Files
sisvietnamvn_01/Media/extract.py
T

16 lines
375 B
Python

import sys
from pypdf import PdfReader
pdf_path = sys.argv[1]
output_path = sys.argv[2]
reader = PdfReader(pdf_path)
text = ""
for i, page in enumerate(reader.pages):
text += f"\n--- Page {i + 1} ---\n"
text += page.extract_text()
with open(output_path, "w", encoding="utf-8") as f:
f.write(text)
print(f"Extracted {len(reader.pages)} pages to {output_path}")