The rest of the owl

This commit is contained in:
2026-02-28 12:13:24 -06:00
parent 54222db887
commit fdba0fdf8c
60 changed files with 1524 additions and 377 deletions

View File

@@ -40,15 +40,30 @@ permalink: robots.txt
User-agent: Google-Extended
Disallow: /
User-agent: Google-CloudVertexBot
Disallow: /
User-agent: Gemini-Deep-Research
Disallow: /
# Google
User-agent: GoogleOther
Disallow: /
User-agent: Googlebot-Image
Disallow: /
User-agent: Googlebot-Video
Disallow: /
User-agent: AdsBot-Google
Disallow: /
# Bing
User-agent: bingbot
Disallow: /
# Common Crawl
User-agent: CCBot
Disallow: /
@@ -60,6 +75,9 @@ Disallow: /
User-agent: ChatGPT
Disallow: /
User-agent: ChatGPT Agent
Disallow: /
User-agent: GPTBot
Disallow: /
@@ -70,48 +88,250 @@ Disallow: /
User-agent: Omgili
Disallow: /
# Facebook AI
# Facebook
User-agent: FacebookBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: meta-externalfetcher
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: meta-webindexer
Disallow: /
# Anthropic
User-agent: anthropic-ai
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-SearchBot
Disallow: /
User-agent: Claude-User
Disallow: /
# Apple AI
User-agent: Applebot-Extended
Disallow: /
# Other AI training known or suspected
User-agent: anthropic-ai
User-agent: AddSearchBot
Disallow: /
User-agent: PerplexityBot
User-agent: AI2Bot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: The Knowledge AI
User-agent: Ai2Bot-Dolma
Disallow: /
User-agent: aiHitBot
Disallow: /
User-agent: Andibot
Disallow: /
User-agent: Awario
Disallow: /
User-agent: bedrockbot
Disallow: /
User-agent: bigsur.ai
Disallow: /
User-agent: Brightbot 1.0
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /
User-agent: Cotoyogi
Disallow: /
User-agent: Crawlspace
Disallow: /
User-agent: Datenbank Crawler
Disallow: /
User-agent: DeepSeekBot
Disallow: /
User-agent: Devin
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: YouBot
User-agent: DuckAssistBot
Disallow: /
User-agent: Echobot Bot
Disallow: /
User-agent: EchoboxBot
Disallow: /
User-agent: Factset_spyderbot
Disallow: /
User-agent: FirecrawlAgent
Disallow: /
User-agent: FriendlyCrawler
Disallow: /
User-agent: iaskspider/2.0
Disallow: /
User-agent: ICC-Crawler
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: ISSCyberRiskCrawler
Disallow: /
User-agent: Kangaroo Bot
Disallow: /
User-agent: LinerBot
Disallow: /
User-agent: MistralAI-User
Disallow: /
User-agent: MistralAI-User/1.0
Disallow: /
User-agent: MyCentralAIScraperBot
Disallow: /
User-agent: netEstate Imprint Crawler
Disallow: /
User-agent: NovaAct
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: Operator
Disallow: /
User-agent: PanguBot
Disallow: /
User-agent: Panscient
Disallow: /
User-agent: panscient.com
Disallow: /
User-agent: Perplexity-User
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: PhindBot
Disallow: /
User-agent: Poseidon Research Crawler
Disallow: /
User-agent: QualifiedBot
Disallow: /
User-agent: QuillBot
Disallow: /
User-agent: quillbot.com
Disallow: /
User-agent: SBIntuitionsBot
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: SemrushBot-OCOB
Disallow: /
User-agent: SemrushBot-SWA
Disallow: /
User-agent: ShapBot
Disallow: /
User-agent: Sidetrade indexer bot
Disallow: /
User-agent: TerraCotta
Disallow: /
User-agent: The Knowledge AI
Disallow: /
User-agent: Thinkbot
Disallow: /
User-agent: TikTokSpider
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: VelenPublicWebCrawler
Disallow: /
User-agent: WARDBot
Disallow: /
User-agent: Webzio-Extended
Disallow: /
User-agent: wpbot
Disallow: /
User-agent: YaK
Disallow: /
User-agent: YandexAdditional
Disallow: /
User-agent: YandexAdditionalBot
Disallow: /
User-agent: YouBot
Disallow: /
# Siri and Alexa yuck
User-agent: Amazonbot
Disallow: /