# robots.txt
# Page is under the FOPL-ZERO license
# https://owly.fans/license/fopl-zero

# This page is also on git:
# Please feel free to suggest a change to this file
# https://github.com/DynTylluan/owly.fans/blob/main/robots.txt (main)
# https://notabug.org/DynTylluan/owly.fans/src/main/robots.txt (mirror)
# https://tildegit.org/cass/owly.fans/src/branch/main/robots.txt (mirror)

# GPTBot is OpenAI's web crawler.
# I do not want it to use my content as it does not cite its sources.
# https://platform.openai.com/docs/gptbot
User-agent: GPTBot
User-agent: ChatGPT-User
Disallow: /

# Common Crawl bot.
# From what I've leant from reading online, «[t]he majority of ChatGPT's
# training data comes from the Common Crawl crawler bot».
# Quote: https://datadome.co/threat-research/how-chatgpt-openai-might-use-your-content-now-in-the-future
# https://commoncrawl.org/faq
User-agent: CCBot
Disallow: /

# Google's AI training bot.
# I also don't want to have my content used without giving me credit.
# https://blog.google/technology/ai/an-update-on-web-publisher-controls
User-agent: Google-Extended
Disallow: /

# Amazon
# Used for Alexa - does not cite sources.
# https://developer.amazon.com/support/amazonbot
User-Agent: Amazonbot
Disallow: /

# Apple's bot.
# Used for Siri and Spotlight Suggestions. Does not cite its sources.
# https://support.apple.com/en-us/HT204683
User-Agent: Applebot
User-Agent: AppleNewsBot
Disallow: /

# Kitty
# This bot is cool - go wild, queen
User-Agent: digikitty_x86
Allow: /

# This is where I copy Bytemoth
# I am taking it in good faith that Bytemoth knows what he's doing and that
# the following bots are for marketers - so I am blocking them.
# As taken from the following URL: http://bytemoth.nfshost.com/robots.txt
User-agent: adsbot
User-agent: AhrefsBot
User-agent: BLEXBot
User-agent: dotbot
User agent: MTRobot
User-agent: SemrushBot
User-agent: SemrushBot-SA
User-agent: SemrushBot-BA
User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA
User-agent: SemrushBot-CT
User-agent: SemrushBot-BM
User-agent: serpstatbot
User-agent: Pandalytics
User-agent: PageThing
Disallow: /