# -*- coding: utf-8 -*-
"""Extract plain text from a PDF (pypdf). Usage: python scripts/extract-pdf-text.py <pdf>"""
import sys
from pypdf import PdfReader

def main():
    path = sys.argv[1]
    reader = PdfReader(path)
    parts = []
    for page in reader.pages:
        t = page.extract_text() or ""
        if t.strip():
            parts.append(t)
    sys.stdout.reconfigure(encoding="utf-8")
    print("\n".join(parts))

if __name__ == "__main__":
    main()