Link Search Menu Expand Document

Make Searchable PDF From Uploaded File (Node.js) - JavaScript

PDF Make Text Searchable or Unsearchable sample in JavaScript demonstrating ‘Make Searchable PDF From Uploaded File (Node.js)’

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 = "";
// OCR language. "eng", "fra", "deu", "spa"  supported currently. Let us know if you need more.
const Language = "eng";
// Destination PDF file name
const DestinationFile = "./result.pdf";


// 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. MAKE UPLOADED PDF FILE SEARCHABLE
                makePdfSearchable(API_KEY, uploadedFileUrl, Password, Pages, Language, 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 makePdfSearchable(apiKey, uploadedFileUrl, password, pages, language, destinationFile) {
    // Prepare request to `Make Searchable PDF` API endpoint
    var queryPath = `/v1/pdf/makesearchable`;

    // JSON payload for api request
    var jsonPayload = JSON.stringify({
        name: path.basename(destinationFile), password: password, pages: pages, lang: language, url: uploadedFileUrl
    });

    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);
            if (data.error == false) {
                // Download PDF file
                var file = fs.createWriteStream(destinationFile);
                https.get(data.url, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated PDF file saved as "${destinationFile}" file.`);
                        });
                });
            }
            else {
                // Service reported error
                console.log("readBarcodes(): " + data.message);
            }
        });
    })
        .on("error", (e) => {
            // Request error
            console.log("readBarcodes(): " + 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 Make Text Searchable or Unsearchable endpoint