# Website Image Extractor — robots.txt
# 10-Vector Client-Side Website Image Extractor, Bulk Picture Downloader & HTML/CSS DOM Scraper — websiteimageextractor.online
# Authored & Verified by: Web Asset & DOM Specification Research Desk
# Last updated: October 2026

# Allow all standard search engines
User-agent: *
Allow: /

# Sitemaps
Sitemap: https://websiteimageextractor.online/sitemap-index.xml

# AI/LLM Crawlers — Selectively Permitted (Attribution-Capable RAG & Search Engines)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

# Blocked AI Crawlers (No attribution, aggressive scraping)
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

# References
# LLMs-Full: https://websiteimageextractor.online/llms-full.txt
# LLMs: https://websiteimageextractor.online/llms.txt
# Media-RSS: https://websiteimageextractor.online/rss.xml