extract_pdf_text.py

#!/usr/bin/env python3

import os
import PyPDF2
from pathlib import Path

def extract_pdf_text(pdf_path, txt_path):
    """Extract text from PDF and save to TXT file"""
    try:
        with open(pdf_path, 'rb') as pdf_file:
            pdf_reader = PyPDF2.PdfReader(pdf_file)
            text_content = []
            
            for page_num in range(len(pdf_reader.pages)):
                page = pdf_reader.pages[page_num]
                text_content.append(page.extract_text())
            
            full_text = '\n'.join(text_content)
            
            with open(txt_path, 'w', encoding='utf-8') as txt_file:
                txt_file.write(full_text)
            
            print(f"✓ Extracted {len(pdf_reader.pages)} pages from {pdf_path.name} -> {txt_path.name}")
            return True
            
    except Exception as e:
        print(f"✗ Error extracting {pdf_path.name}: {str(e)}")
        return False

def main():
    books_dir = Path("books")
    
    if not books_dir.exists():
        print("Books directory not found!")
        return
    
    pdf_files = list(books_dir.glob("*.pdf"))
    
    if not pdf_files:
        print("No PDF files found in books directory!")
        return
    
    print(f"Found {len(pdf_files)} PDF files to process...")
    
    success_count = 0
    for pdf_file in pdf_files:
        txt_file = pdf_file.with_suffix('.txt')
        
        if extract_pdf_text(pdf_file, txt_file):
            success_count += 1
    
    print(f"\nCompleted: {success_count}/{len(pdf_files)} files successfully extracted")

if __name__ == "__main__":
    main()