seo fixes

scripts/enhance-seo-pages.mjs

@@ -0,0 +1,174 @@
+import fs from 'fs';
+import path from 'path';
+import { JSDOM } from 'jsdom';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const DIST_DIR = path.resolve(__dirname, '../dist');
+const SITE_URL = (process.env.SITE_URL || 'https://www.bentopdf.com').replace(
+  /\/+$/,
+  ''
+);
+
+const FALLBACK_SOCIAL_IMAGE = '/images/og-tools.png';
+
+function listTopLevelHtml() {
+  return fs
+    .readdirSync(DIST_DIR)
+    .filter((f) => f.endsWith('.html'))
+    .map((f) => path.join(DIST_DIR, f));
+}
+
+function imageExists(url) {
+  if (!url) return true;
+  let pathname;
+  try {
+    pathname = url.startsWith('http') ? new URL(url).pathname : url;
+  } catch {
+    return true;
+  }
+  if (!pathname.startsWith('/images/')) return true;
+  return fs.existsSync(path.join(DIST_DIR, pathname.replace(/^\//, '')));
+}
+
+function fixSocialImages(document) {
+  const selectors = ['meta[property="og:image"]', 'meta[name="twitter:image"]'];
+  for (const selector of selectors) {
+    for (const meta of document.querySelectorAll(selector)) {
+      const value = meta.getAttribute('content');
+      if (!imageExists(value)) {
+        meta.setAttribute('content', `${SITE_URL}${FALLBACK_SOCIAL_IMAGE}`);
+      }
+    }
+  }
+}
+
+function fixApplicationCategory(document) {
+  for (const script of document.querySelectorAll(
+    'script[type="application/ld+json"]'
+  )) {
+    let data;
+    try {
+      data = JSON.parse(script.textContent || '');
+    } catch {
+      continue;
+    }
+    if (
+      data &&
+      (data['@type'] === 'SoftwareApplication' ||
+        data['@type'] === 'WebApplication') &&
+      data.applicationCategory !== 'UtilitiesApplication'
+    ) {
+      data.applicationCategory = 'UtilitiesApplication';
+      script.textContent = JSON.stringify(data, null, 2);
+    }
+  }
+}
+
+function hasLdType(document, typeName) {
+  return [
+    ...document.querySelectorAll('script[type="application/ld+json"]'),
+  ].some((s) => (s.textContent || '').includes(`"${typeName}"`));
+}
+
+function injectFaqSchema(document) {
+  if (hasLdType(document, 'FAQPage')) return false;
+  const items = [];
+  for (const details of document.querySelectorAll('details.faq-d')) {
+    const summary = details.querySelector('summary');
+    const answer = details.querySelector('p');
+    if (!summary || !answer) continue;
+    const question = summary.textContent.replace(/\s+/g, ' ').trim();
+    const answerText = answer.textContent.replace(/\s+/g, ' ').trim();
+    if (!question || !answerText) continue;
+    items.push({
+      '@type': 'Question',
+      name: question,
+      acceptedAnswer: { '@type': 'Answer', text: answerText },
+    });
+  }
+  if (items.length === 0) return false;
+  const script = document.createElement('script');
+  script.setAttribute('type', 'application/ld+json');
+  script.textContent = JSON.stringify(
+    {
+      '@context': 'https://schema.org',
+      '@type': 'FAQPage',
+      mainEntity: items,
+    },
+    null,
+    2
+  );
+  document.body.appendChild(script);
+  return true;
+}
+
+function injectWebsiteSchema(document) {
+  if (hasLdType(document, 'WebSite')) return;
+  const script = document.createElement('script');
+  script.setAttribute('type', 'application/ld+json');
+  script.textContent = JSON.stringify(
+    {
+      '@context': 'https://schema.org',
+      '@type': 'WebSite',
+      name: 'BentoPDF',
+      alternateName: ['Bento PDF', 'BentoPDF.com'],
+      url: `${SITE_URL}/`,
+    },
+    null,
+    2
+  );
+  document.body.appendChild(script);
+}
+
+function rewriteInternalLinks(document, knownSlugs) {
+  for (const link of document.querySelectorAll('a[href]')) {
+    const href = link.getAttribute('href');
+    if (!href || /^(https?:|\/\/|#|mailto:|tel:|data:)/.test(href)) continue;
+    const match = href.match(
+      /^(?:\.\/|\/)?([a-z0-9][a-z0-9-]{0,64})\.html(#[^#]{0,128})?$/
+    );
+    if (!match) continue;
+    if (!knownSlugs.has(match[1])) continue;
+    const target = match[1] === 'index' ? '/' : `/${match[1]}`;
+    link.setAttribute('href', `${target}${match[2] || ''}`);
+  }
+}
+
+function enhance() {
+  if (!fs.existsSync(DIST_DIR)) {
+    console.error('enhance-seo-pages: dist not found, run vite build first');
+    process.exit(1);
+  }
+  const files = listTopLevelHtml();
+  const knownSlugs = new Set(files.map((f) => path.basename(f, '.html')));
+
+  let faqSchemaCount = 0;
+  for (const file of files) {
+    const slug = path.basename(file, '.html');
+    const dom = new JSDOM(fs.readFileSync(file, 'utf-8'));
+    const document = dom.window.document;
+
+    fixSocialImages(document);
+    fixApplicationCategory(document);
+    rewriteInternalLinks(document, knownSlugs);
+
+    if (slug === 'index') {
+      injectWebsiteSchema(document);
+    }
+
+    if (slug !== '404') {
+      if (injectFaqSchema(document)) faqSchemaCount++;
+    }
+
+    fs.writeFileSync(file, dom.serialize());
+    dom.window.close();
+  }
+  console.log(
+    `SEO enhance: ${files.length} pages processed, ${faqSchemaCount} FAQPage schemas added.`
+  );
+}
+
+enhance();

