# robots.txt: Zazie Productions Horror Composer Portfolio
# GENERATED by scripts/generate-sitemap.mjs from src/data — edit the template
# there, not this file; the build overwrites it.
#
# Mastermind internal ranking architecture - full crawl efficiency, no soft 404 traps
# Updated 2026-10-04 - 84 indexable URLs (19 hubs + 9 productions + 32 cues + 24 catalogue items),
# transactional and duplicate-view paths blocked, audio unblocked for AudioObject rich results.

User-agent: *
Allow: /

# Crawl budget weaponization: block infinite param spaces while allowing clean URLs.
# Scope: a crawler obeys only the most specific group that names it, so these
# lines bind unnamed crawlers only. Googlebot, Bingbot and the other named groups
# below skip them by design: for those engines, parameter URLs (?utm_, ?fbclid...)
# are consolidated by rel=canonical (in each page and in the Link header), and a
# canonical can only be read on a URL that is allowed to be crawled.
Disallow: /*?*boot=
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
Disallow: /*?*ref=

# Transactional paths: never indexable, never useful in a crawl. Nothing on the
# site is sold here - checkout lives on Bandcamp, itch.io, Gumroad and eBay - but
# a future cart must not be discoverable before it exists.
Disallow: /cart
Disallow: /cart/
Disallow: /checkout
Disallow: /checkout/
Disallow: /basket
Disallow: /basket/

# Duplicate query views of otherwise canonical pages (sorting, filtering,
# pagination, print views). The pages themselves stay crawlable at their own
# URLs; only the parameterised variants are dropped.
Disallow: /*?*sort=
Disallow: /*?*filter=
Disallow: /*?*view=
Disallow: /*?*page=
Disallow: /*?*print=
Disallow: /*?*replytocom=

# Preview/no-op states stay crawlable but noindex, so they are not blocked here
# (a Disallow would hide the noindex from the crawler that needs to read it).

# Allow all critical assets - images, audio, fonts, media for rich results
Allow: /audio/
Allow: /images/
Allow: /fonts/
Allow: /*.mp3$
Allow: /*.avif$
Allow: /*.jpg$
Allow: /*.svg$

# Sitemaps - primary and image/video extensions embedded in main sitemap
Sitemap: https://horror.zazieproductions.com/sitemap.xml

# Host directive for canonical domain consolidation (Yandex reads this; Google ignores
# unknown lines). The value must be a bare hostname with no scheme and no path.
Host: horror.zazieproductions.com

# Respectful crawl-delay for aggressive SEO crawlers (preserve budget for Googlebot)
User-agent: AhrefsBot
Crawl-delay: 2
Disallow:

User-agent: SemrushBot
Crawl-delay: 2
Disallow:

User-agent: DotBot
Crawl-delay: 5
Disallow:

User-agent: MJ12bot
Crawl-delay: 5
Disallow:

User-agent: Yandex
Crawl-delay: 3

User-agent: Baiduspider
Crawl-delay: 10

# AI Search & Answer Engine Crawlers - full access for answer citation & entity indexing
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Cohere-ai
Allow: /

# Googlebot - full access, no delay, maximum indexation
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

# Bingbot - full access
User-agent: Bingbot
Allow: /