OpenCV Bungie ID Parsing

test.py

import cv2
import pytesseract
import re

# If Tesseract is not in your PATH, uncomment the following line and provide the installation path:
# pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

#can use image at: https://github.com/mikechambers/lookup/blob/main/images/screenshot.png

def main():
    # Hard-coded path to your image
    IMAGE_PATH = r"screenshot.png"
    
    # 1. Load the image using OpenCV
    image = cv2.imread(IMAGE_PATH)
    if image is None:
        print(f"Error: Could not open {IMAGE_PATH}. Make sure the path is correct.")
        return

    # 2. Convert to grayscale (OCR often performs better on grayscale)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # 3. Perform OCR using pytesseract
    extracted_text = pytesseract.image_to_string(gray)
    print("Extracted Text:")
    print("----------------")
    print(extracted_text)

    # 4. Use regex to find Bungie IDs of the form NAME#CODE where CODE is 4 digits
    pattern = r'[A-Za-z0-9 ]+#[0-9]{4}'
    bungie_ids = re.findall(pattern, extracted_text)

    # 5. Print any Bungie IDs found
    if bungie_ids:
        print("\nBungie IDs Found:")
        for bid in bungie_ids:
            print(bid)
    else:
        print("\nNo Bungie IDs found in the text.")

if __name__ == "__main__":
    main()