1. import html
  2. import re
  4. def encode_html(html_string):
  5. """Encodes HTML for non-production use with limited memory."""
  7. # Use a generator to process the HTML string in chunks.
  8. for line in html_string.splitlines():
  9. if line.strip(): # Skip empty lines
  10. # Encode HTML entities.
  11. encoded_line = html.escape(line)
  12. yield encoded_line + '\n' # Add newline back
  14. def encode_html_file(input_filename, output_filename):
  15. """Encodes an HTML file and writes the encoded output to a new file."""
  16. try:
  17. with open(input_filename, 'r', encoding='utf-8') as infile, \
  18. open(output_filename, 'w', encoding='utf-8') as outfile:
  19. for encoded_line in encode_html(infile.read()):
  20. outfile.write(encoded_line)
  21. except FileNotFoundError:
  22. print(f"Error: File not found: {input_filename}")
  23. except Exception as e:
  24. print(f"An error occurred: {e}")
  27. if __name__ == '__main__':
  28. # Example usage:
  29. # Create a sample HTML file for testing.
  30. sample_html = """
  31. <html>
  32. <head>
  33. <title>Sample HTML</title>
  34. </head>
  35. <body>
  36. <h1>Hello, <b>World</b>!</h1>
  37. <p>This is a <i>test</i>.</p>
  38. <a href="https://www.example.com">Example Link</a>
  39. </body>
  40. </html>
  41. """
  42. with open("sample.html", "w", encoding="utf-8") as f:
  43. f.write(sample_html)
  45. encode_html_file("sample.html", "encoded.html")
  46. print("HTML encoded and saved to encoded.html")

Add your comment