Convert PDF To XLSX From URL (Node.js) - Async API - JavaScript
PDF To XLSX sample in JavaScript demonstrating ‘Convert PDF To XLSX From URL (Node.js) - Async API’
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
const API_KEY = "***********************************";
// Direct URL of source PDF file.
// You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/
const SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-excel/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 XLSX file name
const DestinationFile = "./result.xlsx";
// Prepare request to `PDF To XLSX` API endpoint
var queryPath = `/v1/pdf/convert/to/xlsx`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(DestinationFile), password: Password, pages: Pages, url: SourceFileUrl, async: true
});
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) {
console.log(`Job #${data.jobId} has been created!`);
checkIfJobIsCompleted(data.jobId, data.url);
}
else {
// Service reported error
console.log(data.message);
}
});
}).on("error", (e) => {
// Request error
console.log(e);
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
function checkIfJobIsCompleted(jobId, resultFileUrl) {
let queryPath = `/v1/job/check`;
// JSON payload for api request
let jsonPayload = JSON.stringify({
jobid: jobId
});
let reqOptions = {
host: "api.pdf.co",
path: queryPath,
method: "POST",
headers: {
"x-api-key": API_KEY,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
console.log(`Checking Job #${jobId}, Status: ${data.status}, Time: ${new Date().toLocaleString()}`);
if (data.status == "working") {
// Check again after 3 seconds
setTimeout(function () { checkIfJobIsCompleted(jobId, resultFileUrl); }, 3000);
}
else if (data.status == "success") {
// Download XLSX file
var file = fs.createWriteStream(DestinationFile);
https.get(resultFileUrl, (response2) => {
response2.pipe(file)
.on("close", () => {
console.log(`Generated XLSX file saved as "${DestinationFile}" file.`);
});
});
}
else {
console.log(`Operation ended with status: "${data.status}".`);
}
})
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
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.
Download Source Code (.zip)
return to the previous page explore PDF To XLSX endpoint
Copyright © 2016 - 2024 PDF.co