Parse Document

Extract fields, tables, and values from PDFs and images using Document Parser templates with searchable form fields and multi-page support.

POST /v1/pdf/documentparser

Please refer to the Document Parser Template Editor and PDF.co Document Parser: Template Creation Guide for more information.

Attributes

Attributes are case-sensitive and should be inside JSON for POST request. for example: { "url": "https://example.com/file1.pdf" }

Attribute	Type	Required	Default	Description
url	string	Yes	-	URL to the source file url attribute
callback	string	No	-	The callback URL (or Webhook) used to receive the POST data. see Webhooks & Callbacks. This is only applicable when async is set to true.
httpusername	string	No	-	HTTP auth user name if required to access source URL.
httppassword	string	No	-	HTTP auth password if required to access source URL.
templateId	integer	No	-	Set ID of document parser template to be used. View and manage your templates at Document Parser
template	string	No	-	The raw format of the document parser template to be used directly. see Template
password	string	No	-	Password for the PDF file.
inline	boolean	No	false	Set to true to include the results directly in the response, in addition to providing a URL to the generated output file. Applies only when async mode is enabled.
async	boolean	No	false	Set async to true for long processes to run in the background, API will then return a jobId which you can use with the Background Job Check endpoint. Also see Webhooks & Callbacks
pages	string	No	all pages	Specify page indices as comma-separated values or ranges to process (e.g. “0, 1, 2-” or “1, 2, 3-7”). The first-page index is 0. Use ”!” before a number for inverted page numbers (e.g. “!0” for the last page). If not specified, the default configuration processes all pages. The input must be in string format.
name	string	No	-	File name for the generated output, the input must be in string format.
expiration	integer	No	60	Set the expiration time for the output link in minutes. After this specified duration, any generated output file(s) will be automatically deleted from PDF.co Temporary Files Storage. The maximum duration for link expiration varies based on your current subscription plan. To store permanent input files (e.g. re-usable images, pdf templates, documents) consider using PDF.co Built-In Files Storage.
outputFormat	string	No	JSON	The format of the output file. The output format can be JSON, CSV, or XML.
profiles	object	No	-	See Profiles for more information.
DataEncryptionAlgorithm	string	No	-	Controls the encryption algorithm used for data encryption. See User-Controlled Encryption for more information. The available algorithms are: AES128, AES192, AES256.
DataEncryptionKey	string	No	-	Controls the encryption key used for data encryption. See User-Controlled Encryption for more information.
DataEncryptionIV	string	No	-	Controls the encryption IV used for data encryption. See User-Controlled Encryption for more information.
DataDecryptionAlgorithm	string	No	-	Controls the decryption algorithm used for data decryption. See User-Controlled Encryption for more information. The available algorithms are: AES128, AES192, AES256.
DataDecryptionKey	string	No	-	Controls the decryption key used for data decryption. See User-Controlled Encryption for more information.
DataDecryptionIV	string	No	-	Controls the decryption IV used for data decryption. See User-Controlled Encryption for more information.

Query parameters

No query parameters accepted.

Responses

Parameter	Type	Description
pageCount	integer	Number of pages in the PDF document.
error	boolean	Indicates whether an error occurred (false means success)
status	string	Status code of the request (200, 404, 500, etc.). For more information, see Response Codes.
credits	integer	Number of credits consumed by the request
remainingCredits	integer	Number of credits remaining in the account
duration	integer	Time taken for the operation in milliseconds
body	object	No
objects	array[object]
elapsed	float	Processing time in seconds
templateName	string	Name of the parsing template used
templateVersion	string	Version of the parsing template
timestamp	string	Timestamp when the parsing occurred

Example Payload

To see the request size limits, please refer to the Request Size Limits.

{
  "url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/document-parser/sample-invoice.pdf",
  "outputFormat": "JSON",
  "templateId": "1",
  "async": false,
  "inline": "true",
  "password": "",
  "profiles": ""
}

Example Response

To see the main response codes, please refer to the Response Codes page.

