extract_pdf_improved.py

#!/usr/bin/env python3

import os
import pdfplumber
from pathlib import Path

def extract_pdf_text_plumber(pdf_path, txt_path):
    """Extract text from PDF using pdfplumber and save to TXT file"""
    try:
        with pdfplumber.open(pdf_path) as pdf:
            text_content = []
            
            for page_num, page in enumerate(pdf.pages):
                text = page.extract_text()
                if text:
                    text_content.append(f"--- Page {page_num + 1} ---\n{text}\n")
                else:
                    text_content.append(f"--- Page {page_num + 1} ---\n[No extractable text]\n")
            
            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.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 i, pdf_file in enumerate(pdf_files, 1):
        print(f"Processing {i}/{len(pdf_files)}: {pdf_file.name}")
        txt_file = pdf_file.with_suffix('.txt')
        
        if extract_pdf_text_plumber(pdf_file, txt_file):
            success_count += 1
    
    print(f"\nCompleted: {success_count}/{len(pdf_files)} files successfully extracted")

if __name__ == "__main__":
    main()