mirror of
https://github.com/Alvin-Zilverstand/school.git
synced 2026-04-18 02:57:02 +02:00
161 lines
2.1 KiB
Plaintext
161 lines
2.1 KiB
Plaintext
|
# Allow all well-behaved bots
|
||
|
|
User-agent: *
|
||
|
|
Disallow:
|
||
|
|
|
||
|
|
# Block specific bots
|
||
|
|
User-agent: AI2Bot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Ai2Bot-Dolma
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: aiHitBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Amazonbot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: anthropic-ai
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Applebot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Applebot-Extended
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Brightbot 1.0
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Bytespider
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: CCBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: ChatGPT-User
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Claude-Web
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: ClaudeBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: cohere-ai
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: cohere-training-data-crawler
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Cotoyogi
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Crawlspace
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Diffbot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: DuckAssistBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: FacebookBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Factset_spyderbot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: FirecrawlAgent
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: FriendlyCrawler
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: GPTBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: iaskspider/2.0
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: ICC-Crawler
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: ImagesiftBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: img2dataset
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: imgproxy
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: ISSCyberRiskCrawler
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Kangaroo Bot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Meta-ExternalAgent
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Meta-ExternalFetcher
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: NovaAct
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: OAI-SearchBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: omgili
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: omgilibot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Operator
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: PanguBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Perplexity-User
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: PerplexityBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: PetalBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Scrapy
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: SemrushBot-OCOB
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: SemrushBot-SWA
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Sidetrade indexer bot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: TikTokSpider
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Timpibot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: VelenPublicWebCrawler
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: Webzio-Extended
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
User-agent: YouBot
|
||
|
|
Disallow: /db
|
||
|
|
|
||
|
|
# Sitemap location
|
||
|
|
Sitemap: https://alvnx.xyz/sitemap.xml
|