tools/python/pdf_to_text.py

#!/usr/bin/env python3
"""PDF to Text extractor using PyPDF2."""
import argparse, json, sys
from pathlib import Path

def convert(input_path, output_path):
    from PyPDF2 import PdfReader
    
    reader = PdfReader(input_path)
    text_parts = []
    for i, page in enumerate(reader.pages):
        text = page.extract_text()
        if text:
            text_parts.append(f"--- Page {i+1} ---\n{text}")
    
    full_text = '\n\n'.join(text_parts)
    
    if not output_path:
        output_path = str(Path(input_path).with_suffix('.txt'))
    
    with open(output_path, 'w', encoding='utf-8') as f:
        f.write(full_text)
    
    return output_path

def main():
    parser = argparse.ArgumentParser(description='Extract text from PDF')
    parser.add_argument('--input', required=True)
    parser.add_argument('--output', required=True)
    args = parser.parse_args()
    try:
        result = convert(args.input, args.output)
        print(json.dumps({"success": True, "output": result, "message": "Text extracted successfully"}))
    except Exception as e:
        print(json.dumps({"success": False, "output": "", "message": str(e)}))
        sys.exit(1)

if __name__ == '__main__':
    main()