User-agent: *
Disallow: /data
Disallow: /feedback/?page
Disallow: /galleries/add/*.html
Disallow: /journey/*/maplet*.png
Disallow: /journey/*/change.html
Disallow: /journey/*/return.html
Disallow: /journey/*/*.gpx
Disallow: /journey/*/*.kml
Disallow: /journey/help/osmconversion
Disallow: /journey/places/from/
Disallow: /localauthorities/contacts
Disallow: /location/*/update.html
Disallow: /location/*/delete.html
Allow: /location/*/cyclestreets*-size640.jpg
Allow: /location/*/cyclestreets*-size1200.jpg
Disallow: /location/*/cyclestreets*-size*.jpg
Disallow: /photomap/add/?longitude
Disallow: /photomap/1
Disallow: /photomap/2
Disallow: /photomap/3
Disallow: /photomap/4
Disallow: /photomap/5
Disallow: /photomap/6
Disallow: /photomap/7
Disallow: /photomap/8
Disallow: /photomap/9
Disallow: /photomap/tags/*/page*.html
Disallow: /photos/day
Disallow: /photos/page
Disallow: /photos/space
Disallow: /photos/time
Allow: /photos/all/page*.html
Disallow: /photos/*/page*.html
Disallow: /photos/*/*/page*.html
Disallow: /search/?search
Disallow: /search/page
Disallow: /search/id
Disallow: /search/photoId
Disallow: /search/caption
Disallow: /users/*/*/page
Disallow: /users/*/*/id
Disallow: /users/*/*/plan
Disallow: /users/*/*/name
Disallow: /users/*/*/leaving
Disallow: /users/*/*/length
Disallow: /users/*/*/time
Disallow: /users/*/*/quietness
Disallow: /users/*/*/hasVideo
Disallow: /users/*/*/photoId
Disallow: /users/*/*/caption
Disallow: /view
Disallow: /views/tinkles
Disallow: /tiles
Disallow: /signin/?/
#Disallow: /journey/places/from/
#Disallow: /journey/places/to/

# Slow down Yandex
User-agent: Yandex
Crawl-delay: 5

# Unwanted user-agents that just waste bandwidth/CPU
User-agent: TurnitinBot
User-agent: Nutch
Disallow: /

# AI scraping is NOT PERMITTED without express permission: see: https://www.cyclestreets.net/privacy/
# We additionally list these known agents, but this is not exhaustive and other AI bots not listed are also not permitted
# See: https://neil-clarke.com/block-the-bots-that-feed-ai-models-by-scraping-your-website/
# SeeL 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: 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: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
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
User-agent: VelenPublicWebCrawler
User-agent: AliyunSecBot
Disallow: /