# ============================================================================
# ROBOTS.TXT - APS Art Marketplace
# Last Updated: 2026-01-26
# Languages: 20 (en, es, pt, ru, de, fr, it, pl, nl, ro, hu, cs, sv, el, bg, da, no, sk, fi, uk)
# ============================================================================
# ----------------------------------------------------------------------------
# DEFAULT RULES - All Bots
# ----------------------------------------------------------------------------
User-agent: *
# Allow homepage and language roots
Allow: /
Allow: /en/
Allow: /es/
Allow: /pt/
Allow: /ru/
Allow: /de/
Allow: /fr/
Allow: /it/
Allow: /pl/
Allow: /nl/
Allow: /ro/
Allow: /hu/
Allow: /cs/
Allow: /sv/
Allow: /el/
Allow: /bg/
Allow: /da/
Allow: /no/
Allow: /sk/
Allow: /fi/
Allow: /uk/
# Allow public content paths
Allow: /*/art/
Allow: /*/artists/
Allow: /*/museums/
Allow: /*/articles/
# Block admin and management
Disallow: /admin/
Disallow: /*/accounts/
Disallow: /manage/
# Block user-specific content
Disallow: /*/orders/
Disallow: /users/
# Block media files (except artwork images and products)
Disallow: /media/
Allow: /media/artworks/
Allow: /media/products/
# Block static resources (CSS/JS)
Disallow: /static/css/
Disallow: /static/js/
Disallow: /staticfiles/
# Allow critical static resources for rendering
Allow: /static/images/
Allow: /staticfiles/images/
# Block development/debug URLs
Disallow: /misc_utils_tags/
Disallow: /debug/
Disallow: /__debug__/
Disallow: /ckeditor5/
Disallow: /i18n/
# Block utility endpoints
Disallow: /*/set_country/
Disallow: /*/set_currency/
Disallow: /*/set_language/
Disallow: /*/process-newsletter/
Disallow: /*/process-art-suggestions/
# Block search result pages with parameters
Disallow: /*?q=
Disallow: /*?search=
Disallow: /*?filter=
Disallow: /*&q=
Disallow: /*&search=
# Block pagination beyond page 10 (crawl budget optimization)
Disallow: /*?page=1[1-9]
Disallow: /*?page=[2-9][0-9]
Disallow: /*&page=1[1-9]
Disallow: /*&page=[2-9][0-9]
# Block AJAX and API endpoints
Disallow: /*/favorite/addajax/
Disallow: /*/favorite/removeajax/
Disallow: /api/
# Block low-value paths
Disallow: /*/search-not-found/
Disallow: /*/error/
Disallow: /*/test/
Disallow: /*/empty/
# Block non-indexable artwork pages (diaporama, info, ecard)
Disallow: /*/art/diaporama/
Disallow: /*/art/info/
Disallow: /*/art/ecard/
# Block artwork collection filter URLs (non-default collections)
Disallow: /*/art/*/?collection=
# General crawl delay (0.5 seconds between requests)
Crawl-delay: 0.5
# ----------------------------------------------------------------------------
# GOOGLE BOT - Primary Search
# ----------------------------------------------------------------------------
User-agent: Googlebot
Allow: /
# ----------------------------------------------------------------------------
# GOOGLE IMAGE BOT - Image Search Optimization
# ----------------------------------------------------------------------------
User-agent: Googlebot-Image
Allow: /
Allow: /media/artworks/
Allow: /*/art/
Disallow: /media/users/
Disallow: /media/appraisal_photos/
Disallow: /media/art_consultation_photos/
Disallow: /media/order_custom_reproduction_photos/
# ----------------------------------------------------------------------------
# BING BOT
# ----------------------------------------------------------------------------
User-agent: bingbot
Allow: /
Crawl-delay: 1
# ----------------------------------------------------------------------------
# YANDEX (Russian Market)
# ----------------------------------------------------------------------------
User-agent: Yandex
Allow: /
Allow: /ru/
Crawl-delay: 2
# ----------------------------------------------------------------------------
# OTHER SEARCH ENGINES
# ----------------------------------------------------------------------------
# DuckDuckGo
User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1
