Wechat Article Extractor

What it does

This skill extracts structured article data from WeChat Official Account posts, converting unstructured web content into clean text or JSON formats suitable for AI agent processing. It handles the specific rendering quirks and nested structures often found in WeChat articles to ensure accurate data retrieval.

When to use it

• You need to analyze the full text of a WeChat article that standard scrapers miss due to dynamic loading or complex DOM structures.
• Your AI agent requires structured JSON output containing specific fields like title, author, publish date, and body content from WeChat sources.
• You are building a workflow to aggregate insights from multiple WeChat Official Accounts into a central database or knowledge base.

Key capabilities

• Extracts core article metadata including title, author name, publication time, and cover image URL.
• Parses the main body text while filtering out navigation elements, ads, and unrelated widgets.
• Returns data in flexible formats such as plain text or structured JSON objects for downstream processing.

Example prompts

• "Extract the full article content and metadata from this WeChat link: [URL]"
• "Convert the provided WeChat article into a JSON object with fields for title, author, date, and cleaned body text."
• "Summarize the key points of this WeChat Official Account post after extracting its raw text."

Tips & gotchas

Ensure the input URL is a direct link to a published WeChat article page; preview links or search result snippets may not yield complete data. The skill relies on the current DOM structure of the target article, so formatting may vary if the source updates their rendering engine.