scripts/generate-blog.mjs

@@ -0,0 +1,429 @@
+import fs from 'fs';
+import path from 'path';
+import { marked } from 'marked';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const POSTS_DIR = path.resolve(__dirname, '../blog/posts');
+const BLOG_DIR = path.resolve(__dirname, '../blog');
+const SITE_URL = 'https://www.bentopdf.com';
+const AUTHOR = {
+  name: 'Alam',
+  url: `${SITE_URL}/blog/author-alam`,
+  image: `${SITE_URL}/images/author-alam.jpg`,
+  profiles: [
+    'https://github.com/alam00000',
+    'https://www.linkedin.com/in/abdullah-alam01/',
+  ],
+};
+
+const LINK_CLASS = 'text-indigo-300 hover:text-indigo-400';
+
+function escapeHtml(value) {
+  return value
+    .replace(/&/g, '&')
+    .replace(/</g, '&lt;')
+    .replace(/>/g, '&gt;')
+    .replace(/"/g, '&quot;');
+}
+
+function styleBody(html) {
+  return html
+    .replace(/<h2>/g, '<h2 class="text-2xl font-bold text-white mt-10 mb-4">')
+    .replace(/<h3>/g, '<h3 class="text-xl font-semibold text-white mt-6 mb-2">')
+    .replace(/<p>/g, '<p class="text-gray-300 leading-relaxed mb-5">')
+    .replace(
+      /<ol>/g,
+      '<ol class="list-decimal list-inside text-gray-300 leading-relaxed mb-5 space-y-2">'
+    )
+    .replace(
+      /<ul>/g,
+      '<ul class="list-disc list-inside text-gray-300 leading-relaxed mb-5 space-y-2">'
+    )
+    .replace(
+      /<a href="http/g,
+      `<a rel="noopener" class="${LINK_CLASS}" href="http`
+    )
+    .replace(/<a href="\//g, `<a class="${LINK_CLASS}" href="/`);
+}
+
+function renderInline(markdown) {
+  return styleBody(marked.parseInline(markdown));
+}
+
+function formatDate(iso) {
+  return new Date(`${iso}T12:00:00Z`).toLocaleDateString('en-US', {
+    year: 'numeric',
+    month: 'long',
+    day: 'numeric',
+    timeZone: 'UTC',
+  });
+}
+
+function parsePost(file) {
+  const raw = fs.readFileSync(path.join(POSTS_DIR, file), 'utf-8');
+  if (/[—–]/.test(raw)) {
+    throw new Error(
+      `${file}: contains an em or en dash, which the house style forbids`
+    );
+  }
+  const match = raw.match(/^---\n([\s\S]*?)\n---\n([\s\S]*)$/);
+  if (!match) {
+    throw new Error(`${file}: missing JSON frontmatter between --- markers`);
+  }
+  let meta;
+  try {
+    meta = JSON.parse(match[1]);
+  } catch (err) {
+    throw new Error(`${file}: frontmatter is not valid JSON: ${err.message}`, {
+      cause: err,
+    });
+  }
+  for (const key of [
+    'title',
+    'h1',
+    'description',
+    'date',
+    'breadcrumb',
+    'card',
+  ]) {
+    if (!meta[key]) throw new Error(`${file}: frontmatter missing "${key}"`);
+  }
+  return { slug: file.replace(/\.md$/, ''), meta, body: match[2].trim() };
+}
+
+function plainText(markdown) {
+  return markdown
+    .replace(/\[([^\]]+)\]\([^)]*\)/g, '$1')
+    .replace(/[*_`>#]/g, '')
+    .replace(/^\s*\d+\.\s+/gm, '')
+    .replace(/^\s*[-+]\s+/gm, '')
+    .replace(/\s+/g, ' ')
+    .trim();
+}
+
+function questionSections(body) {
+  const sections = [];
+  const parts = body.split(/^##\s+/m).slice(1);
+  for (const part of parts) {
+    const newline = part.indexOf('\n');
+    const heading = (newline === -1 ? part : part.slice(0, newline)).trim();
+    if (!heading.endsWith('?')) continue;
+    const answer = plainText(newline === -1 ? '' : part.slice(newline + 1));
+    if (!answer) continue;
+    sections.push({ q: heading, a: answer.slice(0, 600) });
+  }
+  return sections;
+}
+
+function faqSchema(entries) {
+  if (entries.length === 0) return '';
+  return `
+    <script type="application/ld+json">
+      ${JSON.stringify(
+        {
+          '@context': 'https://schema.org',
+          '@type': 'FAQPage',
+          mainEntity: entries.map((f) => ({
+            '@type': 'Question',
+            name: f.q,
+            acceptedAnswer: { '@type': 'Answer', text: plainText(f.a) },
+          })),
+        },
+        null,
+        2
+      )}
+    </script>`;
+}
+
+function renderFaqs(faqs) {
+  if (!faqs || faqs.length === 0) return '';
+  const items = faqs
+    .map(
+      (f) => `        <details class="faq-d">
+          <summary class="faq-d-q">${escapeHtml(f.q)}<i data-lucide="plus" class="faq-d-icon"></i></summary>
+          <p class="faq-d-a">
+            ${renderInline(f.a)}
+          </p>
+        </details>`
+    )
+    .join('\n');
+  return `
+      <h2 class="text-2xl font-bold text-white mt-10 mb-4">FAQ</h2>
+      <div class="faq-list">
+${items}
+      </div>`;
+}
+
+function renderCta(cta) {
+  if (!cta) return '';
+  return `
+      <div class="bg-gray-800 border border-gray-700 rounded-xl p-6 my-10">
+        <p class="text-white font-semibold mb-2">${escapeHtml(cta.heading)}</p>
+        <p class="text-gray-400 mb-4">${escapeHtml(cta.text)}</p>
+        <a
+          href="${cta.href}"
+          class="inline-block bg-indigo-600 hover:bg-indigo-700 text-white font-semibold px-5 py-2.5 rounded-lg"
+          >${escapeHtml(cta.label)}</a
+        >
+      </div>`;
+}
+
+function renderPost({ slug, meta, body }) {
+  const url = `${SITE_URL}/blog/${slug}`;
+  const updated = meta.updated || meta.date;
+  const bodyHtml = styleBody(marked.parse(body));
+  const faqEntries =
+    meta.faqs && meta.faqs.length > 0 ? meta.faqs : questionSections(body);
+
+  return `<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>${escapeHtml(meta.title)}</title>
+    <meta name="description" content="${escapeHtml(meta.description)}" />
+    <meta name="robots" content="index, follow, max-image-preview:large" />
+    <link rel="canonical" href="${url}" />
+    <meta property="og:type" content="article" />
+    <meta property="og:url" content="${url}" />
+    <meta property="og:title" content="${escapeHtml(meta.ogTitle || meta.h1)}" />
+    <meta property="og:description" content="${escapeHtml(meta.description)}" />
+    <meta property="og:image" content="${SITE_URL}/images/og-tools.png" />
+    <meta property="og:site_name" content="BentoPDF" />
+    <meta name="twitter:card" content="summary_large_image" />
+    <link rel="manifest" href="/site.webmanifest" />
+    <link rel="icon" type="image/svg+xml" href="/images/favicon.svg" />
+    <link rel="icon" href="/favicon.ico" sizes="32x32" />
+    <link href="/src/css/styles.css" rel="stylesheet" />
+  </head>
+
+  <body class="antialiased bg-gray-900">
+    {{> navbar }}
+
+    <article class="max-w-3xl mx-auto px-4 py-12">
+      <nav
+        class="flex items-center gap-2 text-sm text-gray-400 mb-6"
+        aria-label="Breadcrumb"
+      >
+        <a href="/blog" class="hover:text-indigo-300">Blog</a>
+        <i class="ph ph-caret-right text-xs" aria-hidden="true"></i>
