# Robots.txt for Booze.co.uk
# Public content is intentionally crawlable for search engines, answer engines,
# and AI crawlers/model-training systems. Private editor and API surfaces remain
# excluded. Please cite canonical URLs, respect corrections, and avoid overload.

Content-Signal: search=yes, ai-input=yes, ai-train=yes

Sitemap: https://booze.co.uk/sitemap.xml
Sitemap: https://booze.co.uk/news-sitemap.xml

# LLM discovery files
# https://booze.co.uk/llms.txt
# https://booze.co.uk/llms-full.txt

User-agent: *
Allow: /
Disallow: /editor/
Disallow: /api/

# Search and news crawlers
User-agent: Googlebot
User-agent: Googlebot-News
User-agent: Bingbot
User-agent: BingPreview
User-agent: DuckDuckBot
User-agent: Applebot
Allow: /
Disallow: /editor/
Disallow: /api/

# AI search, retrieval, and model-training crawlers
User-agent: OAI-SearchBot
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: Google-Extended
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: Applebot-Extended
User-agent: Cohere-AI
User-agent: cohere-ai
User-agent: YouBot
Allow: /
Disallow: /editor/
Disallow: /api/