# 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.

# 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
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Allow all search engine bots to crawl the site
User-agent: *
Disallow: 

# Allow generative AI bots to crawl and attribute content
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

# Block irrelevant or sensitive areas
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /temp/
Disallow: /private/
Disallow: /scripts/

# Allow crawlers to index all news content and categories
Allow: /

# Help Google News crawler discover content faster
User-agent: Googlebot-News
Allow: /

# Help search engines prioritise fresh and important content
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# Block parameters that could create duplicate content
Disallow: /*?utm_source=
Disallow: /*?utm_medium=
Disallow: /*?utm_campaign=
Disallow: /*?sessionid=

# Specify the location of the sitemaps
Sitemap: https://newstrends.co.ke/post-sitemap.xml
Sitemap: https://newstrends.co.ke/page-sitemap.xml
Sitemap: https://newstrends.co.ke/post-sitemap3.xml
Sitemap: https://newstrends.co.ke/post-sitemap2.xml
Sitemap: https://newstrends.co.ke/sitemap_index.xml
Sitemap: https://newstrends.co.ke/sitemap.xml