Using itextsharp (or any c# pdf library), i need to open a PDF, replace some placeholder text with actual values, and return it as a byte[].
Can someone suggest how to do this? I've had a look at the itext docs and can't figure out where to get started. So far i'm stuck on how to get the source pdf from a PDFReader to a Document object, i presume i'm probably approaching this the wrong way.
Thanks a lot
In the end, i used PDFescape to open my existing PDF file, and place some form fields in where i need to put my fields, then save it again to create my PDF file.
http://www.pdfescape.com
Then i found this blog entry about how to replace form fields:
http://www.johnnycode.com/blog/2010/03/05/using-a-template-to-programmatically-create-pdfs-with-c-and-itextsharp/
All works nicely! Here's the code:
public static byte[] Generate()
{
var templatePath = HttpContext.Current.Server.MapPath("~/my_template.pdf");
// Based on:
// http://www.johnnycode.com/blog/2010/03/05/using-a-template-to-programmatically-create-pdfs-with-c-and-itextsharp/
var reader = new PdfReader(templatePath);
var outStream = new MemoryStream();
var stamper = new PdfStamper(reader, outStream);
var form = stamper.AcroFields;
var fieldKeys = form.Fields.Keys;
foreach (string fieldKey in fieldKeys)
{
if (form.GetField(fieldKey) == "MyTemplatesOriginalTextFieldA")
form.SetField(fieldKey, "1234");
if (form.GetField(fieldKey) == "MyTemplatesOriginalTextFieldB")
form.SetField(fieldKey, "5678");
}
// "Flatten" the form so it wont be editable/usable anymore
stamper.FormFlattening = true;
stamper.Close();
reader.Close();
return outStream.ToArray();
}
Unfortunately I was looking for something similar and could not figure it out. Below was about as far as I got, maybe you can use this as a starting point. The problem is that PDF does not actually save text, but instead uses lookup tables and some other arcane wizardry. This method reads the byte-values for the page and attempts to convert to string, but as far as I can tell it can only do English and misses on some special characters, so I gave up my project and moved on.
string contents = string.Empty();
Document doc = new Document();
PdfReader reader = new PdfReader("pathToPdf.pdf");
using (MemoryStream memoryStream = new MemoryStream())
{
PdfWriter writer = PdfWriter.GetInstance(doc, memoryStream);
doc.Open();
PdfContentByte cb = writer.DirectContent;
for (int p = 1; p <= reader.NumberOfPages; p++)
{
// add page from reader
doc.SetPageSize(reader.GetPageSize(p));
doc.NewPage();
// pickup here something like this:
byte[] bt = reader.GetPageContent(p);
contents = ExtractTextFromPDFBytes(bt);
if (contents.IndexOf("something")!=-1)
{
// make your own pdf page and add to cb (contentbyte)
}
else
{
PdfImportedPage page = writer.GetImportedPage(reader, p);
int rot = reader.GetPageRotation(p);
if (rot == 90 || rot == 270)
cb.AddTemplate(page, 0, -1.0F, 1.0F, 0, 0, reader.GetPageSizeWithRotation(p).Height);
else
cb.AddTemplate(page, 1.0F, 0, 0, 1.0F, 0, 0);
}
}
reader.Close();
doc.Close();
File.WriteAllBytes("pathToOutputOrSamePathToOverwrite.pdf", memoryStream.ToArray());
This is taken from this site.
private string ExtractTextFromPDFBytes(byte[] input)
{
if (input == null || input.Length == 0) return "";
try
{
string resultString = "";
// Flag showing if we are we currently inside a text object
bool inTextObject = false;
// Flag showing if the next character is literal
// e.g. '\\' to get a '\' character or '\(' to get '('
bool nextLiteral = false;
// () Bracket nesting level. Text appears inside ()
int bracketDepth = 0;
// Keep previous chars to get extract numbers etc.:
char[] previousCharacters = new char[_numberOfCharsToKeep];
for (int j = 0; j < _numberOfCharsToKeep; j++) previousCharacters[j] = ' ';
for (int i = 0; i < input.Length; i++)
{
char c = (char)input[i];
if (inTextObject)
{
// Position the text
if (bracketDepth == 0)
{
if (CheckToken(new string[] { "TD", "Td" }, previousCharacters))
{
resultString += "\n\r";
}
else
{
if (CheckToken(new string[] { "'", "T*", "\"" }, previousCharacters))
{
resultString += "\n";
}
else
{
if (CheckToken(new string[] { "Tj" }, previousCharacters))
{
resultString += " ";
}
}
}
}
// End of a text object, also go to a new line.
if (bracketDepth == 0 &&
CheckToken(new string[] { "ET" }, previousCharacters))
{
inTextObject = false;
resultString += " ";
}
else
{
// Start outputting text
if ((c == '(') && (bracketDepth == 0) && (!nextLiteral))
{
bracketDepth = 1;
}
else
{
// Stop outputting text
if ((c == ')') && (bracketDepth == 1) && (!nextLiteral))
{
bracketDepth = 0;
}
else
{
// Just a normal text character:
if (bracketDepth == 1)
{
// Only print out next character no matter what.
// Do not interpret.
if (c == '\\' && !nextLiteral)
{
nextLiteral = true;
}
else
{
if (((c >= ' ') && (c <= '~')) ||
((c >= 128) && (c < 255)))
{
resultString += c.ToString();
}
nextLiteral = false;
}
}
}
}
}
}
// Store the recent characters for
// when we have to go back for a checking
for (int j = 0; j < _numberOfCharsToKeep - 1; j++)
{
previousCharacters[j] = previousCharacters[j + 1];
}
previousCharacters[_numberOfCharsToKeep - 1] = c;
// Start of a text object
if (!inTextObject && CheckToken(new string[] { "BT" }, previousCharacters))
{
inTextObject = true;
}
}
return resultString;
}
catch
{
return "";
}
}
private bool CheckToken(string[] tokens, char[] recent)
{
foreach (string token in tokens)
{
if ((recent[_numberOfCharsToKeep - 3] == token[0]) &&
(recent[_numberOfCharsToKeep - 2] == token[1]) &&
((recent[_numberOfCharsToKeep - 1] == ' ') ||
(recent[_numberOfCharsToKeep - 1] == 0x0d) ||
(recent[_numberOfCharsToKeep - 1] == 0x0a)) &&
((recent[_numberOfCharsToKeep - 4] == ' ') ||
(recent[_numberOfCharsToKeep - 4] == 0x0d) ||
(recent[_numberOfCharsToKeep - 4] == 0x0a)))
{
return true;
}
}
return false;
}
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