# Rahber Quran Institute — robots.txt
# Canonical host: https://rahberquraninstitute.com
# Last reviewed: 2026-06-10

# ─────────────────────────────────────────────────────────────
# Default: allow all crawlers, block private / system / param-noise
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /api/
Disallow: /lovable/
Disallow: /*?*utm_
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*ref=
Disallow: /*?*session=
Disallow: /*?*sessionid=
Disallow: /*?*sort=
Disallow: /*?*filter=

# ─────────────────────────────────────────────────────────────
# Major search engines (explicit allow for clarity)
# ─────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: Bingbot
Allow: /

User-agent: BingPreview
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: YandexImages
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Baiduspider-image
Allow: /

User-agent: Applebot
Allow: /

User-agent: Sogou web spider
Allow: /

User-agent: Naverbot
Allow: /

User-agent: Yeti
Allow: /

User-agent: SeznamBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterestbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# ─────────────────────────────────────────────────────────────
# AI / LLM crawlers (explicit allow — opt-in to AI search visibility)
# ─────────────────────────────────────────────────────────────
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Diffbot
Allow: /

User-agent: AwarioBot
Allow: /

User-agent: PetalBot
Allow: /

User-agent: AI2Bot
Allow: /

User-agent: Timpibot
Allow: /

User-agent: Webzio-Extended
Allow: /

User-agent: ImagesiftBot
Allow: /

# ─────────────────────────────────────────────────────────────
# Sitemaps (index + per-locale + legacy single sitemap)
# ─────────────────────────────────────────────────────────────
Sitemap: https://rahberquraninstitute.com/sitemap-index.xml
Sitemap: https://rahberquraninstitute.com/sitemap.xml
Sitemap: https://rahberquraninstitute.com/sitemap-en-us.xml
Sitemap: https://rahberquraninstitute.com/sitemap-en-gb.xml
Sitemap: https://rahberquraninstitute.com/sitemap-en-ca.xml
Sitemap: https://rahberquraninstitute.com/sitemap-en-au.xml
Sitemap: https://rahberquraninstitute.com/sitemap-en-nz.xml
Sitemap: https://rahberquraninstitute.com/sitemap-en.xml

# Host directive (Yandex)
Host: https://rahberquraninstitute.com