# ============================================================================
#  robots.txt — 1sh.site
#  Child-directed math games website (COPPA-compliant)
#  Last updated: 2025
# ============================================================================
#
# This robots.txt file guides search engine crawlers and AdSense bots.
# We ALLOW all major search engines and ad networks to crawl the entire site,
# because all content is original, public, and child-safe.
#
# We BLOCK only known bad bots and scrapers to protect our original content.
# ============================================================================

# ---- Default rule: allow all crawlers access to everything ----
User-agent: *
Allow: /
Disallow:

# ---- Explicitly allow Google AdSense crawler ----
User-agent: Mediapartners-Google
Allow: /
Disallow:

# ---- Explicitly allow Google AdsBot ----
User-agent: AdsBot-Google
Allow: /
Disallow:

# ---- Explicitly allow Googlebot (all variants) ----
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

# ---- Explicitly allow Bing ----
User-agent: Bingbot
Allow: /

# ---- Explicitly allow Yandex and Baidu ----
User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

# ---- Explicitly allow Apple, DuckDuckGo, Slurp (Yahoo) ----
User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

# ---- BLOCK content scrapers and AI training bots (protect original content) ----
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Claude-User
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Sogou web spider
Disallow: /

# ---- BLOCK generic bad bots ----
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ---- Crawl delay (polite crawling) ----
Crawl-delay: 1

# ---- Sitemap location ----
Sitemap: https://1sh.site/sitemap.xml

# ---- Host (preferred domain) ----
Host: https://1sh.site/