Link Search Menu Expand Document

PDF Text Search from URL (Node js) - JavaScript

PDF Search Text sample in JavaScript demonstrating ‘PDF Text Search from URL (Node js)’

app.js
// `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 = "***********************************";

// Direct URL of source PDF file.
// You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/    
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://apidocs.pdf.co
var query = `https://api.pdf.co/v1/pdf/find`;
let reqOptions = {
    uri: query,
    headers: { "x-api-key": API_KEY },
    formData: {
        password: Password,
        pages: Pages,
        url: SourceFileUrl,
        searchString: SearchString,
        regexSearch: RegexSearch
    }
};

// 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"]);
    }

});

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 Search Text endpoint