google news phase 1

- Homepage / Industry News query filters wp_imported_posts to
  ai_rewritten_at IS NOT NULL so raw press releases never surface on
  the editorial feed (NewsArticle JSON-LD was already in place).
- New /news-sitemap.xml route emits a Google News sitemap covering
  rewritten editorial published in the last 48 hours, with
  news:publication + news:publication_date + news:title + keywords.
- robots.ts now points crawlers at both sitemap.xml and
  news-sitemap.xml.

After deploy, submit broadcastbeat.com to Google News Publisher Center
to start serving in News.

src/app/news-sitemap.xml/route.ts

@@ -0,0 +1,90 @@
+import { createClient } from '@supabase/supabase-js';
+
+export const dynamic = 'force-dynamic';
+export const revalidate = 600; // 10 min — Google rechecks frequently
+
+// Google News sitemap. Only original-editorial articles (ai_rewritten_at IS
+// NOT NULL or rewritten-articles surface) from the last 48 hours so we
+// stay inside the GN window. Standard sitemap.xml covers older pages.
+const PUBLICATION_NAME = 'Broadcast Beat';
+const PUBLICATION_LANG = 'en';
+const HOST = 'https://broadcastbeat.com';
+
+function esc(s: string): string {
+  return (s || '').replace(/[&<>"']/g, (c) =>
+    ({ '&': '&amp;', '<': '&lt;', '>': '&gt;', '"': '&quot;', "'": '&apos;' }[c] as string));
+}
+
+export async function GET() {
+  const url = process.env.NEXT_PUBLIC_SUPABASE_URL!;
+  const key = process.env.NEXT_PUBLIC_SUPABASE_ANON_KEY!;
+  const schema = process.env.NEXT_PUBLIC_SUPABASE_SCHEMA || 'bb';
+  const sb = createClient(url, key, { db: { schema: schema as 'public' }, auth: { persistSession: false } });
+
+  const since = new Date(Date.now() - 48 * 3600 * 1000).toISOString();
+
+  const [{ data: imported }, { data: rewritten }] = await Promise.all([
+    sb.from('wp_imported_posts')
+      .select('wp_slug, title, wp_published_at, ai_rewritten_at, author_name, tags')
+      .eq('status', 'published')
+      .not('ai_rewritten_at', 'is', null)
+      .gte('wp_published_at', since)
+      .order('wp_published_at', { ascending: false })
+      .limit(1000),
+    sb.from('ai_rewritten_articles')
+      .select('slug, title, published_at, category, source_author')
+      .eq('status', 'published')
+      .gte('published_at', since)
+      .order('published_at', { ascending: false })
+      .limit(1000),
+  ]);
+
+  const entries: string[] = [];
+
+  for (const a of imported || []) {
+    const pubDate = a.wp_published_at || a.ai_rewritten_at;
+    if (!pubDate) continue;
+    const tags = Array.isArray(a.tags) ? (a.tags as string[]).slice(0, 5).join(', ') : '';
+    entries.push(`  <url>
+    <loc>${HOST}/news/${esc(a.wp_slug)}</loc>
+    <news:news>
+      <news:publication>
+        <news:name>${PUBLICATION_NAME}</news:name>
+        <news:language>${PUBLICATION_LANG}</news:language>
+      </news:publication>
+      <news:publication_date>${pubDate}</news:publication_date>
+      <news:title>${esc(a.title)}</news:title>${tags ? `\n      <news:keywords>${esc(tags)}</news:keywords>` : ''}
+    </news:news>
+  </url>`);
+  }
+
+  for (const a of rewritten || []) {
+    if (!a.published_at) continue;
+    entries.push(`  <url>
+    <loc>${HOST}/articles/${esc(a.slug)}</loc>
+    <news:news>
+      <news:publication>
+        <news:name>${PUBLICATION_NAME}</news:name>
+        <news:language>${PUBLICATION_LANG}</news:language>
+      </news:publication>
+      <news:publication_date>${a.published_at}</news:publication_date>
+      <news:title>${esc(a.title)}</news:title>${a.category ? `\n      <news:keywords>${esc(a.category)}</news:keywords>` : ''}
+    </news:news>
+  </url>`);
+  }
+
+  const body = `<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:news="http://www.google.com/schemas/sitemap-news/0.9">
+${entries.join('\n')}
+</urlset>
+`;
+
+  return new Response(body, {
+    status: 200,
+    headers: {
+      'content-type': 'application/xml; charset=utf-8',
+      'cache-control': 'public, max-age=300, s-maxage=600',
+    },
+  });
+}

src/app/robots.ts

@@ -16,7 +16,10 @@ export default function robots(): MetadataRoute.Robots {
         disallow: ['/api/', '/admin/', '/private/', '/dashboard/'],
       },
     ],
-    sitemap: `${baseUrl}/sitemap.xml`,
+    sitemap: [
+      `${baseUrl}/sitemap.xml`,
+      `${baseUrl}/news-sitemap.xml`,
+    ],
     host: baseUrl,
   };
 }

src/lib/articles/legacy-source.ts

@@ -281,6 +281,9 @@ export async function getLegacyArticlesBySection(
       .from("wp_imported_posts")
       .select(SELECT_COLS)
       .eq("status", "published")
+      // Google News-safe surface: only show articles that have been AI-rewritten
+      // into original editorial. Raw press-release imports are excluded.
+      .not("ai_rewritten_at", "is", null)
       .order("wp_published_at", { ascending: false })
       .limit(limit);
     const tags = SECTION_TAGS[section];