# =====================================================================
# robots.txt — 96autorepair.com
# Optimized for SEO (Google/Bing), AEO (Answer Engines), and GEO
# (Generative Engine Optimization) so AI assistants can find, read,
# and cite your service pages accurately.
# Last updated: 2026-08-29
# =====================================================================

# -----------------------------
# DEFAULT RULE (all crawlers)
# -----------------------------
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /cgi-bin/
Disallow: /cart/
Disallow: /checkout/
Disallow: /*?s=
Disallow: /*?add-to-cart=
Disallow: /*.pdf$
Allow: /wp-admin/admin-ajax.php
Crawl-delay: 1

# -----------------------------
# TRADITIONAL SEARCH ENGINES
# -----------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

# -----------------------------
# AI / ANSWER ENGINE CRAWLERS (AEO)
# These fetch your pages to answer real-time user questions
# (e.g., "best auto repair shop near me")
# -----------------------------

# OpenAI - ChatGPT search & browsing
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# OpenAI - training crawler (optional: block if you don't want training use)
User-agent: GPTBot
Allow: /

# Anthropic - Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini / SGE / AI Overviews training signal)
User-agent: Google-Extended
Allow: /

# Microsoft Copilot
User-agent: Bingbot
Allow: /

User-agent: CopilotBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon (Alexa/Rufus)
User-agent: Amazonbot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Common Crawl (feeds many LLM datasets — useful for broad AI visibility)
User-agent: CCBot
Allow: /

# -----------------------------
# GENERATIVE / LLM DATA CRAWLERS (GEO)
# Allowing these increases odds of being referenced in AI-generated
# answers, summaries, and citations across models trained on this data
# -----------------------------
User-agent: Diffbot
Allow: /

User-agent: Timpibot
Allow: /

User-agent: Omgilibot
Allow: /

User-agent: Bytespider
Allow: /

# -----------------------------
# BLOCK LOW-VALUE / AGGRESSIVE SCRAPERS
# (marketing/SEO scrapers, not answer engines — safe to block)
# -----------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# -----------------------------
# SITEMAP LOCATION(S)
# -----------------------------
Sitemap: https://96autorepair.com/sitemap.xml
Sitemap: https://96autorepair.com/sitemap_index.xml
LLMS.TXT: https://96autorepair.com/llms.txt