# ============================================================================
# robots.txt  —  https://worshipwoodworks.com
# WordPress + WooCommerce, hosted on WP Engine
# Last reviewed: 2026-08-11
# ----------------------------------------------------------------------------
# This is a PHYSICAL file placed at the web root. A physical robots.txt
# overrides BOTH WordPress's virtual robots.txt AND WP Engine's default
# generated file.
#
# THROTTLING: No "Crawl-delay" directive appears anywhere below. Googlebot
# ignores crawl-delay entirely, and WP Engine's default can inject
# "Crawl-delay: 10" (which needlessly slows Bing and other crawlers). By
# shipping this file with NO crawl-delay, legitimate search engines are
# never rate-limited by robots.txt. (Any server-level bot throttling on WP
# Engine is separate and is not controlled here.)
# ============================================================================

User-agent: *

# --- WordPress core (keep admin-ajax.php open for front-end AJAX) ---
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php

# NOTE: /wp-content/, /wp-includes/ and uploaded media are intentionally left
# crawlable so Google can fetch CSS/JS/images and render pages correctly.
# Do NOT add Disallow rules for those paths.

# --- Internal site search (thin / duplicate result pages) ---
Disallow: /*?s=
Disallow: /*&s=

# --- WooCommerce: transactional & account pages (should never be indexed) ---
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*add-to-cart=
Disallow: /*wc-ajax=

# --- WooCommerce: faceted / sorted URLs (duplicate content + crawl-budget waste) ---
Disallow: /*orderby=
Disallow: /*min_price=
Disallow: /*max_price=
Disallow: /*filter_
Disallow: /*add_to_wishlist=

# --- Comment reply query strings ---
Disallow: /*?replytocom=

# --- XML sitemap (Google Sitemap Generator) ---
Sitemap: https://worshipwoodworks.com/sitemap.xml

# ============================================================================
# OPTIONAL — Block high-volume AI/scraper bots to save WP Engine bandwidth.
# These do NOT affect Google, Bing, or SEO. Uncomment any you want to block.
# ============================================================================
# User-agent: GPTBot
# Disallow: /
#
# User-agent: CCBot
# Disallow: /
#
# User-agent: ClaudeBot
# Disallow: /
#
# User-agent: Google-Extended
# Disallow: /
#
# User-agent: PerplexityBot
# Disallow: /
#
# User-agent: Bytespider
# Disallow: /