# 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

# robots.txt — Noura Almaazmi (almaazmilawyers.com)
# Allow all standard search crawlers
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /client/
Disallow: /private/

# AI / LLM crawlers — explicitly allowed (GEO/AEO strategy)
# These are the user agents that the major AI engines use to index content for citation.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: meta-externalagent
Allow: /

# Sitemaps — index file lists all three (en at root, ar + ru subdirectories)
Sitemap: https://www.almaazmilawyers.com/sitemap-index.xml
Sitemap: https://www.almaazmilawyers.com/sitemap.xml
Sitemap: https://www.almaazmilawyers.com/sitemap-ar.xml
Sitemap: https://www.almaazmilawyers.com/sitemap-ru.xml

# AI-friendly markdown index
# (Not a robots.txt directive, but kept here for discoverability:
#  see https://www.almaazmilawyers.com/llms.txt, /llms-full.txt, and /services.md)