How to parse from URL asynchronously for document parser API in PHP with PDF.co Web API
What is PDF.co Web API? It 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
---
# Template that demonstrates parsing of multi-page table using only
# macro expressions for the table start, end, and rows.
# If macro expression cannot be written for every table row (for example,
# if the table contains empty cells), try the second method demonstrated
# in `MultiPageTable-template2.yml` template.
templateVersion: 3
templatePriority: 0
sourceId: Multipage Table Test
detectionRules:
keywords:
- Sample document with multi-page table
fields:
total:
expression: 'TOTAL{{Spaces}}({{Number}})'
dataType: decimal
tables:
- name: table1
start:
# macro expression to find the table start in document
expression: 'Item{{Spaces}}Description{{Spaces}}Price'
end:
# macro expression to find the table end in document
expression: 'TOTAL{{Spaces}}{{Number}}'
row:
# macro expression to find table rows
expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})'
# output data types for columns
columns:
- name: itemNo
type: integer
- name: description
type: string
- name: price
type: decimal
- name: qty
type: integer
- name: extPrice
type: decimal
multipage: true
program.php
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Document Parse Results</title>
</head>
<body>
<?php
// Source PDF file
$uploadedFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/document-parser/MultiPageTable.pdf";
// Get submitted form data
$apiKey = $_POST["apiKey"]; // The authentication key (API Key). Get your own by registering at https://app.pdf.co/documentation/api
// Read all template texts
$templateText = file_get_contents($_FILES["fileTemplate"]["tmp_name"]);
// PARSE UPLOADED PDF DOCUMENT
ParseDocument($apiKey, $uploadedFileUrl, $templateText);
function ParseDocument($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" .
"?async=" . $async;
// Post fields
$data = array('url'=>$uploadedFileUrl, 'template'=>$templateText);
// 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_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
// 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?jobid=" . $jobId;
// 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);
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
See also:
ON-DEMAND REST WEB API
Get Your API Key
See also:
printable version:
PDF-co-Web-API-PHP-Parse-From-URL-Asynchronously.pdf
PDF-co-Web-API-PHP-Parse-From-URL-Asynchronously.pdf