WeChat Article Extractor Guide

What This Skill Does

The WeChat Article Extractor skill is designed to reliably retrieve the full content of articles published on WeChat public accounts (微信公众号). It addresses the common challenge of WeChat's bot-detection mechanisms, which often prevent direct content scraping using standard web fetching tools. When direct access fails due to these protections or JavaScript rendering issues, this skill intelligently searches for mirror copies of the article on popular Chinese content aggregator websites. It prioritizes reliable sources like 53ai.com, mp.ofweek.com, juejin.cn, woshipm.com, and 36kr.com to ensure the best available copy is retrieved. Once a suitable mirror is found or if direct fetching is successful, the skill extracts the article's text, images, and metadata, then converts it into a clean Markdown file. The output Markdown file includes a metadata header and is saved to a specified location, defaulting to /tmp/ with a filename derived from the article's title.

Installation

To install the WeChat Article Extractor skill, use the following command in your OpenClaw environment:

clawhub install openclaw/skills/skills/chunhualiao/wechat-article-extractor

This command fetches the skill from the specified source repository (openclaw/skills) and makes it available for use.

Use Cases

This skill is ideal for users who want to:

• Archive valuable WeChat articles for offline reading or personal knowledge bases.
• Extract information from WeChat articles for research, study, or content curation.
• Save articles that might otherwise disappear or become inaccessible due to WeChat's dynamic content policies.
• Convert WeChat articles into a format (Markdown) easily integrated into note-taking applications like Obsidian, Notion, or local markdown editors.
• Overcome the technical hurdles of scraping content from WeChat public accounts.

Example Prompts

1. "Can you save this WeChat article for me? [mp.weixin.qq.com/s/somearticlelink]"
2. "Extract the content from this WeChat post and save it as 'my_wechat_article.md' in my documents folder: [mp.weixin.qq.com/s/anotherlink]"
3. "Please archive this article from WeChat: [mp.weixin.qq.com/s/yetanotherlink]"

Tips & Limitations

Tips:

• Ensure the provided URL is a valid mp.weixin.qq.com link.
• If you need the article saved with a specific name or in a particular directory, provide the Output filename and Save location inputs.
• The skill attempts to find mirrors, which increases the chances of successful extraction even if the original link is protected.

Limitations:

• This skill cannot handle WeChat logins, authentication, or account management.
• It is designed for extracting one article at a time; batch processing is not supported.
• The skill does not perform translation of the article content.
• While it tries to find mirrors, there's no guarantee a mirror will always be available or perfectly preserved.
• The effectiveness of mirror finding depends on the article's title and author information being present or searchable.
• Directly fetching content might fail on articles with extremely aggressive bot detection or complex dynamic rendering.