Extract article content and metadata from web pages.
A Defuddle connector for metascraper
Smart web_fetch with desktop-browser TLS impersonation and defuddle extraction.
OpenClaw web fetch plugin with desktop-browser TLS impersonation and defuddle extraction.
n8n node to extract main content from webpages using Defuddle library
Smart web fetch CLI with desktop-browser TLS impersonation and defuddle extraction.
Fetch content from the web, cleaned up nicely for LLMs (using Defuddle)
Web content extraction for pi — fetch any URL as clean Markdown using Defuddle
Claude Code skill for defuddle - extract clean article content from web pages
n8n community node that wraps Defuddle for HTML content extraction (fetch HTML with the HTTP Request node).
Fetch content from the web, cleaned up nicely for LLMs (using Defuddle)
Extract readable article content and metadata from HTML (Defuddle-powered, Obsidian Clipper–style pipeline)
Extract article content and metadata from web pages (FlickNote fork, optimized for linkedom/Cloudflare Workers)
Extract main content and metadata from HTML pages. Works in browser and Node.js.
MCP server for extracting clean article content from web pages
Extract article content and metadata from web pages (with HTTP proxy support).
PagePocket unit: extract main content from captured HTML using defuddle and rewrite resource URLs to local paths
Intelligent web research for Pi: search, extract, collate, and cache grounded web context in one tool call.
An MCP server for fetching web content in whatever form you need. Every page is first rendered with a headless Chromium (Playwright) so JavaScript-rendered content is captured, then returned as clean Markdown, raw HTML, or a screenshot. Rendered HTML is c
Get X, WeChat, and web articles as Obsidian-friendly Markdown.
CLI tool to extract web content using SimpRead rules and convert to Markdown
n8n node to fetch a URL and convert the page to clean Markdown
Astro integration for full-content RSS, Atom, and JSON feeds.
Mirror Pinboard bookmarks into an Obsidian vault, enriched with extracted page content.
A Rust library for extracting main content and metadata from HTML web pages
Extract clean, readable content from web pages
A fast, secure MCP server that extends its capabilities through WebAssembly plugins
A web content extraction library that removes clutter from web pages