PDFEmbeddedFile Class

Summary

Properties of an embedded file (attachment) in this document.

Syntax

C++/CLI

Java

Python

[SerializableAttribute()] 
public class PDFEmbeddedFile

public class PDFEmbeddedFile

public: 
   [SerializableAttribute] 
   ref class PDFEmbeddedFile

class PDFEmbeddedFile:

Remarks

PDF documents support embedded files of any type. The file can be another PDF, a TIF file, a JPEG image, or any other binary or textual data.

The embedded files (attachments) of a PDF document can be read using the following:

Create a new PDFDocument object for the PDF file.
Call PDFDocument.ParseDocumentStructure with the PDFParseDocumentStructureOptions.EmbeddedFiles flag.
If the PDF file contains any embedded files then they will be read and set in the PDFDocument.EmbeddedFiles collection.
If the PDF file has any embedded file schemas (for PDF portfolios), then they will be read and set in the PDFDocument.EmbeddedFilesSchemas collection.

The binary data of an embedded file can be extracted and saved to an output file or stream using PDFFile.ExtractEmbeddedFile.

PDFEmbeddedFile contains the following members:

Member	Description
FileNumber	1-based file number of this embedded file. This is a unique value
FileName	Embedded file name
ObjectNumber	PDF object number of this embedded file. This is a unique value
Description	Description of this embedded file. This is optional
FileSize	Size of the file in bytes
Created	Date this file was created
Modified	Date this file was last modified
SchemaValues	Values for the PDF schema if this PDF is a portfolio. This is optional

Note that the FileName may not be unique in the collection of embedded files found in a PDF document. Instead, use the FileNumber or ObjectNumber property to get a unique identifier for the embedded file.

FileNumber is used as the parameter to identify the embedded file to extract using PDFFile.ExtractEmbeddedFile.

Refer to PDFDocument.EmbeddedFiles for more information on using a PDFSchema with PDF portfolio and embedded files.

Example

Java

using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Controls; 
using Leadtools.Pdf; 
using Leadtools.Svg; 
using Leadtools.WinForms; 
 
 
public static void ExtractEmbeddedFiles(string inputFileName, string outputDir) 
{ 
   // Load the source document 
   PDFDocument pdfDocument = new PDFDocument(inputFileName); 
   if (!pdfDocument.HasEmbeddedFiles) 
   { 
      Console.WriteLine("PDF does not have embedded files"); 
      // No embedded files 
      pdfDocument.Dispose(); 
      return; 
   } 
 
   // Read the attachments 
   pdfDocument.ParseDocumentStructure(PDFParseDocumentStructureOptions.EmbeddedFiles); 
 
   if (!Directory.Exists(outputDir)) 
      Directory.CreateDirectory(outputDir); 
 
   foreach (PDFEmbeddedFile embeddedFile in pdfDocument.EmbeddedFiles) 
   { 
      // Show this file information 
      Console.WriteLine($"Number:{embeddedFile.FileNumber}"); 
      Console.WriteLine($"  FileName:{embeddedFile.FileName}"); 
      Console.WriteLine($"  FileSize:{embeddedFile.FileSize}"); 
      Console.WriteLine($"  Description:{embeddedFile.Description}"); 
      Console.WriteLine($"  Created:{embeddedFile.Created}"); 
      Console.WriteLine($"  Modified:{embeddedFile.Modified}"); 
 
      // Extract this attachment to the output directory 
      // Note: FileName of an embedded file is not guaranteed to be unique, therefore, we will append 
      // the file number which is unique to the output name 
      string outputFileName = $"{embeddedFile.FileNumber}-{embeddedFile.FileName}"; 
      Console.WriteLine($"  Extracting to {outputFileName}"); 
      outputFileName = Path.Combine(outputDir, outputFileName); 
      PDFFile.ExtractEmbeddedFile(inputFileName, pdfDocument.Password, embeddedFile.FileNumber, outputFileName); 
   } 
 
   pdfDocument.Dispose(); 
}

 
import java.io.BufferedWriter; 
import java.io.Console; 
import java.io.File; 
import java.io.FileWriter; 
import java.io.IOException; 
import java.io.OutputStream; 
import java.io.OutputStreamWriter; 
import java.nio.Buffer; 
import java.nio.file.Files; 
import java.nio.file.Path; 
import java.nio.file.Paths; 
import java.nio.file.StandardOpenOption; 
import java.sql.Date; 
import java.text.SimpleDateFormat; 
import java.time.LocalDateTime; 
import java.util.ArrayList; 
import java.util.List; 
 
import javax.xml.validation.Schema; 
 
import org.apache.lucene.store.Directory; 
import org.junit.*; 
import org.junit.runner.JUnitCore; 
import org.junit.runner.Result; 
import org.junit.runner.notification.Failure; 
import static org.junit.Assert.*; 
 
import leadtools.*; 
import leadtools.barcode.*; 
import leadtools.codecs.*; 
import leadtools.pdf.*; 
import leadtools.svg.*; 
 
 
public void pdfDocumentExtractEmbeddedFilesExample() { 
   String inputFileName = "C:\\LEADTOOLS23\\Resources\\Images\\Leadtools.pdf"; 
   String outputDir = "C:\\LEADTOOLS23\\Bin"; 
   // Load the source document 
   PDFDocument pdfDocument = new PDFDocument(inputFileName); 
   if (!pdfDocument.hasEmbeddedFiles()) { 
      System.out.println("PDF does not have embedded files"); 
      // No embedded files 
      pdfDocument.dispose(); 
      return; 
   } 
 
   // Read the attachments 
   pdfDocument.parseDocumentStructure(PDFParseDocumentStructureOptions.EMBEDDED_FILES.getValue()); 
 
   File directory = new File(String.valueOf(outputDir)); 
   if (!directory.exists()) 
      directory.mkdir(); 
 
   for (PDFEmbeddedFile embeddedFile : pdfDocument.getEmbeddedFiles()) { 
      // Show this file information 
      System.out.println("Number:" + embeddedFile.getFileNumber()); 
      System.out.println("FileName:" + embeddedFile.getFileName()); 
      System.out.println("FileSize:" + embeddedFile.getFileSize()); 
      System.out.println("Description:" + embeddedFile.getDescription()); 
      System.out.println("Created:" + embeddedFile.getCreated()); 
      System.out.println("Modified:" + embeddedFile.getModified()); 
 
      // Extract this attachment to the output directory 
      // Note: FileName of an embedded file is not guaranteed to be unique, therefore, 
      // we will append 
      // the file number which is unique to the output name 
      String outputFileName = embeddedFile.getFileNumber() + "-" + embeddedFile.getFileName(); 
      System.out.println(" Extracting to " + outputFileName); 
      outputFileName = combine(outputDir, outputFileName); 
      PDFFile.extractEmbeddedFile(inputFileName, pdfDocument.getPassword(), embeddedFile.getFileNumber(), 
            outputFileName); 
   } 
 
   pdfDocument.dispose(); 
}

Requirements

Target Platforms

Reference

PDFEmbeddedFile Members

Leadtools.Pdf Namespace

Download our FREE evaluation

Help Version 23.0.2024.2.29

Leadtools.Pdf Assembly

Introduction

Getting Started

Namespaces

Leadtools.Pdf Namespace

Assemblies