#
# robots.txt
#
# This file prevents crawling and indexing of certain parts of the site.
# Place at the root of your host: https://www.hee.nhs.uk/robots.txt
#
# ----------------------------------------------------
# Allow mainstream search engines basic access
# ----------------------------------------------------
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
# 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
# Extra patterns
Disallow: /search
Disallow: /search?
Disallow: /*?amp
# ----------------------------------------------------
# Block AI/data-scraping bots (explicit block per bot)
# ----------------------------------------------------
User-agent: AddSearchBot
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: Ai2Bot-Dolma
Disallow: /
User-agent: aiHitBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Andibot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Applebot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Awario
Disallow: /
User-agent: bedrockbot
Disallow: /
User-agent: bigsur.ai
Disallow: /
User-agent: Brightbot 1.0
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ChatGPT Agent
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: Claude-SearchBot
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CloudVertexBot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /
User-agent: Cotoyogi
Disallow: /
User-agent: Crawlspace
Disallow: /
User-agent: Datenbank Crawler
Disallow: /
User-agent: Devin
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: DuckAssistBot
Disallow: /
User-agent: Echobot Bot
Disallow: /
User-agent: EchoboxBot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: facebookexternalhit
Disallow: /
User-agent: Factset_spyderbot
Disallow: /
User-agent: FirecrawlAgent
Disallow: /
User-agent: FriendlyCrawler
Disallow: /
User-agent: Gemini-Deep-Research
Disallow: /
User-agent: Google-CloudVertexBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Google-Firebase
Disallow: /
User-agent: GoogleAgent-Mariner
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: GoogleOther-Image
Disallow: /
User-agent: GoogleOther-Video
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: iaskspider/2.0
Disallow: /
User-agent: ICC-Crawler
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: ISSCyberRiskCrawler
Disallow: /
User-agent: Kangaroo Bot
Disallow: /
User-agent: LinerBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: meta-externalfetcher
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: meta-webindexer
Disallow: /
User-agent: MistralAI-User
Disallow: /
User-agent: MistralAI-User/1.0
Disallow: /
User-agent: MyCentralAIScraperBot
Disallow: /
User-agent: netEstate Imprint Crawler
Disallow: /
User-agent: NovaAct
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: omgili
Disallow: /
User-agent: omgilibot
Disallow: /
User-agent: OpenAI
Disallow: /
User-agent: Operator
Disallow: /
User-agent: PanguBot
Disallow: /
User-agent: Panscient
Disallow: /
User-agent: panscient.com
Disallow: /
User-agent: Perplexity-User
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: PhindBot
Disallow: /
User-agent: Poseidon Research Crawler
Disallow: /
User-agent: QualifiedBot
Disallow: /
User-agent: QuillBot
Disallow: /
User-agent: quillbot.com
Disallow: /
User-agent: SBIntuitionsBot
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: SemrushBot-OCOB
Disallow: /
User-agent: SemrushBot-SWA
Disallow: /
User-agent: ShapBot
Disallow: /
User-agent: Sidetrade indexer bot
Disallow: /
User-agent: TerraCotta
Disallow: /
User-agent: Thinkbot
Disallow: /
User-agent: TikTokSpider
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: VelenPublicWebCrawler
Disallow: /
User-agent: WARDBot
Disallow: /
User-agent: Webzio-Extended
Disallow: /
User-agent: wpbot
Disallow: /
User-agent: YaK
Disallow: /
User-agent: YandexAdditional
Disallow: /
User-agent: YandexAdditionalBot
Disallow: /
User-agent: YouBot
Disallow: /
# ----------------------------------------------------
# Crawl delay and sitemap
# ----------------------------------------------------
Crawl-delay: 5
Sitemap: https://www.hee.nhs.uk/sitemap.xml