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

More LLM crawlers

merge-requests/30/head
Bob Mottram 2025-01-21 18:35:29 +00:00
parent 6756452e0f
commit d206d6390d
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

@ -144,9 +144,11 @@ def blocked_user_agent(calling_domain: str, agent_str: str,
'omgili', 'imagesiftbot', 'bytespider', 'amazonbot', 'youbot',
'petalbot', 'ai2bot', 'allenai', 'firecrawl', 'friendlycrawler',
'googleother', 'icc-crawler', 'scrapy', 'timpibot',
'velenpublic', 'webzio-extended', 'cohere-ai', 'facebookexternal',
'velenpublic', 'webzio-extended', 'cohere-ai',
'cohere-train', 'crawlspace', 'facebookexternal',
'img2dataset', 'isscyberriskcrawler', 'sidetrade', 'kangaroo.ai',
'kangaroo bot', 'iaskspider', 'duckassistbot'
'kangaroo bot', 'iaskspider', 'duckassistbot', 'pangubot',
'semrush'
)
for bot_str in llm_bot_strings:
if bot_str in agent_str_lower: