# sane defaults for a Forgejo instance
# contributing sources:
# - https://github.com/robots.txt
# - https://codeberg.org/robots.txt

User-agent: *
Disallow: /api/*
Disallow: /avatars
Disallow: /user/*
Disallow: /*/*/src/commit/*
Disallow: /*/*/commit/*
Disallow: /*/*/*/refs/*
Disallow: /*/*/*/star
Disallow: /*/*/*/watch
Disallow: /*/*/labels
Disallow: /*/*/activity/*
Disallow: /vendor/*
Disallow: /swagger.*.json

# Language spam
Disallow: /*?lang=

Disallow: /explore/*?*
Disallow: /*q=

Disallow: /repo/create
Disallow: /repo/migrate
Disallow: /org/create

Disallow: /*/*/activity
Disallow: /*/*/projects
Disallow: /*/*/forks
Disallow: /*/*/commits/
Disallow: /*/*/branches
Disallow: /*/*/contributors
Disallow: /*/*/tags
Disallow: /*/*/stargazers
Disallow: /*/*/watchers
Disallow: /*/*/network
Disallow: /*/*/graphs
Disallow: /*/*/compare

Disallow: /*/*/issues/new
Disallow: /*/*/issues/?*
Disallow: /*/*/pulls/?*

Disallow: /*/tree/
Disallow: /*/download
Disallow: /*/revisions
Disallow: /*/commits/*?author
Disallow: /*/commits/*?path
Disallow: /*/comments
Disallow: /*/blame/
Disallow: /*/raw/
Disallow: /*/cache/
Disallow: /.git/
Disallow: */.git/
Disallow: /*.git
Disallow: /*.atom
Disallow: /*.rss

Disallow: /*/*/archive/
Disallow: *.bundle
Disallow: */commit/*.pacth
Disallow: */commit/*.diff

Disallow: /*source=*
Disallow: /*ref_cta=*
Disallow: /*plan=*
Disallow: /*return_to=*
Disallow: /*ref_loc=*
Disallow: /*setup_organization=*
Disallow: /*source_repo=*
Disallow: /*ref_page=*
Disallow: /*source=*
Disallow: /*referrer=*
Disallow: /*report=*
Disallow: /*author=*
Disallow: /*since=*
Disallow: /*until=*
Disallow: /*commits?author=*
Disallow: /*tab=*
Disallow: /*q=*
Disallow: /*repo-search-archived=*

# Copied from https://codeberg.org/robots.txt
Crawl-delay: 2

User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: Diffbot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GPTBot
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: meta-externalagent
User-agent: OAI-SearchBot
User-agent: Omgili
User-agent: Omgilibot
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Scrapy
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: YouBot
User-agent: SemrushBot
Disallow: /