+        <span class="text-gray-300">${escapeHtml(meta.breadcrumb)}</span>
+      </nav>
+
+      <h1 class="text-3xl md:text-4xl font-bold text-white mb-4 leading-tight">
+        ${escapeHtml(meta.h1)}
+      </h1>
+
+      <div class="flex items-center gap-3 mb-10 text-sm text-gray-400">
+        <img
+          src="/images/author-alam.jpg"
+          alt="${AUTHOR.name}"
+          width="40"
+          height="40"
+          class="rounded-full"
+        />
+        <div>
+          <a href="/blog/author-alam" class="text-gray-200 font-semibold hover:text-indigo-300">${AUTHOR.name}</a>,
+          builds BentoPDF ·
+          <time datetime="${meta.date}">${formatDate(meta.date)}</time>
+        </div>
+      </div>
+
+${bodyHtml}
+${renderCta(meta.cta)}
+${renderFaqs(meta.faqs)}
+    </article>
+
+    {{> footer }}
+    <script type="module" src="/src/js/utils/lucide-init.ts"></script>
+    <script type="module" src="/src/js/mobileMenu.ts"></script>
+    <script type="module">
+      import '@phosphor-icons/web/regular';
+    </script>
+
+    <script type="application/ld+json">
+      ${JSON.stringify(
+        {
+          '@context': 'https://schema.org',
+          '@type': 'BlogPosting',
+          headline: meta.h1,
+          description: meta.description,
+          url,
+          datePublished: meta.date,
+          dateModified: updated,
+          image: `${SITE_URL}/images/og-tools.png`,
+          author: {
+            '@type': 'Person',
+            name: AUTHOR.name,
+            url: AUTHOR.url,
+            sameAs: AUTHOR.profiles,
+          },
+          publisher: {
+            '@type': 'Organization',
+            name: 'BentoPDF',
+            url: SITE_URL,
+          },
+        },
+        null,
+        2
+      )}
+    </script>
+    <script type="application/ld+json">
+      ${JSON.stringify(
+        {
+          '@context': 'https://schema.org',
+          '@type': 'BreadcrumbList',
+          itemListElement: [
+            {
+              '@type': 'ListItem',
+              position: 1,
+              name: 'Blog',
+              item: `${SITE_URL}/blog/`,
+            },
+            {
+              '@type': 'ListItem',
+              position: 2,
+              name: meta.breadcrumb,
+              item: url,
+            },
+          ],
+        },
+        null,
+        2
+      )}
+    </script>${faqSchema(faqEntries)}
+  </body>
+</html>
+`;
+}
+
+function renderIndex(posts) {
+  const cards = posts
+    .map(
+      ({ slug, meta }) => `        <a
+          href="/blog/${slug}"
+          class="block bg-gray-800 border border-gray-700 rounded-xl p-6 hover:border-indigo-500 transition-colors"
+        >
+          <h2 class="text-xl font-bold text-white mb-2">
+            ${escapeHtml(meta.h1)}
+          </h2>
+          <p class="text-gray-400 mb-3">
+            ${escapeHtml(meta.card)}
+          </p>
+          <span class="text-sm text-gray-500">${formatDate(meta.date)}</span>
+        </a>`
+    )
+    .join('\n\n');
+
+  return `<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>The BentoPDF Blog | Privacy-First PDF Guides</title>
+    <meta
+      name="description"
+      content="Guides and honest comparisons from the maintainer of BentoPDF: how PDF tools handle your files, and how to get things done without uploading them."
+    />
+    <meta name="robots" content="index, follow, max-image-preview:large" />
+    <link rel="canonical" href="${SITE_URL}/blog/" />
+    <meta property="og:type" content="website" />
+    <meta property="og:url" content="${SITE_URL}/blog/" />
+    <meta property="og:title" content="The BentoPDF Blog" />
+    <meta
+      property="og:description"
+      content="Guides and honest comparisons from the maintainer of BentoPDF."
+    />
+    <meta property="og:image" content="${SITE_URL}/images/og-tools.png" />
+    <meta property="og:site_name" content="BentoPDF" />
+    <meta name="twitter:card" content="summary_large_image" />
+    <link rel="manifest" href="/site.webmanifest" />
+    <link rel="icon" type="image/svg+xml" href="/images/favicon.svg" />
+    <link rel="icon" href="/favicon.ico" sizes="32x32" />
+    <link href="/src/css/styles.css" rel="stylesheet" />
+  </head>
+
+  <body class="antialiased bg-gray-900">
+    {{> navbar }}
+
+    <section class="max-w-3xl mx-auto px-4 py-12">
+      <h1 class="text-3xl md:text-4xl font-bold text-white mb-4">The BentoPDF Blog</h1>
+      <p class="text-gray-300 leading-relaxed mb-2">
+        I'm <a href="/blog/author-alam" class="${LINK_CLASS}">Alam</a>. I build
+        BentoPDF and write about PDFs, how they work, and the weird things I
+        run into along the way.
+      </p>
+    </section>
+
+    <section class="max-w-3xl mx-auto px-4 pb-16">
+      <div class="space-y-6">
+${cards}
+      </div>
+    </section>
+
+    {{> footer }}
+    <script type="module" src="/src/js/utils/lucide-init.ts"></script>
+    <script type="module" src="/src/js/mobileMenu.ts"></script>
+
+    <script type="application/ld+json">
+      ${JSON.stringify(
+        {
+          '@context': 'https://schema.org',
+          '@type': 'Blog',
+          name: 'The BentoPDF Blog',
+          url: `${SITE_URL}/blog/`,
+          description:
+            'Guides and honest comparisons from the maintainer of BentoPDF.',
+          publisher: {
+            '@type': 'Organization',
+            name: 'BentoPDF',
+            url: SITE_URL,
+          },
+        },
+        null,
+        2
+      )}
+    </script>
+  </body>
+</html>
+`;
+}
+
+function generate() {
+  if (!fs.existsSync(POSTS_DIR)) {
+    console.log('generate-blog: no blog/posts directory, skipping');
+    return;
+  }
+  const files = fs
+    .readdirSync(POSTS_DIR)
+    .filter((f) => f.endsWith('.md'))
+    .sort();
+  const posts = files.map(parsePost);
+  posts.sort((a, b) => (a.meta.date < b.meta.date ? 1 : -1));
+
+  const keep = new Set(['index.html', 'author-alam.html']);
+  for (const post of posts) {
+    fs.writeFileSync(
+      path.join(BLOG_DIR, `${post.slug}.html`),
+      renderPost(post)
+    );
+    keep.add(`${post.slug}.html`);
+  }
+  fs.writeFileSync(path.join(BLOG_DIR, 'index.html'), renderIndex(posts));
+
+  for (const entry of fs.readdirSync(BLOG_DIR)) {
+    if (entry.endsWith('.html') && !keep.has(entry)) {
+      fs.rmSync(path.join(BLOG_DIR, entry));
+      console.log(`generate-blog: removed stale ${entry}`);
+    }
+  }
+
+  console.log(
+    `generate-blog: ${posts.length} posts + index generated from blog/posts/`
+  );
+}
+
+generate();

