From 550e81d32d342b5f064921d528c3e04e172dcc90 Mon Sep 17 00:00:00 2001 From: Bob Mottram Date: Tue, 3 Sep 2024 13:52:04 +0100 Subject: [PATCH] Comment --- crawlers.py | 1 + 1 file changed, 1 insertion(+) diff --git a/crawlers.py b/crawlers.py index d32d068ad..9c5a5cd73 100644 --- a/crawlers.py +++ b/crawlers.py @@ -129,6 +129,7 @@ def blocked_user_agent(calling_domain: str, agent_str: str, llm = False # is this an LLM crawler? + # https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt llm_bot_strings = ( 'gptbot', '-ai/', ' ai/', '-ai ', ' ai ', 'chatgpt', 'anthropic', 'mlbot', 'claude-web', 'claudebot', 'ccbot',