Changing browser testing wording

package.json

@@ -10,6 +10,7 @@
   },
   "dependencies": {
     "@11ty/eleventy": "^3.0.0-beta.1",
+    "@11ty/eleventy-fetch": "^4.0.1",
     "@11ty/eleventy-navigation": "^0.3.5",
     "@11ty/eleventy-plugin-rss": "^2.0.2",
     "@11ty/eleventy-plugin-syntaxhighlight": "^5.0.0",

src/.htaccess.njk

@@ -14,37 +14,5 @@ Header set Cache-Control "no-cache, public"
 RewriteEngine on
 
 # Block bad bots
-RewriteCond %{HTTP_USER_AGENT} (Amazonbot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} {{ robots.htaccess }} [NC]
-RewriteCond %{HTTP_USER_AGENT} (Applebot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Applebot-Extended) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Bytespider) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (CCBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (ChatGPT-User) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Claude-Web) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (ClaudeBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Diffbot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (FacebookBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (FriendlyCrawler) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (GPTBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Google-Extended) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (GoogleOther) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (GoogleOther-Image) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (GoogleOther-Video) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (ICC-Crawler) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (ImagesiftBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Meta-ExternalAgent) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Meta-ExternalFetcher) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (OAI-SearchBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (PerplexityBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (PetalBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Scrapy) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (Timpibot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (VelenPublicWebCrawler) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (YouBot) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (anthropic-ai) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (cohere-ai) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (facebookexternalhit) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (img2dataset) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (omgili) [NC,OR]
-RewriteCond %{HTTP_USER_AGENT} (omgilibot) [NC]
 RewriteRule .* https://nocommercialuse.org/ [L]

src/_data/robots.js

@@ -0,0 +1,32 @@
+// by Robb Knight: https://rknight.me/blog/blocking-bots-with-nginx/
+
+import EleventyFetch from "@11ty/eleventy-fetch";
+
+export default async function () {
+	const url =
+		"https://raw.githubusercontent.com/ai-robots-txt/ai.robots.txt/main/robots.txt";
+	let txt = await EleventyFetch(url, {
+		duration: "1w",
+		type: "text",
+	});
+
+	txt = txt
+		.split("\n")
+		.filter((line) => line !== "User-agent: Applebot")
+		.join("\n");
+
+	const bots = txt
+		.split("\n")
+		.filter((line) => {
+			return (
+				line.startsWith("User-agent:") &&
+				line !== "User-agent: Applebot"
+			);
+		})
+		.map((line) => line.split(":")[1].trim());
+
+	return {
+		txt: txt,
+		htaccess: bots.join("|"),
+	};
+}

src/robots.txt.njk

@@ -1,43 +1,10 @@
 ---
-permalink: /robots.txt
+permalink: robots.txt
 eleventyExcludeFromCollections: true
 ---
-Sitemap: {{ sitemeta.siteUrl }}/sitemap/
-
 User-agent: *
 Disallow:
 
-User-agent: Amazonbot
+{{ robots.txt }}
-User-agent: Applebot
+
-User-agent: Applebot-Extended
+Sitemap: {{ sitemeta.siteUrl }}/sitemap/
-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: YouBot
-User-agent: anthropic-ai
-User-agent: cohere-ai
-User-agent: facebookexternalhit
-User-agent: img2dataset
-User-agent: omgili
-User-agent: omgilibot
-Disallow: /

src/statements/colophon.md

@@ -1,7 +1,7 @@
 ---
 title: Colophon
 keyword: colophon page
-updated: 2024-08-02
+updated: 2024-08-20T09:55:39+0800
 toc: true
 eleventyNavigation:
     order: 14
@@ -14,6 +14,7 @@ Information about how this website is built.
 * Templating languages: Nunjucks and Markdown
 * Code written with Visual Studio Code
 * JavaScript runtime: [Bun](https://bun.sh)
+* Tested browsers: Mozilla Firefox and Lynx
 * Source code available on [GitHub](https://github.com/helenclx/leilukin-site) and its [Gitea mirror](https://git.32bit.cafe/Leilukin/leilukin-site)
 
 ## Host and Domain
@@ -26,6 +27,7 @@ Previously, this website was hosted on [Neocities](https://neocities.org/) until
 * Eleventy's official [RSS](https://www.11ty.dev/docs/plugins/rss/) plugin
 * Eleventy's official [Navigation](https://www.11ty.dev/docs/plugins/navigation/) plugin
 * Eleventy's official [Syntax Highlighting](https://www.11ty.dev/docs/plugins/syntaxhighlight/) plugin
+* Eleventy's official [Fetch](https://www.11ty.dev/docs/plugins/fetch/) plugin
 * [@zachleat/details-utils](https://www.npmjs.com/package/@zachleat/details-utils)
 
 ### Eleventy Community Plugins