scripts/generate-i18n-pages.mjs

@@ -59,7 +59,47 @@ function buildUrl(langPrefix, pagePath) {
   if (BASE_PATH && BASE_PATH !== '') parts.push(BASE_PATH.replace(/^\//, ''));
   if (langPrefix) parts.push(langPrefix);
   if (pagePath) parts.push(pagePath.replace(/^\//, ''));
-  return parts.filter(Boolean).join('/').replace(/\/+$/, '') || SITE_URL;
+  const url = parts.filter(Boolean).join('/').replace(/\/+$/, '') || SITE_URL;
+  return langPrefix && !pagePath ? `${url}/` : url;
+}
+
+function resolveTranslation(langResources, key) {
+  let namespace = 'common';
+  let keyPath = key;
+  const colonIndex = key.indexOf(':');
+  if (colonIndex !== -1) {
+    namespace = key.slice(0, colonIndex);
+    keyPath = key.slice(colonIndex + 1);
+  }
+  let node = langResources[namespace];
+  for (const segment of keyPath.split('.')) {
+    if (node == null || typeof node !== 'object') return null;
+    node = node[segment];
+  }
+  return typeof node === 'string' && node ? node : null;
+}
+
+function applyServerTranslations(document, langResources) {
+  document.querySelectorAll('[data-i18n]').forEach((element) => {
+    const key = element.getAttribute('data-i18n');
+    if (!key) return;
+    const translation = resolveTranslation(langResources, key);
+    if (translation) element.textContent = translation;
+  });
+
+  document.querySelectorAll('[data-i18n-placeholder]').forEach((element) => {
+    const key = element.getAttribute('data-i18n-placeholder');
+    if (!key) return;
+    const translation = resolveTranslation(langResources, key);
+    if (translation) element.setAttribute('placeholder', translation);
+  });
+
+  document.querySelectorAll('[data-i18n-title]').forEach((element) => {
+    const key = element.getAttribute('data-i18n-title');
+    if (!key) return;
+    const translation = resolveTranslation(langResources, key);
+    if (translation) element.setAttribute('title', translation);
+  });
 }
 
 const ORGANIZATION_LD_MARKER = 'data-bentopdf-organization';
@@ -105,10 +145,24 @@ function buildLocalHomeHref(lang) {
   return `${BASE_PATH}${langSegment}`.replace(/\/+/g, '/');
 }
 
