在 ASP.NET C# 中将 HTML 表解析为 JSON

Question

我遇到了问题。我有一个用不同类型的问题（列表、复选框、下拉列表...）编写的调查生成器，还有一个要填写表格的调查生成器。现在的问题是要存储表，我的数据库上有 3 个不同的表，稍后创建表有点复杂。我正在尝试使用 JavaScript 编辑器来执行此操作，以便用户可以像在 word 中一样创建表格。在我后面的代码中，我将表标记作为字符串接收，我想将其作为 JSON 存储在数据库中。

我在这里有这段代码来将表转换为 DataSet 对象，然后我可以使用 JSON.NET 库从这里转换为 XML 并从这里转换为 JSON。所有这些都工作正常，但问题是当表有“colspan”和“rowspan”参数时，不能使用它们。您能帮我完成这段代码，以便每个人都可以以此为例，在 C# 中将 HTML 表解析为 JSON。

protected void Page_Load(object sender, EventArgs e)
{
    string table = @"<table>
                <tbody><tr>
                    <th rowspan='4'>Project</th><th rowspan='4'>Country</th><th colspan='3' rowspan='1'>Header 1</th><th colspan='2' rowspan='1'>Header 2</th>
                </tr><tr>
                    <th colspan='1' rowspan='1'>Child Header 1</th><th colspan='2' rowspan='1'>Child Header 2</th><th colspan='1' rowspan='3'>Child Header 3</th><th colspan='1' rowspan='3'>Child Header 4</th>
                </tr><tr>
                    <th colspan='1' rowspan='2'>Child Child Header 1</th><th colspan='1' rowspan='1'>tee</th><th colspan='1' rowspan='2'>ssss</th>
                </tr><tr>
                    <th colspan='1' rowspan='1'>aas</th>
                </tr><tr>
                    <td>EUS</td><td>ES</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td>
                </tr><tr>
                    <td>ARP</td><td>IE</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td>
                </tr><tr>
                    <td>ARM</td><td>UK</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td>
                </tr><tr>
                    <td>SMRT</td><td>US</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td>
                </tr><tr>
                    <td>CM</td><td></td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td>
                </tr>
            </tbody></table>";

    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_", " ");
}

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

    /// <summary>
    /// Given an HTML string containing n table tables, parse them into a DataSet containing n DataTables.
    /// </summary>
    /// <param name="html">An HTML string containing n HTML tables</param>
    /// <returns>A DataSet containing a DataTable for each HTML table in the input HTML</returns>
    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;
    }

    /// <summary>
    /// Given an HTML string containing a single table, parse that table to form a DataTable.
    /// </summary>
    /// <param name="tableHtml">An HTML string containing a single HTML table</param>
    /// <returns>A DataTable which matches the input HTML table</returns>
    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("<th")
                                       ? ParseColumns(tableHtml)
                                       : GenerateColumns(rowMatches));

        ParseRows(rowMatches, dataTable);

        return dataTable;
    }

    /// <summary>
    /// Strip comments from an HTML stirng
    /// </summary>
    /// <param name="html">An HTML string potentially containing comments</param>
    /// <returns>The input HTML string with comments removed</returns>
    private static string WithoutComments(string html)
    {
        return Regex.Replace(html, CommentPattern, string.Empty, ExpressionOptions);
    }

    /// <summary>
    /// Add a row to the input DataTable for each row match in the input MatchCollection
    /// </summary>
    /// <param name="rowMatches">A collection of all the rows to add to the DataTable</param>
    /// <param name="dataTable">The DataTable to which we add rows</param>
    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("<th"))
            {
                DataRow dataRow = dataTable.NewRow();

                MatchCollection cellMatches = Regex.Matches(
                    rowMatch.Value,
                    CellPattern,
                    ExpressionOptions);

                for (int columnIndex = 0; columnIndex < cellMatches.Count; columnIndex++)
                    dataRow[columnIndex] = cellMatches[columnIndex].Groups[1].ToString();

                dataTable.Rows.Add(dataRow);
            }
        }
    }

    /// <summary>
    /// Given a string containing an HTML table, parse the header cells to create a set of DataColumns
    /// which define the columns in a DataTable.
    /// </summary>
    /// <param name="tableHtml">An HTML string containing a single HTML table</param>
    /// <returns>A set of DataColumns based on the HTML table header cells</returns>
    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();
    }

    /// <summary>
    /// 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).
    /// </summary>
    /// <param name="rowMatches">A collection of all the rows in the HTML table we wish to generate columns for</param>
    /// <returns>A set of DataColumns based on the number of celss in the first row of the input HTML table</returns>
    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();
    }
}

Answer 1

这闻起来像非常糟糕的事情。为什么要使用正则表达式来清理 HTML？ Stack Overflow 上的 most famous answer ever 与此相关。不要这样做。

您将这个 HTML 解析成这个 DataTable 的要求对我来说真的没有意义。在需要您现在将其解析为 JSON 之后，您对 HTML 表做了什么？从您的问题来看，这听起来像是一个相当简单的调查编辑器。

如果您确实需要将此数据解析为对象并将此表中的每个单独字段存储到数据库中，请告诉我们原因。可以这样做，但我强烈建议您重新考虑解析 HTML。