# Food Institute - Robots.txt
# Updated: 2026-01-11

# Allow major search engines (Google, Bing) full access
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# AI Training Bots - Follow same rules as llms.txt
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: anthropic-ai
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-content/uploads/ewww/
Disallow: /wp-content/uploads/ewww-3/
Disallow: /wp-json/
Disallow: /ewww/
Disallow: /ewww-3/
Disallow: /cgi-bin/
Disallow: /.well-known/
Disallow: /securefile/
Disallow: /.sucuriquarantine/
Disallow: /reports/2020/
Disallow: /reports/2021/
Disallow: /reports/2022/
Disallow: /reports/2023/
Disallow: /reports/eco/
Disallow: /reports/fir/
Disallow: /reports/du_pdf/
Disallow: /reports/join/
Disallow: /reports/mcith/
Disallow: /food1/
Disallow: /test-site/
Disallow: /feed/
Disallow: /trackback/
Disallow: /xmlrpc.php
Disallow: /*?
Disallow: /*.php$
Disallow: /*.js$
Disallow: /*.css$
Disallow: /comments/
Disallow: /author/
Disallow: /tag/
Disallow: /page/

# Commercial SEO Bots - Block entirely (also in .htaccess)
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: SERankingBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: SEOkicks
User-agent: Barkrowler
User-agent: Netvibes
User-agent: Amazonbot
Disallow: /

# Known Rule-Breakers - Block entirely (also in .htaccess)
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Bytespider
User-agent: CCBot
User-agent: Omgilibot
User-agent: webzio-extended
User-agent: ImagesiftBot
Disallow: /

# Sitemap location (optional - WordPress generates this)
Sitemap: https://foodinstitute.com/sitemap.xml