public static string RemoveHTMLTags(string content)
{
var cleaned = string.Empty;
try
{
StringBuilder textOnly = new StringBuilder();
using (var reader = XmlNodeReader.Create(new System.IO.StringReader("<xml>" + content + "</xml>")))
{
while (reader.Read())
{
if (reader.NodeType == XmlNodeType.Text)
textOnly.Append(reader.ReadContentAsString());
}
}
cleaned = textOnly.ToString();
}
catch
{
//A tag is probably not closed. fallback to regex string clean.
string textOnly = string.Empty;
Regex tagRemove = new Regex(@"<[^>]*(>|$)");
Regex compressSpaces = new Regex(@"[\s\r\n]+");
textOnly = tagRemove.Replace(content, string.Empty);
textOnly = compressSpaces.Replace(textOnly, " ");
cleaned = textOnly;
}
return cleaned;
}
{
var cleaned = string.Empty;
try
{
StringBuilder textOnly = new StringBuilder();
using (var reader = XmlNodeReader.Create(new System.IO.StringReader("<xml>" + content + "</xml>")))
{
while (reader.Read())
{
if (reader.NodeType == XmlNodeType.Text)
textOnly.Append(reader.ReadContentAsString());
}
}
cleaned = textOnly.ToString();
}
catch
{
//A tag is probably not closed. fallback to regex string clean.
string textOnly = string.Empty;
Regex tagRemove = new Regex(@"<[^>]*(>|$)");
Regex compressSpaces = new Regex(@"[\s\r\n]+");
textOnly = tagRemove.Replace(content, string.Empty);
textOnly = compressSpaces.Replace(textOnly, " ");
cleaned = textOnly;
}
return cleaned;
}
No comments:
Post a Comment