d3fe6b2fcc
- Simplify Dockerfile by removing redundant BASE_URL handling logic and complex RUN commands - Change SIMPLE_MODE default from true to false for production builds - Fix indentation inconsistencies in Dockerfile conditional statements - Move favicon link tags from body to head section in all HTML files for proper semantic structure - Replace inline favicon links with img tag in navigation logo across all pages - Update README.md documentation to clarify BASE_URL trailing slash requirements - Remove commented-out legacy Dockerfile code for cleaner maintenance - Consolidate favicon declarations in document head for better performance and SEO
316 lines
21 KiB
HTML
316 lines
21 KiB
HTML
<!doctype html>
|
|
<html lang="en">
|
|
|
|
<head>
|
|
<meta charset="UTF-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<title>OCR PDF - Make PDF Searchable - BentoPDF</title>
|
|
<meta name="description"
|
|
content="Convert scanned PDFs into searchable documents using OCR. Extract text from images and create searchable PDFs. Free, secure, and runs entirely in your browser.">
|
|
<link rel="icon" type="image/svg+xml" href="/images/favicon.svg" />
|
|
<link rel="icon" type="image/png" href="/images/favicon.png" />
|
|
<link rel="apple-touch-icon" href="/images/favicon.png" />
|
|
<link rel="icon" href="/favicon.ico" sizes="any" />
|
|
<link rel="alternate" hreflang="en" href="/en/ocr-pdf.html" />
|
|
<link rel="alternate" hreflang="de" href="/de/ocr-pdf.html" />
|
|
<link rel="alternate" hreflang="x-default" href="/en/ocr-pdf.html" />
|
|
<link href="/src/css/styles.css" rel="stylesheet" />
|
|
</head>
|
|
|
|
<body class="antialiased bg-gray-900">
|
|
<nav class="bg-gray-800 border-b border-gray-700 sticky top-0 z-30">
|
|
<div class="container mx-auto px-4">
|
|
<div class="flex justify-between items-center h-16">
|
|
<div class="flex-shrink-0 flex items-center cursor-pointer" id="home-logo">
|
|
<img src="/images/favicon.svg" alt="Bento PDF Logo" class="h-8 w-8" />
|
|
<span class="text-white font-bold text-xl ml-2">
|
|
<a href="/">BentoPDF</a>
|
|
</span>
|
|
</div>
|
|
<div class="hidden md:flex items-center space-x-8 text-white">
|
|
<a href="/" class="nav-link" data-i18n="nav.home">Home</a>
|
|
<a href="/about.html" class="nav-link" data-i18n="nav.about">About</a>
|
|
<a href="/contact.html" class="nav-link" data-i18n="nav.contact">Contact</a>
|
|
<a href="/" class="nav-link" data-i18n="nav.allTools">All Tools</a>
|
|
</div>
|
|
<div class="md:hidden flex items-center">
|
|
<button id="mobile-menu-button" type="button"
|
|
class="inline-flex items-center justify-center p-2 rounded-md text-gray-400 hover:text-white hover:bg-gray-700 focus:outline-none focus:ring-2 focus:ring-inset focus:ring-indigo-500 transition-colors"
|
|
aria-controls="mobile-menu" aria-expanded="false">
|
|
<span class="sr-only">Open main menu</span>
|
|
<svg id="menu-icon" class="block h-6 w-6" xmlns="http://www.w3.org/2000/svg" fill="none"
|
|
viewBox="0 0 24 24" stroke="currentColor" aria-hidden="true">
|
|
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2"
|
|
d="M4 6h16M4 12h16M4 18h16" />
|
|
</svg>
|
|
<svg id="close-icon" class="hidden h-6 w-6" xmlns="http://www.w3.org/2000/svg" fill="none"
|
|
viewBox="0 0 24 24" stroke="currentColor" aria-hidden="true">
|
|
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2"
|
|
d="M6 18L18 6M6 6l12 12" />
|
|
</svg>
|
|
</button>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="mobile-menu" class="hidden md:hidden bg-gray-800 border-t border-gray-700">
|
|
<div class="px-2 pt-2 pb-3 space-y-1 text-center">
|
|
<a href="/" class="mobile-nav-link" data-i18n="nav.home">Home</a>
|
|
<a href="/about.html" class="mobile-nav-link" data-i18n="nav.about">About</a>
|
|
<a href="/contact.html" class="mobile-nav-link" data-i18n="nav.contact">Contact</a>
|
|
<a href="/" class="mobile-nav-link" data-i18n="nav.allTools">All Tools</a>
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<div id="uploader" class="min-h-screen flex flex-col items-center justify-start py-12 p-4 bg-gray-900">
|
|
<div id="tool-uploader"
|
|
class="bg-gray-800 rounded-xl shadow-xl px-4 py-8 md:p-8 max-w-2xl w-full text-gray-200 border border-gray-700">
|
|
<button id="back-to-tools"
|
|
class="flex items-center gap-2 text-indigo-400 hover:text-indigo-300 mb-6 font-semibold">
|
|
<i data-lucide="arrow-left" class="cursor-pointer"></i>
|
|
<span class="cursor-pointer" data-i18n="tools.backToTools"> Back to Tools </span>
|
|
</button>
|
|
|
|
<h1 class="text-2xl font-bold text-white mb-2" data-i18n="tools:ocrPdf.name">OCR PDF</h1>
|
|
<p class="text-gray-400 mb-6" data-i18n="tools:ocrPdf.subtitle">
|
|
Convert scanned PDFs into searchable documents. Select one or more languages present in your file for
|
|
the best results.
