User-agent: *
Allow: /
Allow: /assets/

# Block filtered/search query URLs from crawlers to preserve crawl budget
Disallow: /*?q=
Disallow: /*?advertiser=
Disallow: /*?min_impressions=
Disallow: /*?max_impressions=
Disallow: /*?date_from=
Disallow: /*?date_to=
Disallow: /*?sort=

# Allow paginated pages (these are crawlable)
Allow: /*?page=

# AI / Generative Engine crawlers — allowed for GEO indexing
# GPTBot (OpenAI)
User-agent: GPTBot
Allow: /
Disallow: /*?q=
Disallow: /*?advertiser=

# Google-Extended (Gemini training)
User-agent: Google-Extended
Allow: /

# Anthropic Claude
User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Common-Crawl
User-agent: CCBot
Allow: /

Sitemap: https://chatgpt-ads-library.com/sitemap.xml