PDF.co Web API - PDF To XML API - JavaScript - Convert PDF To XML From URL (Node.js)

printable version:
PDF-co-Web-API-JavaScript-Convert-PDF-To-XML-From-URL-(Node-js).pdf

How to convert PDF to XML from URL (node for PDF to XML API in JavaScript with PDF.co Web API

PDF.co Web API: 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

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


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


// Direct URL of source PDF file.
const SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-xml/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 to `PDF To XML` API endpoint
var queryPath = `/v1/pdf/convert/to/xml`;

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

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) => {
        // Parse JSON response
        var data = JSON.parse(d);        
        if (data.error == false) {
            // Download XML file
            var file = fs.createWriteStream(DestinationFile);
            https.get(data.url, (response2) => {
                response2.pipe(file)
                .on("close", () => {
                    console.log(`Generated XML file saved as "${DestinationFile}" file.`);
                });
            });
        }
        else {
            // Service reported error
            console.log(data.message);
        }
    });
}).on("error", (e) => {
    // Request error
    console.log(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"
  }
}