|
|
</p>
|
|
|
|
<!-- How it works info box -->
|
|
<div class="p-3 bg-gray-900 rounded-lg border border-gray-700 mb-6">
|
|
<p class="text-sm text-gray-300"><strong class="text-white">How it works:</strong></p>
|
|
<ul class="list-disc list-inside text-xs text-gray-400 mt-1 space-y-1">
|
|
<li><strong class="text-white">Extract Text:</strong> Uses Tesseract OCR to recognize text from
|
|
scanned images or PDFs.</li>
|
|
<li><strong class="text-white">Searchable Output:</strong> Creates a new PDF with an invisible text
|
|
layer, making your document fully searchable while preserving the original appearance.</li>
|
|
<li><strong class="text-white">Character Filtering:</strong> Use whitelists to filter out unwanted
|
|
characters and improve accuracy for specific document types (invoices, forms, etc.).</li>
|
|
<li><strong class="text-white">Multi-language Support:</strong> Select multiple languages for
|
|
documents containing mixed language content.</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div id="drop-zone"
|
|
class="relative flex flex-col items-center justify-center w-full h-48 md:h-64 border-2 border-dashed border-gray-600 rounded-xl cursor-pointer bg-gray-900 hover:bg-gray-700 transition-colors duration-300">
|
|
<div class="flex flex-col items-center justify-center pt-5 pb-6">
|
|
<i data-lucide="upload-cloud" class="w-10 h-10 mb-3 text-gray-400"></i>
|
|
<p class="mb-2 text-sm text-gray-400"><span class="font-semibold">Click to select PDF</span> <span
|
|
data-i18n="upload.orDragAndDrop">or drag and drop</span></p>
|
|
<p class="text-xs text-gray-500" data-i18n="upload.filesNeverLeave">Your files never leave your
|
|
device.</p>
|
|
</div>
|
|
<input id="file-input" type="file" class="absolute top-0 left-0 w-full h-full opacity-0 cursor-pointer"
|
|
accept="application/pdf">
|
|
</div>
|
|
|
|
<div id="file-display-area" class="mt-4 space-y-2"></div>
|
|
|
|
<!-- OCR Options -->
|
|
<div id="tool-options" class="hidden mt-6 space-y-4">
|
|
<div>
|
|
<label class="block mb-2 text-sm font-medium text-gray-300">Languages in Document</label>
|
|
<div class="relative">
|
|
<input type="text" id="lang-search"
|
|
class="w-full bg-gray-900 border border-gray-600 text-white rounded-lg p-2.5 mb-2"
|
|
placeholder="Search for languages...">
|
|
<div id="lang-list"
|
|
class="max-h-48 overflow-y-auto border border-gray-600 rounded-lg p-2 bg-gray-900">
|
|
<!-- Language checkboxes will be populated by JS -->
|
|
</div>
|
|
</div>
|
|
<p class="text-xs text-gray-500 mt-1">Selected: <span id="selected-langs-display"
|
|
class="font-semibold">None</span></p>
|
|
</div>
|
|
|
|
<!-- Advanced settings -->
|
|
<details class="bg-gray-900 border border-gray-700 rounded-lg p-3">
|
|
<summary class="text-sm font-medium text-gray-300 cursor-pointer flex items-center justify-between">
|
|
<span>Advanced Settings (Recommended to improve accuracy)</span>
|
|
<i data-lucide="chevron-down" class="w-4 h-4 transition-transform details-icon"></i>
|
|
</summary>
|
|
<div class="mt-4 space-y-4">
|
|
<!-- Resolution -->
|
|
<div>
|
|
<label for="ocr-resolution"
|
|
class="block mb-1 text-xs font-medium text-gray-400">Resolution</label>
|
|
<select id="ocr-resolution"
|
|
class="w-full bg-gray-700 border border-gray-600 text-white rounded-lg p-2 text-sm">
|
|
<option value="2.0">Standard (192 DPI)</option>
