PDF管理控件Aspose.PDF for .Net使用教程（三十六）：在表格内添加HTML标签和分页符

Aspose.PDF for .NET是一种高PDF处理和解析API，用于在跨平台应用程序中执行文档管理和操作任务。API可以轻松用于生成、修改、转换、渲染、保护和打印PDF文档，而无需使用Adobe Acrobat。此外，API还提供PDF压缩选项，表格创建和操作，图形和图像功能，广泛的超链接功能，印章和水印任务，扩展的安全控制和自定义字体处理。

在接下来的系列教程中，将为开发者带来Aspose.PDF for .NET的一系列使用教程，例如进行文档间的转换，如何标记PDF文件，如何使用表单和图表等等。本文将在表格内添加HTML标签、在表格行之间插入分页符、将表格边框提取为图像。

>>Aspose.PDF for .NET更新至最新版v20.5，欢迎下载体验。

使用PDF文档时，表格很重要。它们提供了用于以系统方式显示信息的强大功能。该Aspose.PDF.Generator命名空间包含同名的类Table，Cell并且Row它从头开始生成PDF文档时创建表提供的功能。

在表格内添加HTML标签

有时，可能会提出一个要求，即导入具有一些HTML标记的数据库内容，然后将其导入Table对象。导入内容时，应在PDF文档中相应地呈现HTML标记。

// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Tables();

DataTable dt = new DataTable("Employee");
dt.Columns.Add("data", System.Type.GetType("System.String"));

DataRow dr = dt.NewRow();
dr[0] = "<li>Department of Emergency Medicine: 3400 Spruce Street Ground Silverstein Bldg Philadelphia PA 19104-4206</li>";
dt.Rows.Add(dr);
dr = dt.NewRow();
dr[0] = "<li>Penn Observation Medicine Service: 3400 Spruce Street Ground Floor Donner Philadelphia PA 19104-4206</li>";
dt.Rows.Add(dr);
dr = dt.NewRow();
dr[0] = "<li>UPHS/Presbyterian - Dept. of Emergency Medicine: 51 N. 39th Street . Philadelphia PA 19104-2640</li>";
dt.Rows.Add(dr);

Document doc = new Document();
doc.Pages.Add();
// Initializes a new instance of the Table
Aspose.Pdf.Table tableProvider = new Aspose.Pdf.Table();
//Set column widths of the table
tableProvider.ColumnWidths = "400 50 ";
// Set the table border color as LightGray
tableProvider.Border = new Aspose.Pdf.BorderInfo(Aspose.Pdf.BorderSide.All, 0.5F, Aspose.Pdf.Color.FromRgb(System.Drawing.Color.LightGray));
// Set the border for table cells
tableProvider.DefaultCellBorder = new Aspose.Pdf.BorderInfo(Aspose.Pdf.BorderSide.All, 0.5F, Aspose.Pdf.Color.FromRgb(System.Drawing.Color.LightGray));
Aspose.Pdf.MarginInfo margin = new Aspose.Pdf.MarginInfo();
margin.Top = 2.5F;
margin.Left = 2.5F;
margin.Bottom = 1.0F;
tableProvider.DefaultCellPadding = margin;

tableProvider.ImportDataTable(dt, false, 0, 0, 3, 1, true);

doc.Pages[1].Paragraphs.Add(tableProvider);
doc.Save(dataDir + "HTMLInsideTableCell_out.pdf");

在表格行之间插入分页符

作为默认行为，当在PDF文件中创建表格时，表格到达表格底边距时，表格会流向后续页面。但是，当为表添加一定数量的行时，我们可能需要强制插入分页符。以下代码段显示了为表添加10行时插入分页符的步骤。

// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Tables();