+function removeStaticBreadcrumbLd(document) {
+  for (const script of document.querySelectorAll(
+    `script[type="application/ld+json"]:not([${BREADCRUMB_MARKER}])`
+  )) {
+    try {
+      const parsed = JSON.parse(script.textContent || '');
+      if (parsed && parsed['@type'] === 'BreadcrumbList') script.remove();
+    } catch {
+      continue;
+    }
+  }
+}
+
 function injectToolBreadcrumb(document, lang, toolName, toolUrl) {
   const h1 = document.querySelector('h1[data-i18n^="tools:"]');
   if (!h1) return;
   if (document.querySelector(`[${BREADCRUMB_MARKER}]`)) return;
+  removeStaticBreadcrumbLd(document);
 
   const homeUrl = buildUrl(lang === 'en' ? '' : lang, '');
 
@@ -191,6 +245,8 @@ function processFileForLanguage(
   document.documentElement.lang = lang;
   document.documentElement.dir = lang === 'ar' ? 'rtl' : 'ltr';
 
+  applyServerTranslations(document, translations[lang]);
+
   let title = null;
   let description = null;
 
@@ -247,14 +303,13 @@ function processFileForLanguage(
   document.head.appendChild(defaultLink);
 
   const localizedUrl = buildUrl(lang, pagePath);
-  const canonicalUrl = buildUrl('', pagePath);
   let canonical = document.querySelector('link[rel="canonical"]');
   if (!canonical) {
     canonical = document.createElement('link');
     canonical.rel = 'canonical';
     document.head.appendChild(canonical);
   }
-  canonical.href = canonicalUrl;
+  canonical.href = localizedUrl;
 
   const ogUrl = document.querySelector('meta[property="og:url"]');
   if (ogUrl) ogUrl.content = localizedUrl;
@@ -288,6 +343,8 @@ function processFileForLanguage(
 
     if (href.startsWith('/assets/') || href.includes('/assets/')) return;
 
+    if (href === '/blog' || href.startsWith('/blog/')) return;
+
     const langPrefixRegex = new RegExp(
       `^(${BASE_PATH})?/(${languages.join('|')})(/|$)`
     );

scripts/generate-sitemap.mjs

@@ -1,5 +1,6 @@
 import fs from 'fs';
 import path from 'path';
+import { execFileSync } from 'child_process';
 import { fileURLToPath } from 'url';
 
 const __filename = fileURLToPath(import.meta.url);
@@ -32,9 +33,17 @@ const PRIORITY_MAP = {
   'excel-to-pdf': 0.9,
   'powerpoint-to-pdf': 0.9,
   'jpg-to-pdf': 0.9,
-  'pdf-to-docx': 0.9,
+  'pdf-to-word': 0.9,
+  'unlock-pdf': 0.9,
+  'protect-pdf': 0.9,
   'pdf-to-excel': 0.9,
   'pdf-to-jpg': 0.9,
+  'compress-pdf-to-100kb': 0.8,
+  'compress-pdf-to-200kb': 0.8,
+  'compress-pdf-to-500kb': 0.8,
+  'compress-pdf-to-1mb': 0.8,
+  'compress-pdf-to-2mb': 0.8,
+  'compress-pdf-for-email': 0.8,
   about: 0.8,
   faq: 0.8,
   contact: 0.7,
@@ -52,7 +61,7 @@ function buildUrl(lang, pageName) {
   if (lang === 'en') {
     return pagePath ? `${SITE_URL}/${pagePath}` : SITE_URL;
   }
-  return pagePath ? `${SITE_URL}/${lang}/${pagePath}` : `${SITE_URL}/${lang}`;
+  return pagePath ? `${SITE_URL}/${lang}/${pagePath}` : `${SITE_URL}/${lang}/`;
 }
 
 function generateSitemap() {
@@ -66,22 +75,48 @@ function generateSitemap() {
     .map((file) => file.replace('.html', ''))
     .filter((name) => !EXCLUDED_PAGES.has(name));
 
+  const projectRoot = path.resolve(__dirname, '..');
   const lastModCache = new Map();
-  const getLastMod = (lang, pageName) => {
-    const cacheKey = `${lang}::${pageName}`;
-    if (lastModCache.has(cacheKey)) return lastModCache.get(cacheKey);
+  const getLastMod = (pageName) => {
+    if (lastModCache.has(pageName)) return lastModCache.get(pageName);
     const fileName = `${pageName}.html`;
-    const filePath =
-      lang === 'en'
-        ? path.join(DIST_DIR, fileName)
-        : path.join(DIST_DIR, lang, fileName);
-    let iso;
-    try {
-      iso = fs.statSync(filePath).mtime.toISOString().slice(0, 10);
-    } catch {
-      iso = new Date().toISOString().slice(0, 10);
+    const candidates = [
+      path.join(projectRoot, 'src', 'pages', fileName),
+      path.join(projectRoot, fileName),
+    ];
+    let iso = null;
+    for (const sourcePath of candidates) {
+      if (!fs.existsSync(sourcePath)) continue;
+      try {
+        const out = execFileSync(
+          'git',
+          ['log', '-1', '--format=%cI', '--', sourcePath],
+          { cwd: projectRoot, encoding: 'utf-8' }
+        ).trim();
+        if (out) iso = out.slice(0, 10);
+      } catch {
+        iso = null;
+      }
+      if (!iso) {
+        try {
+          iso = fs.statSync(sourcePath).mtime.toISOString().slice(0, 10);
+        } catch {
+          iso = null;
+        }
+      }
+      break;
     }
-    lastModCache.set(cacheKey, iso);
+    if (!iso) {
+      try {
+        iso = fs
+          .statSync(path.join(DIST_DIR, fileName))
+          .mtime.toISOString()
+          .slice(0, 10);
+      } catch {
+        iso = new Date().toISOString().slice(0, 10);
+      }
+    }
+    lastModCache.set(pageName, iso);
     return iso;
   };
 
