import argparse
from pypdf import PdfReader

def convert_pdf_to_txt(pdf_path, txt_path):
    reader = PdfReader(pdf_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text() + "\n\n"  # Add extra newline between pages
    
    with open(txt_path, 'w', encoding='utf-8') as f:
        f.write(text)
    print(f"Converted '{pdf_path}' to '{txt_path}'")

def main():
    parser = argparse.ArgumentParser(description="Convert PDF to TXT")
    parser.add_argument("pdf", help="Path to input PDF file")
    parser.add_argument("-o", "--output", help="Path to output TXT file (default: same as input with .txt extension)")
    args = parser.parse_args()
    
    pdf_path = args.pdf
    txt_path = args.output or pdf_path.replace('.pdf', '.txt')
    
    convert_pdf_to_txt(pdf_path, txt_path)

if __name__ == "__main__":
    main()