import os
import PyPDF2

def convert_pdfs_to_txt(directory):
    # Iterate over all files in the directory
    for filename in os.listdir(directory):
        if filename.endswith(".pdf"):
            pdf_path = os.path.join(directory, filename)
            txt_path = os.path.join(directory, os.path.splitext(filename)[0] + ".txt")

            # Open the PDF file
            with open(pdf_path, "rb") as pdf_file:
                reader = PyPDF2.PdfReader(pdf_file)

                # Create a new TXT file
                with open(txt_path, "w", encoding="utf-8") as txt_file:
                    for page in reader.pages:
                        # Extract text from each page and write it to the TXT file
                        txt_file.write(page.extract_text())

            print(f"Converted {pdf_path} to {txt_path}")

# Provide the directory path where the PDF files are located
directory_path = "/home/ok/Desktop/OneDrive/PDF/"

# Call the function to convert the PDF files to TXT
convert_pdfs_to_txt(directory_path)