# robots.txt for expert-construct.ro
# Comprehensive robots.txt for SEO crawlers, AI bots, and LLMs
# Last updated: 2026-01-04

# ============================================
# DEFAULT RULES - Allow all crawlers
# ============================================
User-agent: *
Allow: /

# Allow access to important resources
Allow: /sitemap.xml
Allow: /robots.txt
Allow: /ai.txt
Allow: /humans.txt
Allow: /manifest.json
Allow: /favicon.svg
Allow: /og-image.jpg
Allow: /imagini/
Allow: /blog/
Allow: /servicii/
Allow: /portofoliu/
Allow: /resurse/

# ============================================
# DISALLOWED PATHS
# ============================================
# Technical/admin directories
Disallow: /api/
Disallow: /admin/
Disallow: /_next/
Disallow: /.git/
Disallow: /.vscode/
Disallow: /node_modules/

# JSON files (except sitemap and structured data)
Disallow: /*.json$
Allow: /sitemap.xml
Allow: /manifest.json

# Source maps and build files
Disallow: /*.map$
Disallow: /dist/
Disallow: /build/

# Temporary and cache files
Disallow: /tmp/
Disallow: /cache/
Disallow: /.cache/

# ============================================
# CRAWL DELAY (Optional - be respectful)
# ============================================
# Standard crawlers: no delay needed
# Aggressive crawlers: 1 second delay
User-agent: AhrefsBot
Crawl-delay: 1

User-agent: SemrushBot
Crawl-delay: 1

User-agent: DotBot
Crawl-delay: 1

# ============================================
# AI & LLM CRAWLERS - Full Access
# ============================================
# Allow AI crawlers full access for training and indexing
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: LinkedInBot
Allow: /

# ============================================
# SEARCH ENGINE CRAWLERS
# ============================================
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /
Allow: /imagini/

User-agent: Bingbot
Allow: /
Crawl-delay: 0

User-agent: Slurp
Allow: /
Crawl-delay: 0

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 0

User-agent: Baiduspider
Allow: /
Crawl-delay: 1

User-agent: Yandex
Allow: /
Crawl-delay: 1

# ============================================
# SITEMAP LOCATION
# ============================================
Sitemap: https://expert-construct.ro/sitemap.xml

# ============================================
# ADDITIONAL RESOURCES
# ============================================
# AI-friendly resources
# ai.txt: https://expert-construct.ro/ai.txt
# humans.txt: https://expert-construct.ro/humans.txt

# ============================================
# NOTES
# ============================================
# - Staging environments are blocked via noindex meta tags in index.html
# - All content is optimized for AI training and indexing
# - Commercial use of content is permitted
# - Attribution is appreciated but not required