README.md

metadata

title: Doc2Page - Document to Webpage Converter
emoji: 🏄
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.47.2
app_file: app.py
pinned: false
license: apache-2.0
short_description: Convert docs to webpages using PaddleOCR and ERNIE

📄➡️🌐 Doc2Page - Document to Webpage Converter

Convert your PDF documents or images into beautiful, responsive HTML webpages!

✨ Features

• 📖 Smart OCR: Extract text from PDFs and images using PaddleOCR
• 🤖 AI Enhancement: Transform content into well-structured HTML using ERNIE
• 🎨 Beautiful Output: Generate responsive, styled webpages with modern CSS
• 🚀 Easy Deployment: Optional one-click deployment to GitHub Pages
• 📱 Mobile Friendly: Responsive design that works on all devices

🔧 How It Works

1. Upload: Drop your PDF or image file
2. Extract: PaddleOCR extracts text and structure
3. Transform: ERNIE converts to beautiful HTML
4. Deploy: Optionally publish to GitHub Pages

📁 Supported Formats

• PDFs: .pdf
• Images: .png, .jpg, .jpeg, .bmp, .tiff

🚀 Quick Start

1. Upload a document using the file picker
2. Click "Convert to Webpage"
3. Preview your generated webpage
4. Download the HTML file
5. Optionally deploy to GitHub Pages

⚙️ Configuration

Setup using .env file:

1. Copy the example environment file:

cp .env.example .env

2. Edit the .env file with your credentials:

# Required API Configuration for PP-StructureV3
API_URL=your_pp_structurev3_api_url
API_TOKEN=your_api_token

# Optional ERNIE API Configuration for enhanced HTML generation
ERNIE_CLIENT_ID=your_client_id_here
ERNIE_CLIENT_SECRET=your_client_secret_here

Note: The .env file is automatically loaded when the application starts. Without ERNIE credentials, the app will use a high-quality fallback HTML generator.

🏗️ Technical Stack

• Frontend: Gradio for the web interface
• OCR Engine: PP-StructureV3 API (PaddlePaddle)
• AI Processing: ERNIE 4.5-X1.1-Preview (optional)
• Image Processing: Pillow

📝 Example Use Cases

• Convert research papers to web format
• Digitize scanned documents
• Create web-friendly versions of presentations
• Transform printed materials to responsive websites
• Archive documents in searchable HTML format

📄 License

This project is licensed under the Apache 2.0 License.