# Blog posts, talks and papers stay open to everyone, including AI crawlers.
# Only the photo gallery is restricted: the photographs are all rights reserved
# and not licensed for AI training. See https://ericphanson.com/photos/license/
#
# Scope note: the images themselves are served from eph-photos.b-cdn.net, a
# different origin, so these rules do not reach them. The binding statement for
# the image files is the IPTC/PLUS `plus:DataMining` property embedded in every
# file, plus the TDMRep declaration at /.well-known/tdmrep.json.
#
# AI crawler list adapted from https://github.com/ai-robots-txt/ai.robots.txt
# Kept verbatim from upstream, including a few tokens that contain spaces or
# slashes ("Brightbot 1.0", "Kangaroo Bot", "iaskspider/2.0"). Those are not
# valid product tokens under a strict reading of RFC 9309, so a strict parser
# may skip them. They are left as-is to stay in sync with upstream, which is
# what the bots themselves publish.

# `Allow: /` is load-bearing, not decorative. Under RFC 9309 a group ends only
# at a rule line -- blank lines, comments and Sitemap: do not end one. Without
# a rule here, `*` merges into the AI-crawler group below and inherits its
# Disallow rules, which silently de-indexes the gallery from Google and Bing.
User-agent: *
Allow: /

Sitemap: https://ericphanson.com/sitemap.xml

# ---------------------------------------------------------------------------
# AI training and dataset crawlers: photo gallery disallowed.
# ---------------------------------------------------------------------------

User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: bedrockbot
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: Cotoyogi
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
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-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-Training
User-agent: NovaAct
User-agent: omgili
User-agent: omgilibot
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: /photos/
Disallow: /tags/photography/
# The site-root search index carries 138 photo entries -- caption, full
# taxonomy, and a direct CDN thumbnail URL each. Leaving it open would hand a
# crawler the whole gallery in one allowed file, which is the /photos/ rule
# undone. It is a machine surface, not "the writing".
Disallow: /index.json