{
  "body": {
    "objects": [
      {
        "name": "companyName",
        "objectType": "field",
        "value": "Amazon Web Services, Inc",
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "companyName2",
        "objectType": "field",
        "value": "Amazon Web Services, Inc",
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "invoiceId",
        "objectType": "field",
        "value": "123456789",
        "pageIndex": 0,
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "dateIssued",
        "objectType": "field",
        "value": "2018-04-03T00:00:00",
        "pageIndex": 0,
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "dateDue",
        "objectType": "field",
        "value": "2018-04-03T00:00:00",
        "pageIndex": 0,
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "bankAccount",
        "objectType": "field",
        "value": "123456789012",
        "pageIndex": 0,
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "total",
        "objectType": "field",
        "value": 6.58,
        "pageIndex": 0,
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "name": "subTotal",
        "objectType": "field",
        "value": ""
      },
      {
        "name": "tax",
        "objectType": "field",
        "value": 1.01,
        "pageIndex": 0,
        "rectangle": [
          0,
          0,
          0,
          0
        ]
      },
      {
        "objectType": "table",
        "name": "table",
        "rows": []
      }
    ],
    "templateName": "Generic Invoice [en]",
    "templateVersion": "4",
    "timestamp": "2020-08-21T19:23:31"
  },
  "pageCount": 1,
  "error": false,
  "status": 200,
  "name": "sample-invoice.json",
  "remainingCredits": 60803
}

Inconsistent URL Encoding in cURL Output: When using cURL to make API requests, the output JSON may show URL characters encoded as Unicode escape sequences. For example, the ampersand character (&) may appear as \u0026 in the cURL output. This is normal JSON encoding behavior and does not affect the validity of the URL. The URL will function correctly when used, as JSON parsers automatically decode these escape sequences. If you’re parsing the response programmatically, your JSON parser will handle this conversion automatically.

Code Samples

CURL

curl --location --request POST 'https://api.pdf.co/v1/pdf/documentparser' \
--header 'Content-Type: application/json' \
--header 'x-api-key: {{x-api-key}}' \
--data-raw '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/document-parser/sample-invoice.pdf",
"outputFormat": "JSON",
"templateId": "1",
"async": false,
"inline": "true",
"password": "",
"profiles": ""
}'

JavaScript/Node.js

var https = require("https");
var path = require("path");
var fs = require("fs");

// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");

// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";

// Source PDF file
const SourceFile = "./MultiPageTable.pdf";
// Document Parser template file
const TemplateFile = "./MultiPageTable-template1.yml";
// PDF document password. Leave empty for unprotected documents.
const Password = "";
// The format of the output file. The output format can be JSON, CSV, or XML.
const OutputFormat = "JSON";
// Destination JSON file name
const DestinationFile = "./result.json";

// Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
// to create templates.
// Read template from file:
const Template = fs.readFileSync(TemplateFile, "utf8");


// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
    .then(([uploadUrl, uploadedFileUrl]) => {
        // 2. UPLOAD THE FILE TO CLOUD.
        uploadFile(API_KEY, SourceFile, uploadUrl)
            .then(() => {
                // 3. PARSE UPLOADED PDF DOCUMENT
                parseDocument(API_KEY, uploadedFileUrl, Template, Password, OutputFormat, DestinationFile);
            })
            .catch(e => {
                console.log(e);
            });
    })
    .catch(e => {
        console.log(e);
    });


function getPresignedUrl(apiKey, localFile) {
    return new Promise(resolve => {
        // Prepare request to `Get Presigned URL` API endpoint
        let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(localFile)}`;
        let reqOptions = {
            host: "api.pdf.co",
            path: encodeURI(queryPath),
            headers: { "x-api-key": API_KEY }
        };
        // Send request
        https.get(reqOptions, (response) => {
            response.on("data", (d) => {
                let data = JSON.parse(d);
                if (data.error == false) {
                    // Return presigned url we received
                    resolve([data.presignedUrl, data.url]);
                }
                else {
                    // Service reported error
                    console.log("getPresignedUrl(): " + data.message);
                }
            });
        })
            .on("error", (e) => {
                // Request error
                console.log("getPresignedUrl(): " + e);
            });
    });
}

function uploadFile(apiKey, localFile, uploadUrl) {
    return new Promise(resolve => {
        fs.readFile(localFile, (err, data) => {
            request({
                method: "PUT",
                url: uploadUrl,
                body: data,
                headers: {
                    "Content-Type": "application/octet-stream"
                }
            }, (err, res, body) => {
                if (!err) {
                    resolve();
                }
                else {
                    console.log("uploadFile() request error: " + err);
                }
            });
        });
    });
}

function parseDocument(apiKey, uploadedFileUrl, template, password, outputFormat, destinationFile) {
    // Prepare request to `Document Parser` API endpoint
    var queryPath = `/v1/pdf/documentparser`;