|
|
<option value="3.0" selected>High (288 DPI)</option>
|
|
<option value="4.0">Ultra (384 DPI)</option>
|
|
</select>
|
|
</div>
|
|
<!-- Binarization -->
|
|
<label class="flex items-center gap-2 text-sm text-gray-300 cursor-pointer">
|
|
<input type="checkbox" id="ocr-binarize"
|
|
class="w-4 h-4 rounded text-indigo-600 bg-gray-700 border-gray-600">
|
|
Binarize Image (Enhance Contrast for Clean Scans)
|
|
</label>
|
|
<!-- Whitelist Presets -->
|
|
<div>
|
|
<label for="whitelist-preset" class="block mb-1 text-xs font-medium text-gray-400">Character
|
|
Whitelist Preset</label>
|
|
<select id="whitelist-preset"
|
|
class="w-full bg-gray-700 border border-gray-600 text-white rounded-lg p-2 text-sm mb-2">
|
|
<option value="">None (All characters)</option>
|
|
<option value="alphanumeric">Alphanumeric + Basic Punctuation</option>
|
|
<option value="numbers-currency">Numbers + Currency Symbols</option>
|
|
<option value="letters-only">Letters Only (A-Z, a-z)</option>
|
|
<option value="numbers-only">Numbers Only (0-9)</option>
|
|
<option value="invoice">Invoice/Receipt (Numbers, $, ., -, /)</option>
|
|
<option value="forms">Forms (Alphanumeric + Common Symbols)</option>
|
|
<option value="custom">Custom...</option>
|
|
</select>
|
|
<p class="text-xs text-gray-500 mt-1">Only these characters will be recognized. Leave empty
|
|
for all characters.</p>
|
|
</div>
|
|
<!-- Whitelist Input -->
|
|
<div>
|
|
<label for="ocr-whitelist" class="block mb-1 text-xs font-medium text-gray-400">Character
|
|
Whitelist (Optional)</label>
|
|
<input type="text" id="ocr-whitelist"
|
|
class="w-full bg-gray-700 border border-gray-600 text-white rounded-lg p-2 text-sm"
|
|
placeholder="e.g., abcdefghijklmnopqrstuvwxyz0123456789$.,">
|
|
<p class="text-xs text-gray-500 mt-1">Only these characters will be recognized. Leave empty
|
|
for all characters.</p>
|
|
</div>
|
|
</div>
|
|
</details>
|
|
|
|
<button id="process-btn" class="btn-gradient w-full disabled:opacity-50" disabled>Start OCR</button>
|
|
</div>
|
|
|
|
<!-- Progress Section -->
|
|
<div id="ocr-progress" class="hidden mt-6 p-4 bg-gray-900 border border-gray-700 rounded-lg">
|
|
<p id="progress-status" class="text-white mb-2">Initializing...</p>
|
|
<div class="w-full bg-gray-700 rounded-full h-4">
|
|
<div id="progress-bar" class="bg-indigo-600 h-4 rounded-full transition-all duration-300"
|
|
style="width: 0%"></div>
|
|
</div>
|
|
<pre id="progress-log"
|
|
class="mt-4 text-xs text-gray-400 max-h-32 overflow-y-auto bg-black p-2 rounded-md"></pre>
|
|
</div>
|
|
|
|
<!-- Results Section -->
|
|
<div id="ocr-results" class="hidden mt-6">
|
|
<h3 class="text-xl font-bold text-white mb-2">OCR Complete</h3>
|
|
<p class="mb-4 text-gray-400">Your searchable PDF is ready. You can also copy or download the extracted
|
|
text below.</p>
|
|
<div class="relative">
|
|
<textarea id="ocr-text-output" rows="10"
|
|
class="w-full bg-gray-900 border border-gray-600 text-gray-300 rounded-lg p-2.5 font-sans"
|
|
readonly></textarea>
|
|
<button id="copy-text-btn"
|
|
class="absolute top-2 right-2 bg-gray-700 hover:bg-gray-600 p-2 rounded-md"
|
|
title="Copy to Clipboard">
|
|
<i data-lucide="clipboard-copy" class="w-4 h-4 text-gray-300"></i>
|
|
</button>
|
|
</div>
|
|
<div class="grid grid-cols-1 sm:grid-cols-2 gap-4 mt-4">
