PDF.co Web API – PDF To HTML API – JavaScript – Convert PDF To HTML From URL (Node.js) – Async API

PDF.co Web API – PDF To HTML API – JavaScript – Convert PDF To HTML From URL (Node.js) – Async API

ConvertPdfToHtmlFromUrl.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://s3-us-west-2.amazonaws.com/bytescout-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}&async=True`;
var reqOptions = {
    host: "api.pdf.co",
    path: encodeURI(queryPath),
    headers: {
        "x-api-key": API_KEY
    }
};
// Send request
https.get(reqOptions, (response) => {
    response.on("data", (d) => {
        // Parse JSON response
        var data = JSON.parse(d);        
        if (data.error == false) {
            // Process returned job
            checkIfJobIsCompleted(data.jobId, data.url);
        }
        else {
            // Service reported error
            console.log(data.message);
        }
    });
}).on("error", (e) => {
    // Request error
    console.log(e);
});

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);
            if (data.Status == "InProgress") {
                // Check again after 2 seconds
                setTimeout((jobId, resultFileUrl) => {
                    checkIfJobIsCompleted(jobId, resultFileUrl);
                }, 2000);
            }
            else if (data.Status == "Finished") {
                // Download HTML file
                var file = fs.createWriteStream(DestinationFile);
                https.get(resultFileUrl, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated HTML file saved as "${DestinationFile}" file.`);
                        });
                });
            }
            else {
                console.log(`Operation ended with status: "${data.Status}".`);
            }
        })
    });
}

  Click here to get your Free Trial version of the SDK