@@ -93,12 +128,11 @@ function generateSitemap() {
   for (const pageName of htmlFiles) {
     const priority = getPriority(pageName);
     const url = buildUrl('en', pageName);
-    const lastmod = getLastMod('en', pageName);
+    const lastmod = getLastMod(pageName);
 
     sitemap += `  <url>
     <loc>${url}</loc>
     <lastmod>${lastmod}</lastmod>
-    <changefreq>weekly</changefreq>
     <priority>${priority}</priority>
 `;
 
@@ -114,6 +148,48 @@ function generateSitemap() {
 `;
   }
 
+  const blogDir = path.join(DIST_DIR, 'blog');
+  let blogCount = 0;
+  if (fs.existsSync(blogDir)) {
+    const blogFiles = fs
+      .readdirSync(blogDir)
+      .filter((file) => file.endsWith('.html'))
+      .map((file) => file.replace('.html', ''));
+    for (const name of blogFiles) {
+      const url =
+        name === 'index' ? `${SITE_URL}/blog/` : `${SITE_URL}/blog/${name}`;
+      const sourcePath = path.join(projectRoot, 'blog', `${name}.html`);
+      let lastmod;
+      try {
+        const out = execFileSync(
+          'git',
+          ['log', '-1', '--format=%cI', '--', sourcePath],
+          { cwd: projectRoot, encoding: 'utf-8' }
+        ).trim();
+        lastmod = out ? out.slice(0, 10) : null;
+      } catch {
+        lastmod = null;
+      }
+      if (!lastmod) {
+        try {
+          lastmod = fs.statSync(sourcePath).mtime.toISOString().slice(0, 10);
+        } catch {
+          lastmod = new Date().toISOString().slice(0, 10);
+        }
+      }
+      sitemap += `  <url>
+    <loc>${url}</loc>
+    <lastmod>${lastmod}</lastmod>
+    <priority>0.7</priority>
+  </url>
+`;
+      blogCount++;
+    }
+  }
+  if (blogCount > 0) {
+    console.log(`   Blog: ${blogCount} URLs added (English only)`);
+  }
+
   sitemap += `</urlset>
 `;
 

scripts/generate-static-tool-links.mjs

@@ -0,0 +1,106 @@
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const TOOLS_CONFIG = path.resolve(__dirname, '../src/js/config/tools.ts');
+const PAGES_DIR = path.resolve(__dirname, '../src/pages');
+const PARTIAL_PATH = path.resolve(
+  __dirname,
+  '../src/partials/tool-links-static.html'
+);
+
+function escapeHtml(value) {
+  return value
+    .replace(/&/g, '&')
+    .replace(/</g, '&lt;')
+    .replace(/>/g, '&gt;')
+    .replace(/"/g, '&quot;');
+}
+
+function unescapeTs(value) {
+  return value.replace(/\\'/g, "'").replace(/\\\\/g, '\\');
+}
+
+function parseCategories(source) {
+  const headers = [
+    ...source.matchAll(/name:\s*'((?:[^'\\]|\\.)*)',\s*\n\s*tools:\s*\[/g),
+  ].map((m) => ({ name: unescapeTs(m[1]), index: m.index }));
+
+  const toolMatches = [
+    ...source.matchAll(
+      /\{[^{}]*?href:\s*import\.meta\.env\.BASE_URL\s*\+\s*'((?:[^'\\]|\\.)*)'[^{}]*?\}/gs
+    ),
+  ];
+  const categories = headers.map((h) => ({ name: h.name, tools: [] }));
+  for (const match of toolMatches) {
+    const block = match[0];
+    const hrefFile = unescapeTs(match[1]);
+    const nameMatch = block.match(/name:\s*'((?:[^'\\]|\\.)*)'/s);
+    const subtitleMatch = block.match(/subtitle:\s*\n?\s*'((?:[^'\\]|\\.)*)'/s);
+    if (!nameMatch) continue;
+
+    let categoryIndex = -1;
+    for (let i = 0; i < headers.length; i++) {
+      if (headers[i].index < match.index) categoryIndex = i;
+    }
+    if (categoryIndex === -1) continue;
+
+    categories[categoryIndex].tools.push({
+      slug: hrefFile.replace(/\.html$/, ''),
+      name: unescapeTs(nameMatch[1]),
+      subtitle: subtitleMatch ? unescapeTs(subtitleMatch[1]) : '',
+    });
+  }
+  return categories.filter((c) => c.tools.length > 0);
+}
+
+function generate() {
+  const source = fs.readFileSync(TOOLS_CONFIG, 'utf-8');
+  const categories = parseCategories(source);
+  const existingPages = new Set(
+    fs
+      .readdirSync(PAGES_DIR)
+      .filter((f) => f.endsWith('.html'))
+      .map((f) => f.replace(/\.html$/, ''))
+  );
+
+  const seen = new Set();
+  const lines = [];
+  let toolCount = 0;
+  for (const category of categories) {
+    const tools = category.tools.filter(
+      (t) => existingPages.has(t.slug) && !seen.has(t.slug)
+    );
+    if (tools.length === 0) continue;
+    for (const t of tools) seen.add(t.slug);
+    lines.push(
+      `<div class="col-span-full mt-6 first:mt-0"><h2 class="text-lg font-semibold text-white">${escapeHtml(category.name)}</h2></div>`
+    );
+    for (const tool of tools) {
+      toolCount++;
+      lines.push(
+        `<a href="/${tool.slug}" class="block bg-gray-800 p-4 rounded-lg border border-gray-700 hover:bg-gray-700 transition-colors">` +
+          `<h3 class="text-white font-semibold mb-1">${escapeHtml(tool.name)}</h3>` +
+          `<p class="text-gray-400 text-sm">${escapeHtml(tool.subtitle)}</p>` +
+          `</a>`
+      );
+    }
+  }
+
+  if (toolCount < 50) {
+    console.error(
+      `generate-static-tool-links: only ${toolCount} tools parsed from tools.ts — parser is likely out of sync with the config format`
+    );
+    process.exit(1);
+  }
+
+  fs.writeFileSync(PARTIAL_PATH, lines.join('\n') + '\n');
+  console.log(
+    `Static tool links: ${toolCount} tools in ${categories.length} categories -> src/partials/tool-links-static.html`
+  );
+}
+
+generate();

