Sitemap: https://www.joopzy.com/wp-sitemap.xml

# =============================================================================
# ONE group, applying to every crawler.
#
# DO NOT add a per-crawler group such as:
#
#     User-agent: Googlebot
#     Allow: /
#
# A crawler obeys ONLY its most specific matching group and ignores the "*"
# group entirely. A group like that therefore switches OFF every rule below for
# that crawler — it does not "additionally allow" anything, because whatever is
# not disallowed is already allowed by default.
#
# This file used to do exactly that. Googlebot's complete ruleset was "Allow: /",
# so it was free to crawl wp-admin, the cart, the checkout and every parameter
# URL on the site. Separately, the WooCommerce and crawler-trap rules were placed
# after "User-agent: YoudaoBot/1.0" with no new User-agent line, so all ~26 of
# them applied to YoudaoBot alone. Search Console reported 22M non-indexed pages,
# millions of duplicate URLs and hundreds of thousands of 404s.
#
# NOTE ON FORMATTING: there must be NO BLANK LINE between a User-agent line and
# its rules, or anywhere inside a group. A blank line ends the record for strict
# parsers, which would orphan every rule after it. Comment lines are safe and are
# used as separators below instead.
#
# Some rules are deliberately redundant: /*?* already covers the ?orderby=,
# ?filter and ?s= patterns. They are kept so that relaxing /*?* later does not
# silently unprotect everything else at the same time.
# =============================================================================
User-agent: *
# --- WordPress internals ---
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /readme.html
Disallow: /license.txt
Disallow: /xmlrpc.php
Disallow: /wp-login.php
Disallow: /wp-register.php
# --- Media stays crawlable, so image search keeps working even though the
#     query-string rule below is broad. ---
Allow: /wp-content/uploads/
# --- Any URL carrying a query string ---
# Shop filters, sorting and pagination parameters generate an effectively
# unbounded URL space. Those pages already return "noindex, follow"; this stops
# them consuming crawl budget that belongs to the ~5,900 real product pages.
Disallow: /*?*
Disallow: /*?
Disallow: /*~*
Disallow: /*~
# --- Personal, transactional, or nothing to index ---
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /search/
Disallow: /search
# --- WooCommerce sorting, filtering and cart actions ---
# (subsumed by /*?* above; kept as defence in depth)
Disallow: /*?orderby=price
Disallow: /*?orderby=price-desc
Disallow: /*?orderby=rating
Disallow: /*?orderby=date
Disallow: /*?orderby=popularity
Disallow: /*?orderby=title
Disallow: /*?orderby=desc
Disallow: /*?filter
Disallow: /*add-to-cart=*
Disallow: /*add_to_wishlist=*
Disallow: /*?paged=&count=*
Disallow: /*?count=*
# --- Crawler traps ---
Disallow: *?s=*
Disallow: *?p=*
Disallow: *&p=*
Disallow: *&preview=*

# =============================================================================
# Search, social and AI crawlers are NOT listed individually any more.
#
# Every one of them previously had a "User-agent: X / Allow: /" group, which
# exempted it from all of the above. They now inherit the rules in "*", which
# still leaves the whole catalogue, every category and the blog crawlable — only
# parameter URLs, the cart, the checkout and account pages are off limits. That
# is the intended behaviour for Google, Bing, Yandex, Baidu, the social preview
# fetchers and the AI search/training crawlers alike.
# =============================================================================
# --- Aggressive crawlers: blocked outright ---
User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /