# 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

# Block search engines from non-HTML feed/discovery files. These targets:
#   - llms.txt / llms-full.txt → AI crawlers (Claude, ChatGPT, Perplexity)
#   - blog/feed.xml             → RSS readers (Feedly, NetNewsWire, etc.)
# None of them belong in Google/Bing search results. Blocking saves crawl
# budget on a young domain and stops them from cluttering Search Console.
User-agent: Googlebot
Disallow: /llms.txt
Disallow: /llms-full.txt
Disallow: /blog/feed.xml

User-agent: Bingbot
Disallow: /llms.txt
Disallow: /llms-full.txt
Disallow: /blog/feed.xml

# Everyone else — GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot, RSS
# clients, human visitors — gets full access. These files exist for them.
User-agent: *
Allow: /

Sitemap: https://adplus.com/sitemap.xml
Sitemap: https://adplus.com/learn/videos.xml