# Baidu (Chinese search)
User-agent: Baiduspider
Allow: /
Crawl-delay: 2
# Sogou (Chinese search)
User-agent: Sogou
Allow: /
Crawl-delay: 2
# 360Spider (Chinese search)
User-agent: 360Spider
Allow: /
Crawl-delay: 2
# ----------------------------------------------------------------------------
# SOCIAL MEDIA BOTS - Rich Preview Cards
# ----------------------------------------------------------------------------
User-agent: facebookexternalhit
Allow: /
Allow: /media/artworks/
Disallow: /*/accounts/
Disallow: /*/orders/
User-agent: Twitterbot
Allow: /
Allow: /media/artworks/
Disallow: /*/accounts/
Disallow: /*/orders/
User-agent: Pinterestbot
Allow: /
Allow: /media/artworks/
Allow: /*/art/
Crawl-delay: 1
User-agent: LinkedInBot
Allow: /
Disallow: /media/
User-agent: WhatsApp
Allow: /
Allow: /media/artworks/medium/
# ----------------------------------------------------------------------------
# AI TRAINING BOTS - Content Usage Control
# ----------------------------------------------------------------------------
# OpenAI GPTBot
User-agent: GPTBot
Allow: /
# OpenAI ChatGPT (browsing feature)
User-agent: ChatGPT-User
Allow: /
# Anthropic Claude
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
# Google AI (Bard/Gemini)
User-agent: Google-Extended
Allow: /
# Microsoft Bing Chat
User-agent: BingChatbot
Allow: /
# Common Crawl (AI training dataset)
User-agent: CCBot
Allow: /
# Cohere AI
User-agent: cohere-ai
Allow: /
# Perplexity AI
User-agent: PerplexityBot
Allow: /
# Apple AI
User-agent: Applebot-Extended
Allow: /
# Meta AI
User-agent: FacebookBot
Allow: /
# Diffbot (AI data extraction)
User-agent: Diffbot
Allow: /
# ByteDance/TikTok AI
User-agent: Bytespider
Allow: /
# Amazon AI
User-agent: Amazonbot
Allow: /
# Omgili AI
User-agent: Omgilibot
Allow: /
# You.com AI
User-agent: YouBot
Allow: /
# ----------------------------------------------------------------------------
# AGGRESSIVE/PROBLEMATIC BOTS
# ----------------------------------------------------------------------------
User-agent: AhrefsBot
Crawl-delay: 10
Disallow: /media/
Disallow: /static/
User-agent: SemrushBot
Crawl-delay: 10
Disallow: /media/
Disallow: /static/
User-agent: MJ12bot
Crawl-delay: 10
Disallow: /media/
Disallow: /static/
User-agent: DotBot
Crawl-delay: 10
Disallow: /media/
Disallow: /static/
User-agent: MauiBot
Disallow: /
User-agent: SurveyBot
Disallow: /
User-agent: masscan
Disallow: /
User-agent: nmap
Disallow: /
User-agent: sqlmap
Disallow: /
User-agent: ia_archiver
Crawl-delay: 5
# ----------------------------------------------------------------------------
# SITEMAPS - PRODUCTION DOMAINS
# ============================================================================
# Allow access to sitemaps
Allow: /sitemap.xml
Allow: /en/sitemap.xml
Allow: /es/sitemap.xml
Allow: /pt/sitemap.xml
Allow: /ru/sitemap.xml
Allow: /de/sitemap.xml
Allow: /fr/sitemap.xml
Allow: /it/sitemap.xml
Allow: /pl/sitemap.xml
Allow: /nl/sitemap.xml
Allow: /ro/sitemap.xml
Allow: /hu/sitemap.xml
Allow: /cs/sitemap.xml
Allow: /sv/sitemap.xml
Allow: /el/sitemap.xml
Allow: /bg/sitemap.xml
Allow: /da/sitemap.xml
Allow: /no/sitemap.xml
Allow: /sk/sitemap.xml
Allow: /fi/sitemap.xml
Allow: /uk/sitemap.xml
# Main sitemap index (points to all 20 language sitemaps)
Sitemap: /sitemap.xml
# Language-specific sitemap indexes (each contains 500 paginated pages)
Sitemap: /en/sitemap.xml
Sitemap: /es/sitemap.xml
Sitemap: /pt/sitemap.xml
Sitemap: /ru/sitemap.xml
Sitemap: /de/sitemap.xml
Sitemap: /fr/sitemap.xml
Sitemap: /it/sitemap.xml
Sitemap: /pl/sitemap.xml
Sitemap: /nl/sitemap.xml
Sitemap: /ro/sitemap.xml
Sitemap: /hu/sitemap.xml
Sitemap: /cs/sitemap.xml
Sitemap: /sv/sitemap.xml
Sitemap: /el/sitemap.xml
Sitemap: /bg/sitemap.xml
Sitemap: /da/sitemap.xml
Sitemap: /no/sitemap.xml
Sitemap: /sk/sitemap.xml
Sitemap: /fi/sitemap.xml
Sitemap: /uk/sitemap.xml