26 lines
690 B
Python
26 lines
690 B
Python
|
import sys
|
||
|
|
import pytesseract
|
||
|
|
from PIL import Image
|
||
|
|
import json
|
||
|
|
|
||
|
|
def ocr_image_to_json(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)
|
||
|
|
|
||
|
|
# Convert the OCR result to JSON
|
||
|
|
ocr_json = json.dumps(ocr_result, indent=4)
|
||
|
|
print(ocr_json)
|
||
|
|
except Exception as e:
|
||
|
|
print(f"Error: {e}")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
if len(sys.argv) != 2:
|
||
|
|
print("Usage: python ocr_to_json.py <image_path>")
|
||
|
|
else:
|
||
|
|
image_path = sys.argv[1]
|
||
|
|
ocr_image_to_json(image_path)
|