Files

12 lines
365 B
Python

from pathlib import Path
from pypdf import PdfReader
for pdf in Path("dokumen").glob("*.pdf"):
r = PdfReader(pdf)
teks = "\n".join((p.extract_text() or "") for p in r.pages)
print("=" * 50)
print("File :", pdf.name)
print("Halaman:", len(r.pages))
print("Panjang teks:", len(teks))
print("500 karakter pertama:")
print(teks[:500])