# robots.txt for http://mirror.accum.se/
# This file specifies what harvesting robots are allowed to index and not.
#
# For information on the original format: 
# http://www.robotstxt.org/
#
# For information on updated format that allows wildcards:
# https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt

User-agent: *
# Rules without wildcards - original spec
Disallow: /cdimage/.debian-mirror
Disallow: /cdimage/snapshot
Disallow: /mirror/cdimage/.debian-mirror
Disallow: /mirror/cdimage/snapshot
Disallow: /debian/pool
Disallow: /mirror/debian/pool
Disallow: /mirror/ubuntu/pool
Disallow: /pub/debian/pool
Disallow: /ubuntu/pool
Disallow: /mirror/archlinux/pool
Disallow: /mirror/debian-multimedia/pool
Disallow: /mirror/linuxdeepin/packages/pool
Disallow: /mirror/linuxmint.com/packages/pool
Disallow: /mirror/osdn.net
Disallow: /mirror/parrotsec.org/parrot/pool
Disallow: /mirror/raspbian/mate/pool
Disallow: /mirror/raspbian/multiarchcross/pool
Disallow: /mirror/raspbian/raspbian/pool
Disallow: /mirror/solydxk.com/repository/pool
Disallow: /mirror/temp
Disallow: /mirror/trisquel/packages/pool
Disallow: /mirror/videolan.org/debian/pool
Disallow: /mirror/videolan.org/ubuntu/pool
Disallow: /mirror/opensuse.org/tumbleweed/repo
Disallow: /mirror/fedora/enchilada/linux
# Rules with wildcards - enhanced spec
Allow: /icons/*.png$
Allow: /icons2/*.png$
Disallow: /*.iso$
Disallow: /*.deb$
Disallow: /*.rpm$
Disallow: /*.gz$
Disallow: /*.bz2$
Disallow: /*.xz$
Disallow: /*.arj$
Disallow: /*.rar$
Disallow: /*.zip$
Disallow: /*.lzh$
Disallow: /*.lha$
Disallow: /*.7z$
Disallow: /*.avi$
Disallow: /*.wmv$
Disallow: /*.mpg$
Disallow: /*.mpeg$
Disallow: /*.mp4$
Disallow: /*.mkv$
Disallow: /*.flv$
Disallow: /*.qt$
Disallow: /*.mov$
Disallow: /*.m4v$
Disallow: /*.webm$
Disallow: /*.mp3$
Disallow: /*.ogg$
Disallow: /*.gif$
Disallow: /*.png$
Disallow: /*.jpg$
Disallow: /*.dmg$
Disallow: /*.zim$

# AI robots, from https://github.com/ai-robots-txt/ai.robots.txt/blob/main/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: 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: 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
Disallow: /