Extract Text from PDF using REST API in Node.js

ExtractTextFromPDF_NodeJs.md

Learn how to extract text from PDF documents using a REST API in Node.js: https://blog.groupdocs.cloud/2021/10/25/extract-text-from-pdf-using-rest-api-in-node-js/

The following topics are covered here:

1. Extract Text from PDF using a REST API in Node.js
2. Get Text by Page Numbers from PDF Documents using Node.js
3. Extract Text From Document Attached with PDF using Node.js

ExtractTextFromPDF_NodeJs_Configurations.js

global.clientId = "112f0f38-9dae-42d5-b4fc-cc84ae644972";
global.clientSecret = "16ad3fe0bdc39c910f57d2fd48a5d618";
global.myStorage = "";

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

ExtractTextFromPDF_NodeJs_ExtractText.js

// Api initialization
let parseApi = groupdocs_parser_cloud.ParseApi.fromConfig(configuration);

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

// Define text options
let options = new groupdocs_parser_cloud.TextOptions();
options.fileInfo = fileInfo;

// Create text request
let request = new groupdocs_parser_cloud.TextRequest(options);

// Extract text
let result = await parseApi.text(request);
console.log(result.text);

ExtractTextFromPDF_NodeJs_ExtractTextByPageNo.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 text options
let options = new groupdocs_parser_cloud.TextOptions();
options.fileInfo = fileInfo;
options.startPageNumber = 0;
options.countPagesToExtract = 1;

// Create text request
let request = new groupdocs_parser_cloud.TextRequest(options);

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

// Show results
let pages = result.pages;
pages.forEach(page => console.log("Page No: " + page.pageIndex + 1 + " - " + page.text));

ExtractTextFromPDF_NodeJs_ExtractTextFromAttachment.js

// Api initialization
let parseApi = groupdocs_parser_cloud.ParseApi.fromConfig(configuration);

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

// Input container item
let containerInfo = new groupdocs_parser_cloud.ContainerItemInfo();
containerInfo.relativePath = "template-document.pdf";

// Define text options
let options = new groupdocs_parser_cloud.TextOptions();
options.fileInfo = fileInfo;
options.containerItemInfo = containerInfo;

// Create text request
let request = new groupdocs_parser_cloud.TextRequest(options);

// Extract text
let result = await parseApi.text(request);
console.log(result.text);

ExtractTextFromPDF_NodeJs_Upload.js

// Construct FileApi
let fileApi = groupdocs_parser_cloud.FileApi.fromConfig(configuration);
let filePath = 'C:\\Files\\Parser\\sample.pdf';

fs.readFile(filePath, (err, fileStream) => {
  // Create file upload request
  let request = new groupdocs_parser_cloud.UploadFileRequest("sample.pdf", fileStream, myStorage);
  // Upload file
  fileApi.uploadFile(request);
});