# itsnum.com — NUM, the verified AI travel concierge, by 5arz.
# Answer engines are welcome here. Structured data on every
# destination and agent page, a plain-language summary at
# /llms.txt and the full corpus at /llms-full.txt.
# Machine-readable business data: /for-ai/
#
# 19 Sep 2026: this said "on every page" and 16 crawlable pages carried no
# JSON-LD. The six that were genuinely indexable now do, and the claim was
# narrowed to what scripts/crawlability.mjs can prove on every run. A site
# selling "verified, real, checked" cannot open its robots.txt with a line a
# crawler disproves in one fetch.

User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Claude-User
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Claude-SearchBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: anthropic-ai
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Perplexity-User
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Google-Extended
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Googlebot-Image
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Applebot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Amazonbot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: meta-externalagent
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: FacebookBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: cohere-ai
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: cohere-training-data-crawler
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: CCBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Diffbot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Timpibot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: YouBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: DuckAssistBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: MistralAI-User
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: Bytespider
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: PetalBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: YandexBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

# Added 29 Aug 2026. Retrieval and agent fetchers that were not named above.
# An unnamed agent falls through to the "User-agent: *" block below, which is
# permissive, so this section changes nothing about access — it makes the
# intent explicit, which is what a compliance review or a vendor allowlist
# actually reads.
#
# NOT LISTED, deliberately: xAI's Grok crawler publishes no user-agent token
# and is reported to fetch behind rotating residential IPs with spoofed Safari
# and Chrome strings. There is nothing to allow or deny by name. Saying so
# here is more honest than inventing a token that matches nothing.

User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

User-agent: Google-CloudVertexBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

User-agent: Google-NotebookLM
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

User-agent: FirecrawlAgent
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

User-agent: AI2Bot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

User-agent: Ai2Bot-Dolma
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

User-agent: Webzio-Extended
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /signin/

# ── SEO CRAWLERS, NAMED (19 Sep 2026) ────────────────────────────────────
#
# These already had access: an unnamed agent falls through to "User-agent: *"
# below, which allows everything except the six paths listed there. Naming
# them changes nothing about what they can fetch.
#
# It is here because "it falls through to the wildcard" is not something a
# vendor's support desk or a compliance review can see. When a Site Audit
# comes back empty the first question asked is "are we in your robots.txt",
# and the honest answer needs to be visible rather than inferred.
#
# WHAT THIS DOES NOT DO: backlinks pointing AT itsnum.com are discovered by
# Semrush crawling the sites that link to us, not by crawling us. Nothing in
# this file affects whether a backlink campaign is found or counted. What it
# affects is Site Audit, On Page SEO Checker and Backlink Audit reading our
# own pages.
#
# The disallow list is identical to the wildcard block on purpose. /api/ is
# an endpoint surface with no content to index; /console/ and /signin/ are
# private; /app-preview/ and /claim/ are transient. A crawler that fetched
# them would report them as thin-content errors we would then be asked to fix.

User-agent: SemrushBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: SiteAuditBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: SemrushBot-BA
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: SemrushBot-SI
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: SemrushBot-SWA
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: SemrushBot-OCOB
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: SplitSignalBot
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

User-agent: *
Allow: /
Disallow: /api/
Disallow: /console/
Disallow: /app-preview/
Disallow: /claim/
Disallow: /signin/
Disallow: /assets/vendor/

# Segmented on purpose. The hand-written pages and the generated set guides
# are separate sitemaps so Search Console reports an indexation rate for each
# on its own — a single blended number cannot tell you which half moved.
Sitemap: https://itsnum.com/sitemap_index.xml
Sitemap: https://itsnum.com/sitemap.xml
Sitemap: https://itsnum.com/sitemap-guides.xml
Sitemap: https://itsnum.com/sitemap-i18n.xml
Sitemap: https://itsnum.com/sitemap-countries.xml
Sitemap: https://itsnum.com/sitemap-entry.xml
Sitemap: https://itsnum.com/sitemap-halloween.xml