Link Search Menu Expand Document

Split PDF By Text From Uploaded File - PHP

PDF Split sample in PHP demonstrating ‘Split PDF By Text From Uploaded File’

sample.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>PDF Splitting Cloud API Example</title>
</head>

<body>

    <form name="form1" enctype="multipart/form-data" method="post" action="split-pdf.php">
        <p>
            <label>Authentication key (API Key). Get your own by registering at <a href="https://apidocs.pdf.co">https://apidocs.pdf.co</a>.</label>
            <br/>
            <input type="text" name="apiKey" placeholder="API Key"/>
        </p>
        <p>
            <label>Input File (*.pdf)</label>
            <input type="hidden" name="MAX_FILE_SIZE" value="8000000"/>
            <input type="file" name="file"/>
        </p>
        <p>
            <label>Split Search Text</label>
            <input type="text" name="splitText" value="invoice number">
        </p>
        <input type="submit" name="submit" value="Proceed" />
    </form>

</body>
</html>
split-pdf.php
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>PDF Splitting Results</title>
</head>
<body>

<?php 
// Note: If you have input files large than 200kb we highly recommend to check "async" mode example.

// Get submitted form data
$apiKey = $_POST["apiKey"]; // The authentication key (API Key). Get your own by registering at https://app.pdf.co
$splitText = $_POST["splitText"];


// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a 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"]["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
        $accessFileUrl = $json["url"];
        
        // 2. UPLOAD THE FILE TO CLOUD.
        
        $localFile = $_FILES["file"]["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($curl))
        {
            // Display request error
            echo "Error: " . curl_error($curl);
        }
        else
        {
            $status_code = curl_getinfo($curl, CURLINFO_HTTP_CODE);
            
            if ($status_code == 200)
            {
                // 3. SPLIT UPLOADED PDF DOCUMENT
                SplitPdf($apiKey, $accessFileUrl, $splitText);
            }
            else
            {
                // Display service reported error
                echo "<p>Status code: " . $status_code . "</p>"; 
                echo "<p>" . $result . "</p>"; 
            }
        }
    }
    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 SplitPdf($apiKey, $fileUrl, $splitText) 
{
    // Prepare URL for `Split PDF By Text` API call
    $url = "https://api.pdf.co/v1/pdf/split2";
        
    // Prepare requests params
    $parameters = array();
    $parameters["name"] = "part.pdf";
    $parameters["url"] = $fileUrl;
    $parameters["searchString"] = $splitText;

    // 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)
            {
                // Display links to splitted parts
                $resultFiles = $json["urls"];
                foreach ($resultFiles as &$resultFileUrl) 
                    echo "<p><a href=" . $resultFileUrl . ">" . $resultFileUrl . "</p>"; 
            }
            else
            {
                // Display service reported error
                echo "<p>Error: " . $json["message"] . "</p>"; 
            }
        }
        else
        {
            // Display request error
            echo "<p>Status code: " . $status_code . "</p>"; 
            echo "<p>" . $result . "</p>"; 
        }
    }
    else
    {
        // Display request error
        echo "Error: " . curl_error($curl);
    }
    
    // Cleanup
    curl_close($curl);
}

?>

</body>
</html>

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 Split endpoint