indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

More LLM user agents

merge-requests/30/head
Bob Mottram 2024-08-19 19:32:38 +01:00
parent caade2aa2b
commit 3852e8dbe7
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
crawlers.py
View File

@ -131,8 +131,10 @@ def blocked_user_agent(calling_domain: str, agent_str: str,
# is this an LLM crawler? # is this an LLM crawler?
llm_bot_strings = ( llm_bot_strings = (
'gptbot', '-ai/', ' ai/', '-ai ', ' ai ', 'chatgpt', 'gptbot', '-ai/', ' ai/', '-ai ', ' ai ', 'chatgpt',
'anthropic', 'mlbot', 'claude-web', 'ccbot', 'facebookbot', 'anthropic', 'mlbot', 'claude-web', 'claudebot', 'ccbot',
'google-extended', 'piplbot', 'oai-search' 'facebookbot', 'google-extended', 'piplbot', 'oai-search',
'applebot-extended', 'meta-external', 'diffbot', 'perplexitybot',
'omgili', 'imagesiftbot', 'bytespider', 'amazonbot', 'youbot'
) )
for bot_str in llm_bot_strings: for bot_str in llm_bot_strings:
if bot_str in agent_str_lower: if bot_str in agent_str_lower: