clean-content-fetch

What problem does it solve?

This Skill addresses the challenge of extracting clean, readable main content from web pages, especially when standard fetching methods are hindered by excessive noise, dynamic rendering, or complex page structures. It is particularly effective for articles, blog posts, news, announcements, and WeChat official account articles.

Core Features & Use Cases

• Web Content Extraction: Fetches the primary text content from a given URL.
• Content Cleaning & Noise Reduction: Removes extraneous elements like ads, navigation, and footers to isolate the core message.
• Markdown Output: Converts the extracted content into Markdown format for easy readability and further processing.
• WeChat Article Capture: Specifically handles the extraction of content from WeChat official account articles.
• Dynamic Page Handling: Utilizes tools like Playwright and Browserforge to manage pages with JavaScript-heavy content or complex rendering.

Quick Start

Use the clean-content-fetch skill to get the main article text from the url https://example.com/article.