# Default — allow all crawlers, with backend path exceptions below
User-agent: *
Allow: /
Disallow: /uploads/
Disallow: /pdfs/
Disallow: /generate_pdf.php
Disallow: /generate_pdf_template
Disallow: /download.php
Disallow: /submit_contact.php
Disallow: /success.php
Disallow: /fpdf/
Disallow: /fpdi/
Disallow: /tcpdf/
Disallow: /razorpay-php/
Disallow: /error_log

# Explicitly welcome AI crawlers (some hosts auto-block these)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Sitemap
Sitemap: https://www.mymarriagebiodata.in/sitemap.xml

# AI-friendly content guide (emerging standard for LLM crawlers)
# See: https://www.mymarriagebiodata.in/llms.txt