Update index.html

mehulimukherjee · web-flow · commit 7fb4e1ba7570 · 2025-08-27T12:13:47.000+12:00
diff --git a/index.html b/index.html
@@ -3,40 +3,50 @@
 <head>
   <meta charset="UTF-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <meta name="description" content="ExtractPDF4J - JVM-native open-source library to extract tables from PDFs using Stream, Lattice, and OCR parsing modes." />
+  <meta property="og:title" content="ExtractPDF4J" />
+  <meta property="og:description" content="Extract tables from PDFs (text & scanned) directly in Java. Stream + Lattice + OCR parsing." />
+  <meta property="og:image" content="assets/og-image.png" />
+  <meta property="og:type" content="website" />
+  <meta name="twitter:card" content="summary_large_image" />
   <title>ExtractPDF4J</title>
   <link rel="stylesheet" href="assets/style.css" />
+  <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600&display=swap" rel="stylesheet">
 </head>
 <body>
-  <header>
+  <header class="hero">
     <h1>ExtractPDF4J</h1>
-    <p>A powerful Java library for extracting tables from PDFs (Stream + Lattice + OCR)</p>
-    <a class="btn" href="https://github.com/yourusername/ExtractPDF4J" target="_blank">⭐ View on GitHub</a>
-    <a class="btn secondary" href="docs/index.html">📖 Documentation</a>
+    <p class="tagline">Extract tables from PDFs — text-based or scanned — with JVM-native power 🚀</p>
+    <div class="buttons">
+      <a class="btn" href="https://github.com/ExtractPDF4J/ExtractPDF4J/" target="_blank">⭐ GitHub</a>
+      <a class="btn secondary" href="docs/index.html">📖 Documentation</a>
+    </div>
   </header>
 
   <section>
-    <h2>✨ Features</h2>
+    <h2>✨ Why ExtractPDF4J?</h2>
+    <p>ExtractPDF4J brings the best of Camelot and Tabula into the Java ecosystem, making PDF table extraction simple, robust, and production-ready.</p>
     <ul>
-      <li>Stream and Lattice parsing (like Camelot, but in Java!)</li>
-      <li>OCR-based extraction for scanned PDFs</li>
-      <li>Multi-page & complex table handling</li>
-      <li>Open-source under Apache 2.0</li>
+      <li>Stream & Lattice parsing (like Camelot, but JVM-native)</li>
+      <li>OCR support for scanned PDFs</li>
+      <li>Multi-page & complex table layouts</li>
+      <li>Apache 2.0 licensed, open-source</li>
     </ul>
   </section>
 
   <section>
     <h2>🚀 Quick Start</h2>
     <pre>
 &lt;dependency&gt;
-  &lt;groupId&gt;com.extractpdf4j&lt;/groupId&gt;
+  &lt;groupId&gt;io.github.mehulimukherjee&lt;/groupId&gt;
   &lt;artifactId&gt;extractpdf4j&lt;/artifactId&gt;
-  &lt;version&gt;1.0.0&lt;/version&gt;
+  &lt;version&gt;0.1.0&lt;/version&gt;
 &lt;/dependency&gt;
     </pre>
   </section>
 
   <footer>
-    <p>Made with ❤️ by Mehuli Mukherjee | <a href="docs/index.html">Read Docs</a></p>
+    <p>Made with ❤️ by Mehuli Mukherjee | <a href="https://github.com/ExtractPDF4J/ExtractPDF4J/">GitHub</a> | Apache 2.0</p>
   </footer>
 </body>
-</html>
+</html>
