fetching-web-content

Community

Fetch pages and get clean markdown fast

Authorleba01
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Fetching web pages for reading or scraping often returns messy HTML packed with navigation, ads, boilerplate, and sometimes blocked-by-bot responses instead of usable content.

Core Features & Use Cases

  • Clean LLM-ready markdown output: Strips navigation, ads, and boilerplate into readable markdown.
  • Automatic anti-bot bypass: Detects common blocks (e.g., Cloudflare/DataDome/PerimeterX/Akamai) and escalates from HTTP fetching to a stealth browser when needed.
  • Optional metadata extraction: Produces a FetchResult with markdown plus page fields like title, author, date, description, canonical URL, hostname, and sitename.
  • Built-in SSRF protection: Validates URLs to reject private/loopback destinations.

Quick Start

Use the fetching-web-content skill to fetch https://en.wikipedia.org/wiki/Web_scraping and return the page as cleaned markdown.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: fetching-web-content
Download link: https://github.com/leba01/stealthfetch/archive/main.zip#fetching-web-content

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.