diff --git a/src/_data/robots.js b/src/_data/robots.js index 2ab051c6..da695e77 100644 --- a/src/_data/robots.js +++ b/src/_data/robots.js @@ -1,28 +1,28 @@ -// by Robb Knight: https://rknight.me/blog/blocking-bots-with-nginx/ +/* + Modified from Robb Knight's script: + 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"; + const url = "https://raw.githubusercontent.com/ai-robots-txt/ai.robots.txt/main/robots.txt"; let txt = await EleventyFetch(url, { duration: "1w", type: "text", }); + const botExceptions = ["Applebot", "CCBot"]; + const botExceptionsFullStr = botExceptions.map(bot => "User-agent: " + bot) + txt = txt .split("\n") - .filter((line) => line !== "User-agent: Applebot") + .filter((line) => !botExceptionsFullStr.includes(line)) .join("\n"); const bots = txt .split("\n") - .filter((line) => { - return ( - line.startsWith("User-agent:") && - line !== "User-agent: Applebot" - ); - }) + .filter((line) => line.startsWith("User-agent:")) .map((line) => line.split(":")[1].trim().replace(/\s/gi, ".*")); return {