mirror of
https://github.com/TecharoHQ/anubis.git
synced 2025-10-04 05:41:59 +08:00
8 lines
1.6 KiB
YAML
8 lines
1.6 KiB
YAML
# Warning: Contains user agents that _must_ be blocked in robots.txt, or the opt-out will have no effect.
|
|
# Note: Blocks human-directed/non-training user agents
|
|
#
|
|
# CCBot is allowed because if Common Crawl is allowed, then scrapers don't need to scrape to get the data.
|
|
- name: "ai-robots-txt"
|
|
user_agent_regex: >-
|
|
AddSearchBot|AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|Awario|bedrockbot|bigsur.ai|Brightbot 1.0|Bytespider|CCBot|ChatGPT Agent|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|CloudVertexBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Datenbank Crawler|Devin|Diffbot|DuckAssistBot|Echobot Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini-Deep-Research|Google-CloudVertexBot|Google-Extended|GoogleAgent-Mariner|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|LinerBot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User|MistralAI-User/1.0|MyCentralAIScraperBot|netEstate Imprint Crawler|NovaAct|OAI-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|Poseidon Research Crawler|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot
|
|
action: DENY
|