scripts/include-docs-in-dist.js

@@ -11,46 +11,95 @@ const mainDistPath = path.join(projectRoot, 'dist');
 const targetDocsPath = path.join(mainDistPath, 'docs');
 
 function copyDir(src, dest) {
-    if (!fs.existsSync(dest)) {
-        fs.mkdirSync(dest, { recursive: true });
-    }
+  if (!fs.existsSync(dest)) {
+    fs.mkdirSync(dest, { recursive: true });
+  }
 
-    const entries = fs.readdirSync(src, { withFileTypes: true });
+  const entries = fs.readdirSync(src, { withFileTypes: true });
 
-    for (const entry of entries) {
-        const srcPath = path.join(src, entry.name);
-        const destPath = path.join(dest, entry.name);
+  for (const entry of entries) {
+    const srcPath = path.join(src, entry.name);
+    const destPath = path.join(dest, entry.name);
 
-        if (entry.isDirectory()) {
-            copyDir(srcPath, destPath);
-        } else {
-            fs.copyFileSync(srcPath, destPath);
-        }
+    if (entry.isDirectory()) {
+      copyDir(srcPath, destPath);
+    } else {
+      fs.copyFileSync(srcPath, destPath);
     }
+  }
 }
 
 console.log('Including docs in dist...');
 
 if (!fs.existsSync(docsDistPath)) {
-    console.error('Error: Docs build not found. Please run "npm run docs:build" first.');
-    process.exit(1);
+  console.error(
+    'Error: Docs build not found. Please run "npm run docs:build" first.'
+  );
+  process.exit(1);
 }
 if (!fs.existsSync(mainDistPath)) {
-    console.error('Error: Main dist folder not found. Please run "npm run build" first.');
-    process.exit(1);
+  console.error(
+    'Error: Main dist folder not found. Please run "npm run build" first.'
+  );
+  process.exit(1);
 }
 
 try {
-    console.log(`Copying from: ${docsDistPath}`);
-    console.log(`Copying to: ${targetDocsPath}`);
+  console.log(`Copying from: ${docsDistPath}`);
+  console.log(`Copying to: ${targetDocsPath}`);
 
-    copyDir(docsDistPath, targetDocsPath);
+  copyDir(docsDistPath, targetDocsPath);
 
-    console.log('Docs successfully included in dist/docs!');
+  console.log('Docs successfully included in dist/docs!');
 
-    const files = fs.readdirSync(targetDocsPath);
-    console.log(`Copied ${files.length} items to dist/docs`);
+  const files = fs.readdirSync(targetDocsPath);
+  console.log(`Copied ${files.length} items to dist/docs`);
+
+  addDocsToSitemap();
 } catch (error) {
-    console.error('Error copying docs:', error.message);
-    process.exit(1);
+  console.error('Error copying docs:', error.message);
+  process.exit(1);
+}
+
+function listDocsHtml(dir, prefix) {
+  const urls = [];
+  for (const entry of fs.readdirSync(dir, { withFileTypes: true })) {
+    if (entry.isDirectory()) {
+      if (entry.name === 'assets' || entry.name.startsWith('.')) continue;
+      urls.push(
+        ...listDocsHtml(path.join(dir, entry.name), `${prefix}/${entry.name}`)
+      );
+    } else if (entry.name.endsWith('.html') && entry.name !== '404.html') {
+      const slug = entry.name.replace(/\.html$/, '');
+      urls.push(slug === 'index' ? `${prefix}/` : `${prefix}/${slug}`);
+    }
+  }
+  return urls;
+}
+
+function addDocsToSitemap() {
+  const siteUrl = (process.env.SITE_URL || 'https://www.bentopdf.com').replace(
+    /\/+$/,
+    ''
+  );
+  const sitemapPath = path.join(mainDistPath, 'sitemap.xml');
+  if (!fs.existsSync(sitemapPath)) {
+    console.warn(
+      'sitemap.xml not found in dist; skipping docs sitemap entries'
+    );
+    return;
+  }
+  let xml = fs.readFileSync(sitemapPath, 'utf-8');
+  if (xml.includes(`<loc>${siteUrl}/docs/</loc>`)) return;
+
+  const urls = listDocsHtml(targetDocsPath, '/docs');
+  const entries = urls
+    .map(
+      (url) =>
+        `  <url>\n    <loc>${siteUrl}${url}</loc>\n    <priority>0.6</priority>\n  </url>\n`
+    )
+    .join('');
+  xml = xml.replace('</urlset>', `${entries}</urlset>`);
+  fs.writeFileSync(sitemapPath, xml);
+  console.log(`Added ${urls.length} docs URLs to sitemap.xml`);
 }

