# ============================================================================
# Saucony.com robots.txt
# Platform: Salesforce Commerce Cloud (SFCC)
# Purpose:
#   - Optimize crawl efficiency
#   - Prevent crawling of low-value URLs
#   - Preserve crawl budget
#   - Support AI search engines (AEO / GEO)
# ============================================================================

User-agent: *

# ----------------------------------------------------------------------------
# Internal Search
# ----------------------------------------------------------------------------
Disallow: /*/search*
Disallow: /*?q=*

# ----------------------------------------------------------------------------
# Faceted Navigation / Filters
# ----------------------------------------------------------------------------
Disallow: /*prefn*
Disallow: /*prefv*
Disallow: /*pmin=*
Disallow: /*pmax=*
Disallow: /*srule=*
Disallow: /*cgid=*

# ----------------------------------------------------------------------------
# Internal Salesforce Commerce Cloud (SFCC) Controllers
# ----------------------------------------------------------------------------
Disallow: /*Product-Variation*
Disallow: /*Product-AddProductReview*
Disallow: /*dwcont=*

# ----------------------------------------------------------------------------
# Customer Account / Transactional Pages
# ----------------------------------------------------------------------------
Disallow: */account*
Disallow: */login*
Disallow: */register*
Disallow: */cart*
Disallow: */checkout*
Disallow: */wishlist*
Disallow: */orders*
Disallow: */order-history*
Disallow: */address-book*
Disallow: */billing*
Disallow: */remembereditems*

# ----------------------------------------------------------------------------
# Product Variant URLs
# ----------------------------------------------------------------------------
# Product variation URLs using the `dwvar_*` parameter remain crawlable.
# These URLs canonicalize to the clean PDP and should not be blocked unless
# crawl data demonstrates a measurable crawl-budget issue.

# ----------------------------------------------------------------------------
# Everything else remains crawlable
# ----------------------------------------------------------------------------
Allow: /

# ============================================================================
# AI Crawlers (AEO / GEO)
# ============================================================================

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: DuckAssistBot
Allow: /

# ============================================================================
# XML Sitemap
# ============================================================================
# Current production sitemap architecture:
# - https://www.saucony.com/sitemap_index.xml
#   ├── /sitemap_0.xml
#   ├── /en/sitemap_discontinuedproducts.xml
#   ├── /CA/sitemap_0.xml
#   └── /CA/en_CA/sitemap_discontinuedproducts.xml
#
# If the sitemap architecture is expanded in the future (e.g., additional
# locale-specific sitemaps or a revised sitemap index), this reference should
# continue to point to the master sitemap index.

Sitemap: https://www.saucony.com/sitemap_index.xml