PDF.co Web API – PDF To Excel API – JavaScript – Convert PDF To XLS From Uploaded File (Node.js)

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

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

Let’s review source code and it’s output first, then we’ll be analyzing source code.

Source Code

app.js

      
/*jshint esversion: 6 */

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");

// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co/documentation/api
const API_KEY = "***********************************";


// 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 XLS file name
const DestinationFile = "./result.xls";


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


function getPresignedUrl(apiKey, localFile) {
    return new Promise(resolve => {
        // Prepare request to `Get Presigned URL` API endpoint
        let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
        let reqOptions = {
            host: "api.pdf.co",
            path: encodeURI(queryPath),
            headers: { "x-api-key": API_KEY }
        };
        // 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(apiKey, 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 convertPdfToXls(apiKey, uploadedFileUrl, password, pages, destinationFile) {
    // Prepare request to `PDF To XLS` API endpoint
    var queryPath = `/v1/pdf/convert/to/xls`;

    // JSON payload for api request
    var jsonPayload = JSON.stringify({
        name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl
    });

    var reqOptions = {
        host: "api.pdf.co",
        method: "POST",
        path: queryPath,
        headers: {
            "x-api-key": API_KEY,
            "Content-Type": "application/json",
            "Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
        }
    };
    // Send request
    var postRequest = https.request(reqOptions, (response) => {
        response.on("data", (d) => {
            response.setEncoding("utf8");
            // Parse JSON response
            let data = JSON.parse(d);
            if (data.error == false) {
                // Download XLS file
                var file = fs.createWriteStream(destinationFile);
                https.get(data.url, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated XLS file saved as "${destinationFile}" file.`);
                        });
                });
            }
            else {
                // Service reported error
                console.log("readBarcodes(): " + data.message);
            }
        });
    })
        .on("error", (e) => {
            // Request error
            console.log("readBarcodes(): " + e);
        });
}

// Write request data
postRequest.write(jsonPayload);
postRequest.end();
    

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"
  }
}

    

Output

Now that we’ve reviewed the source code and its output, let’s analyze the code briefly.

Initially, we’re preparing all necessary inputs such as API key, source file location, page numbers that we want to convert, the output file path, etc. Once the code is ready, we proceed with conversion. We can logically divide the code into two parts. First, we’re uploading the file to PDF.co cloud and getting a temporary public URL and secondly, we’re performing conversion to Excel by using that URL.

In order to upload the input PDF file to PDF.co cloud, we’re first getting its pre-signed URL. The PDF.co endpoint /v1/file/upload/get-presigned-url is used to perform this task. This request primarily returns two URLs as output, pre-signed URL (data.presignedUrl) and public URL (data.url). This pre-signed URL is used to actually perform file upload to the server, whereas public URL points to the uploaded file. Please note, this public URL is temporary and only available for a few minutes.

The PDF.co endpoint /v1/pdf/convert/to/xls is used to convert PDF to XLS. Input parameters are source file URL, the number of pages that needs to be converted, the name of the file, etc. If the size of the input file is larger, then there is the possibility of time out of operation. In these cases, we can execute this request in the asynchronous mode. Please refer API documentation for more information regarding different parameters available. The output of this request contains the URL of the converted XLS file.

Please try this sample in your machine to get the most of this article. Thank you for reading!

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

• Explore Documentation
• Explore Source Code Samples
• Watch Video Course

ON-DEMAND REST WEB API

Get Your API Key

See also:

• Web API Docs
• Learn About Security
• Explore Source Code Samples