Merge pull request #43 from datalogics-tsmith/add-extract-text

PDFCLOUD-2694 Add extract text samples

DotNET/Single Calls/extract-text.cs

@@ -0,0 +1,25 @@
+using System.Text;
+
+using (var httpClient = new HttpClient { BaseAddress = new Uri("https://api.pdfrest.com") })
+{
+    using (var request = new HttpRequestMessage(HttpMethod.Post, "extract-text"))
+    {
+        request.Headers.TryAddWithoutValidation("Api-Key", "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx");
+        request.Headers.Accept.Add(new("application/json"));
+        var multipartContent = new MultipartFormDataContent();
+
+        var byteArray = File.ReadAllBytes("/path/to/file");
+        var byteAryContent = new ByteArrayContent(byteArray);
+        multipartContent.Add(byteAryContent, "file", "file_name");
+        byteAryContent.Headers.TryAddWithoutValidation("Content-Type", "application/pdf");
+
+
+        request.Content = multipartContent;
+        var response = await httpClient.SendAsync(request);
+
+        var apiResult = await response.Content.ReadAsStringAsync();
+
+        Console.WriteLine("API response received.");
+        Console.WriteLine(apiResult);
+    }
+}

Java/Single Calls/ExtractText.java

@@ -0,0 +1,60 @@
+import io.github.cdimascio.dotenv.Dotenv;
+import java.io.File;
+import java.io.IOException;
+import okhttp3.MediaType;
+import okhttp3.MultipartBody;
+import okhttp3.OkHttpClient;
+import okhttp3.Request;
+import okhttp3.RequestBody;
+import okhttp3.Response;
+import org.json.JSONObject;
+
+public class ExtractText {
+
+  // Specify the path to your file here, or as the first argument when running the program.
+  private static final String DEFAULT_FILE_PATH = "/path/to/file.pdf";
+
+  // Specify your API key here, or in the environment variable PDFREST_API_KEY.
+  // You can also put the environment variable in a .env file.
+  private static final String DEFAULT_API_KEY = "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx";
+
+  public static void main(String[] args) {
+    File inputFile;
+    if (args.length > 0) {
+      inputFile = new File(args[0]);
+    } else {
+      inputFile = new File(DEFAULT_FILE_PATH);
+    }
+
+    final Dotenv dotenv = Dotenv.configure().ignoreIfMalformed().ignoreIfMissing().load();
+
+    final RequestBody inputFileRequestBody =
+        RequestBody.create(inputFile, MediaType.parse("application/pdf"));
+    RequestBody requestBody =
+        new MultipartBody.Builder()
+            .setType(MultipartBody.FORM)
+            .addFormDataPart("file", inputFile.getName(), inputFileRequestBody)
+            .build();
+    Request request =
+        new Request.Builder()
+            .header("Api-Key", dotenv.get("PDFREST_API_KEY", DEFAULT_API_KEY))
+            .url("https://api.pdfrest.com/extract-text")
+            .post(requestBody)
+            .build();
+    try {
+      OkHttpClient client = new OkHttpClient().newBuilder().build();
+      Response response = client.newCall(request).execute();
+      System.out.println("Result code " + response.code());
+      if (response.body() != null) {
+        System.out.println(prettyJson(response.body().string()));
+      }
+    } catch (IOException e) {
+      throw new RuntimeException(e);
+    }
+  }
+
+  private static String prettyJson(String json) {
+    // https://stackoverflow.com/a/9583835/11996393
+    return new JSONObject(json).toString(4);
+  }
+}

JavaScript/Single Calls/extract-text.js

@@ -0,0 +1,31 @@
+// This request demonstrates how to extract text from a PDF document.
+var axios = require("axios");
+var FormData = require("form-data");
+var fs = require("fs");
+
+// Create a new form data instance and append the PDF file and parameters to it
+var data = new FormData();
+data.append("file", fs.createReadStream("/path/to/file"));
+
+// define configuration options for axios request
+var config = {
+  method: "post",
+  maxBodyLength: Infinity, // set maximum length of the request body
+  url: "https://api.pdfrest.com/extract-text",
+  headers: {
+    "Api-Key": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx", // Replace with your API key
+    ...data.getHeaders(), // set headers for the request
+  },
+  data: data, // set the data to be sent with the request
+};
+
+// send request and handle response or error
+axios(config)
+  .then(function (response) {
+    console.log(JSON.stringify(response.data));
+  })
+  .catch(function (error) {
+    console.log(error);
+  });
+
+// If you would like to download the file instead of getting the JSON response, please see the 'get-resource-id-endpoint.js' sample.

