/// <summary>
/// Parses the contents of an HTML tag. The current position should
/// be at the first character following the tag's opening less-than
/// character.
///
/// Note: We parse to the end of the tag even if this tag was not
/// requested by the caller. This ensures subsequent parsing takes
/// place after this tag
/// </summary>
/// <param name="name">Name of the tag the caller is requesting,
/// or "*" if caller is requesting all tags</param>
/// <param name="tag">Returns information on this tag if it's one
/// the caller is requesting</param>
/// <returns>True if data is being returned for a tag requested by
/// the caller or false otherwise</returns>
protected bool ParseTag(string name, ref HtmlTag tag)
{
// Get name of this tag
string s = ParseTagName();
// Special handling
bool doctype = _scriptBegin = false;
if (String.Compare(s, "!DOCTYPE", true) == 0)
doctype = true;
else if (String.Compare(s, "script", true) == 0)
_scriptBegin = true;
// Is this a tag requested by caller?
bool requested = false;
if (name == "*" || String.Compare(s, name, true) == 0)
{
// Yes, create new tag object
tag = new HtmlTag();
tag.Name = s;
tag.Attributes = new Dictionary<string, string>();
requested = true;
}
// Parse attributes
SkipWhitespace();
while (Peek() != '>')
{
if (Peek() == '/')
{
// Handle trailing forward slash
if (requested)
tag.TrailingSlash = true;
Move();
SkipWhitespace();
// If this is a script tag, it was closed
_scriptBegin = false;
}
else
{
// Parse attribute name
s = (!doctype) ? ParseAttributeName() : ParseAttributeValue();
SkipWhitespace();
// Parse attribute value
string value = String.Empty;
if (Peek() == '=')
{
Move();
SkipWhitespace();
value = ParseAttributeValue();
SkipWhitespace();
}
// Add attribute to collection if requested tag
if (requested)
{
// This tag replaces existing tags with same name
if (tag.Attributes.Keys.Contains(s))
tag.Attributes.Remove(s);
tag.Attributes.Add(s, value);
}
}
}
// Skip over closing '>'
Move();
return requested;
}
/// <summary>
/// Parses the next tag that matches the specified tag name
/// </summary>
/// <param name="name">Name of the tags to parse ("*" = parse all
/// tags)</param>
/// <param name="tag">Returns information on the next occurrence
/// of the specified tag or null if none found</param>
/// <returns>True if a tag was parsed or false if the end of the
/// document was reached</returns>
public bool ParseNext(string name, out HtmlTag tag)
{
tag = null;
// Nothing to do if no tag specified
if (String.IsNullOrEmpty(name))
return false;
// Loop until match is found or there are no more tags
while (MoveToNextTag())
{
// Skip opening '<'
Move();
// Examine first tag character
char c = Peek();
if (c == '!' && Peek(1) == '-' && Peek(2) == '-')
{
// Skip over comments
const string endComment = "-->";
_pos = _html.IndexOf(endComment, _pos);
NormalizePosition();
Move(endComment.Length);
}
else if (c == '/')
{
// Skip over closing tags
_pos = _html.IndexOf('>', _pos);
NormalizePosition();
Move();
}
else
{
// Parse tag
bool result = ParseTag(name, ref tag);
// Because scripts may contain tag characters,
// we need special handling to skip over
// script contents
if (_scriptBegin)
{
const string endScript = "</script";
_pos = _html.IndexOf(endScript, _pos,
StringComparison.OrdinalIgnoreCase);
NormalizePosition();
Move(endScript.Length);
SkipWhitespace();
if (Peek() == '>')
Move();
}
// Return true if requested tag was found
if (result)
return true;
}
}
return false;
}