Infrastructure

#
# 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: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
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: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
Disallow: /web.config
# Paths (clean URLs)
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
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# AI Bots from
# https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Crawlspace
User-agent: Diffbot
User-agent: FriendlyCrawler
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-ExternalFetcher
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
User-agent: AhrefsBot
User-agent: Barkrowler
User-agent: python-requests/2.31.0
User-agent: Go-http-client/2.0
User-agent: Scrapy/2.11.2
Disallow: /

User-agent: *
Crawl-delay: 10

Sitemap: https://www.sierraclub.org/sitemap.xml