Boost Performance of HTML to PDF Conversion with Aspose.HTML in Python via .NET

html_to_pdf_conversion_complete_code_example.py

import asyncio
import aspose.html as ahtml
from concurrent.futures import ThreadPoolExecutor

# Paths - update these to match your environment
HTML_INPUT = r"C:\Docs\sample.html"
PDF_OUTPUT = r"C:\Docs\sample_converted.pdf"

def create_converter():
    # Load options with performance tweaks
    load_opts = ahtml.loading.HtmlLoadOptions()
    load_opts.resource_loading_timeout = 30
    load_opts.enable_memory_cache = False

    # Custom font settings (reuse across conversions)
    font_opts = ahtml.rendering.FontSettings()
    font_opts.add_font_folder(r"C:\MyFonts")
    load_opts.font_settings = font_opts

    # PDF save options with margins
    save_opts = ahtml.saving.PdfSaveOptions()
    save_opts.page_margins = ahtml.saving.PageMargins(10, 10, 10, 10)  # points

    converter = ahtml.conversion.HtmlToPdfConverter()
    converter.load_options = load_opts
    converter.save_options = save_opts
    return converter

async def async_convert(html_path, pdf_path):
    converter = create_converter()
    try:
        await converter.convert_async(html_path, pdf_path)
    finally:
        # Ensure unmanaged resources are released
        converter.dispose()

def run_sync_conversion():
    converter = create_converter()
    try:
        converter.convert(HTML_INPUT, PDF_OUTPUT)
    finally:
        converter.dispose()

def run_parallel_conversions(file_pairs):
    with ThreadPoolExecutor(max_workers=4) as executor:
        futures = [
            executor.submit(
                lambda pair: create_converter().convert(pair[0], pair[1]),
                pair
            )
            for pair in file_pairs
        ]
        for f in futures:
            f.result()  # Propagate any exceptions

if __name__ == "__main__":
    # Example 1: Simple synchronous conversion
    run_sync_conversion()

    # Example 2: Asynchronous conversion
    asyncio.run(async_convert(HTML_INPUT, PDF_OUTPUT))

    # Example 3: Parallel batch conversion
    batch = [
        (r"C:\Docs\doc1.html", r"C:\Docs\doc1.pdf"),
        (r"C:\Docs\doc2.html", r"C:\Docs\doc2.pdf"),
        (r"C:\Docs\doc3.html", r"C:\Docs\doc3.pdf")
    ]
    run_parallel_conversions(batch)