// Instantiate Document instance
Document doc = new Document();
// Add page to pages collection of PDF file
doc.Pages.Add();
// Create table instance
Aspose.Pdf.Table tab = new Aspose.Pdf.Table();
// Set border style for table
tab.Border = new Aspose.Pdf.BorderInfo(Aspose.Pdf.BorderSide.All, Aspose.Pdf.Color.Red);
// Set default border style for table with border color as Red
tab.DefaultCellBorder = new Aspose.Pdf.BorderInfo(Aspose.Pdf.BorderSide.All, Aspose.Pdf.Color.Red);
// Specify table columsn widht
tab.ColumnWidths = "100 100";
// Create a loop to add 200 rows for table
for (int counter = 0; counter <= 200; counter++) { Aspose.Pdf.Row row = new Aspose.Pdf.Row(); tab.Rows.Add(row); Aspose.Pdf.Cell cell1 = new Aspose.Pdf.Cell(); cell1.Paragraphs.Add(new TextFragment("Cell " + counter + ", 0")); row.Cells.Add(cell1); Aspose.Pdf.Cell cell2 = new Aspose.Pdf.Cell(); cell2.Paragraphs.Add(new TextFragment("Cell " + counter + ", 1")); row.Cells.Add(cell2); // When 10 rows are added, render new row in new page if (counter % 10 == 0 && counter != 0) row.IsInNewPage = true; } // Add table to paragraphs collection of PDF file doc.Pages[1].Paragraphs.Add(tab); dataDir = dataDir + "InsertPageBreak_out.pdf"; // Save the PDF document doc.Save(dataDir);

将表格边框提取为图像

页面边框是路径绘制操作。因此，Pdf-> Html处理逻辑仅执行绘图指令并将背景放在文本后面。因此，要重复此逻辑，您必须手动处理内容运算符并自己绘制图形。另外请注意，以下代码段可能不适用于各种PDF文件，但是如果您遇到任何问题，请随时与我们联系。此代码是为特定的PDF文件开发的。以下代码段显示了从PDF文档中提取表格边框作为Image的步骤。

// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Tables();

Document doc = new Document(dataDir + "input.pdf");
            
Stack graphicsState = new Stack();
System.Drawing.Bitmap bitmap = new System.Drawing.Bitmap((int)doc.Pages[1].PageInfo.Width, (int)doc.Pages[1].PageInfo.Height);
System.Drawing.Drawing2D.GraphicsPath graphicsPath = new System.Drawing.Drawing2D.GraphicsPath();
// Default ctm matrix value is 1,0,0,1,0,0
System.Drawing.Drawing2D.Matrix lastCTM = new System.Drawing.Drawing2D.Matrix(1, 0, 0, -1, 0, 0);
// System.Drawing coordinate system is top left based, while pdf coordinate system is low left based, so we have to apply the inversion matrix
System.Drawing.Drawing2D.Matrix inversionMatrix = new System.Drawing.Drawing2D.Matrix(1, 0, 0, -1, 0, (float)doc.Pages[1].PageInfo.Height);
System.Drawing.PointF lastPoint = new System.Drawing.PointF(0, 0);
System.Drawing.Color fillColor = System.Drawing.Color.FromArgb(0, 0, 0);
System.Drawing.Color strokeColor = System.Drawing.Color.FromArgb(0, 0, 0);

using (System.Drawing.Graphics gr = System.Drawing.Graphics.FromImage(bitmap))
{
    gr.SmoothingMode = SmoothingMode.HighQuality;
    graphicsState.Push(new System.Drawing.Drawing2D.Matrix(1, 0, 0, 1, 0, 0));

    // Process all the contents commands
    foreach (Operator op in doc.Pages[1].Contents)
    {
        Aspose.Pdf.Operators.GSave opSaveState = op as Aspose.Pdf.Operators.GSave;
        Aspose.Pdf.Operators.GRestore opRestoreState = op as Aspose.Pdf.Operators.GRestore;
        Aspose.Pdf.Operators.ConcatenateMatrix opCtm = op as Aspose.Pdf.Operators.ConcatenateMatrix;
        Aspose.Pdf.Operators.MoveTo opMoveTo = op as Aspose.Pdf.Operators.MoveTo;
        Aspose.Pdf.Operators.LineTo opLineTo = op as Aspose.Pdf.Operators.LineTo;
        Aspose.Pdf.Operators.Re opRe = op as Aspose.Pdf.Operators.Re;
        Aspose.Pdf.Operators.EndPath opEndPath = op as Aspose.Pdf.Operators.EndPath;
        Aspose.Pdf.Operators.Stroke opStroke = op as Aspose.Pdf.Operators.Stroke;
        Aspose.Pdf.Operators.Fill opFill = op as Aspose.Pdf.Operators.Fill;
        Aspose.Pdf.Operators.EOFill opEOFill = op as Aspose.Pdf.Operators.EOFill;
        Aspose.Pdf.Operators.SetRGBColor opRGBFillColor = op as Aspose.Pdf.Operators.SetRGBColor;
        Aspose.Pdf.Operators.SetRGBColorStroke opRGBStrokeColor = op as Aspose.Pdf.Operators.SetRGBColorStroke;

