# HTTPS://robotstxt.org/robotstxt.html # 20251103 A Leo-Anga.me robots.txt User-agent: * Crawl-delay: 1 Content-Signal: ai-train=yes, search=yes, ai-input=yes Sitemap: https://Leo-Anga.me/sitemap.xml Allow: * Disallow: /*/__pycache__/ Noindex: /robots.txt Noindex: /sitemap.xml Noindex: /security.txt Noindex: /ads.txt Noindex: /icon/* User-agent: ia_archiver Allow: * # syntax # # comment # User-agent: XOR bot-name * # EG : Googlebot FacebookBot Bingbot Discordbot anthropic-ai Claude-Web Omgilibot Omgili Bytespider magpie-crawler PerplexityBot Perplexity‑User Google-Extended facebookexternalhit CCBot img2dataset # Crawl-delay: 1 # wait 1 second between successive requests # Content-Signal: ai-train=no, search=yes, ai-input=yes # Sitemap: https://Leo-Anga.me/sitemap.xml # see EG : https://matrix.org/sitemap.xml # Disallow: path/?query # you can also use * $ [_0-9a-zA-Z]+ [0-9]+ # Allow: path/?query # you can also use * $ [_0-9a-zA-Z]+ [0-9]+ # Noindex: path/?query # you can also use * $ [_0-9a-zA-Z]+ [0-9]+ # path syntax # EG # /a/*/b.txt # /a/* # /a/[_0-9a-zA-Z]/b.txt # /a/*.pdf$ # /a/*[0-9]$ # /z/$ # /?query=asYouWant # /a/?* # bot list # Alexa/Wayback : ia_archiver # Anthropic : anthropic-ai # Ask/Teoma : Teoma # Baidu : baiduspider # Bing : Bingbot # Byte : Bytespider { owner of, for example TikTok # Claude : Claude-Web # Common Crawl : CCBot # DMOZ Checker : Robozilla # Discord : Discordbot # Facebook : FacebookBot # Facebook : facebookexternalhit # GigaBlast : Gigabot # Google : Googlebot # Google ADs : AdsBot-Google # Google Image : googlebot-image # Google Mobile : googlebot-mobile # Google-Extended : Google-Extended # MSN PicSearch : psbot # MSN Search : MSNBot # Magpie : magpie-crawler # Naver : naverbot # Naver : yeti # Nutch : Nutch # Omgili : Omgili # Omgili : Omgilibot # Perplexity : PerplexityBot # Perplexity‑User : Perplexity‑User # Twitter : Twitterbot # Yahoo : Slurp # Yahoo MM : yahoo-mmcrawler # Yahoo Blogs : yahoo-blogs/v3.9 # Yandex : Yandex # img2dataset : img2dataset { open source