# 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

User-agent: *
Allow: /

# Parameterised utility URLs: a claim form prefilled for one vendor, a quote form
# with vendors preselected, the assistant opened on an occasion. These are actions,
# not content. Each already canonicals back to its base page, so Google drops them
# correctly, but it had crawled 2,018 of them by 2026-09-06 and that was the single
# largest not-indexed bucket on the property. On a domain this new that is crawl
# budget taken from the category pages that can actually rank. People still reach
# these URLs from links and from outreach emails; only crawlers are kept out.
Disallow: /*?claim=
Disallow: /*&claim=
Disallow: /*?vendors=
Disallow: /*&vendors=
Disallow: /ai-assistant.html?occasion=

# Prefilled quote forms and filtered directory views (request-quotes.html?country=&cat=,
# index.html?cat=, index.html?country=). The /find/ pages linked 2,121 distinct such URLs
# on 2026-10-14, and each canonicals back to its base page. rel="nofollow" on those links
# is only a hint and does nothing for URLs Google has already found, which it keeps
# re-fetching while Google fetches about 50 pages a day here and 8,528 pages wait in
# "Discovered - currently not indexed". The bare pages stay open. The homepage with
# tracking tags (/?utm_source=) stays open on purpose: a link carrying them should still
# reach / through its canonical. AdsBot ignores this * group, so ad landing URLs are unaffected.
Disallow: /request-quotes.html?
Disallow: /index.html?

# Per-vendor utility URLs: every vendor page links edit-listing.html?id=<id> (9,248 on
# 2026-10-15), and the 835 venue, hotel and tent pages also link map.html?near=<id>. Each
# is a form or a map that canonicals back to its bare page, so every fetch of one is crawl
# taken from the vendor and category pages. The bare /edit-listing.html and /map.html stay
# open. The map a Featured vendor page embeds (map.html?embed=1) is a widget, not content.
Disallow: /edit-listing.html?
Disallow: /map.html?

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