I found many samples on the web, one of these:
var oldFile = #"C:\Users\XXX\Downloads\3921B2014901_2014_7346.pdf";
var newFile = #"C:\Users\XXX\Downloads\new\3921B2014901_2014_7346.pdf";
RandomAccessFileOrArray raf = new RandomAccessFileOrArray(oldFile);
PdfReader reader = new PdfReader(raf, null);
using (FileStream fs = new FileStream(newFile, FileMode.Create))
{
PdfStamper stamper = new PdfStamper(reader, fs, PdfWriter.VERSION_1_5);
PdfWriter writer = stamper.Writer;
writer.SetPdfVersion(PdfWriter.PDF_VERSION_1_5);
writer.CompressionLevel = PdfStream.BEST_COMPRESSION;
for (int i = 1; i <= reader.NumberOfPages; i++)
{
reader.SetPageContent(i, reader.GetPageContent(i), PdfStream.BEST_COMPRESSION, true);
}
stamper.SetFullCompression();
stamper.Close();
}
reader.Close();
raf.Close();
The original file is 2.75Mb and the resulting new file is 2.77Mb. Why?
I tried online converters and they reduce the same file to 500Kb. How can I achieve the same result?
protected void btnCompressPdf_click(object sender, EventArgs e)
{
string[] filename= Directory.GetFiles(input.Text, ".jpg");
string outputPath = MyDirectory;
if (!System.IO.Directory.Exists(MyDirectory))
System.IO.Directory.CreateDirectory(MyDirectory);
foreach (string filename in files)
{
ImageCollection images = new ImageCollection();
images.Add(filename);
String pdfName = Path.GetFileNameWithoutExtension(file);
for (int pageNumber = 0; pageNumber < images.Count; pageNumber++)
{
images[pageNumber].Save(MyDirectory + "\\" + pageNumber.ToString() + ".jpg");
}
string[] files1 = System.IO.Directory.GetFiles(MyDirectory, ".jpg");
iTextSharp.text.Document myDocument = new iTextSharp.text.Document(iTextSharp.text.PageSize.A4, 0, 0, 0, 0);
//PdfWriter.GetInstance(myDocument, new System.IO.FileStream(uxOutput.Text + "\\" + pdfName + ".pdf", System.IO.FileMode.Create));
PdfWriter writer = PdfWriter.GetInstance(myDocument, new System.IO.FileStream(Output.Text + "\\" + pdfName + ".pdf", System.IO.FileMode.Create));
writer.SetPdfVersion(PdfWriter.PDF_VERSION_1_5);
writer.CompressionLevel = PdfStream.BEST_COMPRESSION;
writer.SetFullCompression();
for (int i = 0; i <= files1.Length - 1; i++)
{
if (myDocument != null)
{
myDocument.Open();
AddImageToPDF(myDocument, MyDirectory + "\\" + (i).ToString() + ".jpg");
}
}
myDocument.Close();
myDocument = null;
System.IO.File.Delete(MyDirectory + "\\" + ".jpg");
}
}
Related
I'm using iTextSharp, version 5.5.8.0 in a Windows Form application. Here is the code I used to merge two pdf files. My task is to add page number in merged file.
private void MergePDFFiles()
{
string fileSuffix = DateTime.Now.ToString("yyyyMMddHHmmss") + ".pdf";
string[] lstFiles = new string[2];
lstFiles[0] = #"/File_1.pdf";
lstFiles[1] = #"/File_2.pdf";
PdfReader reader = null;
Document sourceDocument = null;
PdfCopy pdfCopyProvider = null;
PdfImportedPage importedPage;
string outputPdfPath = #"/MergedPageNo_" + fileSuffix;
sourceDocument = new Document();
pdfCopyProvider = new PdfCopy(sourceDocument, new System.IO.FileStream(outputPdfPath, System.IO.FileMode.Create));
sourceDocument.Open();
try
{
for (int f = 0; f < lstFiles.Length - 0; f++)
{
int pages = get_pageCount(lstFiles[f]);
reader = new PdfReader(lstFiles[f]);
for (int i = 1; i <= pages; i++)
{
importedPage = pdfCopyProvider.GetImportedPage(reader, i);
pdfCopyProvider.AddPage(importedPage);
}
reader.Close();
}
sourceDocument.Close();
}
catch (Exception ex)
{
throw ex;
}
}`
I have a method that fixes my document so it opens on Page Level Zoom, the bookmarks are retained but I can't seem to keep my named destinations (anchors) in my new document. I commented in my method what I thought would fix the problem, I used the code before in another method.
