PDF to excel API in JavaScript using PDF.co Web API

PDF.co Web API is the Rest API that provides set of data extraction functions, tools for documents manipulation, splitting and merging of pdf files. Includes built-in OCR, images recognition, 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 https = require("https"); var path = require("path"); var fs = require("fs"); // 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-excel/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 XLS file name const DestinationFile = "./result.xls"; /* Some of advanced options available through profiles: (JSON can be single/double-quoted and contain comments.) { "profiles": [ { "profile1": { "NumberDecimalSeparator": "", // Allows to customize decimal separator in numbers. "NumberGroupSeparator": "", // Allows to customize thousands separator. "AutoDetectNumbers": true, // Whether to detect numbers. Values: true / false "RichTextFormatting": true, // Whether to keep text style and fonts. Values: true / false "PageToWorksheet": true, // Whether to create separate worksheet for each page of PDF document. Values: true / false "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false "LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows" "ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables" "Unwrap": false, // Unwrap grouped text in table cells. Values: true / false "ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false "DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection. "CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction. "CheckPermissions": true, // Ignore document permissions. Values: true / false } } ] } */ // Sample profile that sets advanced conversion options. // Advanced options are properties of XLSExtractor class from ByteScout PDF Extractor SDK used in the back-end: // https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/2712c05b-9674-5253-df76-2a31ed055afd.htm const Profiles = '{ "profiles": [ { "profile1": { "RichTextFormatting": false, "PageToWorksheet": false } } ] }'; // Prepare request to `PDF To XLS` API endpoint var queryPath = `/v1/pdf/convert/to/xls`; // JSON payload for api request var jsonPayload = JSON.stringify({ name: path.basename(DestinationFile), password: Password, pages: Pages, url: SourceFileUrl, profiles: Profiles, 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: ${new Date().toLocaleString()}`); if (data.status == "working") { // Check again after 3 seconds setTimeout(function () { checkIfJobIsCompleted(jobId, resultFileUrl); }, 3000); } else if (data.status == "success") { // Download XLS file var file = fs.createWriteStream(DestinationFile); https.get(resultFileUrl, (response2) => { response2.pipe(file) .on("close", () => { console.log(`Generated XLS file saved as "${DestinationFile}" file.`); }); }); } 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: