# dadehi.com - robots.txt
# Site: https://www.dadehi.com/
# Generated 2026-10-29

# ---------- Search engines (general) ----------
User-agent: *
Disallow: /captcha.html
Disallow: /404.html
Allow: /

Sitemap: https://www.dadehi.com/sitemap.xml

# ---------- AI search and citation crawlers (allowed) ----------
User-agent: OAI-SearchBot
Disallow: /captcha.html
Disallow: /404.html

Allow: /

User-agent: ChatGPT-User
Disallow: /captcha.html
Disallow: /404.html

Allow: /

User-agent: Claude-SearchBot
Disallow: /captcha.html
Disallow: /404.html

Allow: /

User-agent: PerplexityBot
Disallow: /captcha.html
Disallow: /404.html

Allow: /

User-agent: Perplexity-User
Disallow: /captcha.html
Disallow: /404.html

Allow: /

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

# ---------- AI model training crawlers ----------
# These crawlers collect content for model training. Change any Allow below to
# Disallow if you do not want the site used for training. Search and citation
# access above is unaffected.
User-agent: GPTBot
Disallow: /captcha.html
Disallow: /404.html
Allow: /

User-agent: ClaudeBot
Disallow: /captcha.html
Disallow: /404.html
Allow: /

User-agent: CCBot
Disallow: /captcha.html
Disallow: /404.html
Allow: /

User-agent: Google-Extended
Disallow: /captcha.html
Disallow: /404.html
Allow: /

User-agent: Applebot-Extended
Disallow: /captcha.html
Disallow: /404.html
Allow: /

User-agent: Bytespider
Disallow: /captcha.html
Disallow: /404.html
Allow: /

User-agent: Meta-ExternalAgent
Disallow: /captcha.html
Disallow: /404.html
Allow: /

# ---------- Yandex parameter cleanup ----------
Clean-param: utm_source&utm_medium&utm_campaign&utm_term&utm_content&ref&fbclid&gclid&msclkid