PHP/README.md

@@ -14,11 +14,7 @@ In this directory you will find sample calls to single endpoints, as well as mor
 
 2. Navigate to the directory containing the `php` file.
 
-3. Run the following command to install the required dependencies (Guzzle HTTP client):
-
-```bash
-composer install
-```
+3. Install the required dependencies (Guzzle HTTP client) by following the instructions at https://docs.guzzlephp.org/en/stable/overview.html
 
 ### Usage
 

PHP/Single Calls/extract-text.php

@@ -0,0 +1,31 @@
+<?php
+require 'vendor/autoload.php'; // Require the autoload file to load Guzzle HTTP client.
+
+use GuzzleHttp\Client; // Import the Guzzle HTTP client namespace.
+use GuzzleHttp\Psr7\Request; // Import the PSR-7 Request class.
+use GuzzleHttp\Psr7\Utils; // Import the PSR-7 Utils class for working with streams.
+
+$client = new Client(); // Create a new instance of the Guzzle HTTP client.
+
+$headers = [
+  'Api-Key' => 'xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' // Set the API key in the headers for authentication.
+];
+
+$options = [
+  'multipart' => [
+    [
+      'name' => 'file', // Specify the field name for the file.
+      'contents' => Utils::tryFopen('/path/to/file', 'r'), // Open the file specified by '/path/to/file' for reading.
+      'filename' => '/path/to/file', // Set the filename for the file to be processed, in this case, '/path/to/file'.
+      'headers' => [
+        'Content-Type' => '<Content-type header>' // Set the Content-Type header for the file.
+      ]
+    ]
+  ]
+];
+
+$request = new Request('POST', 'https://api.pdfrest.com/extract-text', $headers); // Create a new HTTP POST request with the API endpoint and headers.
+
+$res = $client->sendAsync($request, $options)->wait(); // Send the asynchronous request and wait for the response.
+
+echo $res->getBody(); // Output the response body, which contains the text extracted from the document.

Python/Single Calls/extract-text.py

@@ -0,0 +1,32 @@
+from requests_toolbelt import MultipartEncoder
+import requests
+import json
+
+extract_text_endpoint_url = 'https://api.pdfrest.com/extract-text'
+
+# The /extract-text endpoint can take a single PDF file or id as input.
+#This sample demonstrates querying the title, page count, document language and author
+mp_encoder_extractText = MultipartEncoder(
+    fields={
+        'file': ('file_name', open('/path/to/file', 'rb'), 'application/pdf'),
+    }
+)
+
+# Let's set the headers that the extract-text endpoint expects.
+# Since MultipartEncoder is used, the 'Content-Type' header gets set to 'multipart/form-data' via the content_type attribute below.
+headers = {
+    'Accept': 'application/json',
+    'Content-Type': mp_encoder_extractText.content_type,
+    'Api-Key': 'xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' # place your api key here
+}
+
+print("Sending POST request to extract-text endpoint...")
+response = requests.post(extract_text_endpoint_url, data=mp_encoder_extractText, headers=headers)
+
+print("Response status code: " + str(response.status_code))
+
+if response.ok:
+    response_json = response.json()
+    print(json.dumps(response_json, indent = 2))
+else:
+    print(response.text)

cURL/Single Calls/extract-text.sh

@@ -0,0 +1,5 @@
+curl -X POST "https://api.pdfrest.com/extract-text" \
+  -H "Accept: application/json" \
+  -H "Content-Type: multipart/form-data" \
+  -H "Api-Key: xxxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
+  -F "file=@/path/to/file"