Function htmlToAscii

htmlToAscii(html: string): string

Converts HTML to ASCII. Closing block-level tags (paragraphs, headings, list items, table rows/cells, …) and <br> become line breaks; every other tag is stripped and the common HTML entities are decoded. Runs of blank lines left by empty or nested blocks are collapsed to a single line break.

Parameters

html: string
The HTML string to convert

Returns string

The ASCII string

Example

htmlToAscii("<h2>Title</h2><p>Hello <b>world</b></p><ul><li>one</li><li>two</li></ul>")
// Returns "Title\nHello world\none\ntwo"

Source

export function htmlToAscii(html: string): string {
  return (
    html
      .replace(BLOCK_CLOSE_REGEX, '\n')
      .replace(/<br\s*\/?>/gi, '\n')
      .replace(/<[^>]+>/g, '')
      .replace(/&amp;/g, '&')
      .replace(/&lt;/g, '<')
      .replace(/&gt;/g, '>')
      .replace(/&nbsp;/g, ' ')
      .replace(/&quot;/g, '"')
      .replace(/&#39;/g, "'")
      // Trim trailing spaces per line and collapse blank-line runs from empty blocks.
      .replace(/[ \t]+\n/g, '\n')
      .replace(/\n{2,}/g, '\n')
      .trim()
  );
}