import os import docx2txt import easyocr import numpy as np import pytesseract from PIL import ImageEnhance, ImageFilter from docx import Document # Import the Document class from docx module from pdf2image import convert_from_path # Path to Tesseract executable pytesseract.pytesseract.tesseract_cmd = r"D:\Tesseract-OCR\tesseract.exe" def preprocess_image(image): """Preprocess an image (enhance contrast and sharpness, denoise)""" image = image.convert("RGB") enhancer = ImageEnhance.Contrast(image) image = enhancer.enhance(2.0) # Increase contrast enhancer = ImageEnhance.Sharpness(image) image = enhancer.enhance(2.0) # Increase sharpness image = image.filter(ImageFilter.GaussianBlur(radius=2)) # Apply Gaussian blur for denoising return image def process_image_tesseract(image): """Process an image using Tesseract OCR""" try: preprocessed_image = preprocess_image(image) text = pytesseract.image_to_string(preprocessed_image) return text except Exception as e: print(f"An error occurred during Tesseract OCR processing: {e}") return "" def process_image_easyocr(image): """Process an image using EasyOCR""" try: preprocessed_image = preprocess_image(image) image_np = np.array(preprocessed_image) reader = easyocr.Reader(lang_list=['en', 'hi', 'mr']) results = reader.readtext(image_np) text = " ".join([result[1] for result in results]) # Concatenate recognized text return text except Exception as e: print(f"An error occurred during EasyOCR processing: {e}") return "" def extract_text_from_docx(docx_path): """Extract text from DOCX file""" try: extracted_text = "" # Extract text from paragraphs text = docx2txt.process(docx_path) extracted_text += text # Extract text from tables doc = Document(docx_path) for table in doc.tables: table_text = extract_table_text(table) extracted_text += table_text + "\n" return extracted_text except Exception as e: print(f"An error occurred during DOCX processing: {e}") return "" def extract_table_text(table): """Extract text from a table in DOCX""" table_text = "" for row in table.rows: for cell in row.cells: cell_text = "" for paragraph in cell.paragraphs: cell_text += paragraph.text + " " table_text += cell_text.strip() + "\t" table_text += "\n" return table_text def process_pdf(pdf_path, poppler_path, output_folder): """Process a PDF file""" try: pdf_filename = os.path.basename(pdf_path) images = convert_from_path(pdf_path, poppler_path=poppler_path) extracted_text = "" for i, image in enumerate(images): text = process_image_tesseract(image) + process_image_easyocr(image) extracted_text += text + "\n" return extracted_text except Exception as e: print(f"An error occurred during PDF processing: {e}") return ""