pytesseract

import pytesseract from PIL import Image import os # Ensure Tesseract-OCR is installed and in your system's PATH. # If not, you may need to specify the path to the tesseract executable: # pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # Example for Windows # pytesseract.pytesseract.tesseract_cmd = r'/usr/local/bin/tesseract' # Example for macOS # Create a dummy image file for demonstration try: from PIL import ImageDraw, ImageFont img = Image.new('RGB', (200, 50), color = (255, 255, 255)) d = ImageDraw.Draw(img) fnt = ImageFont.truetype(os.environ.get('FONT_PATH', 'arial.ttf'), 20) # Use a common font or provide path d.text((10,10), "Hello World", font=fnt, fill=(0,0,0)) img.save('test_image.png') image_path = 'test_image.png' except ImportError: print("Pillow is missing drawing capabilities, cannot create test image. Please ensure you have a full Pillow install.") # Fallback for systems without font support (e.g., some CI environments) # This part would typically be replaced by loading an actual image file. image_path = os.environ.get('TEST_IMAGE_PATH', 'non_existent_image.png') # For testing without generating image if os.path.exists(image_path): try: text = pytesseract.image_to_string(Image.open(image_path)) print(f"Extracted text: {text.strip()}") except Exception as e: print(f"Error during OCR: {e}") print("Please ensure Tesseract-OCR is installed and configured correctly.") else: print(f"Test image '{image_path}' not found. Please provide one or install font for auto-generation.")