zclaw-web-content-fetcher

Community

Extract clean web content into Markdown

Authorzeerd
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Manually extracting and formatting web article content is tedious and error-prone. This skill automatically retrieves the main article content from URLs and converts it into clean Markdown, preserving headings, links, images, and lists, and supports sources like WeChat articles and Weibo posts.

Core Features & Use Cases

  • Extracts and converts web pages into Markdown with headings, links, images, and lists.
  • Uses a three-tier extraction strategy: Playwright for dynamic pages, Scrapling+html2text for broad coverage (including many blogs), and web_fetch as a static fallback.
  • Preserves titles, URLs, images, and list structures for easy reuse in notes, docs, or content pipelines.

Quick Start

Tell me a URL to fetch and I will return its clean Markdown content.

Dependency Matrix

Required Modules

scrapling[fetchers]html2textplaywright

Components

scripts

💻 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: zclaw-web-content-fetcher
Download link: https://github.com/zeerd/zClaw-Skills/archive/main.zip#zclaw-web-content-fetcher

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.