Batch Convert Multiple HTML Files to PDF with Aspose.HTML in Python via .NET

batch_convert_multiple_html_files_to_pdf_complete_.py

from pathlib import Path

from aspose.html import HTMLDocument
from aspose.html.saving import PdfSaveOptions
from aspose.html.converters import Converter


def batch_convert_html_to_pdf(input_dir: str, output_dir: str) -> dict:
    input_path = Path(input_dir)
    output_path = Path(output_dir)

    if not input_path.exists():
        raise FileNotFoundError(f"Input folder not found: {input_path}")

    output_path.mkdir(parents=True, exist_ok=True)

    html_files = sorted(
        p for p in input_path.rglob("*")
        if p.is_file() and p.suffix.lower() in [".html", ".htm"]
    )

    results = {
        "total": len(html_files),
        "succeeded": 0,
        "failed": 0,
        "failures": []
    }

    pdf_options = PdfSaveOptions()

    for html_file in html_files:
        try:
            relative = html_file.relative_to(input_path)
            pdf_file = output_path / relative.with_suffix(".pdf")
            pdf_file.parent.mkdir(parents=True, exist_ok=True)

            with HTMLDocument(str(html_file)) as document:
                Converter.convert_html(document, pdf_options, str(pdf_file))

            results["succeeded"] += 1
            print(f"OK  {relative} -> {pdf_file.relative_to(output_path)}")

        except Exception as ex:
            results["failed"] += 1
            results["failures"].append({"file": str(html_file), "error": str(ex)})
            print(f"ERR {html_file} -> {ex}")

    return results


if __name__ == "__main__":
    summary = batch_convert_html_to_pdf("input", "output")

    print("\nSummary")
    print(f"Total     : {summary['total']}")
    print(f"Succeeded : {summary['succeeded']}")
    print(f"Failed    : {summary['failed']}")