feat: poison ai crawlers

_data/aiBots.json

@@ -0,0 +1,132 @@
+[
+  "AddSearchBot",
+  "AI2Bot",
+  "AI2Bot-DeepResearchEval",
+  "Ai2Bot-Dolma",
+  "aiHitBot",
+  "amazon-kendra",
+  "Amazonbot",
+  "AmazonBuyForMe",
+  "Andibot",
+  "Anomura",
+  "anthropic-ai",
+  "Applebot",
+  "Applebot-Extended",
+  "atlassian-bot",
+  "Awario",
+  "bedrockbot",
+  "bigsur.ai",
+  "Bravebot",
+  "Brightbot 1.0",
+  "BuddyBot",
+  "Bytespider",
+  "CCBot",
+  "Channel3Bot",
+  "ChatGLM-Spider",
+  "ChatGPT Agent",
+  "ChatGPT-User",
+  "Claude-SearchBot",
+  "Claude-User",
+  "Claude-Web",
+  "ClaudeBot",
+  "Cloudflare-AutoRAG",
+  "CloudVertexBot",
+  "cohere-ai",
+  "cohere-training-data-crawler",
+  "Cotoyogi",
+  "Crawl4AI",
+  "Crawlspace",
+  "Datenbank Crawler",
+  "DeepSeekBot",
+  "Devin",
+  "Diffbot",
+  "DuckAssistBot",
+  "Echobot Bot",
+  "EchoboxBot",
+  "FacebookBot",
+  "facebookexternalhit",
+  "Factset_spyderbot",
+  "FirecrawlAgent",
+  "FriendlyCrawler",
+  "Gemini-Deep-Research",
+  "Google-CloudVertexBot",
+  "Google-Extended",
+  "Google-Firebase",
+  "Google-NotebookLM",
+  "GoogleAgent-Mariner",
+  "GoogleOther",
+  "GoogleOther-Image",
+  "GoogleOther-Video",
+  "GPTBot",
+  "iAskBot",
+  "iaskspider",
+  "iaskspider/2.0",
+  "IbouBot",
+  "ICC-Crawler",
+  "ImagesiftBot",
+  "imageSpider",
+  "img2dataset",
+  "ISSCyberRiskCrawler",
+  "Kangaroo Bot",
+  "KlaviyoAIBot",
+  "KunatoCrawler",
+  "laion-huggingface-processor",
+  "LAIONDownloader",
+  "LCC",
+  "LinerBot",
+  "Linguee Bot",
+  "LinkupBot",
+  "Manus-User",
+  "meta-externalagent",
+  "Meta-ExternalAgent",
+  "meta-externalfetcher",
+  "Meta-ExternalFetcher",
+  "meta-webindexer",
+  "MistralAI-User",
+  "MistralAI-User/1.0",
+  "MyCentralAIScraperBot",
+  "netEstate Imprint Crawler",
+  "NotebookLM",
+  "NovaAct",
+  "OAI-SearchBot",
+  "omgili",
+  "omgilibot",
+  "OpenAI",
+  "Operator",
+  "PanguBot",
+  "Panscient",
+  "panscient.com",
+  "Perplexity-User",
+  "PerplexityBot",
+  "PetalBot",
+  "PhindBot",
+  "Poggio-Citations",
+  "Poseidon Research Crawler",
+  "QualifiedBot",
+  "QuillBot",
+  "quillbot.com",
+  "SBIntuitionsBot",
+  "Scrapy",
+  "SemrushBot-OCOB",
+  "SemrushBot-SWA",
+  "ShapBot",
+  "Sidetrade indexer bot",
+  "Spider",
+  "TavilyBot",
+  "TerraCotta",
+  "Thinkbot",
+  "TikTokSpider",
+  "Timpibot",
+  "TwinAgent",
+  "VelenPublicWebCrawler",
+  "WARDBot",
+  "Webzio-Extended",
+  "webzio-extended",
+  "wpbot",
+  "WRTNBot",
+  "YaK",
+  "YandexAdditional",
+  "YandexAdditionalBot",
+  "YouBot",
+  "ZanistaBot"
+]