mp-weixin

What This Skill Does

The mp-weixin skill is a specialized Python-based tool designed for OpenClaw to extract structured data from WeChat public account articles (mp.weixin.qq.com). It allows users to parse URLs and retrieve comprehensive metadata, including the article title, author, full HTML content, cover image, and publishing timestamp. Additionally, it provides specific URL parameters (mid, idx, sn, biz) and detailed account information, making it an essential utility for content curation, digital archiving, and monitoring WeChat-based media channels.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal:

clawhub install openclaw/skills/skills/bozoyan/mp-weixin

Ensure your local environment has the necessary dependencies installed: pip install beautifulsoup4 requests lxml. For users in regions with restricted access to PyPI, you may utilize the Tsinghua mirror as outlined in the installation documentation.

Use Cases

• Content Curation & Archiving: Automatically fetch and store high-quality articles from specific WeChat accounts into your personal knowledge base or database.
• Market Intelligence: Monitor updates from competitors or industry leaders by automating the retrieval of new article metadata.
• Data Analysis: Convert raw HTML WeChat articles into standardized JSON formats for sentiment analysis or keyword extraction.
• Content Migration: Simplify the process of moving content from WeChat to other platforms (like a personal blog or CMS) by programmatically extracting structured content.

Example Prompts

1. "Extract the full content and metadata from this WeChat article URL: https://mp.weixin.qq.com/s/xN1H5s66ruXY9s8aOd4Rcg and save it as a JSON file."
2. "Get the title, author, and publication time for the following list of WeChat articles and print them to the console."
3. "Monitor this公众号 and download the latest article's content, specifically focusing on the main body text."

Tips & Limitations

• Handling Limitations: The skill is not designed for scraping content behind paywalls or bypassing complex anti-bot systems such as CAPTCHAs.
• Rate Limiting: To prevent being blocked by WeChat’s servers, always include a time.sleep() interval when performing bulk extractions.
• Best Practices: Use the returned msg_content to strip HTML tags if you only require the text body, or utilize the beautifulsoup4 library for more granular content manipulation.