    // JSON payload for api request
    var jsonPayload = JSON.stringify({
        url: uploadedFileUrl,
        template: template,
        password: password,
        outputFormat: outputFormat,
        name: path.basename(destinationFile)
    });

    var reqOptions = {
        host: "api.pdf.co",
        method: "POST",
        path: queryPath,
        headers: {
            "x-api-key": apiKey,
            "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);
            if (data.error == false) {
                // Download JSON file
                var file = fs.createWriteStream(destinationFile);
                https.get(data.url, (response2) => {
                    response2.pipe(file)
                        .on("close", () => {
                            console.log(`Generated JSON file saved as "${destinationFile}" file.`);
                        });
                });
            }
            else {
                // Service reported error
                console.log("parseDocument(): " + data.message);
            }
        });
    })
        .on("error", (e) => {
            // Request error
            console.log("parseDocument(): " + e);
        });

    // Write request data
    postRequest.write(jsonPayload);
    postRequest.end();
}

Python

import os
import requests # pip install requests

# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co
API_KEY = "*************************************"

# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"

# Source PDF file
SourceFile = ".\\MultiPageTable.pdf"
# Document Parser template file
TemplateFile = ".\\MultiPageTable-template1.yml"
# PDF document password. Leave empty for unprotected documents.
Password = ""
# The format of the output file. The output format can be JSON, CSV, or XML.
OutputFormat = "JSON"
# Destination JSON file name
DestinationFile = ".\\result.json"

# Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
# to create templates.
# Read template from file:
file_read = open(TemplateFile, mode='r', encoding="utf-8", errors="ignore")
Template = file_read.read()
file_read.close()


def main(args = None):
    uploadedFileUrl = uploadFile(SourceFile)
    if (uploadedFileUrl != None):
        PerformDocumentParser(uploadedFileUrl, Template, DestinationFile)


def PerformDocumentParser(uploadedFileUrl, template, destinationFile):
    """Parses a document using PDF.co Web API"""

    # Prepare requests params as JSON
    # See documentation: https://developer.pdf.co/
    parameters = {}
    parameters["url"] = uploadedFileUrl
    parameters["template"] = template
    parameters["password"] = Password
    parameters["outputFormat"] = OutputFormat
    parameters["name"] = os.path.basename(destinationFile)

    # Prepare URL for 'Document Parser' API request
    url = "{}/pdf/documentparser".format(BASE_URL)

    # Execute request and get response as JSON
    response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
    if (response.status_code == 200):
        json = response.json()

        if json["error"] == False:
            #  Get URL of result file
            resultFileUrl = json["url"]
            # Download result file
            r = requests.get(resultFileUrl, stream=True)
            if (r.status_code == 200):
                with open(destinationFile, 'wb') as file:
                    for chunk in r:
                        file.write(chunk)
                print(f"Result file saved as \"{destinationFile}\" file.")
            else:
                print(f"Request error: {response.status_code} {response.reason}")
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")


def uploadFile(fileName):
    """Uploads file to the cloud"""

    # 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.

    # Prepare URL for 'Get Presigned URL' API request
    url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
        BASE_URL, os.path.basename(fileName))

    # Execute request and get response as JSON
    response = requests.get(url, headers={ "x-api-key": API_KEY })
    if (response.status_code == 200):
        json = response.json()

        if json["error"] == False:
            # URL to use for file upload
            uploadUrl = json["presignedUrl"]
            # URL for future reference
            uploadedFileUrl = json["url"]

            # 2. UPLOAD FILE TO CLOUD.
            with open(fileName, 'rb') as file:
                requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })

            return uploadedFileUrl
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")

    return None


if __name__ == '__main__':
    main()

C#

using Newtonsoft.Json;
  using Newtonsoft.Json.Linq;
  using System;
  using System.Collections.Generic;
  using System.IO;
  using System.Net;

  namespace PDFcoApiExample
  {
      class Program
      {
          // The authentication key (API Key).
          // Get your own by registering at https://app.pdf.co
          const String API_KEY = "***********************************";

          // Source PDF file
          const string SourceFile = @".\MultiPageTable.pdf";
          // PDF document password. Leave empty for unprotected documents.
          const string Password = "";
          // Destination TXT file name
          const string DestinationFile = @".\result.json";

          static void Main(string[] args)
          {
              // Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
              // to create templates.
              // Read template from file:
              String templateText = File.ReadAllText(@".\MultiPageTable-template1.yml");

              // Create standard .NET web client instance
              WebClient webClient = new WebClient();

              // Set API Key
              webClient.Headers.Add("x-api-key", API_KEY);

              // 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
              // * If you already have a direct file URL, skip to the step 3.

