# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# ─────────────────────────────────────────────────────────────────────────────
# Crawl-budget policy (set 19 Aug 2026, from GSC Crawl Stats + nginx logs)
#
#  • Google's whole crawl budget for this host is ~49 requests/day, and 59% of it
#    was spent on IMAGES that returned 0 clicks / 0 impressions in 3 months
#    (GSC → Performance → тип поиска «Изображения»). Googlebot-Image is therefore
#    kept off the image proxies below so that budget goes to HTML instead.
#    NB: only Googlebot-IMAGE is restricted — plain Googlebot may still fetch
#    images for page rendering and Product/JSON-LD rich results.
#
#  • Third-party SEO crawlers were ~50% of ALL requests to this site
#    (AhrefsBot 32k/day, SemrushBot 2.5k, DataForSeoBot 1k, MJ12bot 0.7k) while
#    Googlebot did 1. They bring no search traffic: the freeloaders are blocked,
#    Ahrefs/Semrush are merely slowed so our own link-building audits still work.
#    None of this affects Google or Bing indexing.
# ─────────────────────────────────────────────────────────────────────────────

User-agent: *
Disallow: /admin/
Disallow: /ajax/
Disallow: /api/
Disallow: /css/
Disallow: /js/
Disallow: /vendor/
Disallow: /storage/framework/
Disallow: /search
Disallow: /tag/
Disallow: /posts/
Disallow: /track

# Google Images brings zero traffic — don't spend the host's crawl budget on it.
User-agent: Googlebot-Image
Disallow: /img/
Disallow: /img2/

# SEO-tool crawlers. A per-agent group REPLACES the "*" group for that agent,
# so the shared Disallow list is repeated here on purpose.
User-agent: AhrefsBot
Crawl-delay: 10
Disallow: /admin/
Disallow: /ajax/
Disallow: /api/
Disallow: /vendor/
Disallow: /storage/framework/
Disallow: /search
Disallow: /tag/
Disallow: /posts/
Disallow: /track

User-agent: SemrushBot
Crawl-delay: 10
Disallow: /admin/
Disallow: /ajax/
Disallow: /api/
Disallow: /vendor/
Disallow: /storage/framework/
Disallow: /search
Disallow: /tag/
Disallow: /posts/
Disallow: /track

# No upside for us at all — full stop.
User-agent: DataForSeoBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

Sitemap: https://datingua.com/sitemap.xml