Python | Machine Learning | Coding

❤2

2.81K views10:48

# 📚 Python Tutorial: Convert EPUB to PDF (Preserving Images)
#Python #EPUB #PDF #EbookConversion #Automation

This comprehensive guide will show you how to convert EPUB files (including those with images) to high-quality PDFs using Python.

---

## 🔹 Required Tools & Libraries
We'll use these Python packages:
- ebooklib - For EPUB parsing
- pdfkit (wrapper for wkhtmltopdf) - For PDF generation
- Pillow - For image handling (optional)

pip install ebooklib pdfkit pillow

Also install system dependencies:

# On Ubuntu/Debian
sudo apt-get install wkhtmltopdf

# On MacOS
brew install wkhtmltopdf

# On Windows (download from wkhtmltopdf.org)

---

## 🔹 Step 1: Extract EPUB Contents
First, we'll unpack the EPUB file to access its HTML and images.

from ebooklib import epub
from bs4 import BeautifulSoup
import os

def extract_epub(epub_path, output_dir):
    book = epub.read_epub(epub_path)
    
    # Create output directory
    os.makedirs(output_dir, exist_ok=True)
    
    # Extract all items (chapters, images, styles)
    for item in book.get_items():
        if item.get_type() == epub.ITEM_IMAGE:
            # Save images
            with open(os.path.join(output_dir, item.get_name()), 'wb') as f:
                f.write(item.get_content())
        elif item.get_type() == epub.ITEM_DOCUMENT:
            # Save HTML chapters
            with open(os.path.join(output_dir, item.get_name()), 'wb') as f:
                f.write(item.get_content())
    
    return [item.get_name() for item in book.get_items() if item.get_type() == epub.ITEM_DOCUMENT]

---

## 🔹 Step 2: Convert HTML to PDF
Now we'll convert the extracted HTML files to PDF while preserving images.

import pdfkit
from PIL import Image  # For image validation (optional)

def html_to_pdf(html_files, output_pdf, base_dir):
    options = {
        'encoding': "UTF-8",
        'quiet': '',
        'enable-local-file-access': '',  # Critical for local images
        'no-outline': None,
        'margin-top': '15mm',
        'margin-right': '15mm',
        'margin-bottom': '15mm',
        'margin-left': '15mm',
    }
    
    # Validate images (optional)
    for html_file in html_files:
        soup = BeautifulSoup(open(os.path.join(base_dir, html_file)), 'html.parser')
        for img in soup.find_all('img'):
            img_path = os.path.join(base_dir, img['src'])
            try:
                Image.open(img_path)  # Validate image
            except Exception as e:
                print(f"Image error in {html_file}: {e}")
                img.decompose()  # Remove broken images
    
    # Convert to PDF
    pdfkit.from_file(
        [os.path.join(base_dir, f) for f in html_files],
        output_pdf,
        options=options
    )

---

## 🔹 Step 3: Complete Conversion Function
Combine everything into a single workflow.

def epub_to_pdf(epub_path, output_pdf, temp_dir="temp_epub"):
    try:
        print(f"Converting {epub_path} to PDF...")
        
        # Step 1: Extract EPUB
        print("Extracting EPUB contents...")
        html_files = extract_epub(epub_path, temp_dir)
        
        # Step 2: Convert to PDF
        print("Generating PDF...")
        html_to_pdf(html_files, output_pdf, temp_dir)
        
        print(f"Success! PDF saved to {output_pdf}")
        return True
    
    except Exception as e:
        print(f"Conversion failed: {str(e)}")
        return False
    finally:
        # Clean up temporary files
        if os.path.exists(temp_dir):
            import shutil
            shutil.rmtree(temp_dir)

---

## 🔹 Advanced Options
### 1. Custom Styling
Add CSS to improve PDF appearance:

def html_to_pdf(html_files, output_pdf, base_dir):
    options = {
        # ... previous options ...
        'user-style-sheet': 'styles.css',  # Custom CSS
    }
    
    # Create CSS file if needed
    css = """
    body { font-family: "Times New Roman", serif; font-size: 12pt; }
    img { max-width: 100%; height: auto; }
    """
    with open(os.path.join(base_dir, 'styles.css'), 'w') as f:
        f.write(css)
    
    pdfkit.from_file(/* ... */)

❤5🔥2🎉1

2.8K views10:48