# Robots.txt for Criazo Digital Marketing Agency
# https://criazo.com
# Indexable by major search engines. High-volume AI/SEO crawlers are blocked to
# keep server CPU low.

User-agent: *
Allow: /
Crawl-delay: 10

# Sitemaps - /sitemap.xml is the index (general, services, portfolio, industries, locations, industries-locations)
Sitemap: https://criazo.com/sitemap.xml

# Disallow admin and dashboard areas
Disallow: /dashboard/
Disallow: /api/

# Disallow search results pages (low value for SEO)
Disallow: /search
Disallow: /language/
Disallow: /*?hl=
Disallow: /*?hl=*

# Disallow staging/app source paths that should never be crawled if exposed by a host alias
Disallow: /hub.dablio.pt/
Disallow: /livedata.dablio.pt/
Disallow: /vendor/
Disallow: /resources/
Disallow: /storage/

# Allow important CSS and JS for rendering
Allow: /css/
Allow: /js/
Allow: /images/

# Search engines
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# High-volume AI/SEO crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /
