XML Style

README.md

@@ -39,7 +39,7 @@ data/
 The app serves crawler and answer-engine metadata without adding visible page copy:
 
 - `/robots.txt`
-- `/sitemap.xml` with approved meme image entries
+- `/sitemap.xml` with the home page and approved meme URLs
 - `/feed.json`
 - `/llms.txt`
 - `/site.webmanifest`

server.js

@@ -19,6 +19,13 @@ const PAGE_SIZE_MAX = 48;
 const UPLOAD_MAX_BYTES = 5 * 1024 * 1024;
 const REQUEST_MAX_BYTES = 6 * 1024 * 1024;
 const events = new Set();
+const DISCOVERY_ROUTES = new Set([
+  '/robots.txt',
+  '/llms.txt',
+  '/site.webmanifest',
+  '/feed.json',
+  '/sitemap.xml'
+]);
 const ADMIN_TOKEN = process.env.ADMIN_TOKEN || crypto.randomBytes(24).toString('hex');
 const indexTemplate = await fs.readFile('./public/index.html', 'utf8');
 
@@ -32,10 +39,9 @@ if (!process.env.ADMIN_TOKEN) {
 }
 
 const server = http.createServer(async (req, res) => {
-  withSecurityHeaders(res);
-
   try {
     const url = new URL(req.url || '/', `http://${req.headers.host || 'localhost'}`);
+    withSecurityHeaders(res, { contentSecurityPolicy: !isDiscoveryRoute(req, url) });
     const baseUrl = publicBaseUrl(req);
 
     if (req.method === 'GET' && url.pathname === '/') {
@@ -253,6 +259,11 @@ function positiveInt(value, fallback) {
   return Number.isFinite(parsed) && parsed > 0 ? parsed : fallback;
 }
 
+function isDiscoveryRoute(req, url) {
+  if (req.method !== 'GET') return false;
+  return DISCOVERY_ROUTES.has(url.pathname);
+}
+
 function downloadName(meme) {
   return `meme-protocol-${meme.id.slice(0, 12)}.${meme.ext}`;
 }

src/http.js

@@ -19,6 +19,8 @@ export function withSecurityHeaders(res, options = {}) {
   res.setHeader('X-Content-Type-Options', 'nosniff');
   res.setHeader('X-Frame-Options', 'DENY');
   res.setHeader('Permissions-Policy', 'camera=(), microphone=(), geolocation=()');
+  if (options.contentSecurityPolicy === false) return;
+
   const scriptSrc = options.scriptNonce ? `script-src 'self' 'nonce-${options.scriptNonce}'; ` : '';
   res.setHeader(
     'Content-Security-Policy',

src/seo.js

@@ -87,7 +87,7 @@ export function llmsTxt(baseUrl) {
     'Crawler guidance:',
     '- Public approved meme images are available under /media/<sha256>.',
     '- Admin, review, upload, and API mutation routes are not public knowledge sources.',
-    '- The site is intentionally visual and sparse; use metadata, sitemap image entries, and JSON feed for machine summaries.',
+    '- The site is intentionally visual and sparse; use metadata, sitemap URLs, and JSON feed for machine summaries.',
     ''
   ].join('\n');
 }
@@ -132,22 +132,26 @@ export function feedJson(baseUrl, memes) {
 }
 
 export function sitemapXml(baseUrl, memes) {
-  const images = memes.slice(0, 1000).map((meme) => [
-    '    <image:image>',
-    `      <image:loc>${xmlEscape(`${baseUrl}/media/${meme.id}`)}</image:loc>`,
-    `      <image:caption>${xmlEscape(`Meme ${shortId(meme.id)} with MEME_CONSENSUS_SCORE ${meme.moderationScore}/100`)}</image:caption>`,
-    '    </image:image>'
-  ].join('\n')).join('\n');
+  const latest = memes[0]?.createdAt || new Date().toISOString();
+  const urls = [
+    [
+      '  <url>',
+      `    <loc>${xmlEscape(`${baseUrl}/`)}</loc>`,
+      `    <lastmod>${xmlEscape(latest)}</lastmod>`,
+      '  </url>'
+    ].join('\n'),
+    ...memes.slice(0, 1000).map((meme) => [
+      '  <url>',
+      `    <loc>${xmlEscape(`${baseUrl}/media/${meme.id}`)}</loc>`,
+      `    <lastmod>${xmlEscape(meme.createdAt)}</lastmod>`,
+      '  </url>'
+    ].join('\n'))
+  ].join('\n');
 
   return [
     '<?xml version="1.0" encoding="UTF-8"?>',
-    '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:image="http://www.google.com/schemas/sitemap-image/1.1">',
-    '  <url>',
-    `    <loc>${xmlEscape(`${baseUrl}/`)}</loc>`,
-    '    <changefreq>hourly</changefreq>',
-    '    <priority>1.0</priority>',
-    images,
-    '  </url>',
+    '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">',
+    urls,
     '</urlset>',
     ''
   ].join('\n');