Pragmatic Bookshelf EPUB file processer

epub_processer.py

import re
import zipfile
import tempfile
import os
import shutil
from pathlib import Path

def process_html_content(content):
    """
    Add <pre> tags around <table class="processedcode"> elements
    """
    pattern = r'(<table class="processedcode"[^>]*>[\s\S]*?</table>)'
    
    def replacer(match):
        return f'<pre>{match.group(1)}</pre>'
    
    return re.sub(pattern, replacer, content)

def process_epub(epub_path):
    """
    Process all HTML files in the EPUB file
    """
    # Create temporary directory
    temp_dir = tempfile.mkdtemp()
    temp_epub = os.path.join(temp_dir, 'temp.epub')
    
    try:
        # Copy original file to temp directory
        shutil.copy2(epub_path, temp_epub)
        
        # Create output filename
        output_path = str(Path(epub_path).with_stem(Path(epub_path).stem + '_processed'))
        
        # Process EPUB file
        with zipfile.ZipFile(epub_path, 'r') as zip_ref:
            # Create new ZIP file
            with zipfile.ZipFile(output_path, 'w') as zip_out:
                # Iterate through all files
                for item in zip_ref.infolist():
                    data = zip_ref.read(item.filename)
                    
                    # Process HTML files
                    if item.filename.endswith(('.html', '.xhtml')):
                        content = data.decode('utf-8')
                        processed_content = process_html_content(content)
                        zip_out.writestr(item, processed_content.encode('utf-8'))
                    else:
                        # Copy other files directly
                        zip_out.writestr(item, data)
        
        print(f"Processing complete. Output file: {output_path}")
        return output_path
        
    finally:
        # Clean up temporary files
        shutil.rmtree(temp_dir)

if __name__ == "__main__":
    import sys
    
    if len(sys.argv) != 2:
        print("Usage: python script.py <epub_file_path>")
        sys.exit(1)
    
    epub_path = sys.argv[1]
    process_epub(epub_path)

The eBook from Pragmatic Bookshelf has an issue in the epub file where code may not be wrapped in or

 tags. As a result, when using translation software to translate the epub file, the code is also translated, leading to a poor reading experience. The purpose of this script is to wrap specific code snippets in 
 tags, allowing the translation tool to skip these code segments.