# robots.txt — insulationloft.co.uk
# Loft Insulation London

# ---------------------------------------------------------------------------
# Default: everything is open to well-behaved crawlers.
# ---------------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /submit.php
Disallow: /thank-you.html
Disallow: /*?*

# ---------------------------------------------------------------------------
# Conventional search engines
# ---------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# ---------------------------------------------------------------------------
# OpenAI crawlers — explicitly permitted
#   OAI-SearchBot  : surfaces this site in ChatGPT search results
#   ChatGPT-User   : fetches a page when a user asks ChatGPT to visit it
#   GPTBot         : general crawl for model training
# ---------------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

# ---------------------------------------------------------------------------
# Other AI and answer-engine crawlers — explicitly permitted
# ---------------------------------------------------------------------------
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: MistralAI-User
Allow: /

# ---------------------------------------------------------------------------
# Social preview fetchers (Open Graph / Twitter Cards)
# ---------------------------------------------------------------------------
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

# ---------------------------------------------------------------------------
# Aggressive SEO scrapers — declined
# ---------------------------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# ---------------------------------------------------------------------------
#  Discovery
# ---------------------------------------------------------------------------
Sitemap: https://insulationloft.co.uk/sitemap.xml

# Machine-readable companions for AI systems:
#   /ai.txt    — how AI systems may use this content (permissions + accuracy notes)
#   /llms.txt  — prose summary of the site, in the llms.txt convention
#   /llm.xml   — structured XML feed of every page, with summaries and topics