ByteScout Cloud API Server – PDF Text Search API – JavaScript – PDF Text Search from URL (Node js) – Async API

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

      
// Please NOTE: In this sample we're assuming Cloud Api Server is hosted at "https://localhost". 
// If it's not then please replace this with with your hosting url.

var https = require("https");

// Use "npm install request" command to install.
var request = require("request");

// 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 = "";

// Search string. 
const SearchString = '[4-9][0-9].[0-9][0-9]'; // Regular expression to find numbers in format dd.dd and between 40.00 to 99.99

// Enable regular expressions (Regex) 
const RegexSearch = true;

// Prepare URL for PDF text search API call.
var queryPath = `/pdf/find?password=${Password}&pages=${Pages}&url=${SourceFileUrl}&searchString=${SearchString}&regexSearch=${RegexSearch}&async=True`;

var reqOptions = {
    host: "localhost",
    path: encodeURI(queryPath)
};

// Send request
https.get(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!`);
            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 = `/job/check?jobid=${jobId}`;
    let reqOptions = {
        host: "localhost",
        path: encodeURI(queryPath),
        method: "GET"
    };

    https.get(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") {
                request({ method: 'GET', uri: resultFileUrl, gzip: true },
                    function (error, response, body) {

                        // Parse JSON response
                        let respJsonFileArray = JSON.parse(body);

                        respJsonFileArray.forEach((element) => {
                            console.log("Found text " + element["text"] + " at coordinates " + element["left"] + ", " + element["top"]);
                        }, this);
                    });
            }
            else {
                console.log(`Operation ended with status: "${data.status}".`);
            }
        })
    });
}
    

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"
  }
}

    

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

• Explore Documentation
• Explore Source Code Samples
• Watch Video Course

ON-DEMAND REST WEB API

Get Your API Key

See also:

• Web API Docs
• Learn About Security
• Explore Source Code Samples