# ── General rules ────────────────────────────────────────────────────────
User-agent: *
Disallow: /api/
Disallow: /auth/
Disallow: /profile/
Disallow: /_next/
Disallow: /maintenance/

Allow: /
Allow: /calculators/
Allow: /calculators/*
Allow: /drugs/
Allow: /drugs/*
Allow: /guidelines/
Allow: /guidelines/*
Allow: /about
Allow: /contact
Allow: /privacy
Allow: /terms
Allow: /disclaimer
Allow: /editorial
Allow: /cookies

# ── AI / training crawlers ──────────────────────────────────────────────
# Honor-system opt-out for compliant bots. Non-compliant ones are hard-blocked
# at the edge in middleware.js regardless of what they do here.
#
# GEO exception: real-time answer-lookup bots (fetch triggered by a live user
# query, not bulk training) are explicitly allowed so this content can be
# cited in AI answers. Bulk trainers stay blocked below.
User-agent: OAI-SearchBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Claude-SearchBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: FriendlyCrawler
Disallow: /

# Sitemap Index
Sitemap: https://www.opicalc.com/sitemap.xml


# ── Sogou: block static assets (wastes crawl budget on build artifacts) ──
User-agent: Sogou Spider
Disallow: /_next/


# ── SEO / competitor crawlers ─────────────────────────────────────────
# These bots scrape on a schedule to power competitor intelligence tools.
# None of them drive real user traffic to your site. Allow is moot — they
# are also blocked at the edge in middleware.js — but the explicit
# Disallow here is the honor-system signal Ahrefs / Semrush / Majestic
# check first.
User-agent: AhrefsBot
Disallow: /

User-agent: AhrefsSiteAudit
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SemrushAudit
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: Sitebulb
Disallow: /

User-agent: SEOkicks
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

User-agent: DeepCrawl
Disallow: /

User-agent: Lumar
Disallow: /

User-agent: OnCrawl
Disallow: /

User-agent: Botify
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: CrystalIntelligence
Disallow: /

User-agent: YisouSpider
Disallow: /

User-agent: BUbiNG
Disallow: /

# ── Uptime / monitoring bots ─────────────────────────────────────────
# These probe the site from datacenters. None of them represent user
# traffic. Blocked at the edge in middleware.js.
User-agent: UptimeRobot
Disallow: /

User-agent: Pingdom
Disallow: /

User-agent: Site24x7
Disallow: /

User-agent: StatusCake
Disallow: /

User-agent: GTmetrix
Disallow: /

User-agent: Lighthouse
Disallow: /

User-agent: WebPageTest
Disallow: /