private static void FixZoom(string source)
{
var reader = new PdfReader(new FileStream(source, FileMode.Open, FileAccess.Read));
var size = reader.GetPageSizeWithRotation(1);
using (var document = new iTextSharp.text.Document(size))
{
var path = String.Empty;
var dirName = Path.GetDirectoryName(source);
if (dirName != null)
{
path = Path.Combine(dirName, "Zoom" + Path.GetFileName(source));
}
using (var stream = new FileStream(path, FileMode.Create, FileAccess.ReadWrite))
{
using (var writer = PdfWriter.GetInstance(document, stream))
{
document.Open();
var bookmarks = SimpleBookmark.GetBookmark(reader);
var cb = writer.DirectContent;
var pdfDest = new PdfDestination(PdfDestination.FIT);
var action = PdfAction.GotoLocalPage(1, pdfDest, writer);
for (var pageNumber = 1; pageNumber <= reader.NumberOfPages; pageNumber++)
{
document.SetPageSize(reader.GetPageSizeWithRotation(pageNumber));
document.NewPage();
var page = writer.GetImportedPage(reader, pageNumber);
cb.AddTemplate(page, 0, 0);
}
//BEGIN: This is not working
var map = SimpleNamedDestination.GetNamedDestination(reader, false);
if (map.Count > 0)
{
writer.AddNamedDestinations(map, reader.NumberOfPages);
}
//END: This is not working
var pageMode = 0;
pageMode += PdfWriter.PageLayoutOneColumn;
writer.SetOpenAction(action);
writer.ViewerPreferences = pageMode;
writer.Outlines = bookmarks;
document.Close();
}
}
File.Delete(source);
File.Move(path, source);
}
}
After the comment I fixed it with this code.
private static void FixZoom(string source)
{
var reader = new PdfReader(new FileStream(source, FileMode.Open, FileAccess.Read));
var size = reader.GetPageSizeWithRotation(1);
using (var document = new iTextSharp.text.Document(size))
{
var path = String.Empty;
var dirName = Path.GetDirectoryName(source);
if (dirName != null)
{
path = Path.Combine(dirName, "Zoom" + Path.GetFileName(source));
}
using (var stream = new FileStream(path, FileMode.Create, FileAccess.ReadWrite))
{
using (var stamper = new PdfStamper(reader, stream))
{
document.Open();
var pdfDestination = new PdfDestination(PdfDestination.FIT);
var pdfAction = PdfAction.GotoLocalPage(1, pdfDestination, stamper.Writer);
stamper.Writer.SetOpenAction(pdfAction);
document.Close();
}
}
File.Delete(source);
File.Move(path, source);
}
}
I have 3 pdfs templates that i Fill out and save to a memorystream them merge them together into 1 pdf into a memorystream. The resulting merged pdf is non flattenned. I tried reading the merged pdf and flattening it but it say "pdf header signature not found". Is there a way to flattened merged pdf from a memorystream.
this is what I tried so far without success.
