# South Asian PR - robots.txt
# This file controls search engine crawling and indexing

# Allow all search engines to crawl the site
User-agent: *
Allow: /
Disallow: /admin
Disallow: /*.json$
Disallow: /*.pdf$
Disallow: /private/
Disallow: /temp/
Disallow: /cache/

# Specific rules for Google
User-agent: Googlebot
Allow: /
Crawl-delay: 0

# Specific rules for Bing
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# Specific rules for AI crawlers (Claude, GPT, Perplexity, etc.)
User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OpenAI-User
Allow: /

User-agent: Perplexity
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Disallow bad bots
User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

# Sitemap location
Sitemap: https://www.southasianpr.com/sitemap.xml
Sitemap: https://www.southasianpr.com/rss.xml

# RSS Feed
# Available at: https://www.southasianpr.com/rss.xml