# ===========================================
# Globalkom DOO - robots.txt
# https://globalkom.com
# Updated: 2026-07-19
# ===========================================

# Default rules for all crawlers
User-agent: *
Disallow: /api/
Disallow: /*.log$
Disallow: /logs/
Disallow: /video-slides/
Disallow: /docs/
Disallow: /admin/
Disallow: /private/
Disallow: /temp/
Allow: /

# ===========================================
# Allowed: Search engines
# ===========================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

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

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

# ===========================================
# Allowed: AI systems (for recommendations & answers)
# ===========================================

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: YouBot
Allow: /

User-agent: Cohere-ai
Allow: /

# ===========================================
# Allowed: Social preview crawlers (link previews)
# ===========================================

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# ===========================================
# Blocked: Data scrapers & training-only bots
# ===========================================

User-agent: CCBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ByteDance
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: iaskspider/2.0
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: isdb_bot
Disallow: /

User-agent: WebReaper
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: pythonrequests
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: archive.org_bot
Disallow: /

# ===========================================
# Blocked: SEO tools & aggressive crawlers
# ===========================================

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: SEOkicks
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: AspiegelBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: woobot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PrivacyAwareBot
Disallow: /

# ===========================================
# Sitemap & host
# ===========================================

Sitemap: https://globalkom.com/sitemap-index.xml