var mergedPdf = MergePDFs(AllPdfs);
MemoryStream flattenedMergedPdf = new MemoryStream();
PdfReader Finalpdf = new PdfReader(mergedPdf);
PdfStamper StampFinalMerged = new PdfStamper(Finalpdf,flattenedMergedPdf);
StampFinalMerged.FormFlattening=true;
return flattenedMergedPdf;
the method i use to merge the pdfs(found on SO) is below:
public MemoryStream MergePDFs(List<byte[]> pdfFiles)
{
if (pdfFiles.Count > 1)
{
PdfReader finalPdf;
Document pdfContainer;
PdfCopy pdfCopy;
MemoryStream msFinalPdf = new MemoryStream();
finalPdf = new PdfReader(pdfFiles[0]);
pdfContainer = new Document();
pdfCopy = new PdfSmartCopy(pdfContainer, msFinalPdf);
pdfContainer.Open();
for (int k = 0; k < pdfFiles.Count; k++)
{
finalPdf = new PdfReader(pdfFiles[k]);
for (int i = 1; i < finalPdf.NumberOfPages + 1; i++)
{
((PdfSmartCopy)pdfCopy).AddPage(pdfCopy.GetImportedPage(finalPdf, i));
}
pdfCopy.FreeReader(finalPdf);
}
//tried this here but no success
// PdfReader FinalRead = new PdfReader(finalPdf);
//MemoryStream FinalMS = new MemoryStream();
//var finalStamper = new PdfStamper(FinalRead, FinalMS);
//finalStamper.FormFlattening = true;
pdfCopy.CloseStream = false;
pdfCopy.Close();
finalPdf.Close();
//return FinalMS
return msFinalPdf;
}
Any help will be much appreciated. Thanks
You can try another approach to flatten PDF templates first then merge them into a final PDF file:
string newFile = "... path to the merged pdf file ...";
string[] pdfTemplates = new string[3];
string pdfTemplates[0] = "... path to the 1st pdf template ...";
string pdfTemplates[1] = "... path to the 2nd pdf template ...";
string pdfTemplates[2] = "... path to the 3rd pdf template ...";
string[] pdfFiles = new string[3];
string pdfFiles[0] = "... path to the 1st temp pdf file ...";
string pdfFiles[1] = "... path to the 2nd temp pdf file ...";
string pdfFiles[2] = "... path to the 3rd temp pdf file ...";
for (int i = 0; i < 3; i++)
{
PdfReader pdfReader = new PdfReader(pdfTemplates[i]);
PdfStamper pdfStamper = new PdfStamper(pdfReader, new FileStream(pdfFiles[i], FileMode.Create));
pdfStamper.FormFlattening = true;
pdfStamper.Close();
}
MergeFiles(newFile, pdfFiles);
for (int i = 0; i < 3; i++)
{
FileInfo fi = new FileInfo(pdfFiles[i]);
fi.Delete();
}
private void MergeFiles(string destinationFile, string[] sourceFiles)
{
try
{
int f = 0;
PdfReader reader = new PdfReader(sourceFiles[f]);
int n = reader.NumberOfPages;
Document document = new Document(reader.GetPageSizeWithRotation(1));
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(destinationFile, FileMode.Create));
document.Open();
PdfContentByte cb = writer.DirectContent;
PdfImportedPage page;
int rotation;
while (f < sourceFiles.Length)
{
int i = 0;
while (i < n)
{
i++;
document.SetPageSize(reader.GetPageSizeWithRotation(i));
document.NewPage();
page = writer.GetImportedPage(reader, i);
rotation = reader.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb.AddTemplate(page, 0, -1f, 1f, 0, 0, reader.GetPageSizeWithRotation(i).Height);
}
else
{
cb.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
}
f++;
if (f < sourceFiles.Length)
{
reader = new PdfReader(sourceFiles[f]);
n = reader.NumberOfPages;
}
}
document.Close();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);
}
}
I have a PDF that has a plugin control on one page. I need to merge it with another pdf but when I do, the plugin is redendered as a blank rectangle. Is there a way to merge and preserve the plugin control? If important, the plugin is a Dessault Systemes 3D Via Composer Player control as installed from http://www.3ds.com/products/3dvia/3dvia-composer/resource-center/
The code I'm using is simple writer getinstance, contentbyte directcontent, getimportedpage, addtemplate. Nothing fancy.
FileStream docStream = new FileStream(#"C:\Temp\Merged.pdf", FileMode.Create);
Document newDocument = new Document(PageSize.A4.Rotate());
PdfWriter pdfWriter = PdfWriter.GetInstance(newDocument, docStream);
try
{
newDocument.Open();
PdfContentByte pdfContentByte = pdfWriter.DirectContent;
newDocument.NewPage();
PdfReader mainPage = new PdfReader(#"C:\Temp\PageWithPlugin.pdf");
PdfImportedPage importedPage1 = pdfWriter.GetImportedPage(mainPage, 1);
pdfContentByte.AddTemplate(importedPage1, 0, 0);
mainPage.Close();
PdfReader smgPages = new PdfReader(#"C:\Temp\MorePages.pdf");
for (int page = 1; page <= smgPage.NumberOfPages; page++)
{
newDocument.NewPage();
PdfImportedPage importedPage = pdfWriter.GetImportedPage(smgPages, page);
pdfContentByte.AddTemplate(importedPage, 0, 0);
}
smgPages.Close();
}
finally
{
docStream.Flush();
if (newDocument != null)
newDocument.Close();
docStream.Close();
}
Give this a try.
