# Scraping is not allowed for training AI language models, or selling to AI companies # Amazon: used to improve/enable Alexa to answer questions User-agent: Amazonbot Disallow: / # Anthropic/Claude: provides no documentation whether these are effective User-agent: anthropic-ai ā€¨Disallow: / User-agent: Claude-Web Disallow: / # ByteDance LLMs, including Doubao User-agent: Bytespider Disallow: / # ChatGPT crawler User-agent: GPTBot Disallow: / # ChatGPT plugins User-agent: ChatGPT-User Disallow: / # Common Crawl User-agent: CCBot Disallow: / # Facebook: crawls to improve language models User-Agent: FacebookBot Disallow: / # Google: Bard and Vertex AI generative APIs User-agent: Google-Extended Disallow: / # Omgilibot/webz.io: sells data for training LLMs User-agent: Omgilibot Disallow: / User-agent: Omgili Disallow: / # Disable indexing of native ad images User-agent: Googlebot Disallow: /kaupalliset/*.jpg$ Disallow: /kaupalliset/*.Jpg$ Disallow: /kaupalliset/*.jPg$ Disallow: /kaupalliset/*.jpG$ Disallow: /kaupalliset/*.jPG$ Disallow: /kaupalliset/*.JPg$ Disallow: /kaupalliset/*.JpG$ Disallow: /kaupalliset/*.JPG$ Disallow: /kaupalliset/*.png$ Disallow: /kaupalliset/*.Png$ Disallow: /kaupalliset/*.pNg$ Disallow: /kaupalliset/*.pnG$ Disallow: /kaupalliset/*.pNG$ Disallow: /kaupalliset/*.PNg$ Disallow: /kaupalliset/*.PnG$ Disallow: /kaupalliset/*.PNG$ Disallow: /kaupalliset/*.gif$ Disallow: /kaupalliset/*.Gif$ Disallow: /kaupalliset/*.gIf$ Disallow: /kaupalliset/*.giF$ Disallow: /kaupalliset/*.gIF$ Disallow: /kaupalliset/*.GIf$ Disallow: /kaupalliset/*.GiF$ Disallow: /kaupalliset/*.GIF$ # By default allow everything (else) User-agent: * Allow: / # Sitemap Sitemap: https://www.ita-savo.fi/sitemap.xml