              // Prepare URL for `Get Presigned URL` API call
              string query = Uri.EscapeUriString(string.Format(
                  "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
                  Path.GetFileName(SourceFile)));

              try
              {
                  // Execute request
                  string response = webClient.DownloadString(query);

                  // Parse JSON response
                  JObject json = JObject.Parse(response);

                  if (json["error"].ToObject<bool>() == false)
                  {
                      // Get URL to use for the file upload
                      string uploadUrl = json["presignedUrl"].ToString();
                      string uploadedFileUrl = json["url"].ToString();

                      // 2. UPLOAD THE FILE TO CLOUD.

                      webClient.Headers.Add("content-type", "application/octet-stream");
                      webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
                      webClient.Headers.Remove("content-type");

                      // 3. PARSE UPLOADED PDF DOCUMENT

                      // URL of `Document Parser` API call
                      string url = "https://api.pdf.co/v1/pdf/documentparser";

                      Dictionary<string, string> requestBody = new Dictionary<string, string>();
                      requestBody.Add("template", templateText);
                      requestBody.Add("name", Path.GetFileName(DestinationFile));
                      requestBody.Add("url", uploadedFileUrl);

                      // Convert dictionary of params to JSON
                      string jsonPayload = JsonConvert.SerializeObject(requestBody);

                      // Execute request
                      response = webClient.UploadString(url, "POST", jsonPayload);

                      // Parse response
                      json = JObject.Parse(response);

                      if (json["error"].ToObject<bool>() == false)
                      {
                          // Get URL of generated JSON file
                          string resultFileUrl = json["url"].ToString();

                          // Download JSON file
                          webClient.DownloadFile(resultFileUrl, DestinationFile);

                          Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile);
                      }
                      else
                      {
                          Console.WriteLine(json["message"].ToString());
                      }
                  }
                  else
                  {
                      Console.WriteLine(json["message"].ToString());
                  }
              }
              catch (WebException e)
              {
                  Console.WriteLine(e.ToString());
              }

              webClient.Dispose();

              Console.WriteLine();
              Console.WriteLine("Press any key...");
              Console.ReadKey();
          }
      }
  }

Java

package com.company;

  import com.google.gson.JsonObject;
  import com.google.gson.JsonParser;
  import com.google.gson.JsonPrimitive;
  import okhttp3.*;

  import java.io.File;
  import java.io.FileOutputStream;
  import java.io.IOException;
  import java.io.OutputStream;
  import java.nio.charset.StandardCharsets;
  import java.nio.file.Files;
  import java.nio.file.Path;
  import java.nio.file.Paths;

  public class Main
  {
      // The authentication key (API Key).
      // Get your own by registering at https://app.pdf.co
      final static String API_KEY = "***********************************";

      public static void main(String[] args) throws IOException
      {
          // Source PDF file
          final Path SourceFile = Paths.get(".\\MultiPageTable.pdf");
          // PDF document password. Leave empty for unprotected documents.
          final String Password = "";
          // Destination JSON file name
          final Path DestinationFile = Paths.get(".\\result.json");

          // Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
          // to create templates.
          // Read template from file:
          String templateText = new String(Files.readAllBytes(Paths.get(".\\MultiPageTable-template1.yml")), StandardCharsets.UTF_8);

          // Create HTTP client instance
          OkHttpClient webClient = new OkHttpClient();

          // 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
          // * If you already have a direct file URL, skip to the step 3.

