# 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

# Digimaze — https://digimaze.io
# Full crawl access. Machine-readable site guide: https://digimaze.io/llms.txt

User-agent: *
Allow: /
Disallow: /thank-you

# --- Answer engines / AI crawlers: allowed ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

Sitemap: https://digimaze.io/sitemap.xml

# =====================================================================
# LEGACY URL MAP  (301 redirects are enforced in /_redirects)
# Kept here as a crawl-time reference for the site migration.
# =====================================================================
#   /performance-marketing-services   ->  /services/performance-marketing
#   /seo-services                     ->  /services/seo
#   /creative-design-services         ->  /services/creative-design
#   /get-in-touch                     ->  /contact
#   /submission-received              ->  /thank-you
#   /blog                             ->  /insights
#   /blog/powerlook                   ->  /work/powerlook
#   /blog/summit-group                ->  /work/summit-group
#   /blog/deutsche-bank               ->  /work/deutsche-bank
#   /blog/lilly-and-sid-uk            ->  /work/lilly-and-sid
#   /blog/what-is-seo-and-how-it-works       ->  /insights/seo/what-is-seo
#   /blog/on-page-seo-checklist-...          ->  /insights/seo/on-page-seo-checklist
#   /blog/what-is-ppc-marketing-...          ->  /insights/performance-marketing/what-is-ppc-marketing
#   /blog/google-ads-vs-meta-ads-...         ->  /insights/performance-marketing/google-ads-vs-meta-ads
#   /blog/15-proven-ways-to-increase-...     ->  /insights/conversion/increase-website-conversions
#   /blog/what-is-llm-seo-beginners-guide    ->  /insights/ai-search/what-is-llm-seo
#
# Legacy posts still needing a written replacement (currently 301 to cluster):
#   /blog/types-of-google-ads-a-complete-guide
#   /blog/meta-advantage-plus-sales-campaigns-guide
#   /blog/broad-match-ad-scheduling-the-smartest-way-to-scale-google-ads-in-2026
#   /blog/year-of-growth-ppc-seo-client-success-2025
#
# Regional / campaign pages with no replacement (301 to / — soft-404 risk):
#   /uk            (needs a real UK landing page to keep UK rankings)
#   /meta-day-2026 (dated event page)