skills.rest
xintuchain
xintuchainCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

defuddle-web-cleaner

Extract readable article content from URLs or HTML into Markdown or JSON.

Updated Aug 23, 2026
Search Tags:#markdown#metadata#web-scraping#web-content-extraction#article-content#defuddle
One-click install
npx skills add https://github.com/xintuchain/tongtong --skill defuddle-web-cleaner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle-web-cleaner
Source: https://github.com/xintuchain/tongtong/tree/main/skills/defuddle
Command: npx skills add https://github.com/xintuchain/tongtong --skill defuddle-web-cleaner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The Defuddle Web Cleaner extracts the main readable content from web pages by removing clutter such as navigation bars, ads, and sidebars, delivering clean article text.

Core Features & Use Cases

  • Detect input type (URL, raw HTML, or text) and load the page content.
  • Run the Defuddle parser to extract title, author, site, date, and article body.
  • Convert output to Markdown, JSON, or plain text for easy reuse in notes or research workflows.
  • Use case: clip long-form articles for Obsidian or knowledge bases, or preprocess web content for summaries.

Quick Start

Provide a URL or HTML snippet to extract the clean article content.

Frequently Asked Questions about defuddle-web-cleaner

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract readable article content from a web page and remove ads or sidebars?▼

Web content extraction isolates the main article body by stripping navigation bars, ads, and sidebars. This Skill parses HTML inputs to deliver clean text, detecting the input type and returning structured article content.

Can I convert web page content into Markdown for note-taking in Obsidian?▼

Yes, you can convert web pages into Markdown for Obsidian. The parser extracts the title, author, site, and date, then outputs the clean article body as Markdown, making it directly usable for knowledge base clipping.

What is the best way to get structured metadata from raw HTML?▼

Extracting structured metadata from raw HTML involves parsing the document to identify title, author, and date fields. This Skill processes raw HTML snippets and returns the extracted metadata alongside the article content in JSON format.

Does this web content extraction tool work with both URLs and raw HTML inputs?▼

Yes, the tool works with URLs, raw HTML, and text inputs. It automatically detects the input type you provide, loads the corresponding page content, and runs the parser to extract the readable article text.

What output formats can I get when extracting article text from web pages?▼

You can get clean article content in Markdown, JSON, or plain text formats. This allows for easy reuse in research workflows, note-taking applications, or preprocessing pipelines for summaries.

Why should I use a dedicated article extractor instead of manual web scraping for research?▼

A dedicated article extractor distinguishes main content from page clutter automatically, saving time over manual web scraping. It identifies metadata and body text directly, providing structured output ready for research and note-taking workflows.

Related Skills

Explore More Education & Research Skills→
sockerman04sockerman04

web-reader

utility placeholder

Community
Intermediate
rnbenrnben

feishu-content-extraction

Extract Feishu article content from embedded JSON via curl.

Community
Intermediate
skkarkiskkarki

web-reader

Extract web page content and metadata via CLI or SDK.

Community
Advanced
nicepkgnicepkg
276

article-extractor

Extract clean article text from web URLs and save as a text file.

Official
Intermediate