          // Prepare URL for `Get Presigned URL` API call
          String query = String.format(
                  "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
                  SourceFile.getFileName());

          // Prepare request
          Request request = new Request.Builder()
                  .url(query)
                  .addHeader("x-api-key", API_KEY) // (!) Set API Key
                  .build();
          // Execute request
          Response response = webClient.newCall(request).execute();

          if (response.code() == 200)
          {
              // Parse JSON response
              JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();

              boolean error = json.get("error").getAsBoolean();
              if (!error)
              {
                  // Get URL to use for the file upload
                  String uploadUrl = json.get("presignedUrl").getAsString();
                  // Get URL of uploaded file to use with later API calls
                  String uploadedFileUrl = json.get("url").getAsString();

                  // 2. UPLOAD THE FILE TO CLOUD.

                  if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
                  {
                      // 3. PARSE UPLOADED PDF DOCUMENT

                      ParseDocument(webClient, API_KEY, DestinationFile, Password, uploadedFileUrl, templateText);
                  }
              }
              else
              {
                  // Display service reported error
                  System.out.println(json.get("message").getAsString());
              }
          }
          else
          {
              // Display request error
              System.out.println(response.code() + " " + response.message());
          }
      }

      public static void ParseDocument(OkHttpClient webClient, String apiKey, Path destinationFile,
          String password, String uploadedFileUrl, String templateText) throws IOException
      {
          // Prepare POST request body in JSON format
          JsonObject jsonBody = new JsonObject();
          jsonBody.add("url", new JsonPrimitive(uploadedFileUrl));
          jsonBody.add("template", new JsonPrimitive(templateText));

          RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonBody.toString());

          // Prepare request to `Document Parser` API
          Request request = new Request.Builder()
                  .url("https://api.pdf.co/v1/pdf/documentparser")
                  .addHeader("x-api-key", API_KEY) // (!) Set API Key
                  .addHeader("Content-Type", "application/json")
                  .post(body)
                  .build();

          // Execute request
          Response response = webClient.newCall(request).execute();

          if (response.code() == 200)
          {
              // Parse JSON response
              JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();

              boolean error = json.get("error").getAsBoolean();
              if (!error)
              {
                  // Get URL of generated JSON file
                  String resultFileUrl = json.get("url").getAsString();

                  // Download JSON file
                  downloadFile(webClient, resultFileUrl, destinationFile.toFile());

                  System.out.printf("Generated JSON file saved as \"%s\" file.", destinationFile.toString());
              }
              else
              {
                  // Display service reported error
                  System.out.println(json.get("message").getAsString());
              }
          }
          else
          {
              // Display request error
              System.out.println(response.code() + " " + response.message());
          }
      }

      public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
      {
          // Prepare request body
          RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());

          // Prepare request
          Request request = new Request.Builder()
                  .url(url)
                  .addHeader("x-api-key", apiKey) // (!) Set API Key
                  .addHeader("content-type", "application/octet-stream")
                  .put(body)
                  .build();

          // Execute request
          Response response = webClient.newCall(request).execute();

          return (response.code() == 200);
      }

      public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
      {
          // Prepare request
          Request request = new Request.Builder()
                  .url(url)
                  .build();
          // Execute request
          Response response = webClient.newCall(request).execute();

          byte[] fileBytes = response.body().bytes();

          // Save downloaded bytes to file
          OutputStream output = new FileOutputStream(destinationFile);
          output.write(fileBytes);
          output.flush();
          output.close();

          response.close();
      }
  }

PHP

<?php

// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
$API_KEY = "***********************************";

// Source PDF file
$SourceFile = "./MultiPageTable.pdf";
// Document Parser template file
$TemplateFile = "./MultiPageTable-template1.yml";
// PDF document password. Leave empty for unprotected documents.
$Password = "";
// The format of the output file. The output format can be JSON, CSV, or XML.
$OutputFormat = "JSON";
// Destination JSON file name
$DestinationFile = "./result.json";


$templateText = file_get_contents($TemplateFile);

if ($templateText === false) {
    echo "unable to read " . $TemplateFile . PHP_EOL;
} else {
    // 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
    // * If you already have the direct PDF file link, go to the step 3.
    $presignedUrls = getPresignedUrl($API_KEY, $SourceFile);

    if ($presignedUrls !== null) {
        list($uploadUrl, $uploadedFileUrl) = $presignedUrls;

        // 2. UPLOAD THE FILE TO CLOUD.
        if (uploadFile($API_KEY, $SourceFile, $uploadUrl)) {
            // 3. PARSE UPLOADED PDF DOCUMENT
            parseDocument($API_KEY, $uploadedFileUrl, $templateText, $Password, $OutputFormat, $DestinationFile);
        }
    }
}


function getPresignedUrl($apiKey, $localFile)
{
    // Prepare URL for `Get Presigned URL` API call
    $url = "https://api.pdf.co/v1/file/upload/get-presigned-url"
        . "?contenttype=application/octet-stream"
        . "&name=" . urlencode(basename($localFile));

