How to Split PDFs into Individual Pages using PyMuPDF

pip install PyMuPDF

import pymupdf

def split_pdf_to_pages(input_path, output_folder):
    """
    Split a PDF file into individual pages.
    
    Args:
        input_path (str): Path to the input PDF file
        output_folder (str): Directory to save individual pages
    """
    # Open the PDF document
    pdf_document = pymupdf.open(input_path)
    
    # Create output folder if it doesn't exist
    import os
    os.makedirs(output_folder, exist_ok=True)
    
    # Iterate through each page
    for page_num in range(len(pdf_document)):
        # Create a new PDF document for this page
        new_pdf = pymupdf.open()
        
        # Insert the current page into the new document
        new_pdf.insert_pdf(pdf_document, from_page=page_num, to_page=page_num)
        
        # Save the single-page PDF
        output_path = os.path.join(output_folder, f"page_{page_num + 1:03d}.pdf")
        new_pdf.save(output_path)
        new_pdf.close()
    
    # Close the original document
    pdf_document.close()
    print(f"Successfully split PDF into {len(pdf_document)} pages")

# Usage example
split_pdf_to_pages("input_document.pdf", "output_pages")

import pymupdf
import os
from pathlib import Path

def split_pdf_advanced(input_path, output_folder, 
                      name_prefix="page", 
                      page_range=None, 
                      preserve_bookmarks=False):
    """
    Advanced PDF splitting with customizable options.
    
    Args:
        input_path (str): Path to the input PDF file
        output_folder (str): Directory to save individual pages
        name_prefix (str): Prefix for output filenames
        page_range (tuple): Optional (start, end) page range (1-indexed)
        preserve_bookmarks (bool): Whether to preserve bookmarks in output
    """
    pdf_document = pymupdf.open(input_path)
    
    # Create output directory
    Path(output_folder).mkdir(parents=True, exist_ok=True)
    
    # Determine page range
    total_pages = len(pdf_document)
    if page_range:
        start_page, end_page = page_range
        start_page = max(1, start_page) - 1  # Convert to 0-indexed
        end_page = min(total_pages, end_page)
    else:
        start_page, end_page = 0, total_pages
    
    pages_split = 0
    
    for page_num in range(start_page, end_page):
        # Create new PDF for this page
        new_pdf = pymupdf.open()
        
        # Insert the page
        new_pdf.insert_pdf(pdf_document, from_page=page_num, to_page=page_num)
        
        # Preserve bookmarks if requested
        if preserve_bookmarks:
            # Get bookmarks for this page
            bookmarks = pdf_document.get_toc()
            page_bookmarks = [bm for bm in bookmarks if bm[2] == page_num + 1]
            if page_bookmarks:
                new_pdf.set_toc(page_bookmarks)
        
        # Generate output filename
        output_filename = f"{name_prefix}_{page_num + 1:03d}.pdf"
        output_path = os.path.join(output_folder, output_filename)
        
        # Save the page
        new_pdf.save(output_path)
        new_pdf.close()
        pages_split += 1
    
    pdf_document.close()
    print(f"Successfully split {pages_split} pages from {input_path}")
    return pages_split

# Usage examples
split_pdf_advanced("document.pdf", "output", name_prefix="chapter")
split_pdf_advanced("document.pdf", "output", page_range=(5, 10))

import pymupdf
import os
from pathlib import Path
import glob

def batch_split_pdfs(input_folder, output_base_folder):
    """
    Split multiple PDF files in a folder.
    
    Args:
        input_folder (str): Folder containing PDF files
        output_base_folder (str): Base folder for output
    """
    pdf_files = glob.glob(os.path.join(input_folder, "*.pdf"))
    
    if not pdf_files:
        print("No PDF files found in the input folder")
        return
    
    for pdf_file in pdf_files:
        # Create output folder for this PDF
        pdf_name = Path(pdf_file).stem
        output_folder = os.path.join(output_base_folder, pdf_name)
        
        try:
            split_pdf_to_pages(pdf_file, output_folder)
            print(f"Processed: {pdf_file}")
        except Exception as e:
            print(f"Error processing {pdf_file}: {str(e)}")

# Usage
batch_split_pdfs("input_pdfs", "split_output")

import pymupdf
import os
from pathlib import Path

def split_pdf_safe(input_path, output_folder):
    """
    Split PDF with comprehensive error handling.
    """
    try:
        # Validate input file
        if not os.path.exists(input_path):
            raise FileNotFoundError(f"Input file not found: {input_path}")
        
        if not input_path.lower().endswith('.pdf'):
            raise ValueError("Input file must be a PDF")
        
        # Open and validate PDF
        pdf_document = pymupdf.open(input_path)
        
        if pdf_document.is_encrypted:
            raise ValueError("Encrypted PDFs are not supported")
        
        if len(pdf_document) == 0:
            raise ValueError("PDF contains no pages")
        
        # Create output directory
        Path(output_folder).mkdir(parents=True, exist_ok=True)
        
        # Split pages
        for page_num in range(len(pdf_document)):
            new_pdf = pymupdf.open()
            new_pdf.insert_pdf(pdf_document, from_page=page_num, to_page=page_num)
            
            output_path = os.path.join(output_folder, f"page_{page_num + 1:03d}.pdf")
            new_pdf.save(output_path)
            new_pdf.close()
        
        pdf_document.close()
        return True, f"Successfully split {len(pdf_document)} pages"
        
    except Exception as e:
        return False, f"Error: {str(e)}"

# Usage with error handling
success, message = split_pdf_safe("input.pdf", "output")
print(message)

import pymupdf

def split_pdf_to_images(input_path, output_folder, image_format="PNG", dpi=150):
    """
    Convert PDF pages to image files.
    
    Args:
        input_path (str): Path to input PDF
        output_folder (str): Output directory
        image_format (str): Image format (PNG, JPEG, etc.)
        dpi (int): Resolution for images
    """
    pdf_document = pymupdf.open(input_path)
    
    os.makedirs(output_folder, exist_ok=True)
    
    for page_num in range(len(pdf_document)):
        page = pdf_document[page_num]
        
        # Create transformation matrix for desired DPI
        mat = pymupdf.Matrix(dpi/72, dpi/72)
        
        # Render page to image
        pix = page.get_pixmap(matrix=mat)
        
        # Save image
        output_path = os.path.join(output_folder, f"page_{page_num + 1:03d}.{image_format.lower()}")
        pix.save(output_path)
    
    pdf_document.close()
    print(f"Converted {len(pdf_document)} pages to {image_format} images")