# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: *
Allow: /
Disallow: /test.html
Disallow: /test
Disallow: /admin-review.html
Disallow: /admin-review
Disallow: /tools/email-preview.html
Disallow: /tools/email-preview
Disallow: /tools/outreach-email.html
Disallow: /tools/outreach-email

# Faceted / parameterised URLs are canonicalised to their clean page. Block them
# so crawl budget is spent on real content instead of thousands of duplicate views.
Disallow: /*?region=
Disallow: /*?country=
Disallow: /*?search=
Disallow: /*?claim=
Disallow: /*?q=

# --- Aggressive AI / scraper / heavy crawlers ---
# These consume crawl budget and bandwidth without sending ad-supported human
# traffic. Real search engines (Googlebot, Bingbot, DuckDuckBot, YandexBot,
# Applebot, PerplexityBot, OAI-SearchBot) are intentionally NOT listed here so
# search and AI-search visibility is preserved.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# --- Commercial SEO backlink crawlers (heavy). Remove any you use yourself. ---
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

Sitemap: https://teatrade.co.uk/sitemap.xml
Host: teatrade.co.uk