    // Create request
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_URL, $url);
    curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey));
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);

    // Execute request
    $result = curl_exec($curl);
    $statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
    $curlError = curl_error($curl);
    curl_close($curl);

    if ($result === false) {
        // Display CURL error
        echo "getPresignedUrl(): " . $curlError . PHP_EOL;
        return null;
    }

    if ($statusCode != 200) {
        // Display request error
        echo "getPresignedUrl(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
        return null;
    }

    $json = json_decode($result, true);

    if (!empty($json["error"])) {
        // Display service reported error
        echo "getPresignedUrl(): " . $json["message"] . PHP_EOL;
        return null;
    }

    // Return the URL to use for the file upload, and the URL of the uploaded
    // file to use with later API calls
    return array($json["presignedUrl"], $json["url"]);
}

function uploadFile($apiKey, $localFile, $uploadUrl)
{
    $fileHandle = fopen($localFile, "rb");

    if ($fileHandle === false) {
        echo "uploadFile(): unable to open " . $localFile . PHP_EOL;
        return false;
    }

    // Create request. The presigned URL expects a raw PUT of the file bytes.
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_URL, $uploadUrl);
    curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "content-type: application/octet-stream"));
    curl_setopt($curl, CURLOPT_PUT, true);
    curl_setopt($curl, CURLOPT_INFILE, $fileHandle);
    curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile));
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);

    // Execute request
    $result = curl_exec($curl);
    $statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
    $curlError = curl_error($curl);
    curl_close($curl);
    fclose($fileHandle);

    if ($result === false) {
        // Display CURL error
        echo "uploadFile(): " . $curlError . PHP_EOL;
        return false;
    }

    if ($statusCode != 200) {
        // Display request error
        echo "uploadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
        return false;
    }

    return true;
}

function parseDocument($apiKey, $uploadedFileUrl, $templateText, $password, $outputFormat, $destinationFile)
{
    // Prepare URL for `Document Parser` API call
    $url = "https://api.pdf.co/v1/pdf/documentparser";

    // Prepare requests params
    $parameters = array();
    $parameters["url"] = $uploadedFileUrl;
    $parameters["template"] = $templateText;
    $parameters["password"] = $password;
    $parameters["outputFormat"] = $outputFormat;
    $parameters["name"] = basename($destinationFile);

    // Create Json payload
    $data = json_encode($parameters);

    // Create request
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_URL, $url);
    curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-Type: application/json"));
    curl_setopt($curl, CURLOPT_POST, true);
    curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);

    // Execute request
    $result = curl_exec($curl);
    $statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
    $curlError = curl_error($curl);
    curl_close($curl);

    if ($result === false) {
        // Display CURL error
        echo "parseDocument(): " . $curlError . PHP_EOL;
        return;
    }

    if ($statusCode != 200) {
        // Display request error
        echo "parseDocument(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
        return;
    }

    $json = json_decode($result, true);

    if (!empty($json["error"])) {
        // Display service reported error
        echo "parseDocument(): " . $json["message"] . PHP_EOL;
        return;
    }

    // Get URL of generated JSON file
    $resultFileUrl = $json["url"];

    // Download JSON file
    if (downloadFile($resultFileUrl, $destinationFile)) {
        echo "Generated JSON file saved as \"" . $destinationFile . "\" file." . PHP_EOL;
    }
}

function downloadFile($url, $destinationFile)
{
    // Create request
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_URL, $url);
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);

    // Execute request
    $result = curl_exec($curl);
    $statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
    $curlError = curl_error($curl);
    curl_close($curl);

    if ($result === false) {
        // Display CURL error
        echo "downloadFile(): " . $curlError . PHP_EOL;
        return false;
    }

    if ($statusCode != 200) {
        // Display request error
        echo "downloadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
        return false;
    }

    // Write the file only after a successful response so failures leave no file behind
    if (file_put_contents($destinationFile, $result) === false) {
        echo "downloadFile(): unable to create " . $destinationFile . PHP_EOL;
        return false;
    }

    return true;
}

?>