/// <summary>
/// Remove invalid HTML tags, attributes, and javascript from the HTML.
/// </summary>
/// <returns>Returns a string consisting of clean HTML.</returns>
private string Clean()
{
int dirtyHtmlIndex = 0;
bool foundFirstTag = false;
if (this._allowJavascript)
{
this._dirtyHtml = this._originalHtml;
}
else
{
this._dirtyHtml = DeleteScriptTags(this._originalHtml);
}
while (dirtyHtmlIndex < this._dirtyHtml.Length)
{
// Look for start tag and process if we find it.
Match tagMatch = _startTag.Match(this._dirtyHtml, dirtyHtmlIndex);
if (tagMatch.Success)
{
foundFirstTag = true;
// Increment our index the length of the tag.
dirtyHtmlIndex = tagMatch.Index + tagMatch.Length;
// Process the start tag. The method might increment our index if there is content after this tag.
dirtyHtmlIndex = this.ProcessStartTag(tagMatch, dirtyHtmlIndex);
continue;
}
// Look for end tag and process if we find it.
tagMatch = _endTag.Match(this._dirtyHtml, dirtyHtmlIndex);
if (tagMatch.Success)
{
// Increment our index the length of the tag.
dirtyHtmlIndex = tagMatch.Index + tagMatch.Length;
// Process the end tag. The method might increment our index if their is content after this tag.
dirtyHtmlIndex = this.ProcessEndTag(tagMatch, dirtyHtmlIndex);
continue;
}
if (!foundFirstTag)
{
// We haven't encountered an HTML tag yet, so append the current character.
this._cleanHtml.Append(this._dirtyHtml.Substring(dirtyHtmlIndex, 1));
}
dirtyHtmlIndex++;
}
return(this._cleanHtml.ToString());
}
public static string GetOutterText(string html, Match startTagMatch)
{
StringBuilder sb = new StringBuilder(5000);
//Start searching at the end of the start tag
int index = startTagMatch.Index + startTagMatch.Length;
//Get the string version of the tag
string startTagName = GetTagName(startTagMatch);
string endTag = "";
//loop thru the bml text
while (index < html.Length)
{
Match m = null;
//search out the next ending type of tag
EndTagRegex bmlEndTag = new EndTagRegex();
m = bmlEndTag.Match(html, index);
//check if we find a match
if (m.Success)
{
//verify the tagnames match
endTag = GetTagName(m);
if (endTag == startTagName)
{ //match
//return the outertext of the match.
int endindex = m.Index + m.Length;
int stLength = endindex - startTagMatch.Index;
return(html.Substring(startTagMatch.Index, stLength));
}
{ //No Match, increment index
index = m.Index + m.Length;
continue;
}
}
index++;
}
//TODO: Throw error?
throw new ApplicationException(
string.Format("No end tag match found for tag {0} at position {1}", startTagMatch.Value, startTagMatch.Index));
//return "";
}
