scientia-website/scripts/download-images.mjs

import { mkdir, readFile, writeFile } from "node:fs/promises";
import path from "node:path";

const UA =
  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36";

const entries = JSON.parse(await readFile(".scratch/images.json", "utf8"));

// Map every tildacdn URL (including resize derivatives) to its original full-size URL.
const canonical = new Map();
for (const { url } of entries) {
  let orig = url.replace("thb.tildacdn.com", "static.tildacdn.com");
  orig = orig.replace(/\/-\/resize[^/]*\//, "/");
  orig = orig.replace(/\/20x\//, "/");
  canonical.set(url, orig);
}
const unique = [...new Set(canonical.values())];
console.log(`${entries.length} refs -> ${unique.length} original images`);

await mkdir("public/images", { recursive: true });
const usedNames = new Set();
const map = {};
let ok = 0, fail = 0;

for (const url of unique) {
  if (url.includes("/lib/icons/")) continue; // stock bullet icons, replaced by our own
  let name = decodeURIComponent(path.basename(new URL(url).pathname));
  if (usedNames.has(name)) {
    const ext = path.extname(name);
    name = name.slice(0, -ext.length) + "-" + Math.abs(hash(url)).toString(36) + ext;
  }
  usedNames.add(name);
  try {
    const res = await fetch(url, { headers: { "User-Agent": UA } });
    if (!res.ok) throw new Error("HTTP " + res.status);
    const buf = Buffer.from(await res.arrayBuffer());
    const min = url.endsWith(".svg") ? 50 : 1000;
    if (buf.length < min) throw new Error("too small");
    await writeFile(path.join("public/images", name), buf);
    map[url] = "/images/" + name;
    ok++;
  } catch (e) {
    fail++;
    console.log(`FAIL ${url}: ${e.message}`);
  }
}

// hash helper
function hash(s) {
  let h = 0;
  for (let i = 0; i < s.length; i++) h = (Math.imul(31, h) + s.charCodeAt(i)) | 0;
  return h;
}

await writeFile(".scratch/image-map.json", JSON.stringify(map, null, 2));
console.log(`downloaded ${ok}, failed ${fail}`);