# Chapeau Media Robots.txt
# Last updated: 2025-05-07

# Main directives
User-agent: *
Allow: /
Disallow: /404
Disallow: /api/
Disallow: /*.json$

# XML Sitemap location
Sitemap: https://chapeaumedia.it/sitemap.xml

# Specific search engine bots
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Googlebot-Image
Allow: /
Crawl-delay: 1

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

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

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

# Social media bots - allow them to crawl the site for social cards
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# Archive bots - control how your site is archived
User-agent: ia_archiver
Crawl-delay: 2

# Allow AI web crawlers with a stricter crawl delay
User-agent: GPTBot
Allow: /
Crawl-delay: 5

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 5