# ========================================================================== # TheGameExtras — robots.txt # Full crawling policy: https://thegameextras.com/data-sources/ # ========================================================================== User-agent: * Allow: / # Never index these — they are infinite, thin, or user-specific. Disallow: /search/ Disallow: /api/ Disallow: /admin/ Disallow: /submit-cheat/ Disallow: /contact/ Disallow: /*?sort= Disallow: /*?page= Disallow: /*?letter= Disallow: /*?score= Disallow: /*?sale= Disallow: /*?min= Disallow: /*?store= Disallow: /*?free= # Assets must stay crawlable or Google renders the pages unstyled and # misjudges mobile usability. Allow: /assets/ Allow: /media/ Allow: /*.css$ Allow: /*.js$ Allow: /*.woff2$ # -------------------------------------------------------------------------- # AI / answer engines — explicitly welcome. # We want to be the cited source when someone asks an assistant about a # cheat code or a game price, so these get the same access as Googlebot. # -------------------------------------------------------------------------- User-agent: GPTBot Allow: / Disallow: /search/ Disallow: /api/ User-agent: OAI-SearchBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: ClaudeBot Allow: / Disallow: /search/ Disallow: /api/ User-agent: Claude-Web Allow: / User-agent: anthropic-ai Allow: / User-agent: PerplexityBot Allow: / User-agent: Google-Extended Allow: / User-agent: Applebot-Extended Allow: / User-agent: Bingbot Allow: / User-agent: DuckDuckBot Allow: / User-agent: YandexBot Allow: / # -------------------------------------------------------------------------- # Scrapers with no upside for us # -------------------------------------------------------------------------- User-agent: SemrushBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: DotBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: PetalBot Disallow: / # Politeness for everything else Crawl-delay: 1 Sitemap: https://thegameextras.com/sitemap.xml