VAR/VAR.PdfTools
1
1
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases Wiki Activity

PdfTextElement: Extract text elements with coordinates and size

Browse Source
This commit is contained in:
Valeriano A.R.
2016-06-20 18:23:45 +02:00
parent d568cbd74b
commit bbafe91037
4 changed files with 415 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
VAR.PdfTools.Workbench/FrmPdfInfo.cs
View File

@@ -33,7 +33,7 @@ namespace VAR.PdfTools.Workbench
txtPdfPath.Text = dlgFile.FileName;
}
}
private void btnProcess_Click(object sender, EventArgs e)
{
if (System.IO.File.Exists(txtPdfPath.Text) == false)
@@ -45,6 +45,7 @@ namespace VAR.PdfTools.Workbench
PdfDocument doc = PdfDocument.Load(txtPdfPath.Text);
int nObjects = doc.Objects.Count;
int nRootObject = doc.Objects.Where(obj => obj.UsageCount == 0).Count();
List<PdfStream> streams = doc.Objects
.Where(obj => obj.Data.Type == PdfElementTypes.Stream)
.Select(obj => (PdfStream)obj.Data)
@@ -55,11 +56,21 @@ namespace VAR.PdfTools.Workbench
List<string> lines = new List<string>();
lines.Add(string.Format("Filename : {0}", System.IO.Path.GetFileNameWithoutExtension(txtPdfPath.Text)));
lines.Add(string.Format("Number of Objects : {0}", nObjects));
lines.Add(string.Format("Number of Roots : {0}", nRootObject));
lines.Add(string.Format("Number of Streams : {0}", nStreams));
lines.Add(string.Format("Number of Pages : {0}", nPages));
txtOutput.Lines = lines.ToArray();
foreach (PdfDocumentPage page in doc.Pages)
{
PdfTextExtractor extractor = new PdfTextExtractor(page);
foreach (PdfTextElement textElement in extractor.Elements)
{
lines.Add(string.Format("Text({0}, {1})({2}): \"{3}\"",
textElement.Matrix.Matrix[0, 2], textElement.Matrix.Matrix[1, 2], textElement.VisibleWidth, textElement.VisibleText));
}
}
txtOutput.Lines = lines.ToArray();
}
}