robots.txt

# robots.txt for miraheze

# Throttle access to certain pages
User-Agent: *
Allow: /w/api.php?action=mobileview&
Allow: /w/load.php?
Disallow: /w/
Disallow: /geoip$
Disallow: /rest_v1/
Disallow: /wiki/Special:
Disallow: /wiki/Spezial:
Disallow: /wiki/Spesial:
Disallow: /wiki/Special%3A
Disallow: /wiki/Spezial%3A
Disallow: /wiki/Spesial%3A
Disallow: /wiki/Property:
Disallow: /wiki/Property%3A
Disallow: /wiki/property:
Disallow: /wiki/Especial:
Disallow: /wiki/Especial%3A
Disallow: /wiki/especial:

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

# Throttle BingBot
# Throttle BingBot
User-agent: bingbot
Crawl-delay: 5

# Block SemrushBot
# Block SemrushBot
User-Agent: SemrushBot
Disallow: /

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

# Block AhrefsBot
# Block AhrefsBot
User-agent: AhrefsBot
Disallow: /

# Block Bytespider
# Block Bytespider
User-agent: Bytespider
Disallow: /

# Block PetalBot
# Block PetalBot
User-agent: PetalBot
Disallow: /

# Block DotBot
# Block DotBot
User-agent: DotBot
Disallow: /

# Block MegaIndex
# Block MegaIndex
User-agent: MegaIndex
Disallow: /

# Block serpstatbot
# Block serpstatbot
User-agent: serpstatbot
Disallow: /

# Block Barkrowler
# Block Barkrowler
User-agent: Barkrowler
Disallow: /

# Block SeekportBot
# Block SeekportBot
User-agent: SeekportBot
Disallow: /