# ============================================================================
# etemadyadak.com — robots.txt
# Last modified: 2026-08-09
#
# CHANGELOG
# 2026-08-09  Consolidated duplicate User-agent:* groups into one.
#             Anchored short parameter names to ? and & (see NOTE below).
#             Moved faceted-navigation rules to SECTION 5, disabled pending
#             deindexation of ~1,250 JetSmartFilters URLs via X-Robots-Tag.
#
# NOTE ON PATTERN SYNTAX
# "Disallow: *?jsf=*" only matches when jsf is the FIRST parameter, because it
# requires the literal string "?jsf=". Real URLs on this site carry it as
# "&jsf=", so those rules never fire. Two safe forms:
#   - distinctive names  -> /*jsf=          (matches anywhere, incl. malformed
#                                            paths where the "?" is missing)
#   - short/ambiguous    -> /*?s=  AND  /*&s=   (bare /*s= would also match
#                                                "things=", "options=", etc.)
# ============================================================================

User-agent: *

# --- SECTION 1: infrastructure -------------------------------------------
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-content/plugins/digits/
Disallow: /cdn-cgi/
Disallow: /*/feed/
Disallow: /feed/

# --- SECTION 2: transactional and account --------------------------------
Disallow: /cart
Disallow: /checkout
Disallow: /my-account
Disallow: /wishlist
Disallow: /signin/
Disallow: /*digits          # broad substring match; verify no product slug contains it

# --- SECTION 3: legacy parameter rules ------------------------------------
# Kept deliberately. Each is VALID but POSITION-DEPENDENT: it only fires when
# the parameter happens to be first in the query string. Harmless to retain,
# insufficient on its own. Superseded by SECTION 4.
Disallow: *?s=*
Disallow: *?p=*
Disallow: *&p=*
Disallow: *&preview=*
Disallow: *?attribute_pa_brand*
Disallow: *?jet_search=*
Disallow: *?wc-ajax=get_default_gallery*
Disallow: *?wc-ajax=get_variation_gallery*
Disallow: *?wc-ajax=get_refreshed_fragments*

# --- SECTION 4: corrected parameter rules (position-independent) ----------
# Active now. None of these parameters appear in the current indexed set, so
# blocking crawl here prevents growth without stranding anything.
Disallow: /*?s=
Disallow: /*&s=
Disallow: /*?p=
Disallow: /*&p=
Disallow: /*?page=
Disallow: /*&page=
Disallow: /*?type=
Disallow: /*&type=
Disallow: /*?login=
Disallow: /*&login=
Disallow: /*preview=
Disallow: /*add-to-cart=
Disallow: /*remove_item=
Disallow: /*attribute_pa_brand=
Disallow: /*jet_search=
Disallow: /*wc-ajax=
# Query-anchored so the /model/ taxonomy archive stays crawlable:
Disallow: /*?*model=

# --- SECTION 5: faceted navigation — DISABLED, DO NOT ENABLE YET ----------
# These are the correct patterns for the JetSmartFilters / JetWooBuilder URL
# space. They are switched off on purpose.
#
# WHY: ~1,250 of these URLs are already indexed. They are being removed via
# X-Robots-Tag: noindex, follow (mu-plugin ey-index-hygiene.php). Blocking
# crawl now would prevent Google from ever seeing that noindex.
#
# ENABLE WHEN: GSC "Excluded by noindex" has absorbed the URLs and
# "Indexed" has dropped back toward ~5,600. Expect 6-10 weeks. Re-check on
# 2026-10-15. Uncomment all nine lines together, then re-test in the GSC
# robots.txt tester using a percent-encoded Persian URL.
#
# Disallow: /*jsf=
# Disallow: /*jsf_ajax=
# Disallow: /*pagenum=
# Disallow: /*do_not_redirect=
# Disallow: /*nocache=
# Disallow: /*?*product_cat=
# Disallow: /*?*product_brand=
# Disallow: /*?*paged=
# Disallow: /*&paged=

# --- crawl-rate controls (ignored by Googlebot) --------------------------
User-agent: dotbot
Crawl-delay: 10

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: PetalBot
Disallow: /

Sitemap: https://etemadyadak.com/sitemap_index.xml