# Robots.txt for CartoonPorn.to
# Optimized for SEO and crawl efficiency

# Default rules for all bots
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /trackback/
Disallow: /*?s=
Disallow: /*?p=
Disallow: /*&preview=
Disallow: /cgi-bin/
Disallow: /author/
Disallow: /*.php$
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /tiktok-tag/
Disallow: /*?m_orderby=
Disallow: /*?page=

# Allow important resources for rendering
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-includes/js/
Allow: /wp-includes/css/

# Google specific
User-agent: Googlebot
Allow: /
Crawl-delay: 1

# Google Image Bot
User-agent: Googlebot-Image
Allow: /wp-content/uploads/

# Bing specific
User-agent: Bingbot
Allow: /
Crawl-delay: 2

# Yandex
User-agent: Yandex
Allow: /
Crawl-delay: 3

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /
Crawl-delay: 2

# Block bad bots (scrapers/crawlers that don't provide value)
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

# Block AI training bots (but allow AI search bots for visibility)
User-agent: CCBot
Disallow: /

User-agent: Omgilibot
Disallow: /

# Allow Google-Extended (Gemini/AI Overviews grounding)
User-agent: Google-Extended
Allow: /
Crawl-delay: 2

# Allow AI search bots (for Google AI Overviews, Perplexity, ChatGPT search)
User-agent: GPTBot
Allow: /
Crawl-delay: 2

User-agent: PerplexityBot
Allow: /
Crawl-delay: 2

User-agent: anthropic-ai
Allow: /
Crawl-delay: 2

User-agent: Claude-Web
Allow: /
Crawl-delay: 2

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 2

User-agent: FacebookBot
Allow: /

# Sitemap location (single authoritative source)
Sitemap: https://cartoonporn.to/sitemap_index.xml

# LLMs.txt for AI context
# https://cartoonporn.to/llms.txt

# Host directive
Host: https://cartoonporn.to