Add Robots.txt to block LLM bots

onlineweb4/urls.py

@@ -67,6 +67,10 @@ def get_context_data(self, **kwargs):
     re_path(r"^wiki/", include("wiki.urls")),
 ]
 
+# Robots.txt
+urlpatterns += [
+    re_path(r"^robots.txt$", TemplateView.as_view(template_name="robots.txt", content_type="text/plain"))
+]
 
 # Onlineweb app urls
 

templates/robots.txt

@@ -0,0 +1,49 @@
+# Dark Visitors robots.txt
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/anthropic-ai
+
+User-agent: anthropic-ai
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/bytespider
+
+User-agent: Bytespider
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/ccbot
+
+User-agent: CCBot
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/diffbot
+
+User-agent: Diffbot
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/facebookbot
+
+User-agent: FacebookBot
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/google-extended
+
+User-agent: Google-Extended
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/gptbot
+
+User-agent: GPTBot
+Disallow: /
+
+# AI Data Scraper
+# https://darkvisitors.com/agents/omgili
+
+User-agent: omgili
+Disallow: /