Convert HTML to TXT in Python

readme.md

Convert HTML to TXT in Python

Discover a fast way to convert HTML to TXT in Python with Aspose.HTML for Python via .NET. This tutorial covers installing the SDK, understanding the conversion code, handling encoding, optimizing performance, and validating the output for data processing.

Read the full guide here: https://blog.aspose.com/html/convert-html-to-txt-in-python/

html_to_text.py

import os
import sys
import aspose.html as ah
import aspose.html.saving as ahs

def convert_html_to_txt(input_path: str, output_path: str, encoding: str = "utf-8") -> None:
    """
    Converts an HTML file to a plain text (TXT) file using Aspose.HTML for Python via .NET.
    """
    if not os.path.isfile(input_path):
        raise FileNotFoundError(f"Input file does not exist: {input_path}")

    try:
        # Load the HTML document
        document = ah.HtmlDocument(input_path)

        # Configure TXT save options
        txt_options = ahs.TxtSaveOptions()
        txt_options.encoding = encoding          # Ensure proper character encoding
        txt_options.remove_extra_whitespace = True  # Reduce unnecessary spaces (if supported)

        # Perform the conversion
        document.save(output_path, txt_options)

    except Exception as exc:
        # Capture any Aspose or I/O related errors
        print(f"[Error] Conversion failed: {exc}", file=sys.stderr)
        raise

    finally:
        # Explicitly release resources held by the document
        if 'document' in locals():
            document.dispose()


def validate_txt_output(output_path: str, min_chars: int = 10) -> None:
    """
    Simple validation to ensure the TXT file was created and contains readable content.
    """
    if not os.path.isfile(output_path):
        raise FileNotFoundError(f"Output file was not created: {output_path}")

    with open(output_path, "r", encoding="utf-8") as txt_file:
        content = txt_file.read()

    if len(content) < min_chars:
        raise ValueError("Output text appears to be empty or truncated.")

    # Show a short preview for quick verification
    preview = content[:200].replace("\r", "").replace("\n", " | ")
    print(f"[Info] Conversion succeeded. Preview (first 200 chars):\n{preview}")


if __name__ == "__main__":
    # Example file paths – replace with actual locations as needed
    INPUT_HTML = "sample.html"
    OUTPUT_TXT = "sample.txt"

    try:
        convert_html_to_txt(INPUT_HTML, OUTPUT_TXT)
        validate_txt_output(OUTPUT_TXT)
    except Exception as e:
        print(f"[Fatal] HTML to TXT conversion failed: {e}", file=sys.stderr)
        sys.exit(1)