Parse HTML table to JSON in ASP.NET C#

Question

I'm having a problem. I have a survey builder written with different types of questions (list, checkbox, dropdowns...) and one with a table to fill. The problem is now to store the table I have 3 different tables on my DB and to create the table later is a bit complex. I'm trying to do it, using a JavaScript editor so the user can create the table as in word. On my code behind I receive the table markup as an String and I want to store it as JSON on the DB.

I have this code here to convert the table to a DataSet object and then from here I can convert to XML and from here to JSON using the library JSON.NET. All of this is working fine, but the problem is when the table have "colspan" & "rowspan" parameters, is not working with them. Can you help me to finish this piece of code so everyone can have this as an example to parse HTML table to JSON in C#.

protected void Page_Load(object sender, EventArgs e)
{
    string table = @"
                
                    Project Country Header 1 Header 2
                

                    Child Header 1 Child Header 2 Child Header 3 Child Header 4
                

                    Child Child Header 1 tee ssss
                

                    aas
                

                    EUS ES          
                

                    ARP IE          
                

                    ARM UK          
                

                    SMRT US          
                

                    CM          
                
            ";

    DataSet dataSet = HtmlTableParser.ParseDataSet(table);
    StringWriter sw = new StringWriter();
    dataSet.WriteXml(sw, XmlWriteMode.IgnoreSchema);
    XmlDocument xd = new XmlDocument();
    xd.LoadXml(sw.ToString());

    string jsonText = JsonConvert.SerializeXmlNode(xd).Replace("_x0020_", " ");
}

/// 
/// HtmlTableParser parses the contents of an html string into a System.Data DataSet or DataTable.
/// 
public class HtmlTableParser
{
    private const RegexOptions ExpressionOptions = RegexOptions.Singleline | RegexOptions.Multiline | RegexOptions.IgnoreCase;
    private const string CommentPattern = "";
    private const string TablePattern = "]*>(.*?)";
    private const string HeaderPattern = "]*>(.*?)";
    private const string RowPattern = "]*>(.*?)";
    private const string CellPattern = "]*>(.*?)";

    /// 
    /// Given an HTML string containing n table tables, parse them into a DataSet containing n DataTables.
    /// 
    /// An HTML string containing n HTML tables
    /// A DataSet containing a DataTable for each HTML table in the input HTML
    public static DataSet ParseDataSet(string html)
    {
        DataSet dataSet = new DataSet();
        MatchCollection tableMatches = Regex.Matches(
            WithoutComments(html),
            TablePattern,
            ExpressionOptions);

        foreach (Match tableMatch in tableMatches)
            dataSet.Tables.Add(ParseTable(tableMatch.Value));

        return dataSet;
    }

    /// 
    /// Given an HTML string containing a single table, parse that table to form a DataTable.
    /// 
    /// An HTML string containing a single HTML table
    /// A DataTable which matches the input HTML table
    public static DataTable ParseTable(string tableHtml)
    {
        string tableHtmlWithoutComments = WithoutComments(tableHtml);

        DataTable dataTable = new DataTable();

        MatchCollection rowMatches = Regex.Matches(
            tableHtmlWithoutComments,
            RowPattern,
            ExpressionOptions);

        dataTable.Columns.AddRange(tableHtmlWithoutComments.Contains("
    /// Strip comments from an HTML stirng
    /// 
    /// An HTML string potentially containing comments
    /// The input HTML string with comments removed
    private static string WithoutComments(string html)
    {
        return Regex.Replace(html, CommentPattern, string.Empty, ExpressionOptions);
    }

    /// 
    /// Add a row to the input DataTable for each row match in the input MatchCollection
    /// 
    /// A collection of all the rows to add to the DataTable
    /// The DataTable to which we add rows
    private static void ParseRows(MatchCollection rowMatches, DataTable dataTable)
    {
        foreach (Match rowMatch in rowMatches)
        {
            // if the row contains header tags don't use it - it is a header not a row
            if (!rowMatch.Value.Contains("
    /// Given a string containing an HTML table, parse the header cells to create a set of DataColumns
    /// which define the columns in a DataTable.
    /// 
    /// An HTML string containing a single HTML table
    /// A set of DataColumns based on the HTML table header cells
    private static DataColumn[] ParseColumns(string tableHtml)
    {
        MatchCollection headerMatches = Regex.Matches(
            tableHtml,
            HeaderPattern,
            ExpressionOptions);

        return (from Match headerMatch in headerMatches
                select new DataColumn(headerMatch.Groups[1].ToString())).ToArray();
    }

    /// 
    /// For tables which do not specify header cells we must generate DataColumns based on the number
    /// of cells in a row (we assume all rows have the same number of cells).
    /// 
    /// A collection of all the rows in the HTML table we wish to generate columns for
    /// A set of DataColumns based on the number of celss in the first row of the input HTML table
    private static DataColumn[] GenerateColumns(MatchCollection rowMatches)
    {
        int columnCount = Regex.Matches(
            rowMatches[0].ToString(),
            CellPattern,
            ExpressionOptions).Count;

        return (from index in Enumerable.Range(0, columnCount)
                select new DataColumn("Column " + Convert.ToString(index))).ToArray();
    }
}

Parse HTML table to JSON in ASP.NET C#

Answers (1)

Related Questions