seo: disallow common AI crawlers

Signed-off-by: Luca Zeuch <[email protected]>

Author: l-zeuch

config/_default/hugo.toml

@@ -6,7 +6,7 @@ baseURL = ""
 canonifyURLs = false
 disableAliases = true
 enableGitInfo = false
-enableRobotsTXT = true
+enableRobotsTXT = false
 languageCode = "en-US"
 
 defaultContentLanguage = "en"

static/robots.txt

@@ -0,0 +1,42 @@
+User-agent: *
+Disallow: /admin/
+Sitemap: /sitemap.xml
+
+User-agent: AI2Bot
+User-agent: Ai2Bot-Dolma
+User-agent: Amazonbot
+User-agent: Applebot
+User-agent: Applebot-Extended
+User-agent: Bytespider
+User-agent: CCBot
+User-agent: ChatGPT-User
+User-agent: Claude-Web
+User-agent: ClaudeBot
+User-agent: Diffbot
+User-agent: FacebookBot
+User-agent: FriendlyCrawler
+User-agent: GPTBot
+User-agent: Google-Extended
+User-agent: GoogleOther
+User-agent: GoogleOther-Image
+User-agent: GoogleOther-Video
+User-agent: ICC-Crawler
+User-agent: ImagesiftBot
+User-agent: Meta-ExternalAgent
+User-agent: Meta-ExternalFetcher
+User-agent: OAI-SearchBot
+User-agent: PerplexityBot
+User-agent: PetalBot
+User-agent: Scrapy
+User-agent: Timpibot
+User-agent: VelenPublicWebCrawler
+User-agent: Webzio-Extended
+User-agent: YouBot
+User-agent: anthropic-ai
+User-agent: cohere-ai
+User-agent: facebookexternalhit
+User-agent: iaskspider/2.0
+User-agent: img2dataset
+User-agent: omgili
+User-agent: omgilibot
+Disallow: /