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 2024-10-05 16:39:55 +01:00
parent 60ea8bfbec
commit d4084f6e9e
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
crawlers.py
View File

@ -139,7 +139,8 @@ def blocked_user_agent(calling_domain: str, agent_str: str,
'petalbot', 'ai2bot', 'allenai', 'firecrawl', 'friendlycrawler', 'petalbot', 'ai2bot', 'allenai', 'firecrawl', 'friendlycrawler',
'googleother', 'icc-crawler', 'scrapy', 'timpibot', 'googleother', 'icc-crawler', 'scrapy', 'timpibot',
'velenpublic', 'webzio-extended', 'cohere-ai', 'facebookexternal', 'velenpublic', 'webzio-extended', 'cohere-ai', 'facebookexternal',
'img2dataset' 'img2dataset', 'isscyberriskcrawler', 'sidetrade', 'kangaroo',
'iaskspider'
) )
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: