# vegeats.app robots.txt  (policy of 2026-09-21, lane legal_pages)
#
# ---- LAUNCHED 2026-10-07 ----------------------------------------------
#
# The site is public. All three pre-launch locks are off, in this order
# (never re-order it -- the robots and noindex locks must go in the same
# deploy as the 401 or before it, never after, or the site is briefly
# crawlable while still saying it is private):
#   1. the three `Disallow: /` lines marked PRE-LAUNCH, deleted from this
#      file, one from each of the three groups that are otherwise let in.
#   2. `X-Robots-Tag: noindex` on /*, deleted from app/site/_headers.
#   3. the basic-auth 401 in functions/_middleware.js, lifted by setting the
#      Pages secret SITE_PUBLIC=1.
#
# Nothing else in this file changed at launch, and nothing below this header
# is pre-launch scaffolding: the `Disallow: /` at the foot of the file is the
# deliberate full block on SEO scrapers and unnamed AI crawlers, and it
# stays. See DEPLOY.md, "Launching".
#
# STILL TO DO: submit the sitemap in Search Console and Bing Webmaster.
#
# ---- The policy --------------------------------------------------------
#
# Riley wants Veg Eats found, recommended and cited by search engines and by
# the AI answer products (ChatGPT, Gemini, Claude, Perplexity, Copilot).
# So:
#   * PUBLIC PAGES (/, /place/*, /city/*, /cities.html, /map.html,
#     /search.html, the legal pages) are open to the search and answer
#     agents named below, and to the big labs' training crawlers.
#   * THE DATA BEHIND THE PAGES (bulk files, map tiles, page shards and
#     every API route) is closed to every crawler, named or not.
#   * EVERYONE ELSE -- generic scrapers, dataset builders, data brokers,
#     SEO scrapers, unnamed AI crawlers -- gets nothing (the last group,
#     plus the catch-all `User-agent: *`, which after launch still lets
#     ordinary search engines not named here index the public pages).
#
# A crawler obeys the ONE group that names it most specifically and ignores
# the others, which is why the data rules are repeated in every group.
#
# robots.txt is a request, not a lock. The ones that do not honour it are
# handled by the token gate on /m/*, Cloudflare's per-crawler AI controls,
# bot rules and rate limits, and the Terms (terms.html section 10).
# scratchpad/legal_pages/NOTES.md has the Cloudflare side.

# ---- Everyone else, including search engines not named below -------------
User-agent: *
# The data behind the pages: bulk files, tiles, shards and APIs.
Disallow: /m/
Disallow: /q/
Disallow: /_t/
Disallow: /_p/
Disallow: /_s/
Disallow: /t/
Disallow: /g/
Disallow: /la.
Disallow: /desc.
Disallow: /venues.js
Disallow: /terms.js
Disallow: /cuisines.js
Disallow: /places.js
Disallow: /onboard-stats.js
Disallow: /onboard-places.js
Disallow: /*.json$
Disallow: /v/
Disallow: /signup/
Disallow: /account/
Disallow: /billing/
Disallow: /welcome.html
Disallow: /search.html?
Disallow: /map.html?
Allow: /.well-known/tdmrep.json

# ---- Search and answer agents: public pages yes, data no ------------------
# Googlebot (Google Search, AI Overviews), Bingbot (Bing, Copilot, and part
# of ChatGPT search), OpenAI's search index and user fetches, Anthropic's,
# Perplexity's, DuckDuckGo's AI answers, and Apple (Siri, Spotlight).
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckAssistBot
User-agent: Applebot
Disallow: /m/
Disallow: /q/
Disallow: /_t/
Disallow: /_p/
Disallow: /_s/
Disallow: /t/
Disallow: /g/
Disallow: /la.
Disallow: /desc.
Disallow: /venues.js
Disallow: /terms.js
Disallow: /cuisines.js
Disallow: /places.js
Disallow: /onboard-stats.js
Disallow: /onboard-places.js
Disallow: /*.json$
Disallow: /v/
Disallow: /signup/
Disallow: /account/
Disallow: /billing/
Disallow: /welcome.html
Disallow: /search.html?
Disallow: /map.html?
Allow: /.well-known/tdmrep.json

