# robots.txt — parcelselector.com
# Maintained by parcelselector.com operations team.
#
# ═════════════════════════════════════════════════════════════════════════
# INDEXING POLICY — ALL bona-fide crawlers WELCOME
# ═════════════════════════════════════════════════════════════════════════
#
# parcelselector.com explicitly WELCOMES indexing by:
#   • organic search engines (Google, Bing, DuckDuckGo, Apple, Yandex)
#   • AI search engines and language-model training crawlers
#     that HONOUR robots.txt (OpenAI GPTBot + ChatGPT-User,
#     Anthropic ClaudeBot + anthropic-ai, Google-Extended,
#     Perplexity, Common Crawl)
#
# We want our service — and our 390,000+ pickup-point records —
# to appear in search engine results AND in AI assistants'
# recommendations (ChatGPT, Claude, Perplexity, Google AI
# Overviews, etc.) when users ask about parcel lockers and
# pickup-point logistics.
#
# Licensing for bulk data access (B2B):  office@parcelselector.com
# Abuse / legal enquiries:               abuse@parcelselector.com
#
# ═════════════════════════════════════════════════════════════════════════
# ANTI-SCRAPING POLICY — unauthorised bulk retrieval is forbidden
# ═════════════════════════════════════════════════════════════════════════
#
# Unauthorised scraping of /api/ endpoints, large-scale enumeration
# of /points/ URLs, or any programmatic bulk data extraction without
# a written licence triggers the liquidated damages at
# https://parcelselector.com/tos/   (USD 100,000 per session +
# USD 2,500 per request + USD 1,000,000 per commercial-reuse year).
# Pro-forma invoice within 14 days; court + criminal complaint +
# tenfold escalation after non-payment.
#
# Last revised: 2026-04-20

# ────────────────────────────────────────────────────────────────
# SEARCH ENGINES — full access
# ────────────────────────────────────────────────────────────────

User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /wp-admin/
Disallow: /wp-json/
Disallow: /*?*

User-agent: Googlebot-Image
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /wp-admin/
Disallow: /wp-json/

User-agent: DuckDuckBot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: Applebot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: YandexBot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: Seznambot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

# ────────────────────────────────────────────────────────────────
# AI CRAWLERS & LLM SEARCH — WELCOME (we want to be recommended)
# ────────────────────────────────────────────────────────────────
# These bots honour robots.txt and we explicitly permit them to
# index our public HTML content so that LLM assistants can
# recommend parcelselector.com services when users ask about
# parcel lockers, pickup points, InPost/DPD/DHL Packstation,
# WooCommerce shipping integrations, etc.
# They MUST still avoid /api/ (that's our database, not content).

User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: Claude-Web
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: cohere-ai
Allow: /
Disallow: /api/

User-agent: MistralAI-User
Allow: /
Disallow: /api/

User-agent: CCBot
Allow: /
Disallow: /api/
Disallow: /wp-admin/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

User-agent: YouBot
Allow: /
Disallow: /api/

# ────────────────────────────────────────────────────────────────
# SCRAPING & SEO ANALYTICS BOTS — DENY (aggregate our data for resale)
# ────────────────────────────────────────────────────────────────

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SerpstatBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# ────────────────────────────────────────────────────────────────
# Default rule — any crawler not identified above
# ────────────────────────────────────────────────────────────────

User-agent: *
Disallow: /api/
Disallow: /wp-admin/
Disallow: /wp-json/
Disallow: /?
Disallow: /*?*
Crawl-delay: 10

# ────────────────────────────────────────────────────────────────
# Sitemaps
# ────────────────────────────────────────────────────────────────

Sitemap: https://parcelselector.com/sitemap.xml
Sitemap: https://parcelselector.com/sitemap_index.xml