Merger-HTML.py

from bs4 import BeautifulSoup

# Define your HTML files in order
html_files = [
    'DS-1-250-AliBook.html',
    'ds-251-500-AliBook.html',
    'ds-501-750-AliBook.html',
    'ds-750-1000-AliBook.html'
]

output_file = 'merged_output.html'

# Load the first file as base (it contains the proper structure, styles, etc.)
try:
    with open(html_files[0], 'r', encoding='utf-8') as f:
        merged_soup = BeautifulSoup(f.read(), 'html.parser')
except FileNotFoundError:
    print(f"Error: First file {html_files[0]} not found!")
    exit()

# Ensure proper Arabic/RTL attributes
if not merged_soup.html.has_attr('lang'):
    merged_soup.html['lang'] = 'ar'
if not merged_soup.html.has_attr('dir'):
    merged_soup.html['dir'] = 'rtl'

# Find or create the main .book container
book_div = merged_soup.find('div', class_='book')
if not book_div:
    # Fallback: create it if missing
    book_div = merged_soup.new_tag('div', attrs={'class': 'book'})
    body = merged_soup.find('body')
    if body:
        body.append(book_div)
    else:
        new_body = merged_soup.new_tag('body')
        new_body.append(book_div)
        merged_soup.html.append(new_body)

# Keep track of the last <hr> or last hukm to avoid duplicate separators
for index, file_name in enumerate(html_files[1:], start=1):  # Skip first file
    try:
        with open(file_name, 'r', encoding='utf-8') as f:
            soup = BeautifulSoup(f.read(), 'html.parser')
        
        print(f"Processing: {file_name}")
        
        # Extract content from .book div
        file_book = soup.find('div', class_='book')
        content_to_add = []
        
        if file_book:
            # Get all children inside .book
            for child in file_book.find_all(recursive=False):
                # Skip title/subtitle/author section (only keep from first file)
                if child.name == 'div' and any(cls in ['title', 'subtitle', 'author'] for cls in child.get('class', [])):
                    continue
                if child.name == 'hr' and len(content_to_add) == 0:  # Skip first hr in subsequent files
                    continue
                content_to_add.append(child)
        else:
            # Fallback: take everything from body if no .book found
            if soup.body:
                content_to_add = soup.body.find_all(recursive=False)
        
        if content_to_add:
            # Add a separator comment
            separator = BeautifulSoup(f"\n<!-- ==================== Content from {file_name} ==================== -->\n", "html.parser")
            book_div.append(separator)
            
            # Add the content
            for element in content_to_add:
                book_div.append(element)
                
    except FileNotFoundError:
        print(f"Warning: {file_name} not found, skipped.")
    except Exception as e:
        print(f"Error processing {file_name}: {e}")

# Clean up any duplicate titles or meta tags (optional safety)
for tag in merged_soup.head.find_all('title')[1:]:
    tag.decompose()
for tag in merged_soup.head.find_all('meta'):
    if tag.get('charset') or tag.get('http-equiv'):
        continue  # keep charset

# Save with nice formatting
with open(output_file, 'w', encoding='utf-8') as f:
    f.write(merged_soup.prettify())

print(f"\nSuccess! Merged file saved as: {output_file}")
print("The original styling, RTL direction, and .book layout have been preserved.")