How to extract line items from tables on multiple pages for document parser API in PHP with 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)

MultiPageTable-template1.yml

      
templateName: Multipage Table Test templateVersion: 4 templatePriority: 0 detectionRules: keywords: - Sample document with multi-page table objects: - name: total objectType: field fieldProperties: fieldType: macros expression: TOTAL{{Spaces}}({{Number}}) regex: true dataType: decimal - name: table1 objectType: table tableProperties: start: expression: Item{{Spaces}}Description{{Spaces}}Price regex: true end: expression: TOTAL{{Spaces}}{{Number}} regex: true row: expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})' regex: true columns: - name: itemNo dataType: integer - name: description dataType: string - name: price dataType: decimal - name: qty dataType: integer - name: extPrice dataType: decimal multipage: true

MultiPageTable-template2.yml

      
templateName: Multipage Table Test templateVersion: 4 templatePriority: 0 detectionRules: keywords: - Sample document with multi-page table objects: - name: total objectType: field fieldProperties: fieldType: regex expression: TOTAL{{Spaces}}({{Number}}) regex: true dataType: decimal - name: table1 objectType: table tableProperties: start: expression: Item{{Spaces}}Description{{Spaces}}Price regex: true end: expression: (Page {{Digits}} of {{Digits}})|(TOTAL{{Spaces}}{{Number}}) regex: true left: 51 right: 528 columns: - x: 51 name: itemNo dataType: integer - x: 102 name: description dataType: string - x: 324 name: price dataType: decimal - x: 396 name: qty dataType: integer - x: 441 name: extPrice dataType: decimal multipage: true

program.php

      
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <title>Document Parse Results</title> </head> <body> <?php // 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://api.pdf.co/v1/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://api.pdf.co/v1/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://api.pdf.co/v1/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:

Related Pages:

Related Samples: