#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
Crawl-delay: 1760
# Directories
Disallow: /chairmansblog3/wp-login.php*
Disallow: /chairmansblog3/*.php*
Disallow: /sites/default/files/*
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
#Disallow: /mass-listings/
#Disallow: /mass-listings
#Disallow: /mass-listings*
Disallow: /mass-listings/*
Disallow: /mass-listings-notanymore
Disallow: /mass-listings-notanymore*
Disallow: /mass-listings-notanymore/*
# Files
#added by gjcopp 21-07-21 remove when document is published
Disallow: /sites/default/files/resource_documents/Trad_Cust_canonical_notes.pdf 
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
#added by gjcopp 21-07-21 remove when document is published
Disallow: /tradcust/canonical_notes
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/
Disallow: /?q=mass-listings*
Disallow: /mass-listings?*

#
# spiderslap
Disallow: /now/bugoff







Disallow: /photo-files/*
Disallow: /find-a-mass/*
Disallow: /news-and-events/*
Disallow: /resources/shop/*
Disallow: /autodiscover/*


User-agent: Baiduspider 
Disallow: /

User-agent: Curl 
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: oBot
Disallow: /

User-agent: SemrushBot
Disallow: /


User-agent: Baiduspider 
Disallow: 

User-agent: Curl 
Disallow: 

User-agent: MJ12bot
Disallow: 

User-agent: AhrefsBot
Disallow: 

User-agent: oBot
Disallow: 

User-agent: SemrushBot
Disallow: 

User-agent: YandexBot
Disallow: 

User-Agent: The Knowledge AI
Disallow: /

User-agent: * 
Crawl-delay: 1760
Disallow: /cgi-bin/ 
Disallow: /private/ 
Disallow: /tmp/
Disallow: /feed
Disallow: /rss
Disallow: /feeds/
Disallow: /photo-files/
Disallow: /cache/
Disallow: /taxonomy/term/*/all/*
Disallow: /church/*?page=*

Allow: /product/daily-missal-1962
Allow: /product/ordinary-prayers-traditional-latin-mass
Allow: /catalog/missals
Allow: /mp3-chant-downloads
Allow: /about


User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: Amazonbot
User-agent: Andibot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: bedrockbot
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: EchoboxBot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User/1.0
User-agent: MyCentralAIScraperBot
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: Operator
User-agent: PanguBot
User-agent: Panscient
User-agent: panscient.com
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: PhindBot
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SemrushBot-CT
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: wpbot
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YouBot
Disallow: /