string StripHtml(string html)
{
// create whitespace between html elements, so that words do not run together
html = html.Replace(">","> ");
// parse html
var doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);
// strip html decoded text from html
string text = HttpUtility.HtmlDecode(doc.DocumentNode.InnerText);
// replace all whitespace with a single space and remove leading and trailing whitespace
return Regex.Replace(text, @"\s+", " ").Trim();
lwensauer
commented
2 years ago
string StripHtml(string html) { // create whitespace between html elements, so that words do not run together html = html.Replace(">","> ");
}
...