# ===================================================================
# Online Khadamate - SEO, GEO & AI Optimized Robots.txt (2026)
# ===================================================================

# --- Core AI & LLM Crawlers (OpenAI, Anthropic, Google, Perplexity) ---
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /

# --- Tech Giants & Social AI Crawlers (Meta, Apple, Amazon, ByteDance) ---
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: Applebot
User-agent: Amazonbot
User-agent: Bytespider
User-agent: TikTok Spider
Allow: /

# --- General AI Assistants & Data Scrapers ---
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: Manus Bot
User-agent: ProRataInc
User-agent: Novellum AI Crawl
User-agent: Anchor Browser
User-agent: CCBot
User-agent: Cloudflare Crawler
Allow: /

# --- Traditional Search Engines & Archivers ---
User-agent: Googlebot
User-agent: BingBot
User-agent: PetalBot
User-agent: Terracotta Bot
User-agent: Timpibot
User-agent: archive.org_bot
User-agent: Arquivo Web Crawler
Allow: /

# ===================================================================
# --- Main Rules For All Other Agents ---
# ===================================================================
User-agent: *

# Core protection
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /cgi-bin/
Disallow: /wp-content/cache/

# Low-value pages (Crawl Budget Optimization)
Disallow: /search/
Disallow: /author/
Disallow: /trackback/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /?s=
Disallow: /*/page/

# Assets (Important for Rendering & AI Vision)
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/
Allow: /wp-includes/

# Sitemaps
Sitemap: https://ar.onlinekhadamate.com/sitemap.xml
Sitemap: https://ar.onlinekhadamate.com/sitemap_llm.xml