Parse Document

`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
}

Code Samples

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": ""
}'

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": ""
}'

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();
      }
  }

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"

  # 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(".\\MultiPageTable-template1.yml", 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):

      # Content
      data = {
          'url': uploadedFileUrl,
          'template': template
      }

      # 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= data, 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()

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();
          }
      }
  }

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();
      }
  }

<!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


  // 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" .
      "?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://developer.pdf.co/api/document-parser
      $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 (!isset($json["error"]) || $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 (!isset($json["error"]) || $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>

Welcome

Extraction

Editing

PDF Conversion

Excel Conversion

PDF Merging & Splitting

Forms

Find & Search

Document, File & System

Pages

Barcodes

Glossary

`POST /v1/pdf/documentparser`

Attributes

Query parameters

Responses

`Example` Payload

`Example` Response

Code Samples

Welcome

Extraction

Editing

PDF Conversion

Excel Conversion

PDF Merging & Splitting

Forms

Find & Search

Document, File & System

Pages

Barcodes

Glossary

​POST /v1/pdf/documentparser

​Attributes

​Query parameters

​Responses

​Example Payload

​Example Response

​Code Samples

`POST /v1/pdf/documentparser`

Attributes

Query parameters

Responses

`Example` Payload

`Example` Response

Code Samples