|
|
<button id="download-txt-btn"
|
|
class="w-full bg-gray-700 text-white font-semibold py-3 rounded-lg hover:bg-gray-600">Download
|
|
as .txt</button>
|
|
<button id="download-searchable-pdf"
|
|
class="w-full bg-green-600 text-white font-semibold py-3 rounded-lg hover:bg-green-700">Download
|
|
Searchable PDF</button>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Loader Modal -->
|
|
<div id="loader-modal" class="hidden fixed inset-0 bg-black bg-opacity-75 flex items-center justify-center z-50">
|
|
<div class="bg-gray-800 p-8 rounded-lg flex flex-col items-center gap-4 border border-gray-700 shadow-xl">
|
|
<div class="solid-spinner"></div>
|
|
<p id="loader-text" class="text-white text-lg font-medium" data-i18n="loader.processing"
|
|
data-i18n="loader.processing">Processing...</p>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Alert Modal -->
|
|
<div id="alert-modal" class="fixed inset-0 bg-gray-900 bg-opacity-90 flex items-center justify-center z-50 hidden">
|
|
<div class="bg-gray-800 rounded-lg shadow-xl p-6 max-w-sm w-full border border-gray-700">
|
|
<h3 id="alert-title" class="text-xl font-bold text-white mb-2" data-i18n="alert.title"
|
|
data-i18n="alert.title">Alert</h3>
|
|
<p id="alert-message" class="text-gray-300 mb-6"></p>
|
|
<button id="alert-ok"
|
|
class="w-full bg-indigo-600 hover:bg-indigo-700 text-white font-semibold py-2 px-4 rounded-lg transition-colors duration-200">
|
|
OK
|
|
</button>
|
|
</div>
|
|
</div>
|
|
|
|
<footer class="mt-16 border-t-2 border-gray-700 py-8">
|
|
<div class="container mx-auto px-4">
|
|
<div class="grid grid-cols-1 md:grid-cols-4 gap-8 text-center md:text-left">
|
|
<div class="mb-8 md:mb-0">
|
|
<div class="flex items-center justify-center md:justify-start mb-4">
|
|
<img src="/images/favicon.svg" alt="Bento PDF Logo" class="h-10 w-10 mr-3" />
|
|
<span class="text-xl font-bold text-white">BentoPDF</span>
|
|
</div>
|
|
<p class="text-gray-400 text-sm">© 2025 BentoPDF. All rights reserved.</p>
|
|
<p class="text-gray-500 text-xs mt-2">Version <span id="app-version"></span></p>
|
|
</div>
|
|
<div>
|
|
<h3 class="font-bold text-white mb-4">Company</h3>
|
|
<ul class="space-y-2 text-gray-400">
|
|
<li><a href="/about.html" class="hover:text-indigo-400">About Us</a></li>
|
|
<li><a href="/faq.html" class="hover:text-indigo-400">FAQ</a></li>
|
|
<li><a href="/contact.html" class="hover:text-indigo-400">Contact Us</a></li>
|
|
</ul>
|
|
</div>
|
|
<div>
|
|
<h3 class="font-bold text-white mb-4">Legal</h3>
|
|
<ul class="space-y-2 text-gray-400">
|
|
<li><a href="/licensing.html" class="hover:text-indigo-400">Licensing</a></li>
|
|
<li><a href="/terms.html" class="hover:text-indigo-400">Terms and Conditions</a></li>
|
|
<li><a href="/privacy.html" class="hover:text-indigo-400">Privacy Policy</a></li>
|
|
</ul>
|
|
</div>
|
|
<div>
|
|
<h3 class="font-bold text-white mb-4">Follow Us</h3>
|
|
<div class="flex justify-center md:justify-start space-x-4">
|
|
<a href="https://github.com/nicholaschen09/BentoPDF" target="_blank" rel="noopener noreferrer"
|
|
class="text-gray-400 hover:text-indigo-400" title="GitHub">
|
|
<svg class="w-6 h-6" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true">
|
|
<path fill-rule="evenodd"
|
|
