A local scraping engine designed to batch identify and pull historical articles from WeChat Official Accounts into structured Markdown and JSON formats.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wechat-articles-crawler
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-crawler 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 Official Account Article Fetcher?
The WeChat Official Account Article Fetcher is a specialized tool within the Openclaw Skills ecosystem that automates the extraction of content from specific WeChat authors. It provides a standardized workflow to convert high-quality WeChat articles into local data repositories, which are essential for creating author corpora, style analysis, and content archiving.
Unlike generic web scrapers, this skill handles the specific authentication challenges of the WeChat ecosystem locally, ensuring that login states and sensitive profile data never leave your machine. It produces clean Markdown for AI training, raw HTML for layout preservation, and an articles.json index for programmatic analysis.
WeChat Official Account Article Fetcher Use Cases
Primary Scenarios
- Creating a comprehensive author corpus for AI style imitation or template generation.
- Batch downloading the latest 20, 50, or 100 articles from a specific creator for offline reading.
- Fact-checking and cross-referencing historical content across multiple articles.
- Transitioning a WeChat-based content strategy to a self-hosted or Markdown-based knowledge base.
How WeChat Official Account Article Fetcher Works
Operational Lifecycle
- Environment Check: The agent verifies the presence of local scripts, including the main.py logic and the run_fetcher.sh bridge.
- Authentication Management: It checks the login status using Openclaw Skills protocols; if the session has expired, it generates a QR code for the user to scan locally.
- Account Identification: Based on a single provided article link, the tool identifies the target account's metadata.
- Batch Fetching: The scraper iterates through the account's history based on the configured limit (e.g., the last 50 articles).
- Data Serialization: Content is processed and saved into structured folders containing Markdown, HTML, and a JSON index.
WeChat Official Account Article Fetcher Setup
Installation and Execution
Ensure you have Python installed, then navigate to the skill directory to initialize the environment:
cd "content_production/wechat_article_fetcher"
# The script automatically creates a .venv and installs requirements on first run
./scripts/run_fetcher.sh ensure-login --json --display silent
To fetch articles after login:
./scripts/run_fetcher.sh fetch "ARTICLE_URL" --json
WeChat Official Account Article Fetcher Data Schema & Taxonomy
Output Structure
Data is organized within the output_parent directory defined in config.json:
| File/Folder | Description |
|---|---|
/markdown/ |
Articles converted to clean Markdown files. |
/html/ |
The original source HTML of the articles. |
articles.json |
Metadata index including titles, publish dates, and local paths. |
.playwright-profile |
Local browser session data (remains private). |
WeChat Official Account Article Fetcher Advanced Features
Power-User Capabilities
- Flexible Display Modes: Supports silent mode for IM bots, terminal mode for CLI users, and image mode for desktop GUI environments.
- Configurable Concurrency: Adjust the
concurrencysetting in config.json to balance speed and anti-scraping safety. - Session Management: Explicit
clear-logincommands to wipe local credentials before handing off the machine or project. - Downstream Integration: Seamlessly passes scraped Markdown to other Openclaw Skills for style extraction or automated rewriting.
SKILL.md
Loading
Related Openclaw Skills
RagClaw Knowledge Base Skill
RagClaw provides a private, local-first knowledge base for Openclaw Skills to index and search documents, code, and web pages without external APIs.
Trending Bar Navigator
An intelligent guide for discovering trending bars, providing curated recommendation lists, transit routes, and essential check-in tips.
Scrape-It.Cloud Integration
A powerful integration for Scrape-It.Cloud that enables AI agents to manage web scraping projects, schedules, and proxies through secure, automated authentication.
Social Community Monetization
A professional framework for converting community engagement into sustainable revenue through structured monetization paths.
Community Group Buying Monetization Skill
A comprehensive strategic blueprint for establishing and scaling a community group buying business with a focus on sustainable cash flow.
AI Sales Closing & Offer Generator
A specialized AI tool designed to transform stalled sales conversations into signed contracts through high-conversion messaging and strategic offer design.
Featured*
