AgentSkillsCN

article-extraction

从网页中提取干净的文章内容，去除广告和杂乱元素，便于阅读和存档

SKILL.md
--- frontmatter
name: article-extraction
description: Extract clean article content from web pages, removing ads and clutter for reading and archiving

Article Extraction Skill

Extract clean article text from web pages, removing ads, navigation, and clutter.

When to Use

  • •Content archiving
  • •Research collection
  • •Reading list management
  • •Content analysis

Core Capabilities

  • •Main content extraction
  • •Metadata extraction (title, author, date)
  • •Image extraction
  • •Clean HTML/Markdown output
  • •Multi-page article handling
  • •Paywall bypass (where legal)

Tools

bash
# Readability (Node.js)
npm install @mozilla/readability

# newspaper3k (Python)
pip install newspaper3k
python -c "from newspaper import Article; a = Article('URL'); a.download(); a.parse(); print(a.text)"

# Trafilatura (Python)
pip install trafilatura
trafilatura -u "URL"

Best Practices

  • •Respect robots.txt
  • •Cache extracted content
  • •Preserve attribution
  • •Handle different CMS formats

Resources