High Yield Asset Engine: Self-hosted Python & Claude AI web data extraction toolkit

Hey Product Hunt community! 👋 I’m Simon, solo maker behind HYAE (High Yield Asset Engine). I built HYAE because traditional web scrapers constantly break when target sites change layouts, and cloud extraction APIs can quickly get absurdly expensive. HYAE is a self-hosted, lightweight engine that pairs standard polite scraping (respecting robots.txt, rate limits, and crawl delays) with Claude AI. Instead of writing complex CSS/XPath selectors, Claude dynamically parses unstructured HTML into clean JSON or CSV data pipelines. Key highlights: 🎛️ Simple YAML configurations 🤖 Claude-powered flexible data extraction 🛡️ Built-in polite crawling & anti-block protections 💻 100% self-hosted — your data stays under your control I'd love to hear your thoughts, feedback, or any questions about self-hosting or scraping workflows!