build: 添加 postbuild sitemap 生成脚本 + robots.txt SEO

- package.json: 添加 postbuild 钩子自动生成 sitemap - scripts/generate-sitemap.js: 站点地图生成器（78 条 URL） - public/robots.txt: SEO 爬虫引导 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-06-23 21:24:20 +08:00
parent c10a33e9f8
commit f4f17c10d8
3 changed files with 92 additions and 0 deletions
@@ -0,0 +1,87 @@
+const fs = require('fs');
+const path = require('path');
+
+const SITE_URL = 'https://yuzhiran.com';
+const OUT_DIR = path.join(__dirname, '..', 'out');
+
+const PRIORITIES = {
+  '/': 1.0,
+  '/tools': 0.9,
+  '/courses': 0.9,
+  '/skills': 0.8,
+  '/marketplace': 0.8,
+  '/practices': 0.8,
+  '/contents': 0.8,
+  '/prompts': 0.8,
+  '/models': 0.7,
+  '/sandbox': 0.7,
+  '/about': 0.5,
+  '/privacy': 0.3,
+  '/terms': 0.3,
+};
+
+function walkDir(dir, basePath = '') {
+  const entries = fs.readdirSync(dir, { withFileTypes: true });
+  const urls = [];
+  for (const entry of entries) {
+    const fullPath = path.join(dir, entry.name);
+    const relativeName = path.join(basePath, entry.name);
+    if (entry.isDirectory()) {
+      if (entry.name.startsWith('_') || entry.name.startsWith('.')) continue;
+      urls.push(...walkDir(fullPath, relativeName));
+    } else if (entry.name === 'page.html' || entry.name.endsWith('.html')) {
+      if (relativeName === 'index.html' || relativeName === 'page.html') {
+        urls.push({ path: '/', file: fullPath });
+      } else {
+        let urlPath = '/' + relativeName.replace(/\.html$/, '').replace(/\/index$/, '').replace(/\/page$/, '');
+        urls.push({ path: urlPath, file: fullPath });
+      }
+    }
+  }
+  return urls;
+}
+
+function generateSitemap(urls) {
+  const now = new Date().toISOString().split('T')[0];
+  let xml = '<?xml version="1.0" encoding="UTF-8"?>\n';
+  xml += '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n';
+  const seen = new Set();
+  for (const url of urls) {
+    if (seen.has(url.path)) continue;
+    seen.add(url.path);
+    if (url.path.startsWith('/admin') || url.path.startsWith('/_next') || url.path.startsWith('/api') || url.path === '/404') continue;
+    if (url.path.includes('/[') || url.path.includes(']')) continue;
+    const depth = url.path.split('/').filter(Boolean).length;
+    const changefreq = depth <= 1 ? 'weekly' : 'monthly';
+    const priority = PRIORITIES[url.path];
+    const computedPriority = priority !== undefined ? priority : Math.max(0.1, 0.7 - depth * 0.1);
+    xml += '  <url>\n';
+    xml += `    <loc>${SITE_URL}${url.path}</loc>\n`;
+    xml += `    <lastmod>${now}</lastmod>\n`;
+    xml += `    <changefreq>${changefreq}</changefreq>\n`;
+    xml += `    <priority>${computedPriority.toFixed(1)}</priority>\n`;
+    xml += '  </url>\n';
+  }
+  xml += '</urlset>';
+  return xml;
+}
+
+if (!fs.existsSync(OUT_DIR)) {
+  console.error('out/ directory not found. Run next build first.');
+  process.exit(1);
+}
+
+const urls = walkDir(OUT_DIR);
+console.log(`Found ${urls.length} HTML pages in output.`);
+const sitemap = generateSitemap(urls);
+const outputPath = path.join(OUT_DIR, 'sitemap.xml');
+fs.writeFileSync(outputPath, sitemap, 'utf-8');
+console.log(`Generated sitemap.xml with ${sitemap.split('<url>').length - 1} URLs → ${outputPath}`);
+
+// Copy robots.txt from public/ to out/
+const robotsSrc = path.join(__dirname, '..', 'public', 'robots.txt');
+const robotsDst = path.join(OUT_DIR, 'robots.txt');
+if (fs.existsSync(robotsSrc)) {
+  fs.copyFileSync(robotsSrc, robotsDst);
+  console.log(`Copied robots.txt → ${robotsDst}`);
+}