# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# =============================================================================
# MULTI-DOMAIN SEO ROBOTS.TXT (Google Algorithm Friendly)
# =============================================================================

# =============================================================================
# MAIN DOMAIN - istanbules.com
# =============================================================================
User-agent: *
Crawl-delay: 1

# Allow all content
Allow: /

# Disallow admin and sensitive areas
Disallow: /admin/
Disallow: /*.php$
Disallow: /*?*
Disallow: /assets/
Disallow: /uploads/
Disallow: /config.php
Disallow: /*.log$
Disallow: /*.sql$
Disallow: /tmp/

# Allow specific PHP files for SEO
Allow: /ilan/
Allow: /blog/
Allow: /kategori/

# Special directives for Googlebot
User-agent: Googlebot
Allow: /
Crawl-delay: 1
Disallow: /admin/
Disallow: /assets/
Disallow: /uploads/

# Special directives for Bingbot
User-agent: Bingbot
Allow: /
Crawl-delay: 2
Disallow: /admin/
Disallow: /assets/
Disallow: /uploads/

# =============================================================================
# CDN DOMAIN - escortistanbul.net (AMP Pages)
# =============================================================================
User-agent: *
Crawl-delay: 1

# Allow all AMP content
Allow: /

# Disallow admin and sensitive areas
Disallow: /admin/
Disallow: /*.php$
Disallow: /*?*
Disallow: /assets/
Disallow: /uploads/

# Allow AMP pages
Allow: /ilan/
Allow: /blog/
Allow: /kategori/

# =============================================================================
# NETWORK DOMAIN - vipendik.com
# =============================================================================
User-agent: *
Crawl-delay: 1

# Limited crawling for network domain
Allow: /
Allow: /istanbul-escort-rehberi
Allow: /escort-bayan
Allow: /pendik-escort
Allow: /kartal-escort
Allow: /tuzla-escort
Allow: /maltepe-escort
Allow: /kurtkoy-escort

# Disallow sensitive areas
Disallow: /admin/
Disallow: /*.php$
Disallow: /assets/
Disallow: /uploads/

# =============================================================================
# SITEMAPS (Multi-Domain)
# =============================================================================

# Main Domain Sitemap
Sitemap: https://istanbules.com/sitemap.xml

# CDN Domain Sitemap (AMP)
Sitemap: https://escortistanbul.net/sitemap.xml

# Network Domain Sitemap
Sitemap: https://vipendik.com/sitemap.xml

# =============================================================================
# SPECIAL DIRECTIVES (Google Algorithm Friendly)
# =============================================================================

# Image indexing (Google Images)
User-agent: Googlebot-Image
Allow: /uploads/
Allow: /ilan/
Allow: /blog/

# Video indexing (Google Videos)
User-agent: Googlebot-Video
Allow: /

# News indexing (Google News)
User-agent: Googlebot-News
Allow: /blog/
Disallow: /ilan/

# Mobile indexing
User-agent: Googlebot-Mobile
Allow: /

# =============================================================================
# PERFORMANCE OPTIMIZATION
# =============================================================================

# Reduce server load
Crawl-delay: 1

# Request rate (for advanced crawlers)
User-agent: *
Request-rate: 1/1

# =============================================================================
# SECURITY DIRECTIVES
# =============================================================================

# Prevent access to sensitive files
Disallow: /*.conf$
Disallow: /*.config$
Disallow: /*.env$
Disallow: /*.key$
Disallow: /*.pem$
Disallow: /*.crt$

# Prevent access to backup files
Disallow: /*.bak$
Disallow: /*.backup$
Disallow: /*.old$
Disallow: /*.orig$

# =============================================================================
# ADDITIONAL INSTRUCTIONS
# =============================================================================

# This robots.txt file supports multi-domain SEO strategy
# Each domain has specific crawling rules optimized for its purpose
# Main domain: Full content indexing
# CDN domain: AMP page indexing
# Network domain: Limited contextual indexing

# Last updated: 2026-01-16
# Compatible with Google algorithms and SEO best practices