vifreefly/nukitori

Nukitori is a Ruby gem for HTML data extraction. It uses an LLM once to generate reusable XPath schemas, then extracts structured data from similarly structured pages using plain Nokogiri. This makes scraping fast, predictable, and cheap for repeated runs.

1 best points · 0 comments · 1 Hacker News post · 30 GitHub stars · View on GitHub

Hacker News discussions

• Nukitori is a Ruby gem for HTML data extraction (1 points, 0 comments, by thunderbong, 2026-01-13)