70 lines
1.4 KiB
Plaintext
70 lines
1.4 KiB
Plaintext
|
# from https://neil-clarke.com/block-the-bots-that-feed-ai-models-by-scraping-your-website/
|
||
|
|
|
||
|
|
User-agent: CCBot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: ChatGPT-User
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: GPTBot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: Google-Extended
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: anthropic-ai
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: Omgilibot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: Omgili
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: FacebookBot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: Bytespider
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# from https://github.com/healsdata/ai-training-opt-out
|
||
|
|
|
||
|
|
# may not work, needs more research (see https://github.com/rom1504/img2dataset/issues/48)
|
||
|
|
User-agent: img2dataset
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: Claude-Web
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: magpie-crawler
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# AhrefsBot crawls for data for an "SEO Dataset"—one of their "products" based on this dataset is "AI Writing Tools"
|
||
|
|
User-agent: AhrefsBot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# from https://www.cyberciti.biz/web-developer/block-openai-bard-bing-ai-crawler-bots-using-robots-txt-file/
|
||
|
|
User-agent: PerplexityBot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# from https://netfuture.ch/2023/07/blocking-ai-crawlers-robots-txt-chatgpt/
|
||
|
|
User-agent: cohere-ai
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# from https://claytonerrington.com/blog/robots-and-ai/
|
||
|
|
|
||
|
|
User-agent: Amazonbot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# from https://darkvisitors.com/
|
||
|
|
|
||
|
|
User-agent: Applebot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
User-agent: YouBot
|
||
|
|
Disallow: /
|
||
|
|
|
||
|
|
# from https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler/
|
||
|
|
User-agent: FriendlyCrawler
|
||
|
|
Disallow: /
|