Is there a possibility to extract plain text from a PDF-File with PdfSharp? I don't want to use iTextSharp because of its license.
Took Sergio's answer and made some extension methods. I also changed the accumulation of strings into an iterator.
public static class PdfSharpExtensions
{
public static IEnumerable<string> ExtractText(this PdfPage page)
{
var content = ContentReader.ReadContent(page);
var text = content.ExtractText();
return text;
}
public static IEnumerable<string> ExtractText(this CObject cObject)
{
if (cObject is COperator)
{
var cOperator = cObject as COperator;
if (cOperator.OpCode.Name== OpCodeName.Tj.ToString() ||
cOperator.OpCode.Name == OpCodeName.TJ.ToString())
{
foreach (var cOperand in cOperator.Operands)
foreach (var txt in ExtractText(cOperand))
yield return txt;
}
}
else if (cObject is CSequence)
{
var cSequence = cObject as CSequence;
foreach (var element in cSequence)
foreach (var txt in ExtractText(element))
yield return txt;
}
else if (cObject is CString)
{
var cString = cObject as CString;
yield return cString.Value;
}
}
}
I have implemented it somehow similar to how David did it. Here is my code:
...
{
// ....
var page = document.Pages[1];
CObject content = ContentReader.ReadContent(page);
var extractedText = ExtractText(content);
// ...
}
private IEnumerable<string> ExtractText(CObject cObject)
{
var textList = new List<string>();
if (cObject is COperator)
{
var cOperator = cObject as COperator;
if (cOperator.OpCode.Name == OpCodeName.Tj.ToString() ||
cOperator.OpCode.Name == OpCodeName.TJ.ToString())
{
foreach (var cOperand in cOperator.Operands)
{
textList.AddRange(ExtractText(cOperand));
}
}
}
else if (cObject is CSequence)
{
var cSequence = cObject as CSequence;
foreach (var element in cSequence)
{
textList.AddRange(ExtractText(element));
}
}
else if (cObject is CString)
{
var cString = cObject as CString;
textList.Add(cString.Value);
}
return textList;
}
PDFSharp provides all the tools to extract the text from a PDF. Use the ContentReader
class to access the commands within each page and extract the strings from TJ/Tj operators.
I've uploaded a simple implementation to github.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With