import os
from PyPDF2 import PdfReader


def find_pdf(start_dir: str, filename: str) -> str:
    """Return the absolute path to the target PDF, searching downward if needed."""
    candidate = os.path.join(start_dir, filename)
    if os.path.exists(candidate):
        return candidate

    for root, _, files in os.walk(start_dir):
        if filename in files:
            return os.path.join(root, filename)

    raise FileNotFoundError(f"Unable to locate {filename} under {start_dir}")


def main() -> None:
    script_dir = os.path.dirname(os.path.abspath(__file__))
    pdf_name = "2025 APMCM Problem B.pdf"
    pdf_path = find_pdf(script_dir, pdf_name)

    reader = PdfReader(pdf_path)
    pages = []
    for idx, page in enumerate(reader.pages, start=1):
        text = page.extract_text() or ""
        pages.append(f"\n=== Page {idx} ===\n{text.strip()}")

    output_text = "".join(pages)
    print(output_text)

    output_path = os.path.join(script_dir, "problem_text_pypdf.txt")
    with open(output_path, "w", encoding="utf-8") as f:
        f.write(output_text)

    print(f"\nText saved to: {output_path}")


if __name__ == "__main__":
    main()