pdf-to-text.py

import argparse

import pdftotext


def main(pdf_file, password=None):
    # Load your PDF
    with open(pdf_file, "rb") as f:
        if password:
            pdf = pdftotext.PDF(f, password)
        else:
            pdf = pdftotext.PDF(f)

    # How many pages?
    print(f"Number of pages: {len(pdf)}")

    # Iterate over all the pages
    for i, page in enumerate(pdf):
        print(f"\n--- Page {i + 1} ---")
        print(page)

    # Read all the text into one string
    print("\n\n--- All Text ---\n")
    print("\n\n".join(pdf))


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Extract text from a PDF file.")
    parser.add_argument("pdf_file", help="Path to the PDF file")
    parser.add_argument(
        "--password", help="Password for password-protected PDF files", default=None
    )

    args = parser.parse_args()
    main(args.pdf_file, args.password)