How to Extract Text from PowerPoint PPT/PPTX in Node.js

Extract_All_Text_from_PowerPoint_PPT_PPTX_using_NodeJs_Parser.js

// How to Extract All Text from PowerPoint PPT/PPTX in Node.js using REST API
const parse = async () => {
  global.parseApi = groupdocs_parser_cloud.ParseApi.fromKeys(clientId, clientSecret);

  let fileInfo = new groupdocs_parser_cloud.FileInfo();
  fileInfo.filePath = "nodejs-testing/sample-file.pptx";

  let options = new groupdocs_parser_cloud.TextOptions();
  options.fileInfo = fileInfo;

  let formattedTextOptions = new groupdocs_parser_cloud.FormattedTextOptions();
  formattedTextOptions.mode = "PlainText";
  options.formattedTextOptions = formattedTextOptions;

  try {
    // Create parse document request
    let request = new groupdocs_parser_cloud.TextRequest(options);
    let response = await parseApi.text(request);
    // Display results
    console.log(response.text);
  }
  catch (err) {
    throw err;
  }
}

parse()
.then(() => {
  console.log("Successfully extracted text from PowerPoint PPTX document.");
})
.catch((err) => {
  console.log("Error occurred while extracting text from PowerPoint PPTX file:", err);
})

Extract_Specific_Text_from_PowerPoint_using_NodeJs_Parser.js

// How to Extract Text from PowerPoint PPT by Page Number Range in Node.js
const parse = async () => {
  global.parseApi = groupdocs_parser_cloud.ParseApi.fromKeys(clientId, clientSecret);

  let fileInfo = new groupdocs_parser_cloud.FileInfo();
  fileInfo.filePath = "nodejs-testing/sample-file.pptx";

  let options = new groupdocs_parser_cloud.TextOptions();
  options.fileInfo = fileInfo;
  options.startPageNumber = 0;
  options.countPagesToExtract = 2;

  let formattedTextOptions = new groupdocs_parser_cloud.FormattedTextOptions();
  formattedTextOptions.mode = "PlainText";
  options.formattedTextOptions = formattedTextOptions;

  try {
    // Create parse document request
    let request = new groupdocs_parser_cloud.TextRequest(options);
    let response = await parseApi.text(request);
    // Display results
    let pages = response.pages;
    pages.forEach(page => console.log("Page No: " + page.pageIndex + " - " + page.text));
  }
  catch (err) {
    throw err;
  }
}

parse()
.then(() => {
  console.log("Successfully extracted text from PowerPoint Presentation.");
})
.catch((err) => {
  console.log("Error occurred while extracting text from PowerPoint file:", err);
})

How_to_Extract_Text_from_PowerPoint_PPT_in_NodeJs.md

You can extract Text from PowerPoint programmatically on the cloud. In this article, we will learn how to extract Text from PowerPoint PPT/PPTX in Node.js.

The following topics are covered in this article:

1. Node.js Library to Extract Text from PowerPoint PPT
2. Extract All Text from PowerPoint PPT/PPTX in Node.js using REST API
3. Extract Text from PowerPoint PPT by Page Number Range in Node.js

Upload_to_Extract_Text_from_PPT_using_NodeJs_Parser.js

// open file in IOStream from your system drive.
var resourcesFolder = 'H:\\groupdocs-cloud-data\\sample-file.pptx';
// read file
fs.readFile(resourcesFolder, (err, fileStream) => {
  // construct FileApi
  var fileApi = groupdocs_parser_cloud.FileApi.fromConfig(config);
  // create upload file request
  var request = new groupdocs_parser_cloud.UploadFileRequest("sample-file.pptx", fileStream, myStorage);
  // upload file
  fileApi.uploadFile(request)
    .then(function (response) {
      console.log("Expected response type is FilesUploadResult: " + response.uploaded.length);
    })
    .catch(function (error) {
      console.log("Error: " + error.message);
    });
});

Utils_to_Extract_Text_from_PowerPoint_using_NodeJs_Parser.js

# Import Node.js SDK in your node application from http://api.groupdocs.cloud
global.groupdocs_parser_cloud = require("groupdocs-parser-cloud");
global.fs = require("fs");

// get clientId and clientSecret from https://dashboard.groupdocs.cloud (free registration is required).
global.clientId = "xxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx";
global.clientSecret = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx";
global.myStorage = "test-internal-storage";
const config = new groupdocs_parser_cloud.Configuration(clientId, clientSecret);
config.apiBaseUrl = "https://api.groupdocs.cloud";