Develop Reference

ItextSharp Find text in pdf and highlight it

I am working on PDF functionality, I want to search text in PDF and highlight the found text in the PDF. For that I am using iTextsharp.
I did not get any solution yet, please provide me with a solution.
I have written following code;
public ActionResult Index1()
{
string outputFile = #"D:\Test.pdf";
using (FileStream fs = new FileStream(outputFile, FileMode.Create, FileAccess.Write, FileShare.None))
{
using (Document doc = new Document(PageSize.LETTER))
{
using (PdfWriter w = PdfWriter.GetInstance(doc, fs))
{
doc.Open();
doc.Add(new Paragraph("This is a test and sample pdf for test and wait for it"));
doc.Close();
}
}
}
List<int> pages = new List<int>();
PdfReader pdfReader = new PdfReader(outputFile);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
if (currentPageText.Contains("test"))
{
pages.Add(page);
}
}
pdfReader.Close();
//Create a new file from our test file with highlighting
string highLightFile = #"D:\Test1.pdf";
//Bind a reader and stamper to our test PDF
PdfReader reader = new PdfReader(outputFile);
using (FileStream fs = new FileStream(highLightFile, FileMode.Create, FileAccess.Write, FileShare.None))
{
using (PdfStamper stamper = new PdfStamper(reader, fs))
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(60.6755f, 749.172f, 94.0195f, 735.3f);
float[] quad = { rect.Left, rect.Bottom, rect.Right, rect.Bottom, rect.Left, rect.Top, rect.Right, rect.Top };
PdfAnnotation highlight = PdfAnnotation.CreateMarkup(stamper.Writer, rect, null, PdfAnnotation.MARKUP_HIGHLIGHT, quad);
//Set the color
highlight.Color = BaseColor.YELLOW;
//Add the annotation
stamper.AddAnnotation(highlight, 1);
}
}
return View();
}
Above code creates one PDF (test1.pdf)
And in another PDF it highlights some text with hard-coded coordinates, I need to find the coordinates of some text in the PDF.
But I could not find the coordinates of the text I'm looking for.

In iText7, we have implemented this functionality.
It can be found in the class RegexBasedLocationExtractionStrategy.
I suggest you have a look to see how it was done, since this functionality was not backported to iText5.

Adding PDF template page to new inserted page. using itextsharp

I have created one pdf file that i want to use as template page (contain header and border), so when i add new page to existing pdf it automatically set header and border to newly added page.
I am using ITextSharp PDF library.
I have try using PdfImportedPage as below but it's not working:
PdfReader templateFile;
templateFile = new PdfReader("D:\\templatefile.pdf");
PdfImportedPage template_page;
var fileStream1 = new FileStream("D:\\temp.pdf", FileMode.Create, FileAccess.Write);
var stamper1 = new PdfStamper(templateFile, fileStream1);
template_page = stamper1.GetImportedPage(templateFile, 1);
// now i want to add this template_page to existing pdf at specific position
//this is the file(existingpdf.pdf) in which i want to add template_page create above using stamper
var bytes = File.ReadAllBytes("D:\\existingpdf.pdf");
var reader = new PdfReader(bytes);
var numberofPages = reader.NumberOfPages;
var fileStream = new FileStream("D:\\result.pdf", FileMode.Create, FileAccess.Write);
//stamper of result pdf
var stamper = new PdfStamper(reader, fileStream);
stamper.InsertPage(numberofPages + 1, templateFile.GetPageSize(1));
//below code i have tried to add template but its not working in result pdf
stamper.GetUnderContent(2).AddTemplate(template_page, 0, 0);
stamper.Close();

Replace text in pdf file using itextshape in c#

am using the below code for replace image and text on pdf, its is good working on the image replace part, but i dont know the how can write the text replace in same code.
private void AddAnImage()
{
string qrfile = qrcode();
using (var inputPdfStream = new FileStream(Server.MapPath("PDF/input.pdf"), FileMode.Open))
using (var inputImageStream = new FileStream(qrfile, FileMode.Open))
using (var outputPdfStream = new FileStream(Server.MapPath("PDF/output.pdf"), FileMode.Create))
{
PdfReader reader = new PdfReader(inputPdfStream);
PdfStamper stamper = new PdfStamper(reader, outputPdfStream);
PdfContentByte pdfContentByte = stamper.GetOverContent(1);
var image = iTextSharp.text.Image.GetInstance(inputImageStream);
image.SetAbsolutePosition(50, 75);
pdfContentByte.AddImage(image);
PdfContentByte canvas = stamper.GetOverContent(2);
ColumnText.ShowTextAligned(canvas, Element.ALIGN_LEFT, new Phrase(DateTime.Now.ToShortDateString()), 0, 0, 0);
stamper.Close();
}
}

How to set zoom level to pdf using iTextSharp?

