#
# 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: 10

User-agent: *
# CSS, JS, Images
Allow: /misc/*.css$
Allow: /misc/*.css?
Allow: /misc/*.js$
Allow: /misc/*.js?
Allow: /misc/*.gif
Allow: /misc/*.jpg
Allow: /misc/*.jpeg
Allow: /misc/*.png
Allow: /modules/*.css$
Allow: /modules/*.css?
Allow: /modules/*.js$
Allow: /modules/*.js?
Allow: /modules/*.gif
Allow: /modules/*.jpg
Allow: /modules/*.jpeg
Allow: /modules/*.png
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /themes/*.css$
Allow: /themes/*.css?
Allow: /themes/*.js$
Allow: /themes/*.js?
Allow: /themes/*.gif
Allow: /themes/*.jpg
Allow: /themes/*.jpeg
Allow: /themes/*.png

# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/

# Files
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)
Disallow: /admin/
# set canonical (2021-01-20)
#Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
# should be excluded by noindex, but disallowed for linebot (2022-09-29) and msnbot/bingbot (2023-06-21)
Disallow: /search/
# 2022-10-25 yasuda
Disallow: /apachesolr_autocomplete_callback/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/

# Paths (no clean URLs)
Disallow: /?q=admin/
# set canonical (2021-01-20)
#Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
# should be excluded by noindex, but disallowed for linebot (2022-09-29) and msnbot/bingbot (2023-06-21)
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/

# Paths (clean URLs) added by YASUDA
# do these with noindex, not robots.txt
#Disallow: /node/*/edit
#Disallow: /node/*/revisions
#Disallow: /node/*/revisions/*
#Disallow: /node/*/draft
#Disallow: /node/*/draft_yahoo_news
#Disallow: /node/*/flightcheck
#Disallow: /myarticles

# 2014-10-09 by YASUDA
# to prevent not found error in webmaster tool
Disallow: /7623538/
Disallow: /7623538/
Disallow: /mollom/


#User-agent指定系は、基本的なdisallowの後に書くこと
#https://twitter.com/tsuj/status/1586225824256049153


# 2020-05-12 by YASUDA
User-agent: NaverBot
Crawl-delay: 180
User-agent: Yetibot
Crawl-delay: 180
User-agent: Baiduspider
Crawl-delay: 180
User-agent: Baiduspider+
Crawl-delay: 180

# Google-Extended
# GPTBot

#bingbot用crawl-delayは10らしいけど*で10を指定してるのでいいや
#https://blogs.bing.com/webmaster/2012/05/03/to-crawl-or-not-to-crawl-that-is-bingbots-question/
#https://blogs.bing.com/webmaster/2009/08/10/crawl-delay-and-the-bing-crawler-msnbot