# Robots.txt for Truthy Systems
# Allow all search engines to crawl the site

User-agent: *
Allow: /

# Disallow crawling of admin areas and sensitive files
Disallow: /admin/
Disallow: /_next/
Disallow: /api/
Disallow: /*.json$
Disallow: /*.xml$
Disallow: /sitemap*.xml

# Allow specific files that should be crawled
Allow: /sitemap.xml
Allow: /robots.txt
Allow: /manifest.json

# Crawl-delay for polite crawling (1 second)
Crawl-delay: 1

# Sitemap location
Sitemap: https://truthy-systems-web-app.web.app/sitemap.xml

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 1

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

# Block unwanted bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SemrushBot
Disallow: /