Extract Images from PDF Files using a REST API in Node.js

ExtractImagesFromPDF_NodeJs.md

Learn how to extract images from PDF files using a REST API in Node.js: https://blog.groupdocs.cloud/2022/01/21/extract-images-from-pdf-files-using-node-js/(opens in a new tab)

The following topics shall be covered in this article:

1. Image Extractor REST API and Node.js SDK
2. Extract Images from PDF using a REST API in Node.js
3. Save Images by Page Numbers from PDF Documents in Node.js
4. Extract Images From Document Attached with PDF in Node.js

ExtractImagesFromPDF_NodeJs_Configurations.js

// This code example demonstrates how to add your cliend ID and Secret in the code.
global.clientId = '659fe7da-715b-4744-a0f7-cf469a392b73';
global.clientSecret = 'b377c36cfa28fa69960ebac6b6e36421';
global.myStorage = "";

const configuration = new groupdocs_parser_cloud.Configuration(clientId, clientSecret);
configuration.apiBaseUrl = "https://api.groupdocs.cloud";

ExtractImagesFromPDF_NodeJs_Download.js

// This code example demonstrates how to download images from the cloud using Node.js
// Construct necessory api instances
var folderApi = groupdocs_parser_cloud.FolderApi.fromConfig(configuration);
var fileApi = groupdocs_parser_cloud.FileApi.fromConfig(configuration);

// Get files list request
var filesListRequest = new groupdocs_parser_cloud.GetFilesListRequest("parser/images/sample_pdf/", myStorage);

// Get files list
var filesList = await folderApi.getFilesList(filesListRequest);

for (var count = 0; count < filesList.value.length; count++) {
  // Download file request
  let request = new groupdocs_parser_cloud.DownloadFileRequest(filesList.value[count].path, myStorage);

  // Download file
  let response = await fileApi.downloadFile(request);

  // Save file to the folder on disk
  fs.writeFile("C:\\Files\\parser\\images\\" + filesList.value[count].name, response, "binary", function (err) { });
  console.log(response);
}

ExtractImagesFromPDF_NodeJs_ExtractAllImages.js

// This code example demonstrates how to extract all the images from a PDF in Node.js.
//Api initialization
let parseApi = groupdocs_parser_cloud.ParseApi.fromConfig(configuration);

// Input file path
let fileInfo = new groupdocs_parser_cloud.FileInfo();
fileInfo.filePath = "sample.pdf";

// define image options
let options = new groupdocs_parser_cloud.ImagesOptions();
options.fileInfo = fileInfo;

// Image request
let request = new groupdocs_parser_cloud.ImagesRequest(options);

// Extract images
let result = await parseApi.images(request);

// Show results
let images = result.images;
images.forEach(image => {
  console.log("Image path in storage: " + image.path);
  console.log("Download url: " + image.downloadUrl);
  console.log("Image format: " + image.fileFormat + ". Page index: " + image.pageIndex);
});

ExtractImagesFromPDF_NodeJs_ExtractImagesFromAttachment.js

// This code example demonstrates how to extract images from a document attached in a PDF in Node.js.
// Api initialization
let parseApi = groupdocs_parser_cloud.ParseApi.fromConfig(configuration);

// Input file path
let fileInfo = new groupdocs_parser_cloud.FileInfo();
fileInfo.filePath = "PDF_with_Attachment.pdf";
fileInfo.password = "password";

// Define image options
let options = new groupdocs_parser_cloud.ImagesOptions();
options.fileInfo = fileInfo;

// Container item
options.ContainerItemInfo = new groupdocs_parser_cloud.ContainerItemInfo();
options.ContainerItemInfo.relativePath = "template-document.pdf";

// Image request
let request = new groupdocs_parser_cloud.ImagesRequest(options);

// Extract images
let result = await parseApi.images(request);

// Show results
let images = result.images;
images.forEach(image => {
  console.log("Image path: " + image.path);
  console.log("Image format: " + image.fileFormat + ". Page index: " + image.pageIndex);
});

ExtractImagesFromPDF_NodeJs_ExtractImagesFromPages.js

// This code example demonstrates how to extract images from specific pages of a PDF in Node.js.
//Api initialization
let parseApi = groupdocs_parser_cloud.ParseApi.fromConfig(configuration);

// Input file path
let fileInfo = new groupdocs_parser_cloud.FileInfo();
fileInfo.filePath = "sample.pdf";

// Define image options
let options = new groupdocs_parser_cloud.ImagesOptions();
options.fileInfo = fileInfo;
options.startPageNumber = 1;      // Start page number
options.countPagesToExtract = 1;  // Total pages

// Image request
let request = new groupdocs_parser_cloud.ImagesRequest(options);

// Extract images
let result = await parseApi.images(request);

// Show results
let pages = result.pages;
pages.forEach(page => {
  console.log("Page index: " + page.pageIndex);
  page.images.forEach(image => {
    console.log("Download url: " + image.downloadUrl);
    console.log("Image format: " + image.fileFormat + ". Page index: " + image.pageIndex);
  });
});

ExtractImagesFromPDF_NodeJs_Upload.js

// This code example demonstrates how to upload a PDF to the cloud in node.js 
// Construct FileApi
let fileApi = groupdocs_parser_cloud.FileApi.fromConfig(configuration);

// Input file path
let resourcesFolder = 'C:\\Files\\Parser\\sample.pdf';
fs.readFile(resourcesFolder, (err, fileStream) => {
  // Upload file request
  let request = new groupdocs_parser_cloud.UploadFileRequest("sample.pdf", fileStream, myStorage);
  // Upload file
  fileApi.uploadFile(request);
});