ByteScout Cloud API Server - Document Parser API - PHP - Parse with OCR - ByteScout

ByteScout Cloud API Server – Document Parser API – PHP – Parse with OCR

  • Home
  • /
  • Articles
  • /
  • ByteScout Cloud API Server – Document Parser API – PHP – Parse with OCR

How to parse with OCR for document parser API in PHP with ByteScout Cloud API Server

ByteScout Cloud API Server is API server that is ready to use and can be installed and deployed in less than 30 minutes on your own Windows server or server in a cloud. It can save data and files on your local server-based file storage or in Amazon AWS S3 storage. Data is processed solely on the API server and is powered by ByteScout engine, no cloud services or Internet connection is required for data processing..

On-demand (REST Web API) version:
 Web API (on-demand version)

On-premise offline SDK for Windows:
 60 Day Free Trial (on-premise)

DigitalOcean.yml

      
templateName: DigitalOcean Invoice templateVersion: 4 templatePriority: 0 detectionRules: keywords: - DigitalOcean - 101 Avenue of the Americas - Invoice Number objects: - name: companyName objectType: field fieldProperties: fieldType: static expression: DigitalOcean regex: true - name: invoiceId objectType: field fieldProperties: fieldType: macros expression: 'Invoice Number: ({{Digits}})' regex: true - name: dateIssued objectType: field fieldProperties: fieldType: macros expression: 'Date Issued: ({{SmartDate}})' regex: true dataType: date dateFormat: auto-mdy - name: total objectType: field fieldProperties: fieldType: macros expression: 'Total: ({{Money}})' regex: true dataType: decimal - name: currency objectType: field fieldProperties: fieldType: static expression: USD regex: true - name: table1 objectType: table tableProperties: start: expression: Description{{Spaces}}Hours regex: true end: expression: 'Total:' regex: true row: expression: '{{LineStart}}{{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<hours>{{Digits}}){{Spaces}}(?<start>{{2Digits}}{{Minus}}{{2Digits}}{{Space}}{{2Digits}}{{Colon}}{{2Digits}}){{Spaces}}(?<end>{{2Digits}}{{Minus}}{{2Digits}}{{Space}}{{2Digits}}{{Colon}}{{2Digits}}){{Spaces}}{{Dollar}}(?<unitPrice>{{Number}})' regex: true columns: - name: hours dataType: integer - name: unitPrice dataType: decimal

