python-doctr

import os from doctr.io import DocumentFile from doctr.models import ocr_predictor # For demonstration, create a dummy image file if it doesn't exist # In a real scenario, you'd have an actual image or PDF path dummy_image_path = 'sample.png' if not os.path.exists(dummy_image_path): try: from PIL import Image # Create a simple image with text img = Image.new('RGB', (200, 100), color = (255, 255, 255)) from PIL import ImageDraw, ImageFont d = ImageDraw.Draw(img) try: # Try a common font, or fallback font = ImageFont.truetype("arial.ttf", 20) except IOError: font = ImageFont.load_default() d.text((10,10), "Hello docTR!", fill=(0,0,0), font=font) img.save(dummy_image_path) print(f"Created dummy image: {dummy_image_path}") except ImportError: print("Pillow not installed, cannot create dummy image. Please provide a real image file.") print("Skipping quickstart example as no image is available.") dummy_image_path = None if dummy_image_path and os.path.exists(dummy_image_path): # Load your document (image or PDF) # For a PDF: doc = DocumentFile.from_pdf("path/to/your/document.pdf") # For multiple images: doc = DocumentFile.from_images(["path/to/img1.jpg", "path/to/img2.png"]) doc = DocumentFile.from_images(dummy_image_path) # Load a pre-trained OCR model # Since v1.0.0, PyTorch is the default and only backend. model = ocr_predictor(pretrained=True) # Analyze the document result = model(doc) # Print the extracted text content # The result object contains detailed information about words, lines, blocks, and pages. print("\n--- OCR Result ---") for page in result.pages: for block in page.blocks: for line in block.lines: print(" ".join([word.value for word in line.words])) # You can also export the full structured output as JSON # print(result.export()) else: print("Quickstart skipped due to missing image.")