Link Search Menu Expand Document

Convert PDF To HTML From Uploaded File (Node.js) - Async API - JavaScript

PDF to HTML sample in JavaScript demonstrating ‘Convert PDF To HTML From Uploaded File (Node.js) - Async API’

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
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 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;


// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
    .then(([uploadUrl, uploadedFileUrl]) => {
        // 2. UPLOAD THE FILE TO CLOUD.
        uploadFile(API_KEY, SourceFile, uploadUrl)
            .then(() => {
                // 3. CONVERT UPLOADED PDF FILE TO HTML
                convertPdfToHtml(API_KEY, uploadedFileUrl, Password, Pages, PlainHtml, ColumnLayout, DestinationFile);
            })
            .catch(e => {
                console.log(e);
            });
    })
    .catch(e => {
        console.log(e);
    });


function getPresignedUrl(apiKey, localFile) {
    return new Promise(resolve => {
        // Prepare request to `Get Presigned URL` API endpoint
        let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
        let reqOptions = {
            host: "api.pdf.co",
            path: encodeURI(queryPath),
            headers: { "x-api-key": API_KEY }
        };
        // Send request
        https.get(reqOptions, (response) => {
            response.on("data", (d) => {
                let data = JSON.parse(d);
                if (data.error == false) {
                    // Return presigned url we received
                    resolve([data.presignedUrl, data.url]);
                }
                else {
                    // Service reported error
                    console.log("getPresignedUrl(): " + data.message);
                }
            });
        })
            .on("error", (e) => {
                // Request error
                console.log("getPresignedUrl(): " + e);
            });
    });
}

function uploadFile(apiKey, localFile, uploadUrl) {
    return new Promise(resolve => {
        fs.readFile(SourceFile, (err, data) => {
            request({
                method: "PUT",
                url: uploadUrl,
                body: data,
                headers: {
                    "Content-Type": "application/octet-stream"
                }
            }, (err, res, body) => {
                if (!err) {
                    resolve();
                }
                else {
                    console.log("uploadFile() request error: " + e);
                }
            });
        });
    });
}

function convertPdfToHtml(apiKey, uploadedFileUrl, password, pages, plainHtml, columnLayout, destinationFile) {
    // Prepare request to `PDF To HTML` API endpoint
    var queryPath = `/v1/pdf/convert/to/html`;

    // JSON payload for api request
    var jsonPayload = JSON.stringify({
        name: path.basename(destinationFile), password: password, pages: pages, simple: plainHtml, columns: columnLayout, url: uploadedFileUrl, async: true
    });

    var reqOptions = {
        host: "api.pdf.co",
        method: "POST",
        path: queryPath,
        headers: {
            "x-api-key": apiKey,
            "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(`Job #${data.jobId} has been created!`);

            if (data.error == false) {
                checkIfJobIsCompleted(data.jobId, data.url, destinationFile);
            }
            else {
                // Service reported error
                console.log("convertPdfToHtml(): " + data.message);
            }
        });
    })
        .on("error", (e) => {
            // Request error
            console.log("convertPdfToHtml(): " + e);
        });

    // Write request data
    postRequest.write(jsonPayload);
    postRequest.end();
}

function checkIfJobIsCompleted(jobId, resultFileUrl, destinationFile) {
    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, destinationFile); }, 3000);
            }
            else if (data.status == "success") {
                // 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}".`);
            }
        })
    });

    // 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