# TRI NORTHWEST - Pacific Northwest Triathlon Hub
# https://tri-northwest.com

# --- Allowed: search engines & AI assistants that drive traffic or citations ---
# Google, Bing, Apple, DuckDuckGo, OAI-SearchBot, ChatGPT-User, PerplexityBot,
# and social previewers (facebookexternalhit) surface our events to users.
User-agent: *
Allow: /
Disallow: /api/
Disallow: /cdn-cgi/
Disallow: /event_images/
Disallow: /event_images_sm/
Disallow: /rd_images/
Disallow: /ows_images/
Disallow: /gear_logo/
Disallow: /misc_images/
Disallow: /club_logos/
Disallow: /favicons/
Disallow: /triathlon-101/*.avif
Disallow: /triathlon-101/*.webp
Disallow: /fun_scale.avif
Disallow: /george-la-tri.avif
Disallow: /goals.avif
Disallow: /map-preview.avif
Disallow: /race_ready.avif
Disallow: /tri_northwest_hero.avif
Disallow: /sbrlogo.avif
Disallow: /PNWTR-logo-text.svg
Disallow: /_build/
Disallow: /.vercel/

# --- Deliberately NOT disallowed: icons Google must be able to fetch ---
# /favicon.ico, /favicon.svg, /apple-touch-icon.png, /site.webmanifest and the
# two web-app-manifest PNGs are all valid favicon sources Google's crawler
# selects from for the search-result icon. web-app-manifest-512x512.png is also
# the Organization "logo" in our JSON-LD. Blocking any of them risks a fallback
# globe in the SERP and an unusable logo in structured data. They total ~42 KB;
# there is no crawl budget worth saving here. Do not re-add these.

# --- Block: AI training crawlers (bandwidth cost, no traffic benefit) ---
User-agent: Amazonbot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-User
Allow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: ProRataInc
Disallow: /

User-agent: YouBot
Disallow: /

# --- Block: pure scrapers with no ranking or referral benefit ---
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MajesticBot
Disallow: /

User-agent: Sogouwebspider
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BDBrandProtect
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: SiteAuditBot
Disallow: /

Sitemap: https://tri-northwest.com/sitemap.xml