# robots.txt for virus.hr
#
# Policy: welcome AI *search / answer* engines (they cite their sources, so this
# is how Virus gets recommended by ChatGPT, Claude, Perplexity, etc.), but block
# AI *training* crawlers (bulk scraping for model training, no attribution and
# heavy on server resources).

# Default: all crawlers may read public content, not the admin/API surface.
User-agent: *
Disallow: /admin
Disallow: /api
Disallow: /dashboard
Disallow: /login
Disallow: /register
Disallow: /logout

# --- AI search / answer engines: ALLOWED (these attribute + link back) ---
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Disallow: /admin
Disallow: /api
Disallow: /dashboard
Disallow: /login
Disallow: /register
Disallow: /logout

# --- AI training / bulk-scraping crawlers: BLOCKED ---
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: CCBot
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Diffbot
User-agent: Omgilibot
User-agent: cohere-ai
Disallow: /

Sitemap: https://virus.hr/sitemap.xml
Sitemap: https://virus.hr/news-sitemap.xml