program.php

      
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <title>Document Parse Results</title> </head> <body> <?php // Please NOTE: In this sample we're assuming Cloud Api Server is hosted at "https://localhost". // If it's not then please replace this with with your hosting url. // Get submitted form data $apiKey = $_POST["apiKey"]; // The authentication key (API Key). Get your own by registering at https://app.pdf.co/documentation/api // 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE. // * If you already have the direct PDF file link, go to the step 3. // Create URL $url = "https://localhost/file/upload/get-presigned-url" . "?name=" . $_FILES["file"]["tmp_name"] . "&contenttype=application/octet-stream"; // Create request $curl = curl_init(); curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey)); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); // Execute request $result = curl_exec($curl); if (curl_errno($curl) == 0) { $status_code = curl_getinfo($curl, CURLINFO_HTTP_CODE); if ($status_code == 200) { $json = json_decode($result, true); // Get URL to use for the file upload $uploadFileUrl = $json["presignedUrl"]; // Get URL of uploaded file to use with later API calls $uploadedFileUrl = $json["url"]; // 2. UPLOAD THE FILE TO CLOUD. $localFile = $_FILES["fileInput"]["tmp_name"]; $fileHandle = fopen($localFile, "r"); curl_setopt($curl, CURLOPT_URL, $uploadFileUrl); curl_setopt($curl, CURLOPT_HTTPHEADER, array("content-type: application/octet-stream")); curl_setopt($curl, CURLOPT_PUT, true); curl_setopt($curl, CURLOPT_INFILE, $fileHandle); curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile)); // Execute request curl_exec($curl); fclose($fileHandle); if (curl_errno($curl) == 0) { $status_code = curl_getinfo($curl, CURLINFO_HTTP_CODE); if ($status_code == 200) { // Read all template texts $templateText = file_get_contents($_FILES["fileTemplate"]["tmp_name"]); // 3. PARSE UPLOADED PDF DOCUMENT ParseDocument($apiKey, $uploadedFileUrl, $templateText); } else { // Display request error echo "<p>Status code: " . $status_code . "</p>"; echo "<p>" . $result . "</p>"; } } else { // Display CURL error echo "Error: " . curl_error($curl); } } else { // Display service reported error echo "<p>Status code: " . $status_code . "</p>"; echo "<p>" . $result . "</p>"; } curl_close($curl); } else { // Display CURL error echo "Error: " . curl_error($curl); } function ParseDocument($apiKey, $uploadedFileUrl, $templateText) { // (!) Make asynchronous job $async = TRUE; // Prepare URL for Document parser API call. // See documentation: https://apidocs.pdf.co/?#1-pdfdocumentparser $url = "https://localhost/pdf/documentparser"; // Prepare requests params $parameters = array(); $parameters["url"] = $uploadedFileUrl; $parameters["template"] = $templateText; $parameters["async"] = $async; // Create Json payload $data = json_encode($parameters); // Create request $curl = curl_init(); curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-type: application/json")); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_POST, true); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); curl_setopt($curl, CURLOPT_POSTFIELDS, $data); // Execute request $result = curl_exec($curl); echo $result . "<br/>"; if (curl_errno($curl) == 0) { $status_code = curl_getinfo($curl, CURLINFO_HTTP_CODE); if ($status_code == 200) { $json = json_decode($result, true); if ($json["error"] == false) { // URL of generated JSON file that will available after the job completion $resultFileUrl = $json["url"]; // Asynchronous job ID $jobId = $json["jobId"]; // Check the job status in a loop do { $status = CheckJobStatus($jobId, $apiKey); // Possible statuses: "working", "failed", "aborted", "success". // Display timestamp and status (for demo purposes) echo "<p>" . date(DATE_RFC2822) . ": " . $status . "</p>"; if ($status == "success") { // Display link to JSON file with information about parsed fields echo "<div><h2>Parsing Result:</h2><a href='" . $resultFileUrl . "' target='_blank'>" . $resultFileUrl . "</a></div>"; break; } else if ($status == "working") { // Pause for a few seconds sleep(3); } else { echo $status . "<br/>"; break; } } while (true); } else { // Display service reported error echo "<p>Error: " . $json["message"] . "</p>"; } } else { // Display request error echo "<p>Status code: " . $status_code . "</p>"; echo "<p>" . $result . "</p>"; } } else { // Display CURL error echo "Error: " . curl_error($curl); } } function CheckJobStatus($jobId, $apiKey) { $status = null; // Create URL $url = "https://localhost/job/check"; // Prepare requests params $parameters = array(); $parameters["jobid"] = $jobId; // Create Json payload $data = json_encode($parameters); // Create request $curl = curl_init(); curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-type: application/json")); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_POST, true); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); curl_setopt($curl, CURLOPT_POSTFIELDS, $data); // Execute request $result = curl_exec($curl); if (curl_errno($curl) == 0) { $status_code = curl_getinfo($curl, CURLINFO_HTTP_CODE); if ($status_code == 200) { $json = json_decode($result, true); if ($json["error"] == false) { $status = $json["status"]; } else { // Display service reported error echo "<p>Error: " . $json["message"] . "</p>"; } } else { // Display request error echo "<p>Status code: " . $status_code . "</p>"; echo "<p>" . $result . "</p>"; } } else { // Display CURL error echo "Error: " . curl_error($curl); } // Cleanup curl_close($curl); return $status; } ?> </body> </html>

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

ON-DEMAND REST WEB API

Get Your API Key

See also:

Tutorials:

prev
next