2024-12-10 05:29:54 +00:00
|
|
|
# Please see <https://seirdy.one/meta/scrapers-i-block/> for an explanation on almost every entry, including intentionally-excluded entries.
|
|
|
|
|
|
|
|
|
|
User-agent: *
|
|
|
|
|
Disallow: /noindex/
|
|
|
|
|
Disallow: /misc/
|
|
|
|
|
|
|
|
|
|
User-Agent: peer39_crawler/1.0
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
## IP-violation scanners ##
|
|
|
|
|
|
|
|
|
|
User-Agent: TurnitinBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
2024-12-15 03:53:26 +00:00
|
|
|
User-Agent: AcademicBotRTU
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
2024-12-10 05:29:54 +00:00
|
|
|
User-Agent: SlySearch
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-Agent: BLEXBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: CheckMarkNetwork/1.0 (+https://www.checkmarknetwork.com/spider.html)
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: BrandVerity/1.0
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
## Misc. icky stuff ##
|
|
|
|
|
|
|
|
|
|
User-agent: PiplBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Well-known overly-aggressive bot that claims to respect robots.txt: http://mj12bot.com/
|
|
|
|
|
User-agent: MJ12bot
|
|
|
|
|
Crawl-Delay: 10
|
|
|
|
|
|
|
|
|
|
## Gen-AI data scrapers ##
|
|
|
|
|
|
|
|
|
|
User-agent: GPTBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Google-Extended
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Applebot-Extended
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: ClaudeBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-Agent: FacebookBot
|
|
|
|
|
User-Agent: meta-externalagent
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Cotoyogi
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Webzio-extended
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Kangaroo Bot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-Agent: GenAI
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-Agent: SemrushBot-OCOB
|
|
|
|
|
User-Agent: SemrushBot-FT
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-Agent: VelenPublicWebCrawler
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
Sitemap: https://seirdy.one/sitemap.xml
|
