# Block some general WP endpoints
# -------------------------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /wp-json/
Disallow: /?rest_route=
Disallow: /wp-admin/
Disallow: /wp-content/cache/
Disallow: /wp-content/plugins/
Disallow: /wp-login.php
Disallow: /xmlrpc.php

# Special handling for /wp-includes/
# ----------------------------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /wp-includes/
Allow: /wp-includes/css/
Allow: /wp-includes/js/

# Block internal search
# ---------------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /?s=
Disallow: /page/*/?s=
Disallow: /search/

# Adsbot doesn't ever need to crawl fonts
# ---------------------------------------
User-agent: AdsBot-Google
Disallow: /*.woff2

# Block legacy Ezoic URLs
# -----------------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /ezoic/
Disallow: /porpoiseant/
Disallow: /detroitchicago/

# Block workers
# -------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /workers/

# Block partytown
# ---------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /~partytown

# Block leaky plugins
# -------------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /wp-content/uploads/complianz/
Disallow: /?wp-ajax=

# Block leaky Cloudflare endpoints
# --------------------------------
User-agent: *
User-agent: AdsBot-Google
Disallow: /cdn-cgi/bm/cv/
Disallow: /cdn-cgi/challenge-platform/
Disallow: /cdn-cgi/images/trace/
Disallow: /cdn-cgi/rum
Disallow: /cdn-cgi/scripts/
Disallow: /cdn-cgi/styles/
Disallow: /cdn-cgi/zaraz/

# Ban noisy bots
# --------------
User-agent: Nuclei
User-agent: WikiDo
User-agent: Riddler
User-agent: PetalBot
User-agent: Zoominfobot
User-agent: Go-http-client
User-agent: Node/simplecrawler
User-agent: CazoodleBot
User-agent: dotbot/1.0
User-agent: Gigabot
User-agent: Barkrowler
User-agent: BLEXBot
User-agent: magpie-crawler
User-agent: MJ12bot
User-agent: AhrefsBot
Disallow: /

# Sitemap
# -------
Sitemap: https://www.daysoftheyear.com/sitemap_index.xml