ByteScout Cloud API Server – PDF To Text API – JavaScript – Convert PDF To Text From Uploaded File (Node.js) – Async API

Home
/
Articles
/
ByteScout Cloud API Server – PDF To Text API – JavaScript – Convert PDF To Text From Uploaded File (Node.js) – Async API

printable version:
ByteScout-Cloud-API-Server-JavaScript-Convert-PDF-To-Text-From-Uploaded-File-(Node-js)-Async-API.pdf

How to convert PDF to text from uploaded file (node for PDF to text API in JavaScript with ByteScout Cloud API Server

Learn in simple ways: How to convert PDF to text from uploaded file (node for PDF to text API in JavaScript

This page displays the code samples for programming in JavaScript. ByteScout Cloud API Server was designed to assist PDF to text API in JavaScript. ByteScout Cloud API Server is the ready to deploy Web API Server that can be deployed in less than thirty minutes into your own in-house Windows server (no Internet connnection is required to process data!) or into private cloud server. Can store data on in-house local server based storage or in Amazon AWS S3 bucket. Processing data solely on the server using built-in ByteScout powered engine, no cloud services are used to process your data!.

Use the code displayed below in your application to save a lot of time on writing and testing code. Open your JavaScript project and simply copy & paste the code and then run your app! Check JavaScript sample code examples to see if they respond to your needs and requirements for the project.

Our website provides free trial version of ByteScout Cloud API Server that gives source code samples to assist with your JavaScript project.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

app.js

      /*jshint esversion: 6 */

// Please NOTE: In this sample we're assuming Cloud Api Server is hosted at "https://localhost". 
// If it's not then please replace this with with your hosting url.

var https = require("https");
var path = require("path");
var fs = require("fs");

// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");

// Source PDF file
const SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const Pages = "";
// PDF document password. Leave empty for unprotected documents.
const Password = "";
// Destination TXT file name
const DestinationFile = "./result.txt";

// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(SourceFile)
    .then(([uploadUrl, uploadedFileUrl]) => {
        // 2. UPLOAD THE FILE TO CLOUD.
        uploadFile(SourceFile, uploadUrl)
            .then(() => {
                // 3. CONVERT UPLOADED PDF FILE TO TEXT
                convertPdfToText(uploadedFileUrl, Password, Pages, DestinationFile);
            })
            .catch(e => {
                console.log(e);
            });
    })
    .catch(e => {
        console.log(e);
    });


function getPresignedUrl(localFile) {
    return new Promise(resolve => {
        // Prepare request to `Get Presigned URL` API endpoint
        let queryPath = `/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
        let reqOptions = {
            host: "localhost",
            path: encodeURI(queryPath)
        };
        // Send request
        https.get(reqOptions, (response) => {
            response.on("data", (d) => {
                let data = JSON.parse(d);
                if (data.error == false) {
                    // Return presigned url we received
                    resolve([data.presignedUrl, data.url]);
                }
                else {
                    // Service reported error
                    console.log("getPresignedUrl(): " + data.message);
                }
            });
        })
            .on("error", (e) => {
                // Request error
                console.log("getPresignedUrl(): " + e);
            });
    });
}

function uploadFile(localFile, uploadUrl) {
    return new Promise(resolve => {
        fs.readFile(SourceFile, (err, data) => {
            request({
                method: "PUT",
                url: uploadUrl,
                body: data,
                headers: {
                    "Content-Type": "application/octet-stream"
                }
            }, (err, res, body) => {
                if (!err) {
                    resolve();
                }
                else {
                    console.log("uploadFile() request error: " + e);
                }
            });
        });
    });
}


function convertPdfToText(uploadedFileUrl, password, pages, destinationFile) {
    // Prepare request to `PDF To Text` API endpoint
    var queryPath = `/pdf/convert/to/text?name=${path.basename(destinationFile)}&password=${password}&pages=${pages}&url=${uploadedFileUrl}&async=True`;
    let reqOptions = {
        host: "localhost",
        path: encodeURI(queryPath),
        method: "GET" 
    };
    // Send request
    https.get(reqOptions, (response) => {
        response.on("data", (d) => {
            response.setEncoding("utf8");

            // Parse JSON response
            let data = JSON.parse(d);

            if (data.error == false) {
                console.log(`Job #${data.jobId} has been created!`);

                // Process returned job
                checkIfJobIsCompleted(data.jobId, data.url, destinationFile)
            }
            else {
                // Service reported error
                console.log("convertPdfToText(): " + data.message);
            }
        });
    })
        .on("error", (e) => {
            // Request error
            console.log("convertPdfToText(): " + e);
        });
}

function checkIfJobIsCompleted(jobId, resultFileUrl, destinationFile) {
    let queryPath = `/job/check?jobid=${jobId}`;
    let reqOptions = {
        host: "localhost",
        path: encodeURI(queryPath),
        method: "GET" 
    };

    https.get(reqOptions, (response) => {
        response.on("data", (d) => {
            response.setEncoding("utf8");

            // Parse JSON response
            let data = JSON.parse(d);
            console.log(`Checking Job #${jobId}, Status: ${data.status}, Time: ${new Date().toLocaleString()}`);

            if (data.status == "working") {
                // Check again after 3 seconds
                setTimeout(function(){
                    checkIfJobIsCompleted(jobId, resultFileUrl, destinationFile);
                }, 3000);
            }
            else if (data.status == "success") {
                // Download TXT file
                var file = fs.createWriteStream(destinationFile);
                https.get(resultFileUrl, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated TXT file saved as "${destinationFile}" file.`);
                        });
                });
            }
            else {
                console.log(`Operation ended with status: "${data.status}".`);
            }
        })
    });
}

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Cloud API Server Home Page

Explore ByteScout Cloud API Server Documentation

Explore Samples

Sign Up for ByteScout Cloud API Server Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

package.json

      {
  "name": "test",
  "version": "1.0.0",
  "description": "PDF.co",
  "main": "app.js",
  "scripts": {
  },
  "keywords": [
    "pdf.co",
    "web",
    "api",
    "bytescout",
    "api"
  ],
  "author": "ByteScout & PDF.co",
  "license": "ISC",
  "dependencies": {
    "request": "^2.88.2"
  }
}