PDF.co Web API - PDF Text Search API - JavaScript - PDF Text Search from File (Node js)

printable version:
PDF-co-Web-API-JavaScript-PDF-Text-Search-from-File-(Node-js).pdf

How to PDF Text Search API in JavaScript and PDF.co Web API

PDF.co Web API is the Rest API that provides a set of data extraction functions, tools for documents manipulation, splitting and merging of PDF files. Includes built-in OCR, images recognition, it 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 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/documentation/api
const API_KEY = "***********************************";

// Source file name
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 = "";

// 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 query = `https://api.pdf.co/v1/pdf/find`;
let reqOptions = {
    uri: query,
    headers: { "x-api-key": API_KEY },
    formData: {
        password: Password,
        pages: Pages,
        searchString: SearchString,
        regexSearch: RegexSearch,
        file: fs.createReadStream(SourceFile)
    }
};

// Send request
request.post(reqOptions, function (error, response, body) {
    if (error) {
        return console.error("Error: ", error);
    }

    // Parse JSON response
    let data = JSON.parse(body);
    for (let index = 0; index < data.body.length; index++) {
        const element = data.body[index];
        console.log("Found text " + element["text"] + " at coordinates " + element["left"] + ", " + element["top"]);
    }
});

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"
  }
}