使用htmlagilitypack从字符串中删除html标记

Question

我想知道如何使用htmlagilitypack删除html标签，如下所示？

var htmlDoc = new HtmlDocument();

htmlDoc.LoadHtml(Description);
//markups to be removed
var markups = new List<string> { "br","ol","ul","li" };

感谢

Answer 1

你可以使用这种方法

 public static string RemoveHTMLTags(string content)
        {
            var cleaned = string.Empty;
            try
            {
                string textOnly = string.Empty;
                Regex tagRemove = new Regex(@"<[^>]*(>|$)");
                Regex compressSpaces = new Regex(@"[\s\r\n]+");
                textOnly = tagRemove.Replace(content, string.Empty);
                textOnly = compressSpaces.Replace(textOnly, " ");
                cleaned = textOnly;
            }
            catch
            {
                //A tag is probably not closed. fallback to regex string clean.

            }

            return cleaned;
        }

Answer 2

//markups to be removed
var markups = new List<string> { "br", "ol", "ul", "li" };

var xpath = String.Join(" | ", markups.Select(x => "//" + x));
var nodes = htmlDoc.DocumentNode.SelectNodes(xpath);
if (nodes != null)
{
    foreach (var node in nodes)
    {
        node.Remove();
    }
}