I need to set the zoom level 75% to pdf file using iTextSharp. I am using following code to set the zoom level.
PdfReader reader = new PdfReader("input.pdf".ToString());
iTextSharp.text.Document doc = new iTextSharp.text.Document(reader.GetPageSize(1));
doc.OpenDocument();
PdfWriter writer = PdfWriter.GetInstance(doc, new FileStream("Zoom.pdf", FileMode.Create));
PdfDestination pdfDest = new PdfDestination(PdfDestination.XYZ, 0, doc.PageSize.Height, 0.75f);
doc.Open();
PdfAction action = PdfAction.GotoLocalPage(1, pdfDest, writer);
writer.SetOpenAction(action);
doc.Close();
But I am getting the error "the page 1 was request but the document has only 0 pages" in the doc.Close();

You need to use PdfStamper (as indicated by mkl) instead of PdfWriter (as made clear by Chris Haas). Please take a look at the AddOpenAction example:
public void manipulatePdf(String src, String dest) throws IOException, DocumentException {
PdfReader reader = new PdfReader(src);
PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(dest));
PdfDestination pdfDest = new PdfDestination(PdfDestination.XYZ, 0, reader.getPageSize(1).getHeight(), 0.75f);
PdfAction action = PdfAction.gotoLocalPage(1, pdfDest, stamper.getWriter());
stamper.getWriter().setOpenAction(action);
stamper.close();
reader.close();
}
The result is a PDF that opens with a zoom factor of 75%.

ITextSharp insert text to an existing pdf

The title sums it all.
I want to add a text to an existing PDF file using iTextSharp, however i can't find how to do it anywhere in the web...
PS: I cannot use PDF forms.

I found a way to do it (dont know if it is the best but it works)
string oldFile = "oldFile.pdf";
string newFile = "newFile.pdf";
// open the reader
PdfReader reader = new PdfReader(oldFile);
Rectangle size = reader.GetPageSizeWithRotation(1);
Document document = new Document(size);
// open the writer
FileStream fs = new FileStream(newFile, FileMode.Create, FileAccess.Write);
PdfWriter writer = PdfWriter.GetInstance(document, fs);
document.Open();
// the pdf content
PdfContentByte cb = writer.DirectContent;
// select the font properties
BaseFont bf = BaseFont.CreateFont(BaseFont.HELVETICA, BaseFont.CP1252,BaseFont.NOT_EMBEDDED);
cb.SetColorFill(BaseColor.DARK_GRAY);
cb.SetFontAndSize(bf, 8);
// write the text in the pdf content
cb.BeginText();
string text = "Some random blablablabla...";
// put the alignment and coordinates here
cb.ShowTextAligned(1, text, 520, 640, 0);
cb.EndText();
cb.BeginText();
text = "Other random blabla...";
// put the alignment and coordinates here
cb.ShowTextAligned(2, text, 100, 200, 0);
cb.EndText();
// create the new page and add it to the pdf
PdfImportedPage page = writer.GetImportedPage(reader, 1);
cb.AddTemplate(page, 0, 0);
// close the streams and voilá the file should be changed :)
document.Close();
fs.Close();
writer.Close();
reader.Close();
I hope this can be usefull for someone =) (and post here any errors)

In addition to the excellent answers above, the following shows how to add text to each page of a multi-page document:
using (var reader = new PdfReader(#"C:\Input.pdf"))
{
using (var fileStream = new FileStream(#"C:\Output.pdf", FileMode.Create, FileAccess.Write))
{
var document = new Document(reader.GetPageSizeWithRotation(1));
var writer = PdfWriter.GetInstance(document, fileStream);
document.Open();
for (var i = 1; i <= reader.NumberOfPages; i++)
{
document.NewPage();
var baseFont = BaseFont.CreateFont(BaseFont.HELVETICA_BOLD, BaseFont.CP1252, BaseFont.NOT_EMBEDDED);
var importedPage = writer.GetImportedPage(reader, i);
var contentByte = writer.DirectContent;
contentByte.BeginText();
contentByte.SetFontAndSize(baseFont, 12);
var multiLineString = "Hello,\r\nWorld!".Split('\n');
foreach (var line in multiLineString)
{
contentByte.ShowTextAligned(PdfContentByte.ALIGN_LEFT, line, 200, 200, 0);
}
contentByte.EndText();
contentByte.AddTemplate(importedPage, 0, 0);
}
document.Close();
writer.Close();
}
}

