Link Search Menu Expand Document

Convert PDF To HTML From URL (Node.js) - JavaScript

PDF to HTML sample in JavaScript demonstrating ‘Convert PDF To HTML From URL (Node.js)’

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-html/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 HTML file name
const DestinationFile = "./result.html";
// Set to `true` to get simplified HTML without CSS. Default is the rich HTML keeping the document design.
const PlainHtml = false;
// Set to `true` if your document has the column layout like a newspaper.
const ColumnLayout = false;


// Prepare request to `PDF To HTML` API endpoint
var queryPath = `/v1/pdf/convert/to/html?name=${path.basename(DestinationFile)}&password=${Password}&pages=${Pages}` +
    `&simple=${PlainHtml}&columns=${ColumnLayout}&url=${SourceFileUrl}`;

// JSON payload for api request
var jsonPayload = JSON.stringify({
    name: path.basename(DestinationFile), password: Password, pages: Pages, simple: PlainHtml, columns: ColumnLayout, 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 HTML file
            var file = fs.createWriteStream(DestinationFile);
            https.get(data.url, (response2) => {
                response2.pipe(file)
                    .on("close", () => {
                        console.log(`Generated HTML 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();

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.

Get your PDF.co API key here!

Download Source Code (.zip)

return to the previous page explore PDF to HTML endpoint