scripts/seo-audit.mjs

@@ -67,6 +67,12 @@ function findAll(html, regex) {
   return out;
 }
 
+const LOCALE_DIRS = new Set(
+  fs
+    .readdirSync(LOCALES_DIR)
+    .filter((d) => fs.statSync(path.join(LOCALES_DIR, d)).isDirectory())
+);
+
 function expectedCanonicalForFile(rel) {
   const parts = rel.split('/');
   const fileName = parts.pop();
@@ -74,12 +80,40 @@ function expectedCanonicalForFile(rel) {
   const slug = baseName === 'index' ? '' : baseName;
   const segments = [SITE_URL];
   if (BASE_PATH) segments.push(BASE_PATH.replace(/^\//, ''));
+  for (const dir of parts) {
+    if (LOCALE_DIRS.has(dir) || dir === 'blog') segments.push(dir);
+  }
   if (slug) segments.push(slug);
   return segments.join('/').replace(/\/+$/, '') || SITE_URL;
 }
 
-function auditHtml(file) {
+function auditHtml(file, knownSlugs) {
   const html = fs.readFileSync(file.full, 'utf-8');
+  const isLocalized = file.rel.split('/').some((seg) => LOCALE_DIRS.has(seg));
+
+  if (!isLocalized && /[—–]/.test(html)) {
+    fail(
+      'em-dash',
+      `${file.rel}: contains an em or en dash (house style forbids them)`
+    );
+  }
+
+  if (!isLocalized) {
+    const internal = findAll(html, /<a[^>]+href=["'](\/[^"'#?]*)["']/g);
+    for (const href of internal) {
+      const clean = href.replace(/\/$/, '');
+      if (clean === '') continue;
+      const seg = clean.slice(1);
+      if (seg.includes('/')) continue;
+      if (LOCALE_DIRS.has(seg) || seg === 'blog' || seg === 'docs') continue;
+      if (!knownSlugs.has(seg)) {
+        fail(
+          'dead-link',
+          `${file.rel}: links to "${href}" but no such page exists in dist`
+        );
+      }
+    }
+  }
   const titles = findAll(html, /<title[^>]*>[\s\S]*?<\/title>/g);
   if (titles.length === 0) {
     fail('title', `${file.rel}: no <title>`);
@@ -147,7 +181,7 @@ function auditHtml(file) {
     );
   }
 
-  const emptyI18n = html.match(/<span[^>]*data-i18n="[^"]+"[^>]*>\s*<\/span>/g);
+  const emptyI18n = html.match(/<span[^>]*data-i18n="[^"]+"[^>]*><\/span>/g);
   if (emptyI18n && emptyI18n.length > 0) {
     fail(
       'data-i18n',
@@ -176,10 +210,76 @@ function auditHtml(file) {
           `${file.rel}: hreflang href host "${url.hostname}" != expected "${HOST}"`
         );
       }
+      const trimmed = url.pathname.replace(/^\/|\/$/g, '');
+      if (LOCALE_DIRS.has(trimmed) && !url.pathname.endsWith('/')) {
+        fail(
+          'hreflang',
+          `${file.rel}: language-home hreflang "${m[1]}" must end with "/" (the server 301s the slashless form)`
+        );
+      }
     } catch {
       fail('hreflang', `${file.rel}: hreflang href "${m[1]}" not a valid URL`);
     }
   }
+
+  const descriptions = findAll(
+    html,
+    /<meta[^>]+name=["']description["'][^>]*content=["']([^"']*)["']/g
+  );
+  if (descriptions.length > 1) {
+    fail(
+      'description',
+      `${file.rel}: ${descriptions.length} meta description tags (expected 1)`
+    );
+  }
+  for (const desc of descriptions) {
+    if (desc.includes('★')) {
+      fail('description', `${file.rel}: meta description contains "★"`);
+    }
+  }
+
+  const isTopLevel = !file.rel.includes('/');
+  if (isTopLevel) {
+    const socialImages = findAll(
+      html,
+      /<meta[^>]+(?:property=["']og:image["']|name=["']twitter:image["'])[^>]*content=["']([^"']+)["']/g
+    );
+    for (const image of socialImages) {
+      let pathname;
+      try {
+        pathname = image.startsWith('http') ? new URL(image).pathname : image;
+      } catch {
+        continue;
+      }
+      if (
+        pathname.startsWith('/images/') &&
+        !fs.existsSync(path.join(DIST_DIR, pathname.replace(/^\//, '')))
+      ) {
+        fail(
+          'social-image',
+          `${file.rel}: og/twitter image "${pathname}" does not exist in dist`
+        );
+      }
+    }
+
+    if (html.includes('faq-d') && !html.includes('"FAQPage"')) {
+      fail(
+        'faq-schema',
+        `${file.rel}: visible FAQ section without FAQPage JSON-LD`
+      );
+    }
+
+    const internalHtmlLinks = findAll(
+      html,
+      /<a[^>]+href=["'](\/?[a-z0-9][a-z0-9-]*\.html)["']/g
+    );
+    for (const href of internalHtmlLinks) {
+      fail(
+        'internal-link',
+        `${file.rel}: internal link "${href}" should be extensionless`
+      );
+    }
+  }
 }
 
 function auditSitemap() {
@@ -248,7 +348,12 @@ function main() {
     fail('audit', 'no HTML files found in dist/');
   }
 
-  for (const file of files) auditHtml(file);
+  const knownSlugs = new Set(
+    files
+      .filter((f) => !f.rel.includes('/'))
+      .map((f) => f.rel.replace(/\.html$/, ''))
+  );
+  for (const file of files) auditHtml(file, knownSlugs);
   auditSitemap();
 
   const total = failures.length + warnings.length;