Files
VLM-OCR/model_services/deepseek_ocr/main.py
2025-10-27 15:36:17 +09:00

25 lines
981 B
Python

import os
import argparse
import subprocess
def main():
parser = argparse.ArgumentParser(description="Run OCR based on file type.")
parser.add_argument("input_path", type=str, help="Path to the input file (PDF or image).")
args = parser.parse_args()
input_path = args.input_path
file_extension = os.path.splitext(input_path)[1].lower()
if file_extension == '.pdf':
print(f"Detected PDF file. Running PDF OCR script for: {input_path}")
subprocess.run(["python", "run_dpsk_ocr_pdf.py", "--input", input_path])
elif file_extension in ['.jpg', '.jpeg', '.png', '.bmp', '.gif']:
print(f"Detected image file. Running image OCR script for: {input_path}")
subprocess.run(["python", "run_dpsk_ocr_image.py", "--input", input_path])
else:
print(f"Unsupported file type: {file_extension}")
print("Please provide a PDF or an image file (.jpg, .jpeg, .png, .bmp, .gif).")
if __name__ == "__main__":
main()