This worked for me and includes using OutputStream:
PdfReader reader = new PdfReader(new RandomAccessFileOrArray(Request.MapPath("Template.pdf")), null);
Rectangle size = reader.GetPageSizeWithRotation(1);
using (Stream outStream = Response.OutputStream)
{
Document document = new Document(size);
PdfWriter writer = PdfWriter.GetInstance(document, outStream);
document.Open();
try
{
PdfContentByte cb = writer.DirectContent;
cb.BeginText();
try
{
cb.SetFontAndSize(BaseFont.CreateFont(), 12);
cb.SetTextMatrix(110, 110);
cb.ShowText("aaa");
}
finally
{
cb.EndText();
}
PdfImportedPage page = writer.GetImportedPage(reader, 1);
cb.AddTemplate(page, 0, 0);
}
finally
{
document.Close();
writer.Close();
reader.Close();
}
}

Here is a method that uses stamper and absolute coordinates showed in the different PDF clients (Adobe, FoxIt and etc. )
public static void AddTextToPdf(string inputPdfPath, string outputPdfPath, string textToAdd, System.Drawing.Point point)
{
//variables
string pathin = inputPdfPath;
string pathout = outputPdfPath;
//create PdfReader object to read from the existing document
using (PdfReader reader = new PdfReader(pathin))
//create PdfStamper object to write to get the pages from reader
using (PdfStamper stamper = new PdfStamper(reader, new FileStream(pathout, FileMode.Create)))
{
//select two pages from the original document
reader.SelectPages("1-2");
//gettins the page size in order to substract from the iTextSharp coordinates
var pageSize = reader.GetPageSize(1);
// PdfContentByte from stamper to add content to the pages over the original content
PdfContentByte pbover = stamper.GetOverContent(1);
//add content to the page using ColumnText
Font font = new Font();
font.Size = 45;
//setting up the X and Y coordinates of the document
int x = point.X;
int y = point.Y;
y = (int) (pageSize.Height - y);
ColumnText.ShowTextAligned(pbover, Element.ALIGN_CENTER, new Phrase(textToAdd, font), x, y, 0);
}
}

Here is a method To print over images:
taken from here.
Use a different layer for your text you're putting over the images, and also make sure to use the GetOverContent() method.
string oldFile = "FileWithImages.pdf";
string watermarkedFile = "Layers.pdf";
// Creating watermark on a separate layer
// Creating iTextSharp.text.pdf.PdfReader object to read the Existing PDF Document
PdfReader reader1 = new PdfReader(oldFile);
using (FileStream fs = new FileStream(watermarkedFile, FileMode.Create, FileAccess.Write, FileShare.None))
// Creating iTextSharp.text.pdf.PdfStamper object to write Data from iTextSharp.text.pdf.PdfReader object to FileStream object
using (PdfStamper stamper = new PdfStamper(reader1, fs))
{
// Getting total number of pages of the Existing Document
int pageCount = reader1.NumberOfPages;
// Create New Layer for Watermark
PdfLayer layer = new PdfLayer("Layer", stamper.Writer);
// Loop through each Page
for (int i = 1; i <= pageCount; i++)
{
// Getting the Page Size
Rectangle rect = reader1.GetPageSize(i);
// Get the ContentByte object
PdfContentByte cb = stamper.GetOverContent(i);
// Tell the cb that the next commands should be "bound" to this new layer
cb.BeginLayer(layer);
BaseFont bf = BaseFont.CreateFont(BaseFont.HELVETICA, BaseFont.CP1252, BaseFont.NOT_EMBEDDED);
cb.SetColorFill(BaseColor.RED);
cb.SetFontAndSize(bf, 100);
cb.BeginText();
cb.ShowTextAligned(PdfContentByte.ALIGN_CENTER, "Some random blablablabla...", rect.Width / 2, rect.Height / 2, - 90);
cb.EndText();
// Close the layer
cb.EndLayer();
}
}