        if (opSaveState != null)
        {
            // Save previous state and push current state to the top of the stack
            graphicsState.Push(((System.Drawing.Drawing2D.Matrix)graphicsState.Peek()).Clone());
            lastCTM = (System.Drawing.Drawing2D.Matrix)graphicsState.Peek();
        }
        else if (opRestoreState != null)
        {
            // Throw away current state and restore previous one
            graphicsState.Pop();
            lastCTM = (System.Drawing.Drawing2D.Matrix)graphicsState.Peek();
        }
        else if (opCtm != null)
        {
            System.Drawing.Drawing2D.Matrix cm = new System.Drawing.Drawing2D.Matrix(
                (float)opCtm.Matrix.A,
                (float)opCtm.Matrix.B,
                (float)opCtm.Matrix.C,
                (float)opCtm.Matrix.D,
                (float)opCtm.Matrix.E,
                (float)opCtm.Matrix.F);

            // Multiply current matrix with the state matrix
            ((System.Drawing.Drawing2D.Matrix)graphicsState.Peek()).Multiply(cm);
            lastCTM = (System.Drawing.Drawing2D.Matrix)graphicsState.Peek();
        }
        else if (opMoveTo != null)
        {
            lastPoint = new System.Drawing.PointF((float)opMoveTo.X, (float)opMoveTo.Y);
        }
        else if (opLineTo != null)
        {
            System.Drawing.PointF linePoint = new System.Drawing.PointF((float)opLineTo.X, (float)opLineTo.Y);
            graphicsPath.AddLine(lastPoint, linePoint);

            lastPoint = linePoint;
        }
        else if (opRe != null)
        {
            System.Drawing.RectangleF re = new System.Drawing.RectangleF((float)opRe.X, (float)opRe.Y, (float)opRe.Width, (float)opRe.Height);
            graphicsPath.AddRectangle(re);
        }
        else if (opEndPath != null)
        {
            graphicsPath = new System.Drawing.Drawing2D.GraphicsPath();
        }
        else if (opRGBFillColor != null)
        {
            fillColor = opRGBFillColor.getColor();
        }
        else if (opRGBStrokeColor != null)
        {
            strokeColor = opRGBStrokeColor.getColor();
        }
        else if (opStroke != null)
        {
            graphicsPath.Transform(lastCTM);
            graphicsPath.Transform(inversionMatrix);
            gr.DrawPath(new System.Drawing.Pen(strokeColor), graphicsPath);
            graphicsPath = new System.Drawing.Drawing2D.GraphicsPath();
        }
        else if (opFill != null)
        {
            graphicsPath.FillMode = FillMode.Winding;
            graphicsPath.Transform(lastCTM);
            graphicsPath.Transform(inversionMatrix);
            gr.FillPath(new System.Drawing.SolidBrush(fillColor), graphicsPath);
            graphicsPath = new System.Drawing.Drawing2D.GraphicsPath();
        }
        else if (opEOFill != null)
        {
            graphicsPath.FillMode = FillMode.Alternate;
            graphicsPath.Transform(lastCTM);
            graphicsPath.Transform(inversionMatrix);
            gr.FillPath(new System.Drawing.SolidBrush(fillColor), graphicsPath);
            graphicsPath = new System.Drawing.Drawing2D.GraphicsPath();
        }
    }
}
dataDir = dataDir + "ExtractBorder_out.png";
bitmap.Save(dataDir, ImageFormat.Png);