PDF to text API in JavaScript with PDF.co Web API

What is PDF.co Web API? It is the Rest API that provides set of data extraction functions, tools for documents manipulation, splitting and merging of pdf files. Includes built-in OCR, images recognition, can generate and read barcodes from images, scans and pdf.

On-demand (REST Web API) version:
 Web API (on-demand version)

On-premise offline SDK for Windows:
 60 Day Free Trial (on-premise)

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/documentation/api
const API_KEY = "***********************************";

// Direct URL of source PDF file.
const SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/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 TXT file name
const DestinationFile = "./result.txt";

/*
Some of advanced options available through profiles:
(JSON can be single/double-quoted and contain comments.)
{
    "profiles": [
        {
            "profile1": {                
                "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
                "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
                "ExtractAnnotations": true, // Whether to extract PDF annotations.
                "CheckPermissions": true, // Ignore document permissions. Values: true / false
                "DetectNewColumnBySpacesRatio": 1.2, // A ratio affecting number of spaces between words. 
            }
        }
    ]
}
*/

// Sample profile that sets advanced conversion options
// Advanced options are properties of TextExtractor class from ByteScout Text Extractor SDK used in the back-end:
// https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/8a2bae5a-346f-8338-b5aa-6f3522dca0d4.htm
const Profiles = '{ "profiles": [ { "profile1": { "TrimSpaces": "False", "PreserveFormattingOnTextExtraction": "True", "Unwrap": "True" } } ] }';

// Prepare request to `PDF To Text` API endpoint
var queryPath = `/v1/pdf/convert/to/text`;

// JSON payload for api request
var jsonPayload = JSON.stringify({
    name: path.basename(DestinationFile), password: Password, pages: Pages, url: SourceFileUrl, profiles: Profiles, 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!`);

            // Process returned job
            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 TXT file
                var file = fs.createWriteStream(DestinationFile);
                https.get(resultFileUrl, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated TXT file saved as "${DestinationFile}" file.`);
                        });
                });
            }
            else {
                console.log(`Operation ended with status: "${data.status}".`);
            }
        })
    });

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

package.json

      
{
  "name": "test",
  "version": "1.0.0",
  "description": "PDF.co",
  "main": "app.js",
  "scripts": {
  },
  "keywords": [
    "pdf.co",
    "web",
    "api",
    "bytescout",
    "api"
  ],
  "author": "ByteScout & PDF.co",
  "license": "ISC",
  "dependencies": {
    "request": "^2.88.2"
  }
}

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

ON-DEMAND REST WEB API

Get Your API Key

See also: