img_to_text.py

# /// script
# requires-python = ">=3.11"
# dependencies = [
#   "pytesseract",
#   "pillow",
#   "rich"
# ]
# ///

import pytesseract
from PIL import Image
import sys
from pathlib import Path
from rich.progress import track


def img_to_text(file: Path) -> str:
    image = Image.open(file)
    text = pytesseract.image_to_string(image)
    return text


def main(folder: Path, results: Path):
    for file in track(folder.glob("*.png"), description="Processing..."):
        text = img_to_text(file)
        with open(results / f"{file.stem}.txt", "w") as f:
            f.write(text)


if __name__ == "__main__":
    folder = Path(sys.argv[1])
    try:
        results = Path(sys.argv[2])
    except IndexError:
        results = Path("results")
    results.mkdir(exist_ok=True)

    main(folder, results)