Show HN: Robust LLM Extractor for Websites in TypeScript

We&#x27;ve been building data pipelines that scrape websites and extract structured data for a while now. If you&#x27;ve done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers.<p>LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it&#x27;s more painful than that:<p>- Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you&#x27;d expect, especially with nested arrays and complex schemas. One bad bracket and your pipeline crashes. - Relative URLs, markdown-escaped links, tracking parameters — the &quot;small&quot; URL issues compound fast when you&#x27;re processing thousands of pages. - You end up writing the same boilerplate: HTML cleanup → markdown conversion → LLM call → JSON parsing → error recovery → schema validation. O