# ========================================================= # Welcome to Ustadio's robots.txt # ========================================================= User-agent: * # Disallow access to system/core/internal directories Disallow: /admin/ Disallow: /api/ Disallow: /components/ Disallow: /config/ Disallow: /includes/ Disallow: /libs/ Disallow: /seo/ Disallow: /services/ Disallow: /views/ # --------------------------------------------------------- # Sitemaps # --------------------------------------------------------- Sitemap: https://ustadio.com/sitemap.xml Sitemap: https://ustadio.com/sitemap-static.xml Sitemap: https://ustadio.com/sitemap-tutors.xml Sitemap: https://ustadio.com/sitemap-cities.xml Sitemap: https://ustadio.com/sitemap-subjects.xml Sitemap: https://ustadio.com/sitemap-levels.xml Sitemap: https://ustadio.com/sitemap-exams.xml # Disallow specific scripts and sensitive files Disallow: /setupdb Disallow: /alterdb Disallow: /setup_db.php Disallow: /alter_db.php Disallow: /*.sql$ # Prevent indexing of chaotic query parameters Disallow: /*?sort=* Disallow: /*?filter=* Disallow: /*&sort=* Disallow: /*&filter=* Disallow: /*?q=* Disallow: /*?search=* Disallow: /*?category=* Disallow: /*?slug=* # --------------------------------------------------------- # Search Engine Bots # --------------------------------------------------------- User-agent: Googlebot Allow: / User-agent: Bingbot Allow: / User-agent: Slurp Allow: / User-agent: DuckDuckBot Allow: / User-agent: Baiduspider Allow: / User-agent: YandexBot Allow: / # --------------------------------------------------------- # Ad Bots # --------------------------------------------------------- User-agent: Mediapartners-Google Allow: / User-agent: AdsBot-Google Allow: / User-agent: AdsBot-Google-Mobile Allow: / # --------------------------------------------------------- # IMAGE CRAWLERS - ALLOWED: OG, Twitter, Tutor Photos, Logos # --------------------------------------------------------- # GOOGLE IMAGE BOT User-agent: Googlebot-Image # FIRST: Block EVERYTHING in images folder Disallow: /assets/images/ # THEN: Allow the specific allowed folders Allow: /assets/images/og-images/ Allow: /assets/images/tutors/profile-photos/ # Allow specific logo files (even if they're in blocked folders) Allow: /assets/images/ustadio_logo.png # THEN: Block the default avatars WITHIN the allowed tutor folder Disallow: /assets/images/tutors/profile-photos/male-avatar.png Disallow: /assets/images/tutors/profile-photos/female-avatar.png Disallow: /*.svg$ Disallow: /*.webp$ # BING IMAGE BOT User-agent: Bingbot-Image # Block EVERYTHING first Disallow: /assets/images/ # Allow the specific allowed folders Allow: /assets/images/og-images/ Allow: /assets/images/tutors/profile-photos/ # Allow specific logo files (even if they're in blocked folders) Allow: /assets/images/ustadio_logo.png # Block default avatars Disallow: /assets/images/tutors/profile-photos/male-avatar.png Disallow: /assets/images/tutors/profile-photos/female-avatar.png # Block SVGs and WebPs Disallow: /*.svg$ Disallow: /*.webp$ User-agent: ChatGPT-User Allow: / User-agent: OAI-SearchBot Allow: / User-agent: Claude-Web Allow: / User-agent: PerplexityBot Allow: / # --------------------------------------------------------- # AI / LLM Scrapers (Block entirely) # --------------------------------------------------------- User-agent: CCBot Disallow: / User-agent: GPTBot Disallow: / User-agent: Google-Extended Disallow: / User-agent: Anthropic-ai Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Omgili Disallow: / User-agent: Omgilibot Disallow: / User-agent: FacebookBot Disallow: / User-agent: Diffbot Disallow: / User-agent: Bytespider Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: Cohere-ai Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Amazonbot Disallow: / # --------------------------------------------------------- # SEO Audit Scraping Bots (Aggressive) # --------------------------------------------------------- User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: /