WeChat Article Parser for Openclaw

A high-performance parser designed to extract full text, metadata, and images from WeChat Official Account articles for local storage or cloud synchronization.

reknottycat
v1.0.0
Apr 5, 2026
0
492
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install wechat-article-parser-local

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 wechat-article-parser-local 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 Parser?

The WeChat Article Parser is a specialized tool within the Openclaw Skills ecosystem that enables developers to programmatically retrieve data from WeChat Official Account links. It handles the nuances of WeChat's HTML structure to isolate the article title, author, publication date, and complete body text while maintaining image references.

This skill is essential for users who need to archive content, conduct media research, or migrate WeChat data into other productivity platforms. By providing clean JSON or TXT outputs, it eliminates the manual effort of copy-pasting and formatting web content.

WeChat Article Parser Use Cases

  • Archiving WeChat articles for long-term personal knowledge management.
  • Automating content research by extracting clean text for AI summarization.
  • Synchronizing article metadata directly to Feishu Bitable for editorial tracking.
  • Batch processing WeChat links to generate word count and media frequency reports.

How WeChat Article Parser Works

  1. The user inputs a WeChat Official Account URL (mp.weixin.qq.com) into the script or chat interface.
  2. The system fetches the HTML content using specialized headers to ensure successful retrieval.
  3. A parsing engine processes the DOM to extract structured data including title, author, and timestamp.
  4. The article body is cleaned and converted into a readable format while identifying all embedded image URLs.
  5. The final payload is either displayed in the console, saved as a local file, or pushed to a Feishu Bitable database via API.

WeChat Article Parser Setup

To get started with this component of Openclaw Skills, install the required Python dependencies:

pip3 install requests beautifulsoup4 python-dotenv

If you intend to use the Feishu synchronization feature, create a .env file in the root directory with your credentials:

FEISHU_APP_ID=your_app_id
FEISHU_APP_SECRET=your_app_secret
FEISHU_APP_TOKEN=your_bitable_app_token
FEISHU_TABLE_ID=your_table_id

Run the core parser using the following command:

python3 scripts/wechat_parser.py "https://mp.weixin.qq.com/s/example" --save

WeChat Article Parser Data Schema & Taxonomy

The parser organizes extracted data into a structured JSON format to ensure compatibility with various Openclaw Skills workflows:

Key Type Description
title string The headline of the article
author string The name of the publishing Official Account
publish_time string The date the article was published (YYYY-MM-DD)
content string The full extracted text of the article
word_count integer Total character count of the body text
images array A list of URLs for all images found in the article
url string The original source link
parsed_at string Timestamp of the extraction process

WeChat Article Parser Advanced Features

  • Direct integration with Feishu Bitable for automated database population.
  • Support for both standard long URLs and WeChat shortened links.
  • Automated image count and word count statistics for content analysis.
  • Flexible output options including console preview, TXT, or comprehensive JSON files.
  • Seamless compatibility with AI agents for instant content summarization upon link detection.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*