# robots.txt — citychurchtallahassee.com
# Purpose: stop crawling of the infinite URL space generated by
# The Events Calendar (pagination x tribe-bar-date x ical feeds)
# and limit AI bots that were consuming ~50% of server resources.

# ---------------------------------------------------------------
# 1. General rules for all bots
# ---------------------------------------------------------------
User-agent: *

# WordPress core
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /?author=
Disallow: /author/

# The Events Calendar — infinite URL trap.
#
# What stays crawlable (the pages that actually rank + the navigation path):
#   /events/                          main landing page (default view = List)
#   /events/list/                     clean list, page 1
#   /events/list/page/2..5/           the "next" chain, including its
#                                     ?tribe-bar-date= parameter
#   /events/category/<cat>/           all 10 category landing pages
#   /event/<slug>/                    all 199 individual events
#
# IMPORTANT: the site's own "next" button emits
#   /events/list/page/2/?tribe-bar-date=2026-08-05
# so ?tribe-bar-date= is NOT junk — it is the real pagination chain, with
# today's date injected automatically. A blanket Disallow on that parameter
# would cut the crawl path to every event past page 1.
#
# So we block deep pagination (page 6+) instead, where events are 6+ months
# out and have no search value. Log hits per page: p2=128, p3=109, p4=94,
# p5=83 (real sequential navigation), then a long flat tail out to page 21.
# Duplicate calendar views of the same events.
Disallow: /events/month/
Disallow: /events/today/

# Deep pagination: pages 6 and up are blocked, pages 1-5 stay open.
# Every blocked page number is written out in full — no wildcards and no
# Allow/Disallow precedence tricks, because those two mechanisms interact
# badly with the ?tribe-bar-date= query string the "next" button appends.
# Pages 22-29 are listed too, in case the calendar grows.
Disallow: /events/list/page/6/
Disallow: /events/list/page/7/
Disallow: /events/list/page/8/
Disallow: /events/list/page/9/
Disallow: /events/list/page/10/
Disallow: /events/list/page/11/
Disallow: /events/list/page/12/
Disallow: /events/list/page/13/
Disallow: /events/list/page/14/
Disallow: /events/list/page/15/
Disallow: /events/list/page/16/
Disallow: /events/list/page/17/
Disallow: /events/list/page/18/
Disallow: /events/list/page/19/
Disallow: /events/list/page/20/
Disallow: /events/list/page/21/
Disallow: /events/list/page/22/
Disallow: /events/list/page/23/
Disallow: /events/list/page/24/
Disallow: /events/list/page/25/
Disallow: /events/list/page/26/
Disallow: /events/list/page/27/
Disallow: /events/list/page/28/
Disallow: /events/list/page/29/

# Same for category archives (10 categories, one wildcard for the slug only).
Disallow: /events/category/*/page/6/
Disallow: /events/category/*/page/7/
Disallow: /events/category/*/page/8/
Disallow: /events/category/*/page/9/
Disallow: /events/category/*/page/10/
Disallow: /events/category/*/page/11/
Disallow: /events/category/*/page/12/
Disallow: /events/category/*/page/13/
Disallow: /events/category/*/page/14/
Disallow: /events/category/*/page/15/
Disallow: /events/category/*/page/16/
Disallow: /events/category/*/page/17/
Disallow: /events/category/*/page/18/
Disallow: /events/category/*/page/19/
Disallow: /events/category/*/page/20/
Disallow: /events/category/*/page/21/
Disallow: /*?eventDisplay=
Disallow: /*&eventDisplay=
Disallow: /*?eventDate=
Disallow: /*&eventDate=
Disallow: /*?post_type=tribe_events

# Calendar feeds (1,144 requests in 12h)
Disallow: /*ical=1
Disallow: /*outlook-ical=1
Disallow: /*?ical
Disallow: /*&ical

# Cache / optimization parameters — should never be indexed
Disallow: /*?nowprocket=
Disallow: /*&nowprocket=
Disallow: /*?no_optimize=
Disallow: /*?wpr_imagedimensions=

# Internal search and other parasitic parameters
Disallow: /*?s=
Disallow: /*?format=
Disallow: /*&format=
Disallow: /*?replytocom=
Disallow: /*?add-to-cart=

# RSS feeds (canonical pages remain indexable)
Disallow: /comments/feed/
Disallow: /*/feed/

# Explicitly allow assets — Google needs them to render pages
Allow: /wp-content/uploads/
Allow: /wp-includes/js/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.webp$
Allow: /*.gif$
Allow: /*.svg$

# ---------------------------------------------------------------
# 2. AI bots — full block
#    (ClaudeBot + GPTBot generated 1,592 req/12h and got 220 x 429)
# ---------------------------------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-User
Disallow: /

User-agent: Claude-SearchBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

# ---------------------------------------------------------------
# 3. SEO bots / commercial scrapers — no value for this site
# ---------------------------------------------------------------
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: ZoominfoBot
Disallow: /

# ---------------------------------------------------------------
# 4. Legitimate search engines — keep access, but with throttling
#    and the same calendar restrictions
# ---------------------------------------------------------------
# NOTE: a user-agent block does NOT inherit from "User-agent: *" — the most
# specific matching block replaces it entirely. So every rule these crawlers
# need has to be repeated here, including the WordPress core ones.
User-agent: bingbot
Crawl-delay: 10
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /author/
Disallow: /events/month/
Disallow: /events/today/
Disallow: /events/list/page/6/
Disallow: /events/list/page/7/
Disallow: /events/list/page/8/
Disallow: /events/list/page/9/
Disallow: /events/list/page/10/
Disallow: /events/list/page/11/
Disallow: /events/list/page/12/
Disallow: /events/list/page/13/
Disallow: /events/list/page/14/
Disallow: /events/list/page/15/
Disallow: /events/list/page/16/
Disallow: /events/list/page/17/
Disallow: /events/list/page/18/
Disallow: /events/list/page/19/
Disallow: /events/list/page/20/
Disallow: /events/list/page/21/
Disallow: /events/category/*/page/6/
Disallow: /events/category/*/page/7/
Disallow: /events/category/*/page/8/
Disallow: /events/category/*/page/9/
Disallow: /events/category/*/page/10/
Disallow: /events/category/*/page/11/
Disallow: /events/category/*/page/12/
Disallow: /*ical=1
Disallow: /*outlook-ical=1
Disallow: /*?nowprocket=
Disallow: /*?s=

User-agent: Applebot
Crawl-delay: 10
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /author/
Disallow: /events/month/
Disallow: /events/today/
Disallow: /events/list/page/6/
Disallow: /events/list/page/7/
Disallow: /events/list/page/8/
Disallow: /events/list/page/9/
Disallow: /events/list/page/10/
Disallow: /events/list/page/11/
Disallow: /events/list/page/12/
Disallow: /*ical=1
Disallow: /*outlook-ical=1
Disallow: /*?nowprocket=

User-agent: YandexBot
Crawl-delay: 20
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /author/
Disallow: /events/month/
Disallow: /events/today/
Disallow: /events/list/page/6/
Disallow: /events/list/page/7/
Disallow: /events/list/page/8/
Disallow: /events/list/page/9/
Disallow: /events/list/page/10/
Disallow: /events/list/page/11/
Disallow: /events/list/page/12/
Disallow: /*ical=1
Disallow: /*outlook-ical=1
Disallow: /*?nowprocket=

# ---------------------------------------------------------------
# 5. Sitemap
# ---------------------------------------------------------------
Sitemap: https://www.citychurchtallahassee.com/sitemap.xml