Link Search Menu Expand Document

Convert PDF To CSV From Uploaded File (Node.js) - JavaScript

PDF To CSV sample in JavaScript demonstrating ‘Convert PDF To CSV 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 PDF file
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 = "";
// Destination CSV file name
const DestinationFile = "./result.csv";


// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
    .then(([uploadUrl, uploadedFileUrl]) => {
        // 2. UPLOAD THE FILE TO CLOUD.
        uploadFile(API_KEY, SourceFile, uploadUrl)
            .then(() => {
                // 3. CONVERT UPLOADED PDF FILE TO CSV
                convertPdfToCsv(API_KEY, uploadedFileUrl, Password, Pages, DestinationFile);
            })
            .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?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.setEncoding('utf8');

            // Build response body in a string
            let resBody = '';
    
            // Listen for data and add
            response.on('data', function (chunk) {
                resBody += chunk
            });
    
            response.on("end", () => {
                let data = JSON.parse(resBody);
                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,
            }, (err, res, body) => {
                if (!err) {
                    resolve();
                }
                else {
                    console.log("uploadFile() request error: " + e);
                }
            });
        });
    });
}

function convertPdfToCsv(apiKey, uploadedFileUrl, password, pages, destinationFile) {
    // Prepare request to `PDF To CSV` API endpoint
    const queryPath = `/v1/pdf/convert/to/csv`;

    // JSON payload for api request
    const jsonPayload = JSON.stringify({
        name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl
    });

    const reqOptions = {
        host: "api.pdf.co",
        method: "POST",
        path: queryPath,
        headers: {
            "x-api-key": apiKey,
            "Content-Type": "application/json",
            "Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
        }
    };
    // Send request
    const postRequest = https.request(reqOptions, (response) => {

        response.setEncoding('utf8');

        // Build response body in a string
        let resBody = '';

        // Listen for data and add
        response.on('data', function (chunk) {
            resBody += chunk
        });

        response.on("end", () => {
            // Parse JSON response
            const data = JSON.parse(resBody);
            if (data.error == false) {
                // Download CSV file
                var file = fs.createWriteStream(destinationFile);
                https.get(data.url, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated CSV file saved as "${destinationFile}" file.`);
                        });
                });
            }
            else {
                // Service reported error
                console.log("convertPdfToCsv(): " + data.message);
            }
        });
    })
        .on("error", (e) => {
            // Request error
            console.log("convertPdfToCsv(): " + e);
        });

    // Write request data
    postRequest.write(jsonPayload);
    postRequest.end();
}


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 To CSV endpoint