List<byte[]> fileList = new List<byte[]>();
using (FileStream fileSteam = File.OpenRead((#"C:\Temp\PageWithPlugin.pdf")))
{
Byte[] byteArray = new byte[fileSteam.Length];
fileSteam.Read(byteArray, 0, byteArray.Length);
fileList.Add(byteArray);
}
using (FileStream fileSteam = File.OpenRead((#"C:\Temp\MorePages.pdf")))
{
Byte[] byteArray = new byte[fileSteam.Length];
fileSteam.Read(byteArray, 0, byteArray.Length);
fileList.Add(byteArray);
}
using(MemoryStream msOutput = new MemoryStream())
{
PdfReader pdfFile = new PdfReader(fileList[0]);
Document doc = new Document();
PdfWriter pCopy = new PdfSmartCopy(doc, msOutput);
doc.Open();
for (int k = 0; k < fileList.Count; k++)
{
for (int i = 1; i < pdfFile.NumberOfPages + 1; i++)
{
pdfFile = new PdfReader(fileList[k]);
((PdfSmartCopy)pCopy).AddPage(pCopy.GetImportedPage(pdfFile, i));
pCopy.FreeReader(pdfFile);
}
}
pdfFile.Close();
pCopy.Close();
doc.Close();
fileList.Clear();
byte[] form = msOutput.ToArray();
using (FileStream fileSteam = new FileStream(#"C:\Temp\Merged.pdf", FileMode.Create))
{
fileStream.Write(form, 0, form.Length);
}
}
Not to look a gift horse in the mouth but... In case anyone else uses the solution, there is a small problem with the k loop. The numberofpages would be off by one document after the zeroth one and the pdfReader keeps getting freed and reread for every page, which isn't necessary. I think this is an improvement for that part of the code:
using (MemoryStream msOutput = new MemoryStream())
{
Document doc = new Document();
PdfWriter pCopy = new PdfCopy(doc, msOutput);
doc.Open();
for (int k = 0; k < fileList.Count; k++)
{
PdfReader pdfFile = new PdfReader(fileList[k]);
for (int i = 1; i < pdfFile.NumberOfPages + 1; i++)
{
((PdfCopy)pCopy).AddPage(pCopy.GetImportedPage(pdfFile, i));
}
pCopy.FreeReader(pdfFile);
pdfFile.Close();
}
pCopy.Close();
doc.Close();
fileList.Clear();
What is the optimum way to merge 2 PDF files with ITextSharp in C#? I'm using ASP.NET/.NET3.5.
public static void Merge(List<String> InFiles, String OutFile)
{
using (FileStream stream = new FileStream(OutFile, FileMode.Create))
using (Document doc = new Document())
using (PdfCopy pdf = new PdfCopy(doc, stream))
{
doc.Open();
PdfReader reader = null;
PdfImportedPage page = null;
//fixed typo
InFiles.ForEach(file =>
{
reader = new PdfReader(file);
for (int i = 0; i < reader.NumberOfPages; i++)
{
page = pdf.GetImportedPage(reader, i + 1);
pdf.AddPage(page);
}
pdf.FreeReader(reader);
reader.Close();
});
}
}
The last answer works if you don't want to delete the original files. In my case, I want to delete and when I tried I got exception. My solution is:
public static bool MergePDFs(List<String> InFiles, String OutFile)
{
bool merged = true;
try
{
List<PdfReader> readerList = new List<PdfReader>();
foreach (string filePath in InFiles)
{
PdfReader pdfReader = new PdfReader(filePath);
readerList.Add(pdfReader);
}
//Define a new output document and its size, type
Document document = new Document(PageSize.A4, 0, 0, 0, 0);
//Create blank output pdf file and get the stream to write on it.
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(OutFile, FileMode.Create));
document.Open();
foreach (PdfReader reader in readerList)
{
PdfReader.unethicalreading = true;
for (int i = 1; i <= reader.NumberOfPages; i++)
{
PdfImportedPage page = writer.GetImportedPage(reader, i);
document.Add(iTextSharp.text.Image.GetInstance(page));
}
}
document.Close();
foreach (PdfReader reader in readerList)
{
reader.Close();
}
}
catch (Exception ex)
{
merged = false;
}
return merged;
}
I copied the code from Original Code