recipt-ocr-api/printall.py

26 lines
712 B
Python

import sys
import pytesseract
from PIL import Image
def ocr_image_to_text(image_path):
try:
# Open the image file
image = Image.open(image_path)
# Perform OCR on the image
ocr_result = pytesseract.image_to_data(image, output_type=pytesseract.Output.DICT)
# Extract and print the text portion
text = [word for word in ocr_result['text'] if word.strip() != ""]
print(" ".join(text))
except Exception as e:
print(f"Error: {e}")
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python ocr_to_text.py <image_path>")
else:
image_path = sys.argv[1]
ocr_image_to_text(image_path)