web-article-extractor

Community

Automate web article extraction, including WeChat content.

Authordongbeixiaohuo
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the extraction and transformation of web articles into structured data, enabling quick integration into knowledge bases, summaries, and content workflows. It excels at handling articles from diverse sources, including 微信公众号 (WeChat) articles, which often have dynamic content and safety constraints.

Core Features & Use Cases

  • Automated article extraction: Extracts title, author, publish date, content, images, and metadata from web pages.
  • Markdown export ready: Converts content to Markdown with YAML front matter for easy publishing and archiving.
  • Image handling: Downloads embedded images and updates references to local paths for offline use.
  • WeChat support: Includes specialized flows for 微信公众号 content with configurable user-agent and selectors.
  • Use Case: Create a personal knowledge library by batch extracting articles from blogs, news sites, and WeChat public accounts.

Quick Start

Use the web-article-extractor skill to extract content from a URL, e.g. https://example.com/article

Dependency Matrix

Required Modules

fspathhttpshttpurl

Components

scriptsreferences

💻 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: web-article-extractor
Download link: https://github.com/dongbeixiaohuo/writing-agent/archive/main.zip#web-article-extractor

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 223,000+ vetted skills library on demand.