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

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

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

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

How to convert PDF to JSON from uploaded file (node for PDF to JSON API in JavaScript: Step By Step Instructions

This page displays the step-by-step instructions and algorithm of how to convert PDF to JSON from uploaded file (node and how to apply it in your application. PDF to JSON API in JavaScript can be applied with ByteScout Cloud API Server. 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. For implementation of this functionality, please copy and paste the code below into your app using code editor. Then compile and run your app. Want to see how it works with your data then code testing will allow the function to be tested and work properly.

Trial version of ByteScout is available for free download from our website. This and other source code samples for JavaScript and other programming languages are available.

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 JSON file name
const DestinationFile = "./result.json";


// 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 JSON
        convertPdfToJson(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 convertPdfToJson(uploadedFileUrl, password, pages, destinationFile) {
    // Prepare request to `PDF To JSON` API endpoint
    var queryPath = `/pdf/convert/to/json?name=${path.basename(destinationFile)}&password=${password}&pages=${pages}&url=${uploadedFileUrl}`;
    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) {
                // Download JSON file
                var file = fs.createWriteStream(destinationFile);
                https.get(data.url, (response2) => {
                    response2.pipe(file)
                    .on("close", () => {
                        console.log(`Generated JSON file saved as "${destinationFile}" file.`);
                    });
                });
            }
            else {
                // Service reported error
                console.log("convertPdfToJson(): " + data.message);
            }
        });
    })
    .on("error", (e) => {
        // Request error
        console.log("convertPdfToJson(): " + e);
    });
}

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"
  }
}