#
# 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-triggered AI agents: someone asked their assistant to fetch/browse this
# specific page in real time (not bulk crawling/training). Deliberately kept
# separate from the AI crawler opt-out block below — matches the same
# distinction already made in scripts/ai-robots/bglog-nginx-block-ai-crawlers.conf.
User-agent: ChatGPT Agent
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Manus-User
User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
User-agent: NotebookLM
User-agent: NovaAct
User-agent: Operator
User-agent: Perplexity-User
Allow: /

# Social sharing/link preview crawlers need access to Open Graph metadata.
User-agent: facebookexternalhit
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Facebot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: meta-externalfetcher
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: meta-webindexer
Disallow: /search/
Disallow: /user/login
Allow: /

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
# Legacy uploaded documents. These URLs are migrated file attachments, not
# landing pages, and should not be indexed as standalone search results.
Disallow: /ClientFiles/
Disallow: /sites/default/files/legacy-clientfiles/ClientFiles/
# 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

# SEO backlink/research crawlers: pure resource drain, no benefit to
# bglog.net (they feed their own paid tools, not Google/Bing search
# results). SemrushBot is deliberately left crawlable - kept for the
# site's own SEO monitoring.
User-agent: DotBot
User-agent: AhrefsBot
User-agent: MJ12bot
Disallow: /

# AI crawler opt-out. Based on https://github.com/ai-robots-txt/ai.robots.txt
# Added as a polite robots.txt layer; nginx can hard-block selected crawlers.
User-agent: AddSearchBot
User-agent: AI2Bot
User-agent: AI2Bot-DeepResearchEval
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: amazon-kendra
User-agent: Amazonbot
User-agent: AmazonBuyForMe
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: Andibot
User-agent: Anomura
User-agent: anthropic-ai
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Aranet-SearchBot
User-agent: atlassian-bot
User-agent: Awario
User-agent: AzureAI-SearchBot
User-agent: bedrockbot
User-agent: bigsur.ai
User-agent: Bravebot
User-agent: Brightbot
User-agent: Brightbot 1.0
User-agent: BuddyBot
User-agent: Bytespider
User-agent: CCBot
User-agent: Channel3Bot
User-agent: ChatGLM-Spider
User-agent: Claude-Code
User-agent: Claude-SearchBot
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Cloudflare-AutoRAG
User-agent: CloudVertexBot
User-agent: Code
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawl4AI
User-agent: Crawlspace
User-agent: Datenbank Crawler
User-agent: DeepSeekBot
User-agent: Devin
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: ExaBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Gemini-Deep-Research
User-agent: GPTBot
User-agent: HenkBot
User-agent: iAskBot
User-agent: iaskspider
User-agent: iaskspider/2.0
User-agent: IbouBot
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: imageSpider
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: kagi-fetcher
User-agent: Kangaroo Bot
User-agent: KlaviyoAIBot
User-agent: KunatoCrawler
User-agent: laion-huggingface-processor
User-agent: LAIONDownloader
User-agent: LCC
User-agent: LinerBot
User-agent: Linguee Bot
User-agent: LinkupBot
User-agent: MyCentralAIScraperBot
User-agent: NagetBot
User-agent: netEstate Imprint Crawler
User-agent: newsai
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: OpenAI
User-agent: opencode
User-agent: PanguBot
User-agent: Panscient
User-agent: panscient.com
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: PhindBot
User-agent: Poggio-Citations
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: ShapBot
User-agent: Sidetrade indexer bot
User-agent: Spider
User-agent: TavilyBot
User-agent: Terra Cotta
User-agent: TerraCotta
User-agent: Thinkbot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: Trae
User-agent: TwinAgent
User-agent: VelenPublicWebCrawler
User-agent: WARDBot
User-agent: Webzio-Extended
User-agent: webzio-extended
User-agent: wpbot
User-agent: WRTNBot
User-agent: YaK
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YouBot
User-agent: ZanistaBot
Disallow: /

Sitemap: https://bglog.net/sitemap.xml