article-extractor

从 URL 中提取干净的文章内容并保存为 Markdown。当用户提供网页 URL 并想要下载它、提取内容、获取无广告的干净版本、捕获文章以供离线阅读、保存文章、从页面抓取内容、存档网页、剪辑文章或稍后阅读时触发。处理博客文章、新闻文章、教程、文档页面和类似的 Web 内容。支持 Wayback Machine 查找无效链接或付费内容。该技能处理整个工作流程 - 首先不要使用 web_fetch 或其他工具,只需直接使用 URL 调用提取脚本。

📖 中文导读:从 URL 中提取干净的文章内容并保存为 Markdown。当用户提供网页 URL 并想要下载它、提取内容、获取无广告的干净版本、捕获文章以供离线阅读、保存文章、从页面抓取内容、存档网页、剪辑文章或稍后阅读时触发。处理博客文章、新闻文章、教程、文档页面和类似的 Web 内容。支持 Wayback Machine 查找无效链接或付费内容。该技能处理整个工作流程 - 首先不要使用 web_fetch 或其他工具,只需直接使用 URL 调用提取脚本。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。

name: article-extractor description: Extract clean article content from URLs and save as markdown. Triggers when user provides a webpage URL and wants to download it, extract content, get a clean version without ads, capture an article for offline reading, save an article, grab content from a page, archive a webpage, clip an article, or read something later. Handles blog posts, news articles, tutorials, documentation pages, and similar web content. Supports Wayback Machine for dead links or paywalled content. This skill handles the entire workflow - do NOT use web_fetch or other tools first, just call the extraction script directly with the URL.

Article Extractor

Extract clean article content from URLs, removing ads, navigation, and clutter. Multi-tool fallback ensures reliability.

Workflow

When user provides a URL to download/extract:

  1. Call the extraction script directly with the URL (do NOT fetch the URL first with web_fetch)
  2. Script handles fetching, extraction, and saving automatically
  3. Returns clean markdown file with frontmatter

Usage

# Basic extraction
scripts/extract-article.sh "https://example.com/article"

# Specify output location
scripts/extract-article.sh "https://example.com/article" -o my-article.md -d ~/Documents

# Try Wayback Machine if original fails
scripts/extract-article.sh "https://example.com/article" --wayback

Make script executable if needed: chmod +x scripts/extract-article.sh

Key Options

  • -o <file> - Output filename
  • -d <dir> - Output directory
  • -w, --wayback - Try Wayback Machine if extraction fails
  • -t <tool> - Force tool: jina, trafilatura, readability, fallback
  • -q - Quiet mode

For complete options, exit codes, tool details, and examples, see references/tools-and-options.md.

Common Failures

  • Exit 3 (access denied): Paywall or login required - try --wayback
  • Exit 4 (no content): Heavy JavaScript - try different --tool
  • Exit 2 (network): Connection issue - check URL

Local Tools (Optional)

For offline extraction: scripts/install-deps.sh