How to PDF text search API in JavaScript using PDF.co Web API

What is PDF.co Web API? It is the flexible Web API that includes full set of functions from e-signature requests to data extraction, OCR, images recognition, pdf splitting and pdf splitting. Can also generate barcodes 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"); // 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/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 = ""; // 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. // See documentation: https://app.pdf.co/documentation/api/1.0/pdf/find.html var queryPath = `/v1/pdf/find`; // JSON payload for api request var jsonPayload = JSON.stringify({ password: Password, pages: Pages, url: SourceFileUrl, searchString: SearchString, regexSearch: RegexSearch, 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 #${data.jobId} has been created!`); checkIfJobIsCompleted(data.jobId, data.url); } else { // Service reported error console.log(data.message); } }); }).on("error", (e) => { // Request error console.log(e); }); // Write request data postRequest.write(jsonPayload); postRequest.end(); function checkIfJobIsCompleted(jobId, resultFileUrl) { let queryPath = `/v1/job/check`; // JSON payload for api request let jsonPayload = JSON.stringify({ jobid: jobId }); let reqOptions = { host: "api.pdf.co", path: queryPath, method: "POST", headers: { "x-api-key": API_KEY, "Content-Type": "application/json", "Content-Length": Buffer.byteLength(jsonPayload, 'utf8') } }; // Send request var postRequest = https.request(reqOptions, (response) => { response.on("data", (d) => { response.setEncoding("utf8"); // Parse JSON response let data = JSON.parse(d); console.log(`Checking Job #${jobId}, Status: ${data.status}, Time: ${new Date().toLocaleString()}`); if (data.status == "working") { // Check again after 3 seconds setTimeout(function () { checkIfJobIsCompleted(jobId, resultFileUrl); }, 3000); } else if (data.status == "success") { request({ method: 'GET', uri: resultFileUrl, gzip: true }, function (error, response, body) { // Parse JSON response let respJsonFileArray = JSON.parse(body); respJsonFileArray.forEach((element) => { console.log("Found text " + element["text"] + " at coordinates " + element["left"] + ", " + element["top"]); }, this); }); } else { console.log(`Operation ended with status: "${data.status}".`); } }) }); // 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:

Related Samples: