C++

Extract Embedded Files from PDF

Demonstrates how to get information about the embedded files (if any) contained within a PDF, and shows how to extract each file.

Note: This example requires Chilkat v9.5.0.95 or greater.

C++

#include <CkPdf.h>
#include <CkJsonObject.h>
#include <CkBinData.h>

void ChilkatSample(void)
    {
    bool success = false;

    //  This example requires the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    CkPdf pdf;

    success = pdf.LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf");
    if (success == false) {
        std::cout << pdf.lastErrorText() << "\r\n";
        return;
    }

    //  Note: The embedded file functionality was added in Chilkat v9.5.0.95

    //  How many embedded files exist within the opened PDF?
    int numFiles = pdf.get_NumEmbeddedFiles();
    std::cout << "Number of embedded files: " << numFiles << "\r\n";

    CkJsonObject json;
    json.put_EmitCompact(false);

    CkBinData bd;

    //  Get information about each file, and extract each to the filesystem.
    int i = 0;
    while (i < numFiles) {

        success = pdf.GetEmbeddedFileInfo(i,json);
        if (success == false) {
            std::cout << pdf.lastErrorText() << "\r\n";
            return;
        }

        std::cout << json.emit() << "\r\n";

        //  Get the filename from the JSON.
        const char *filename = "someFile.dat";

        //  The filename SHOULD always be present..
        if (json.HasMember("filename") == true) {
            filename = json.stringOf("filename");
        }

        //  Get the file data.
        success = pdf.GetEmbeddedFileBd(i,bd);
        if (success == false) {
            std::cout << pdf.lastErrorText() << "\r\n";
            return;
        }

        //  Save the contents of the bd to the filename (in the current working directory) in the filesystem.
        success = bd.WriteFile(filename);
        if (success == false) {
            std::cout << "Failed to write output file." << "\r\n";
        }

        i = i + 1;
    }

    //  Sample output for the above code:

    //  Number of embedded files: 3
    //  {
    //    "filename": "employees.json",
    //    "desc": "JSON",
    //    "subType": "application/json",
    //    "size": 159,
    //    "creationDate": "D:20230715170506-05'00'",
    //    "modDate": "D:20160207153838-05'00'"
    //  }
    //  
    //  {
    //    "filename": "rsaPubKey.pem",
    //    "desc": "RSA Public Key PEM",
    //    "size": 451,
    //    "creationDate": "D:20230715170546-05'00'",
    //    "modDate": "D:20150724133153-05'00'"
    //  }
    //  
    //  {
    //    "filename": "starfish.jpg",
    //    "desc": "Starfish JPG",
    //    "subType": "image/jpeg",
    //    "size": 6229,
    //    "creationDate": "D:20230715170356-05'00'",
    //    "modDate": "D:20080529103055-05'00'"
    //  }
    }