Michael Yousrie

Full-stack engineer with 8+ years building production APIs and data pipelines — now focused on the AI/LLM side.

I build web-scraping & data-extraction Actors that turn the messy public web into clean, structured, LLM-ready data for RAG indexes, agents, and fine-tuning sets.

• Clean output — Markdown/JSON, boilerplate stripped.
• Honest pricing — pay-per-result: only charged for data you actually get.
• Solid docs — clear schemas and examples; running in minutes.
• Maintained — I use these tools myself.

• LLM-Ready Web Extractor  — any URL or site → clean Markdown/JSON for LLMs, RAG, agents.
• PDF to Markdown & JSON Extractor  — any PDF → clean Markdown/JSON with tables and metadata.
• SEO Audit & Site Health Checker  — crawl a site for per-page SEO issues and a health score.
• Job Board Scraper — Greenhouse, Lever & Ashby  — filter open jobs across three ATS platforms.
• App Store & Google Play Reviews Scraper  — app reviews & ratings from both stores.
• Stack Overflow & Stack Exchange Q&A Scraper  — Q&A from any SE site.
• llms.txt Generator  — make any website LLM-ready.
• Hacker News Scraper  — stories & comments search API.
• Bluesky Scraper  — posts, profiles & followers.