Link Search Menu Expand Document

PDF Text Search from Uploaded File (Node js) - JavaScript

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

app.js
/*jshint esversion: 6 */
var https = require("https");
var path = require("path");
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
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';

// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
getPresignedUrl(API_KEY, SourceFile)
    .then(([uploadUrl, uploadedFileUrl]) => {
        // 2. UPLOAD THE FILE TO CLOUD.
        uploadFile(API_KEY, SourceFile, uploadUrl)
            .then(() => {
                // 3. PDF Text Search FROM UPLOADED FILE
                pdfTextSearch(uploadedFileUrl);
            })
            .catch(e => {
                console.log(e);
            });
    })
    .catch(e => {
        console.log(e);
    });


function getPresignedUrl(apiKey, localFile) {
    return new Promise(resolve => {
        // Prepare request to `Get Presigned URL` API endpoint
        let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
        let reqOptions = {
            host: "api.pdf.co",
            path: encodeURI(queryPath),
            headers: { "x-api-key": API_KEY }
        };
        // Send request
        https.get(reqOptions, (response) => {
            response.on("data", (d) => {
                let data = JSON.parse(d);
                if (data.error == false) {
                    // Return presigned url we received
                    resolve([data.presignedUrl, data.url]);
                }
                else {
                    // Service reported error
                    console.log("getPresignedUrl(): " + data.message);
                }
            });
        })
            .on("error", (e) => {
                // Request error
                console.log("getPresignedUrl(): " + e);
            });
    });
}

function uploadFile(apiKey, localFile, uploadUrl) {
    return new Promise(resolve => {
        fs.readFile(SourceFile, (err, data) => {
            request({
                method: "PUT",
                url: uploadUrl,
                body: data,
                headers: {
                    "Content-Type": "application/octet-stream"
                }
            }, (err, res, body) => {
                if (!err) {
                    resolve();
                }
                else {
                    console.log("uploadFile() request error: " + e);
                }
            });
        });
    });
}

function pdfTextSearch(uploadedFileUrl) {
    // 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: uploadedFileUrl,
            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