CyberSecurity
Back to postsCyberSecurity
Thoth: Scraping the Dark Web Without Trusting the Dark Web
Thoth is a dark web scraper built for cyber threat intelligence. It takes a raw analyst query, rewrites it into a compact CTI search phrase, fans it out across multiple .onion search engines over Tor, deduplicates the results, asks an LLM to rank the most relevant links, scrapes the selected pages under hard safety limits, and converts the harvested text into structured intelligence.