/// <summary>
/// Parse HTML into a Document
/// </summary>
/// <param name="html"></param>
/// <param name="baseUri"></param>
/// <returns></returns>
public Document ParseInput(string html, string baseUri)
{
errors = CanTrackErrors ? ParseErrorList.Tracking(maxErrors) : ParseErrorList.NoTracking();
Document doc = treeBuilder.Parse(html, baseUri, errors);
return(doc);
}
/// <summary>
/// Utility method to unescape HTML entities from a string
/// </summary>
/// <param name="string">HTML escaped string</param>
/// <param name="inAttribute">if the string is to be escaped in strict mode (as attributes are)</param>
/// <returns>an unescaped string</returns>
public static string UnescapeEntities(string @string, bool inAttribute)
{
Tokeniser tokeniser = new Tokeniser(new CharacterReader(@string), ParseErrorList.NoTracking());
return(tokeniser.UnescapeEntities(inAttribute));
}
/// <summary>
/// Parse a fragment of XML into a list of nodes.
/// </summary>
/// <param name="fragmentXml">the fragment of XML to parse</param>
/// <param name="baseUri">base URI of document (i.e. original fetch location), for resolving relative URLs.</param>
/// <returns>list of nodes parsed from the input XML.</returns>
public static IReadOnlyList <Node> ParseXmlFragment(string fragmentXml, string baseUri)
{
XmlTreeBuilder treeBuilder = new XmlTreeBuilder();
return(treeBuilder.ParseFragment(fragmentXml, baseUri, ParseErrorList.NoTracking()));
}
/// <summary>
/// Parse a fragment of HTML into a list of nodes.
/// </summary>
/// <remarks>
/// The context element, if supplied, supplies parsing context.
/// </remarks>
/// <param name="fragmentHtml">the fragment of HTML to parse</param>
/// <param name="context">
/// (optional) the element that this HTML fragment is being parsed for (i.e. for inner HTML). This
/// provides stack context (for implicit element creation).
/// </param>
/// <param name="baseUri">
/// base URI of document (i.e. original fetch location), for resolving relative URLs.
/// </param>
/// <returns>
/// list of nodes parsed from the input HTML. Note that the context element, if supplied, is not modified.
/// </returns>
public static IReadOnlyList <Node> ParseFragment(string fragmentHtml, Element context, string baseUri)
{
HtmlTreeBuilder treeBuilder = new HtmlTreeBuilder();
return(treeBuilder.ParseFragment(fragmentHtml, context, baseUri, ParseErrorList.NoTracking()));
}
// utility methods
/// <summary>
/// Parse HTML into a Document.
/// </summary>
/// <param name="html">HTML to parse</param>
/// <param name="baseUri">base URI of document (i.e. original fetch location), for resolving relative URLs.</param>
/// <returns>parsed Document</returns>
public static Document Parse(string html, string baseUri)
{
TreeBuilder treeBuilder = new HtmlTreeBuilder();
return(treeBuilder.Parse(html, baseUri, ParseErrorList.NoTracking()));
}
internal Document Parse(string input, string baseUri)
{
return(Parse(input, baseUri, ParseErrorList.NoTracking()));
}