d="M12 2C6.477 2 2 6.484 2 12.017c0 4.425 2.865 8.18 6.839 9.504.5.092.682-.217.682-.483 0-.237-.008-.868-.013-1.703-2.782.605-3.369-1.343-3.369-1.343-.454-1.158-1.11-1.466-1.11-1.466-.908-.62.069-.608.069-.608 1.003.07 1.531 1.032 1.531 1.032.892 1.53 2.341 1.088 2.91.832.092-.647.35-1.088.636-1.338-2.22-.253-4.555-1.113-4.555-4.951 0-1.093.39-1.988 1.029-2.688-.103-.253-.446-1.272.098-2.65 0 0 .84-.27 2.75 1.026A9.564 9.564 0 0112 6.844c.85.004 1.705.115 2.504.337 1.909-1.296 2.747-1.027 2.747-1.027.546 1.379.202 2.398.1 2.651.64.7 1.028 1.595 1.028 2.688 0 3.848-2.339 4.695-4.566 4.943.359.309.678.92.678 1.855 0 1.338-.012 2.419-.012 2.747 0 .268.18.58.688.482A10.019 10.019 0 0022 12.017C22 6.484 17.522 2 12 2z"
|
|
clip-rule="evenodd" />
|
|
</svg>
|
|
</a>
|
|
<a href="https://discord.gg/Bgq3Ay3f2w" target="_blank" rel="noopener noreferrer"
|
|
class="text-gray-400 hover:text-indigo-400" title="Discord">
|
|
<svg class="w-6 h-6" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true">
|
|
<path
|
|
d="M20.317 4.37a19.791 19.791 0 0 0-4.885-1.515a.074.074 0 0 0-.079.037c-.21.375-.444.864-.608 1.25a18.27 18.27 0 0 0-5.487 0a12.64 12.64 0 0 0-.617-1.25a.077.077 0 0 0-.079-.037A19.736 19.736 0 0 0 3.677 4.37a.07.07 0 0 0-.032.027C.533 9.046-.32 13.58.099 18.057a.082.082 0 0 0 .031.057a19.9 19.9 0 0 0 5.993 3.03a.078.078 0 0 0 .084-.028a14.09 14.09 0 0 0 1.226-1.994a.076.076 0 0 0-.041-.106a13.107 13.107 0 0 1-1.872-.892a.077.077 0 0 1-.008-.128a10.2 10.2 0 0 0 .372-.292a.074.074 0 0 1 .077-.01c3.928 1.793 8.18 1.793 12.062 0a.074.074 0 0 1 .078.01c.12.098.246.198.373.292a.077.077 0 0 1-.006.127a12.299 12.299 0 0 1-1.873.892a.077.077 0 0 0-.041.107c.36.698.772 1.362 1.225 1.993a.076.076 0 0 0 .084.028a19.839 19.839 0 0 0 6.002-3.03a.077.077 0 0 0 .032-.054c.5-5.177-.838-9.674-3.549-13.66a.061.061 0 0 0-.031-.03zM8.02 15.33c-1.183 0-2.157-1.085-2.157-2.419c0-1.333.956-2.419 2.157-2.419c1.21 0 2.176 1.096 2.157 2.42c0 1.333-.956 2.418-2.157 2.418zm7.975 0c-1.183 0-2.157-1.085-2.157-2.419c0-1.333.955-2.419 2.157-2.419c1.21 0 2.176 1.096 2.157 2.42c0 1.333-.946 2.418-2.157 2.418z" />
|
|
</svg>
|
|
</a>
|
|
<a href="https://www.instagram.com/thebentopdf/" class="text-gray-400 hover:text-indigo-400"
|
|
title="Instagram"><i data-lucide="instagram"></i></a>
|
|
<a href="https://www.linkedin.com/company/bentopdf/" class="text-gray-400 hover:text-indigo-400"
|
|
title="LinkedIn"><i data-lucide="linkedin"></i></a>
|
|
<a href="https://x.com/BentoPDF" class="text-gray-400 hover:text-indigo-400"
|
|
title="X (Twitter)">
|
|
<svg class="w-6 h-6" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true">
|
|
<path
|
|
d="M18.244 2.25h3.308l-7.227 8.26 8.502 11.24H16.17l-5.214-6.817L4.99 21.75H1.68l7.73-8.835L1.254 2.25H8.08l4.713 6.231zm-1.161 17.52h1.833L7.084 4.126H5.117z" />
|
|
</svg>
|
|
</a>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</footer>
|
|
<script type="module" src="/src/js/utils/lucide-init.ts"></script>
|
|
<script type="module" src="/src/js/utils/full-width.ts"></script>
|
|
<script type="module" src="/src/js/utils/simple-mode-footer.ts"></script>
|
|
<script type="module" src="/src/version.ts"></script>
|
|
<script type="module" src="/src/js/logic/ocr-pdf-page.ts"></script>
|
|
<script type="module" src="/src/js/mobileMenu.ts"></script>
|
|
|
|
<script type="module" src="/src/js/main.ts"></script>
|
|
</body>
|
|
|
|
</html> |