import datetime import os import tkinter as tk from tkinter import filedialog from PIL import Image from src.ocr_utils import process_image_tesseract, process_image_easyocr, \ extract_text_from_docx, process_pdf if __name__ == "__main__": root = tk.Tk() root.withdraw() file_path = filedialog.askopenfilename(title="Select Input File") if not file_path: print("No file selected. Exiting...") else: output_folder = "output_files" os.makedirs(output_folder, exist_ok=True) extracted_text = "" if file_path.lower().endswith('.docx'): extracted_text = extract_text_from_docx(file_path) elif file_path.lower().endswith(('.png', '.jpg', '.jpeg', '.tiff')): image = Image.open(file_path) extracted_text = process_image_tesseract(image) + process_image_easyocr(image) if extracted_text: print("Extracted Text:\n", extracted_text) elif file_path.lower().endswith('.pdf'): try: poppler_path = r"C:\Program Files (x86)\poppler-23.08.0\Library\bin" extracted_text = process_pdf(file_path, poppler_path, output_folder) except Exception as e: print(f"An error occurred during PDF processing: {e}") else: print(f"Unsupported file format: {file_path}") if extracted_text: try: current_datetime = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S") txt_filename = f"extracted_text_{current_datetime}.txt" with open(os.path.join(output_folder, txt_filename), "w", encoding="utf-8") as txt_file: txt_file.write(extracted_text) print("Extraction completed. Text saved as:", txt_filename) except Exception as e: print("Error while saving extracted content:", str(e))