How to convert PDF to XML from file (node for PDF to XML API in JavaScript and PDF.co Web API

What is PDF.co Web API? It is the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.

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 */ 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 XML file name const DestinationFile = "./result.xml"; // Prepare request uri for `PDF To XML` API endpoint var query = `https://api.pdf.co/v1/pdf/convert/to/xml`; let reqOptions = { uri: query, headers: { "x-api-key": API_KEY }, formData: { name: path.basename(DestinationFile), password: Password, pages: Pages, async: 'True', file: fs.createReadStream(SourceFile) }, }; // Send request request.post(reqOptions, function (error, response, body) { if (error) { return console.error("Error: ", error); } // Parse JSON response let data = JSON.parse(body); console.log(`Job #${data.jobId} has been created!`); checkIfJobIsCompleted(data.jobId, data.url); }); function checkIfJobIsCompleted(jobId, resultFileUrl) { let queryPath = `/v1/job/check?jobid=${jobId}`; let reqOptions = { host: "api.pdf.co", path: encodeURI(queryPath), method: "GET", headers: { "x-api-key": API_KEY } }; 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: ${new Date().toLocaleString()}`); if (data.status == "working") { // Check again after 3 seconds setTimeout(function(){ checkIfJobIsCompleted(jobId, resultFileUrl); }, 3000); } else if (data.status == "success") { // Download XML file var file = fs.createWriteStream(DestinationFile); https.get(resultFileUrl, (response2) => { response2.pipe(file) .on("close", () => { console.log(`Generated XML file saved as "${DestinationFile}" file.`); }); }); } else { console.log(`Operation ended with status: "${data.status}".`); } }) }); }

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" } }

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

ON-DEMAND REST WEB API

Get Your API Key

See also:

Related Samples: