PDF OCR API - Multi-Model Text Extraction

Extract and convert text from PDF documents using advanced optical character recognition technology with support for multiple AI models.

🌟 Features

Multi-Model OCR Support

Choose from 8 different OCR engines based on your needs:

• Google Vision API - High accuracy commercial OCR with excellent language support
• DeepSeek OCR - Advanced AI-powered text extraction
• Amazon Textract - AWS-powered document analysis optimized for PDFs
• Azure AI Vision - Microsoft's computer vision OCR service
• OpenAI GPT-4 Vision - State-of-the-art multimodal AI for complex documents
• Hugging Face - Open-source transformer models for text extraction
• Google Gemini - Latest Google multimodal AI technology
• Native (Tesseract.js) - Free, no API key required, runs entirely in-container

Document Processing Features

• ✅ Batch Processing - Process multiple PDFs simultaneously
• ✅ Multi-Language Support - English, Spanish, French, German, Italian, Portuguese, Russian, Chinese, Japanese, Korean, Arabic, Danish
• ✅ Structure Preservation - Maintain document layout and formatting
• ✅ Page Range Selection - Process specific pages or page ranges
• ✅ Multiple Output Formats - JSON, Plain Text, or Markdown
• ✅ High Resolution - 300 DPI conversion for optimal OCR accuracy
• ✅ Metadata Extraction - Extract PDF metadata (title, author, dates)
• ✅ Pay-Per-Page Pricing - Fair billing based on actual pages processed (see ./BILLING.md)

📋 Input Parameters

Required

• ocrModel - OCR model to use (default: "native")
• pdfUrls - Array of PDF document URLs to process

Optional

• language - Document language (default: "eng")
• preserveFormatting - Maintain document structure (default: true)
• extractImages - Extract images from PDF (default: false)
• outputFormat - Output format: "json", "text", or "markdown" (default: "json")
• pageRange - Pages to process: "all", "1-5", "1,3,5" (default: "all")

API Keys (model-specific)

• googleVisionApiKey - For Google Vision API
• deepseekApiKey - For DeepSeek OCR
• awsAccessKeyId, awsSecretAccessKey, awsRegion - For Amazon Textract
• azureEndpoint, azureApiKey - For Azure AI Vision
• openaiApiKey - For OpenAI GPT-4 Vision
• huggingfaceApiKey - For Hugging Face models
• geminiApiKey - For Google Gemini

🚀 Quick Start

Example Input (Native OCR - No API Key Required)

{
  "ocrModel": "native",
  "pdfUrls": [
    "https://example.com/document.pdf"
  ],
  "language": "eng",
  "outputFormat": "json",
  "pageRange": "all"
}

Example with Google Vision API

{
  "ocrModel": "google-vision",
  "googleVisionApiKey": "YOUR_API_KEY",
  "pdfUrls": [
    "https://example.com/document.pdf",
    "https://example.com/another-document.pdf"
  ],
  "language": "eng",
  "preserveFormatting": true,
  "outputFormat": "markdown"
}

Process Specific Pages

{
  "ocrModel": "native",
  "pdfUrls": ["https://example.com/large-document.pdf"],
  "pageRange": "1-5,10,15-20",
  "outputFormat": "text"
}

📤 Output Format

JSON Output (default)

{
  "pdfUrl": "https://example.com/document.pdf",
  "fileName": "document.pdf",
  "ocrModel": "native",
  "language": "eng",
  "success": true,
  "extractedAt": "2024-11-04T10:30:00.000Z",
  "pageCount": 5,
  "totalCharacters": 12450,
  "averageConfidence": 0.94,
  "pages": [
    {
      "pageNumber": 1,
      "text": "Page 1 content...",
      "confidence": 0.95,
      "width": 2480,
      "height": 3508
    }
  ],
  "fullText": "Complete document text..."
}

Text Output

{
  "output": "Complete document text as plain string...",
  "pages": [
    {
      "pageNumber": 1,
      "text": "Page 1 content..."
    }
  ]
}

Markdown Output

{
  "output": "# document.pdf\n\n**Pages:** 5\n\n## Page 1\n\nContent...",
  "pages": [
    {
      "pageNumber": 1,
      "markdown": "## Page 1\n\nContent..."
    }
  ]
}

💡 Use Cases

Business & Legal

• Contract analysis and digitization
• Legal document processing
• Invoice and receipt extraction
• Compliance document archiving

Academic & Research

• Research paper text extraction
• Academic document digitization
• Literature review automation
• Citation extraction

Content & Publishing

• Book digitization
• Magazine and newspaper archiving
• Historical document preservation
• Content migration projects

Development & Integration

• Document management systems
• Search and indexing pipelines
• Data extraction workflows
• Archive digitization projects

🔧 Supported Languages

• English (eng)
• Spanish (spa)
• French (fra)
• German (deu)
• Italian (ita)
• Portuguese (por)
• Russian (rus)
• Chinese Simplified (chi_sim)
• Japanese (jpn)
• Korean (kor)
• Arabic (ara)

📊 Model Comparison

Model	Speed	Accuracy	Cost	Best For
Native (Tesseract)	⚡⚡⚡	85%	Free	Testing, simple docs
Google Vision	⚡⚡	95%	$$	Production, multi-language
Amazon Textract	⚡⚡	96%	$$	Forms, tables, structured docs
Azure Vision	⚡⚡	94%	$$	Enterprise integration
OpenAI GPT-4	⚡	94%	$$$	Complex layouts, handwriting
Gemini	⚡⚡	93%	$$	Modern documents

🎯 Best Practices

For Optimal Results

1. Use high-quality PDF sources (not scanned at low resolution)
2. Select the appropriate language setting
3. Use premium models for complex layouts or handwriting
4. Process pages in batches for large documents
5. Enable formatting preservation for structured documents

Performance Tips

1. Use page ranges to process only needed pages
2. Batch multiple PDFs in a single run
3. Choose Native OCR for simple, clear documents
4. Use premium models only when necessary

Cost Optimization

1. Start with Native OCR for testing
2. Use page ranges to avoid processing unnecessary pages
3. Batch process to reduce overhead
4. Monitor API costs for premium models

📈 Performance

• Processing Speed: 5-30 seconds per page (varies by model)
• Concurrent Processing: Up to 10 PDFs simultaneously
• Maximum File Size: 100MB per PDF
• Supported Formats: PDF (any version)
• Resolution: 300 DPI conversion

💰 Pricing

This actor uses pay-per-event pricing:

• $0.01 per PDF processed successfully (configurable)
• Failed PDFs are not charged
• Events tracked: pdf_processed

🆘 Support

For issues, questions, or feature requests:

• Check the Apify documentation
• Review the input schema for parameter details
• Ensure API keys are valid and have sufficient quota
• Verify PDF files are accessible and not corrupted

🔄 Version History

v1.0

• Initial release
• Support for 8 OCR models
• Multi-language support (12 languages)
• Batch processing capabilities
• Multiple output formats (JSON, Text, Markdown)
• Page range selection
• Structure preservation
• Pay-per-event pricing

📚 Related Actors

• Receipt OCR API - Specialized for receipt processing
• Invoice OCR API - Optimized for invoice extraction
• Form OCR API - Structured form data extraction

🔗 Links

• Actor on Apify Store
• Documentation
• Support

---

Transform your PDF documents into searchable, structured data! 📄✨