robots.txt

# robots.txt for Miraheze

# Throttle access to certain pages
# Do not include special pages and other pages where indexing is undesirable if they are likely to be linked to; use noindex instead.
# That's because Google can still index pages in here without crawling them if the pages are linked to
# See https://developers.google.com/search/docs/crawling-indexing/robots/intro
User-Agent: *
Allow: /w/api.php?action=mobileview&
Allow: /w/load.php?
Disallow: /w/
Disallow: /geoip$
Disallow: /rest_v1/

# Block SemrushBot
User-Agent: SemrushBot
Disallow: /

# Block AhrefsBot
User-agent: AhrefsBot
Disallow: /

# Block Bytespider
User-agent: Bytespider
Disallow: /

# Block PetalBot
User-agent: PetalBot
Disallow: /

# Block DotBot
User-agent: DotBot
Disallow: /

# Block MegaIndex
User-agent: MegaIndex
Disallow: /

# Block serpstatbot
User-agent: serpstatbot
Disallow: /

# Block Barkrowler
User-agent: Barkrowler
Disallow: /

# Block SeekportBot
User-agent: SeekportBot
Disallow: /

# Keep Crawl-Delay rules at the bottom
# Bots that don't understand Crawl-Delay might break when encountering it
# See https://github.com/otwcode/otwarchive/pull/4411#discussion_r1044351129 (English) and https://webtan.impress.co.jp/e/2022/11/04/43611 (Japanese)

# Throttle MJ12Bot
User-agent: MJ12bot
Crawl-Delay: 10

# Throttle YandexBot
# TODO: Crawl-delay is not respected since 2018
User-Agent: YandexBot
Crawl-Delay: 2.5

# Throttle BingBot
User-agent: bingbot
Crawl-delay: 20