(Node.js) 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.

Install Chilkat for Node.js and Electron using npm at Chilkat npm packages for Node.js Chilkat npm packages for Electron on Windows, Linux, MacOSX, and ARM

var os = require('os');
if (os.platform() == 'win32') {  
    if (os.arch() == 'ia32') {
        var chilkat = require('@chilkat/ck-node21-win-ia32');
    } else {
        var chilkat = require('@chilkat/ck-node21-win64'); 
    }
} else if (os.platform() == 'linux') {
    if (os.arch() == 'arm') {
        var chilkat = require('@chilkat/ck-node21-arm');
    } else if (os.arch() == 'x86') {
        var chilkat = require('@chilkat/ck-node21-linux32');
    } else {
        var chilkat = require('@chilkat/ck-node21-linux64');
    }
} else if (os.platform() == 'darwin') {
    if (os.arch() == 'arm64') {
        var chilkat = require('@chilkat/ck-node21-mac-m1');
    } else {
        var chilkat = require('@chilkat/ck-node21-macosx');
    }
}

function chilkatExample() {

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

    var pdf = new chilkat.Pdf();

    var success = pdf.LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf");
    if (success == false) {
        console.log(pdf.LastErrorText);
        return;
    }

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

    // How many embedded files exist within the opened PDF?
    var numFiles = pdf.NumEmbeddedFiles;
    console.log("Number of embedded files: " + numFiles);

    var json = new chilkat.JsonObject();
    json.EmitCompact = false;

    var bd = new chilkat.BinData();

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

        success = pdf.GetEmbeddedFileInfo(i,json);
        if (success == false) {
            console.log(pdf.LastErrorText);
            return;
        }

        console.log(json.Emit());

        // Get the filename from the JSON.
        var 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) {
            console.log(pdf.LastErrorText);
            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) {
            console.log("Failed to write output file.");
        }

        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'"
    // }

}

chilkatExample();