# ============================================================
# KazaUmri — robots.txt
# Updated: 2026-06-06
# Full AI crawler directives for GEO/AEO visibility
# Malicious/aggressive bots explicitly blocked
# ============================================================

# ── Traditional search crawlers ──
User-agent: Googlebot
Allow: /
Disallow: /api/

User-agent: Bingbot
Allow: /
Disallow: /api/

User-agent: Slurp
Allow: /
Disallow: /api/

User-agent: DuckDuckBot
Allow: /
Disallow: /api/

# ── OpenAI / ChatGPT ──
User-agent: GPTBot
Allow: /
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

# ── Anthropic / Claude ──
User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: Claude-User
Allow: /
Disallow: /api/

User-agent: Claude-SearchBot
Allow: /
Disallow: /api/

# ── Perplexity AI ──
User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /api/

# ── Google AI (Gemini, AI Overviews, Vertex) ──
User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: GoogleOther
Allow: /
Disallow: /api/

# ── Microsoft Copilot ──
User-agent: msnbot
Allow: /
Disallow: /api/

# ── Common Crawl (used by many AI training datasets) ──
User-agent: CCBot
Allow: /
Disallow: /api/

# ── Amazon Alexa ──
User-agent: Amazonbot
Allow: /
Disallow: /api/

# ── ByteDance (Doubao, etc.) ──
User-agent: Bytespider
Allow: /
Disallow: /api/

# ── Apple (Siri, Apple Intelligence) ──
User-agent: Applebot
Allow: /
Disallow: /api/

# ============================================================
# BLOCKED — Aggressive SEO scrapers (honor robots.txt)
# ============================================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SemrushBot-SA
Disallow: /

User-agent: SemrushBot-SI
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: AspiegelBot
Disallow: /

User-agent: Serpstatbot
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: SiteAuditBot
Disallow: /

User-agent: screamingfrogseospider
Disallow: /

User-agent: 360Spider
Disallow: /

User-agent: YisouSpider
Disallow: /

User-agent: linkdexbot
Disallow: /

User-agent: spbot
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: GrapeshotCrawler
Disallow: /

# ── Bulk downloaders / script scrapers (honor robots.txt) ──

User-agent: HTTrack
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: NetAnts
Disallow: /

User-agent: ia_archiver
Disallow: /

# ── Vulnerability scanners / pentest tools (honor robots.txt) ──

User-agent: Nikto
Disallow: /

User-agent: sqlmap
Disallow: /

User-agent: nmap
Disallow: /

User-agent: masscan
Disallow: /

User-agent: zgrab
Disallow: /

User-agent: dirbuster
Disallow: /

User-agent: gobuster
Disallow: /

User-agent: wfuzz
Disallow: /

# ── Spam harvesters ──

User-agent: EmailCollector
Disallow: /

User-agent: EmailSiphon
Disallow: /

User-agent: EmailWolf
Disallow: /

User-agent: ExtractorPro
Disallow: /

User-agent: CherryPicker
Disallow: /

User-agent: Harvest
Disallow: /

# ── All other crawlers: allow public pages, block API ──
User-agent: *
Allow: /
Disallow: /api/
Disallow: /payment-success.html

# ── Sitemaps ──
Sitemap: https://kazaumri.com/sitemap.xml
Sitemap: https://kazaumri.com/sitemap-ar.xml