# ---- Model TRAINING crawlers: public pages yes, data no --------------------
# FLIP THIS BLOCK ALONE to change the training decision: replace everything
# under these four User-agent lines with a single `Disallow: /`.
# Riley's call (2026-09-21): being in the models is part of being
# recommended. Google-Extended also governs whether Gemini may ground its
# answers in our pages; Applebot-Extended is Apple Intelligence's. Both are
# opt-out tokens that never crawl, and neither affects Google or Apple
# search.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
Disallow: /m/
Disallow: /q/
Disallow: /_t/
Disallow: /_p/
Disallow: /_s/
Disallow: /t/
Disallow: /g/
Disallow: /la.
Disallow: /desc.
Disallow: /venues.js
Disallow: /terms.js
Disallow: /cuisines.js
Disallow: /places.js
Disallow: /onboard-stats.js
Disallow: /onboard-places.js
Disallow: /*.json$
Disallow: /v/
Disallow: /signup/
Disallow: /account/
Disallow: /billing/
Disallow: /welcome.html
Disallow: /search.html?
Disallow: /map.html?
Allow: /.well-known/tdmrep.json

# ---- Blocked entirely: dataset builders, generic scrapers, data brokers,
# SEO scrapers and AI crawlers not on the allow lists above ------------------
# From the community list at github.com/ai-robots-txt/ai.robots.txt
# (checked 2026-09-21). Link-preview agents (facebookexternalhit, Slackbot,
# Twitterbot, Discordbot, LinkedInBot) are deliberately NOT here, so shared
# links still unfurl.
User-agent: AddSearchBot
User-agent: AgentTimes
User-agent: AI2Bot
User-agent: AI2Bot-DeepResearchEval
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: AIWebIndex
User-agent: amazon-kendra
User-agent: amazon-QBusiness
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: Aranet-SearchBot
User-agent: atlassian-bot
User-agent: Awario
User-agent: AzureAI-SearchBot
User-agent: bedrockbot
User-agent: bigsur.ai
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: ChatGPT Agent
User-agent: Claude-Code
User-agent: Claude-Web
User-agent: Cloudflare-AutoRAG
User-agent: CloudVertexBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: CragCrawler
User-agent: Crawl4AI
User-agent: Crawlspace
User-agent: Cursor
User-agent: Datenbank Crawler
User-agent: DeepSeekBot
User-agent: Devin
User-agent: Diffbot
User-agent: Diffbot-User
User-agent: DoubaoBot
User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: ERNIEBot
User-agent: ExaBot
User-agent: ExaSearchBot
User-agent: FacebookBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: GeistHaus-PageFetcher
User-agent: Gemini-Deep-Research
User-agent: Google-Agent
User-agent: Google-CloudVertexBot
User-agent: Google-Firebase
User-agent: Google-Gemini-CLI
User-agent: Google-NotebookLM
User-agent: GoogleAgent-Mariner
User-agent: GoogleAgent-URLContext
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: HenkBot
User-agent: iAskBot
User-agent: iaskspider
User-agent: iaskspider/2.0
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: Kimi-SearchBot
User-agent: Kimi-User
User-agent: KimiBot
User-agent: KlaviyoAIBot
User-agent: KunatoCrawler
User-agent: laion-huggingface-processor
User-agent: LAIONDownloader
User-agent: Lightpanda
User-agent: LinerBot
User-agent: Linguee Bot
User-agent: LinkupBot
User-agent: Manus-User
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: meta-webindexer
User-agent: MistralAI-Index
User-agent: MistralAI-Training
User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
User-agent: Mozilla-Tabstack
User-agent: MyCentralAIScraperBot
User-agent: NagetBot
User-agent: netEstate Imprint Crawler
User-agent: newsai
User-agent: NotebookLM
User-agent: NovaAct
User-agent: OAI-AdsBot
User-agent: omgili
User-agent: omgilibot
User-agent: OpenAI
User-agent: opencode
User-agent: Operator
User-agent: PanguBot
User-agent: Panscient
User-agent: panscient.com
User-agent: PhindBot
User-agent: Poggio-Citations
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: Querit-SearchBot
User-agent: QueritBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: QwenBot
User-agent: Reflectionbot
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Shap-User
User-agent: ShapBot
User-agent: Sidetrade indexer bot
User-agent: TavilyBot
User-agent: Terra Cotta
User-agent: TerraCotta
User-agent: Thinkbot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: TongyiBot
User-agent: Trae
User-agent: TwinAgent
User-agent: UseAI
User-agent: VelenPublicWebCrawler
User-agent: WARDBot
User-agent: Webzio-Extended
User-agent: webzio-extended
User-agent: wpbot
User-agent: WRTNBot
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YiyanBot
User-agent: YouBot
User-agent: ZanistaBot
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: DataForSeoBot
User-agent: BLEXBot
User-agent: serpstatbot
Disallow: /

Sitemap: https://vegeats.app/sitemap.xml