utils/pdf_utils.py

import PyPDF2
from pathlib import Path
from typing import List, Dict


def extract_text_from_pdf(file_path: str) -> str:
    """
    Extract text from PDF file
    
    Args:
        file_path: Path to PDF file
        
    Returns:
        Extracted text
    """
    try:
        with open(file_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            text = ''
            
            for page in pdf_reader.pages:
                text += page.extract_text() + '\n\n'
            
            return text.strip()
    except Exception as e:
        print(f"PDF extraction error: {e}")
        return ""


def get_pdf_metadata(file_path: str) -> Dict:
    """
    Get PDF metadata
    
    Args:
        file_path: Path to PDF file
        
    Returns:
        Dictionary of metadata
    """
    try:
        with open(file_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            
            metadata = {
                'num_pages': len(pdf_reader.pages),
                'author': '',
                'title': '',
                'subject': '',
                'creator': ''
            }
            
            if pdf_reader.metadata:
                metadata['author'] = pdf_reader.metadata.get('/Author', '')
                metadata['title'] = pdf_reader.metadata.get('/Title', '')
                metadata['subject'] = pdf_reader.metadata.get('/Subject', '')
                metadata['creator'] = pdf_reader.metadata.get('/Creator', '')
            
            return metadata
    except Exception as e:
        print(f"Metadata extraction error: {e}")
        return {'error': str(e)}


def split_pdf_pages(file_path: str, output_dir: str) -> List[str]:
    """
    Split PDF into individual page files
    
    Args:
        file_path: Path to PDF file
        output_dir: Output directory for page files
        
    Returns:
        List of output file paths
    """
    try:
        output_path = Path(output_dir)
        output_path.mkdir(parents=True, exist_ok=True)
        
        with open(file_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            output_files = []
            
            for i, page in enumerate(pdf_reader.pages):
                writer = PyPDF2.PdfWriter()
                writer.add_page(page)
                
                output_file = output_path / f"page_{i+1}.pdf"
                with open(output_file, 'wb') as output:
                    writer.write(output)
                
                output_files.append(str(output_file))
            
            return output_files
    except Exception as e:
        print(f"PDF split error: {e}")
        return []