Analyzing your prompt, please hold on...
An error occurred while retrieving the results. Please refresh the page and try again.
从PDF文档中提取表格
Contents
[
Hide
]
以下代码片段也适用于 Aspose.PDF.Drawing 库。
从PDF中提取表格
// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void Extract_Table()
{
// The path to the documents directory
var dataDir = RunExamples.GetDataDir_AsposePdf_Tables();
// Open PDF document
using (var document = new Aspose.Pdf.Document(dataDir + "the_worlds_cities_in_2018_data_booklet 7.pdf"))
{
foreach (var page in document.Pages)
{
Aspose.Pdf.Text.TableAbsorber absorber = new Aspose.Pdf.Text.TableAbsorber();
absorber.Visit(page);
foreach (var table in absorber.TableList)
{
foreach (var row in table.RowList)
{
foreach (var cell in row.CellList)
{
var textfragment = new Aspose.Pdf.Text.TextFragment();
TextFragmentCollection textFragmentCollection = cell.TextFragments;
foreach (var fragment in textFragmentCollection)
{
string txt = "";
foreach (var seg in fragment.Segments)
{
txt += seg.Text;
}
Console.WriteLine(txt);
}
}
}
}
}
}
}
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处理逻辑仅执行绘制指令，并将背景放置在文本后面。因此，要重复该逻辑，您必须手动处理内容操作符并自己绘制图形。还请注意，以下代码片段可能无法准确处理各种PDF文件，但如果您遇到任何问题，请随时与我们联系。此代码是为特定PDF文件开发的。以下代码片段显示了从PDF文档中提取表格边框作为图像的步骤。
// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ExtractTableBorder()
{
// The path to the documents directory
var dataDir = RunExamples.GetDataDir_AsposePdf_Tables();
// Open PDF document
using (var document = new Aspose.Pdf.Document(dataDir + "input.pdf"))
{
Stack graphicsState = new Stack();
using (var bitmap = new System.Drawing.Bitmap((int)document.Pages[1].PageInfo.Width, (int)document.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)document.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 (var op in document.Pages[1].Contents)
{
var opSaveState = op as Aspose.Pdf.Operators.GSave;
var opRestoreState = op as Aspose.Pdf.Operators.GRestore;
var opCtm = op as Aspose.Pdf.Operators.ConcatenateMatrix;
var opMoveTo = op as Aspose.Pdf.Operators.MoveTo;
var opLineTo = op as Aspose.Pdf.Operators.LineTo;
var opRe = op as Aspose.Pdf.Operators.Re;
var opEndPath = op as Aspose.Pdf.Operators.EndPath;
var opStroke = op as Aspose.Pdf.Operators.Stroke;
var opFill = op as Aspose.Pdf.Operators.Fill;
var opEOFill = op as Aspose.Pdf.Operators.EOFill;
var opRGBFillColor = op as Aspose.Pdf.Operators.SetRGBColor;
var 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();
}
}
}
bitmap.Save(dataDir + "ExtractTableBorder_out.png", ImageFormat.Png);
}
}
}