# robots.txt for www.jains.com
# Updated: 2026-05-27
# Generator: SEO audit — Step 3

# ======================================================
# ALLOW ALL MAJOR SEARCH ENGINES
# ======================================================

User-agent: Googlebot
Allow: /
Disallow: /search/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /admin/
Disallow: /includes/
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Disallow: /search/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /admin/
Crawl-delay: 2

User-agent: Slurp
Allow: /
Disallow: /search/
Disallow: /admin/

# ======================================================
# ALLOW AI CRAWLERS (for AI engine visibility)
# ======================================================

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /
Disallow: /admin/
Disallow: /cgi-bin/

# OpenAI web browse
User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude
User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google Gemini / AI Overview
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

# Microsoft Copilot
User-agent: msnbot
Allow: /

# Common AI research crawlers
User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

# ======================================================
# BLOCK BAD BOTS (saves bandwidth, prevents scraping)
# ======================================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ======================================================
# DEFAULT RULE FOR ALL OTHER BOTS
# ======================================================

User-agent: *
Allow: /
Disallow: /search/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /admin/
Disallow: /includes/
Disallow: /*.pdf$
Crawl-delay: 5

# ======================================================
# SITEMAP LOCATION
# ======================================================

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