# robots.txt — iptvmn.ca
# Robots Exclusion Protocol, RFC 9309.
#
# Policy: this is a fully static site of ~61 pages with no database, no login,
# no internal search, no filters and no query-string URLs. There is nothing
# here that needs protecting from a crawler, so nothing is blocked from one.
# Every Disallow is a chance to block something by accident; on a site this
# shape they buy nothing.
#
# Two deliberate choices worth stating:
#
#  * /checkout/ is NOT disallowed. It carries a `noindex` robots meta, and a
#    crawler must be able to FETCH a page to read that meta. Blocking it would
#    leave 12+ internal "Buy Now" links pointing at a URL Google can discover
#    but never evaluate — the classic way a page ends up indexed as a bare URL
#    with no title. Crawl it, read the noindex, drop it. That is the correct
#    pairing.
#
#  * No `crawl-delay`. Googlebot does not implement it; crawl rate is set
#    algorithmically from response time and error rate.

# ---------------------------------------------------------- Google crawlers
# Explicit groups. Under RFC 9309 a crawler obeys the MOST SPECIFIC matching
# group and ignores every other, so these guarantee Google an unrestricted
# path regardless of anything in the wildcard group below.

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Google-InspectionTool
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Google-Site-Verification
Allow: /

User-agent: Storebot-Google
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: AdsBot-Google-Mobile
Allow: /

User-agent: Mediapartners-Google
Allow: /

# ------------------------------------------------------------- other search

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

# ------------------------------------------------------- AI answer engines
# Welcome by design. The content is written to be quoted, and citations from
# these surfaces send qualified Canadian traffic.

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

# ---------------------------------------------------------- known bad bots
# Aggressive scrapers that provide no referral value. Blocked outright rather
# than rate-limited, since they ignore crawl-delay anyway.

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: Bytespider
Disallow: /

# ---------------------------------------------------------------- everyone
# Wide open, including every rendering asset. The Web Rendering Service loads
# the page in a real browser to score mobile-friendliness and Core Web Vitals;
# starving it of CSS, JS or fonts would make the site look broken to Google.

User-agent: *
Allow: /

# ------------------------------------------------------------------ sitemap
# Absolute HTTPS. The index first, then every segment, so a crawler finds the
# whole set on first contact without waiting to parse the index.

Sitemap: https://iptvmn.ca/sitemap-index.xml
Sitemap: https://iptvmn.ca/sitemap-core.xml
Sitemap: https://iptvmn.ca/sitemap-blog.xml
Sitemap: https://iptvmn.ca/sitemap-guides.xml
Sitemap: https://iptvmn.ca/sitemap-cities.xml
Sitemap: https://iptvmn.ca/sitemap-support.xml
Sitemap: https://iptvmn.ca/sitemap-legal.xml
Sitemap: https://iptvmn.ca/sitemap-resources.xml