import os
import pypdf

def extract_pdf_pages_to_file(pdf_path, start_page, end_page, output_txt):
    print(f"Extracting {os.path.basename(pdf_path)} from page {start_page} to {end_page}...")
    reader = pypdf.PdfReader(pdf_path)
    total_pages = len(reader.pages)
    
    with open(output_txt, "w", encoding="utf-8") as f:
        for p_idx in range(start_page - 1, min(end_page, total_pages)):
            f.write(f"\n--- PAGE {p_idx + 1} (Thesis Page {p_idx - 12}) ---\n")
            text = reader.pages[p_idx].extract_text()
            f.write(text)
            f.write("\n")
    print(f"Extraction complete. Output written to {output_txt}")

if __name__ == "__main__":
    pdf_file = "PERANCANGAN SISTEM REKOMENDASI KAMERA PADA PERSEWAAN KAMERA DENGAN BERBASIS WEBSITE MENGUNAKAN ALGORITMA TOPSIS (Revisi 3).pdf"
    if os.path.exists(pdf_file):
        extract_pdf_pages_to_file(pdf_file, 108, 120, "extracted_pages.txt")
    else:
        print(f"File {pdf_file} not found.")