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

Extra LLM crawler

main
Bob Mottram 2024-09-01 20:42:19 +01:00
parent a738e1316e
commit 0ec43c6323
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
crawlers.py
View File

@ -135,7 +135,7 @@ def blocked_user_agent(calling_domain: str, agent_str: str,
'facebookbot', 'google-extended', 'piplbot', 'oai-search', 'facebookbot', 'google-extended', 'piplbot', 'oai-search',
'applebot-extended', 'meta-external', 'diffbot', 'perplexitybot', 'applebot-extended', 'meta-external', 'diffbot', 'perplexitybot',
'omgili', 'imagesiftbot', 'bytespider', 'amazonbot', 'youbot', 'omgili', 'imagesiftbot', 'bytespider', 'amazonbot', 'youbot',
'petalbot' 'petalbot', 'ai2bot', 'allenai'
) )
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: