# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a content-signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a content-signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a content signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via content signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-Agent: *
Content-signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# GoToSocial robots.txt -- to edit, see internal/api/util/robots.go
# More info @ https://developers.google.com/search/docs/crawling-indexing/robots/intro

# AI scrapers and the like.
# https://github.com/ai-robots-txt/ai.robots.txt/
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: FriendlyCrawler
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: imgproxy
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: Operator
User-agent: PanguBot
User-agent: Perplexity-User
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
Disallow: /

# Marketing/SEO "intelligence" data scrapers
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: DataForSeoBot
User-agent: magpie-crawler
User-agent: Meltwater
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: PiplBot
User-agent: scoop.it
User-agent: Seekr
Disallow: /

# Well-known.dev crawler. Indexes stuff under /.well-known.
# https://well-known.dev/about/
User-agent: WellKnownBot
Disallow: /

# Rules for everything else.
User-agent: *
Crawl-delay: 500

# API endpoints.
Disallow: /api/

# Auth/Sign in endpoints.
Disallow: /auth/
Disallow: /oauth/
Disallow: /check_your_email
Disallow: /wait_for_approval
Disallow: /account_disabled
Disallow: /signup

# Fileserver/media.
Disallow: /fileserver/

# Fedi S2S API endpoints.
Disallow: /users/
Disallow: /emoji/

# Settings panels.
Disallow: /admin
Disallow: /user
Disallow: /settings/

# Domain blocklist.
Disallow: /about/suspended

# Webfinger endpoint.
Disallow: /.well-known/webfinger

# Disallow nodeinfo
Disallow: /.well-known/nodeinfo
Disallow: /nodeinfo/