Openclaw Skills framework to implement a multi-layered retrieval strategy. It identifies mirror sites, processes aggregator content, and uses fallback browser relays to ensure developers can reliably archive Chinese social media content.
By synthesizing metadata, author information, and high-quality image links, the skill transforms transient social media posts into permanent, searchable Markdown documents. This makes it an essential component of the Openclaw Skills library for researchers and developers working with regional data sources.
WeChat Article Extractor Use Cases
- Archiving technical WeChat public account articles for long-term storage in local knowledge bases.
- Importing Chinese tech news or business analysis into Markdown-based tools like Obsidian or Notion.
- Automating the research process by extracting clean text from WeChat URLs without manual copy-pasting.
- Bypassing WeChat's browser-detection blocks to read content via automated agents.
How WeChat Article Extractor Works
- The skill first attempts a direct fetch of the WeChat URL to see if the content is accessible without a CAPTCHA.
- If direct access is blocked, it extracts article metadata such as the title and author name from the page headers.
- It performs an automated search across prioritized mirror sites like 53ai.com, mp.ofweek.com, and Juejin to find an unblocked copy.
- Once a mirror is found, it uses a Python-based extraction script to parse the HTML and convert it into structured Markdown.
- If no mirrors are available, it triggers a fallback to the Chrome Extension Relay to take a snapshot of the rendered page.
- The final output is formatted with a standardized metadata header and delivered as a clean .md file.
WeChat Article Extractor Setup
To get started with this component of Openclaw Skills, ensure your environment meets the following technical requirements:
# Verify Python 3.8+ is installed
python3 --version
# Ensure curl is available for mirror page downloads
curl --version
The skill requires access to standard tools including web_fetch, web_search, and exec. For the most reliable results with niche articles, the OpenClaw Browser Relay extension should be active in your Chrome profile to facilitate the snapshot fallback mechanism.
WeChat Article Extractor Data Schema & Taxonomy
The skill organizes extracted data into a strictly structured Markdown format to ensure compatibility with knowledge management systems:
| Section | Content |
|---|---|
| Header | Includes Title, Author, Source (Account Name), Date, and Original URL |
| Summary | A concise 1-2 sentence summary generated from the article content |
| Content | Full article body text with preserved paragraphs and section dividers |
| Images | Preserved image tags using valid URLs from mirrors or proxies |
| Metadata | Filename defaults to kebab-case of the title for easy file system navigation |
WeChat Article Extractor Advanced Features
- Smart mirror prioritization that ranks aggregator sites by content quality and reliability.
- Automated bot-detection bypass that switches between direct fetch, mirror searching, and browser snapshots.
- Integrated Python extraction engine that cleans HTML artifacts while preserving WeChat-specific styling like section dividers.
- Metadata-rich header generation that automatically populates author and source information for better archival organization within Openclaw Skills workflows.
SKILL.md
Loading
Related Openclaw Skills
Mermaid Diagram Generator
A powerful automation skill for creating professional, consistently styled Mermaid diagrams from technical content using smart templates.
Skill Engineer
An advanced multi-agent framework for designing, auditing, and maintaining high-quality Openclaw Skills through automated design and testing loops.
Save to Obsidian
A specialized automation skill for saving markdown content and diagrams from an AI agent directly into a remote Obsidian vault via secure SSH transfer.
Rotate OpenRouter Key
A specialized utility to securely replace OpenRouter API keys across multiple configuration files and environment variables.
X-Extract
A specialized browser automation tool for extracting rich content from X.com and Twitter URLs without requiring official API credentials.
Epstein Files Search
A powerful CLI utility for searching over 44,886 declassified Jeffrey Epstein documents released by the DOJ in 2026.
Featured*
