Fetch WeChat Article for Openclaw

A specialized tool for scraping WeChat Public Account articles and converting them into clean, structured Markdown format.

tomjamescn
v1.0.0
Mar 14, 2026
0
1.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install fetch-wx-article

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install fetch-wx-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 Fetch WeChat Article?

The Fetch WeChat Article skill is designed to bridge the gap between WeChat's closed ecosystem and your local development environment. By utilizing advanced scraping techniques, this Openclaw Skills component targets the mp.weixin.qq.com domain to extract titles, authors, and body text while stripping away unnecessary styling and scripts.

This utility is particularly valuable for developers who need to ingest high-quality content from one of the world's largest content platforms into their own systems. Whether you are building a knowledge base or training an AI, this tool ensures the content is delivered in a highly portable Markdown format.

Fetch WeChat Article Use Cases

  • Archiving WeChat Public Account articles into personal knowledge management tools.
  • Extracting clean text from WeChat links shared in chat for LLM-based summarization.
  • Automating content research by fetching article metadata and body text programmatically.
  • Converting mobile-optimized WeChat posts into readable Markdown for documentation.

How Fetch WeChat Article Works

  1. The user inputs a WeChat article URL following the standard mp.weixin.qq.com/s/ format.
  2. The Openclaw Skills script invokes the scrapling library to handle the complex, dynamic HTML structure typical of WeChat pages.
  3. The system identifies key content segments including the article title, author information, and the main text body.
  4. Using html2text, the extracted HTML is sanitized and transformed into standard Markdown syntax.
  5. The final output is returned as a clean text stream ready for archiving or further processing.

Fetch WeChat Article Setup

To use this skill within your Openclaw Skills environment, you must first install the required Python libraries. Run the following command in your terminal:

pip install "scrapling[ai]" html2text

Once installed, you can fetch an article by running the script with a target URL:

python3 scripts/fetch_wx_article.py https://mp.weixin.qq.com/s/xxx

Fetch WeChat Article Data Schema & Taxonomy

The skill organizes extracted data into a structured format suitable for further automation. Below is the typical output structure:

Property Description Format
Title The primary headline of the article String
Author The WeChat Official Account name String
Content The full body of the article Markdown
Source The original URL provided URL

Note: By default, images and external links are ignored to ensure the output remains focused on text content.

Fetch WeChat Article Advanced Features

  • Intelligent CSS/JS handling: Uses scrapling[ai] to navigate complex web layouts that traditional scrapers fail to parse.
  • Custom output filters: The script can be modified to selectively include or exclude specific HTML elements like images or hyperlinks.
  • Seamless Integration: Designed to work as a modular component within the broader Openclaw Skills ecosystem for multi-step agent workflows.
  • Robust Error Management: Includes built-in handling for network timeouts and invalid URL formats.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*