Add robots.txt

robots.txt

@@ -0,0 +1,101 @@
+# ======================================================================
+# Disclaimer:
+#
+# Any form of web crawling for AI-based technologies or similar purposes
+# is strictly prohibited, regardless of whether the specific service is
+# listed in this robots.txt file or not.
+#
+# Legal actions will be taken in case of violations of this policy.
+#
+# This information is considered binding, as this file is read by web
+# crawlers.
+# ======================================================================
+
+# Block all Google bots
+User-agent: Google-Extended
+Disallow: /
+
+User-agent: AdsBot-Google
+Disallow: /
+
+User-agent: GoogleOther
+Disallow: /
+
+# Block AppleBot
+User-agent: Applebot-Extended
+Disallow: /
+
+# Block FacebookBot
+User-agent: FacebookBot
+Disallow: /
+
+# Block Amazonbot
+User-agent: Amazonbot
+Disallow: /
+
+# Block OpenAI GPT-Bots and custom ChatGPT-User
+User-agent: GPTBot
+Disallow: /
+
+User-agent: ChatGPT-User
+Disallow: /
+
+# Block Anthropic Claude bots
+User-agent: ClaudeBot
+Disallow: /
+
+User-agent: Claude-Web
+Disallow: /
+
+# Block PerplexityBot
+User-agent: PerplexityBot
+Disallow: /
+
+# Block other anthropic bot
+User-agent: anthropic-ai
+Disallow: /
+
+# Block Cohere's bot
+User-agent: cohere-ai
+Disallow: /
+
+# Block Diffbot
+User-agent: Diffbot
+Disallow: /
+
+# Block img2dataset crawler
+User-agent: img2dataset
+Disallow: /
+
+# Block various friendly crawlers
+User-agent: FriendlyCrawler
+Disallow: /
+
+User-agent: Bytespider
+Disallow: /
+
+# Block CCBot
+User-agent: CCBot
+Disallow: /
+
+# Block Omgili crawlers
+User-agent: omgili
+Disallow: /
+
+User-agent: omgilibot
+Disallow: /
+
+# Block Peer39 crawlers
+User-agent: peer39_crawler
+Disallow: /
+
+User-agent: peer39_crawler/1.0
+Disallow: /
+
+# Block web crawler financed by the Russian state
+User-agent: Awakari
+Disallow: /
+
+# Block YouBot
+User-agent: YouBot
+Disallow: /