# ===========================================
# Saddleback Leather Co. — robots.txt
# Updated: July 2026
# Strategy: Allow AI answer engines, block AI training crawlers
# ===========================================
# --- AI Answer Engine Bots (ALLOW) ---
# These power search features and AI answers that drive traffic & sales
# OpenAI Search (ChatGPT search results)
User-agent: OAI-SearchBot
Allow: /

# OpenAI ChatGPT browsing (when users ask ChatGPT to visit pages)
User-agent: ChatGPT-User
Allow: /

# Perplexity AI search
User-agent: PerplexityBot
Allow: /

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

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

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

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

# Microsoft Copilot (uses Bing infrastructure)
User-agent: Bingbot
Allow: /

# --- AI Training-Only Bots (BLOCK) ---
# These scrape content for model training, not search answers
# OpenAI training crawler (NOT the search bot)
User-agent: GPTBot
Disallow: /

# Common Crawl (feeds training datasets)
User-agent: CCBot
Disallow: /

# ByteDance/TikTok training crawler
User-agent: Bytespider
Disallow: /

# --- General Rules for All Other Bots ---
User-agent: *
Disallow: /account.php
Disallow: /cart.php
Disallow: /checkout.php
Disallow: /checkout
Disallow: /finishorder.php
Disallow: /login.php
Disallow: /orderstatus.php
Disallow: /postreview.php
Disallow: /productimage.php
Disallow: /productupdates.php
Disallow: /remote.php
Disallow: /search.php
Disallow: /viewfile.php
Disallow: /wishlist.php
Disallow: /admin/
Disallow: /__socialshop/
Disallow: /cdn-cgi/
Disallow: /*?_bc_fsnf=1*
Disallow: /*&_bc_fsnf=1*

User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Diffbot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: GPTBot
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: ICC-Crawler
User-agent: ISSCyberRiskCrawler
User-agent: ImagesiftBot
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalAds
User-agent: Meta-ExternalFetcher
User-agent: Meta-WebIndexer
User-agent: OAI-SearchBot
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Scrapy
User-agent: Sidetrade indexer bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: facebookexternalhit
User-agent: iaskspider/2.0
User-agent: img2dataset
User-agent: omgili
User-agent: omgilibot
Crawl-delay: 10
Disallow: /account.php
Disallow: /cart.php
Disallow: /checkout.php
Disallow: /checkout
Disallow: /admin/
Disallow: /*?_bc_fsnf=1*
Disallow: /*&_bc_fsnf=1*

# XML Sitemap (proper machine-readable version)
Sitemap: https://saddlebackleather.com/xmlsitemap.php