- Cloudmersive Documentation

Node.JS Python C# Java PHP Objective-C Ruby Apex C/C++ cURL Swift JavaScript Go

Run this command to install the SDK:

npm install cloudmersive-convert-api-client --save

Or add this snippet to your package.json:

  "dependencies": {
    "cloudmersive-convert-api-client": "^2.6.3"
  }

var CloudmersiveConvertApiClient = require('cloudmersive-convert-api-client');
var defaultClient = CloudmersiveConvertApiClient.ApiClient.instance;

// Configure API key authorization: Apikey
var Apikey = defaultClient.authentications['Apikey'];
Apikey.apiKey = 'YOUR API KEY';



var apiInstance = new CloudmersiveConvertApiClient.EditPdfApi();

var inputFile = Buffer.from(fs.readFileSync("C:\\temp\\inputfile").buffer); // File | Input file to perform the operation on.

var opts = { 
  'textFormattingMode': "textFormattingMode_example" // String | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'.
};

var callback = function(error, data, response) {
  if (error) {
    console.error(error);
  } else {
    console.log('API called successfully. Returned data: ' + data);
  }
};
apiInstance.editPdfGetPdfTextByPages(inputFile, opts, callback);

Run this command to install the SDK:

pip install cloudmersive-convert-api-client

from __future__ import print_function
import time
import cloudmersive_convert_api_client
from cloudmersive_convert_api_client.rest import ApiException
from pprint import pprint

# Configure API key authorization: Apikey
configuration = cloudmersive_convert_api_client.Configuration()
configuration.api_key['Apikey'] = 'YOUR_API_KEY'



# create an instance of the API class
api_instance = cloudmersive_convert_api_client.EditPdfApi(cloudmersive_convert_api_client.ApiClient(configuration))
input_file = '/path/to/file' # file | Input file to perform the operation on.
text_formatting_mode = 'text_formatting_mode_example' # str | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'. (optional)

try:
    # Get text in a PDF document by page
    api_response = api_instance.edit_pdf_get_pdf_text_by_pages(input_file, text_formatting_mode=text_formatting_mode)
    pprint(api_response)
except ApiException as e:
    print("Exception when calling EditPdfApi->edit_pdf_get_pdf_text_by_pages: %s\n" % e)

.NET Framework | .NET Core

Run this command to install the SDK:

Install-Package Cloudmersive.APIClient.NET.DocumentAndDataConvert -Version 3.4.2

using System;
using System.Diagnostics;
using Cloudmersive.APIClient.NET.DocumentAndDataConvert.Api;
using Cloudmersive.APIClient.NET.DocumentAndDataConvert.Client;
using Cloudmersive.APIClient.NET.DocumentAndDataConvert.Model;

namespace Example
{
    public class EditPdfGetPdfTextByPagesExample
    {
        public void main()
        {
            // Configure API key authorization: Apikey
            Configuration.Default.AddApiKey("Apikey", "YOUR_API_KEY");
            
            

            var apiInstance = new EditPdfApi();
            var inputFile = new System.IO.FileStream("C:\\temp\\inputfile", System.IO.FileMode.Open); // System.IO.Stream | Input file to perform the operation on.
            var textFormattingMode = textFormattingMode_example;  // string | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'. (optional) 

            try
            {
                // Get text in a PDF document by page
                PdfTextByPageResult result = apiInstance.EditPdfGetPdfTextByPages(inputFile, textFormattingMode);
                Debug.WriteLine(result);
            }
            catch (Exception e)
            {
                Debug.Print("Exception when calling EditPdfApi.EditPdfGetPdfTextByPages: " + e.Message );
            }
        }
    }
}

using System;
using System.Diagnostics;
using Cloudmersive.APIClient.NETCore.DocumentAndDataConvert.Api;
using Cloudmersive.APIClient.NETCore.DocumentAndDataConvert.Client;
using Cloudmersive.APIClient.NETCore.DocumentAndDataConvert.Model;

namespace Example
{
    public class EditPdfGetPdfTextByPagesExample
    {
        public void main()
        {
            // Configure API key authorization: Apikey
            Configuration.Default.AddApiKey("Apikey", "YOUR_API_KEY");
            
            

            var apiInstance = new EditPdfApi();
            var inputFile = new System.IO.FileStream("C:\\temp\\inputfile", System.IO.FileMode.Open); // System.IO.Stream | Input file to perform the operation on.
            var textFormattingMode = textFormattingMode_example;  // string | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'. (optional) 

            try
            {
                // Get text in a PDF document by page
                PdfTextByPageResult result = apiInstance.EditPdfGetPdfTextByPages(inputFile, textFormattingMode);
                Debug.WriteLine(result);
            }
            catch (Exception e)
            {
                Debug.Print("Exception when calling EditPdfApi.EditPdfGetPdfTextByPages: " + e.Message );
            }
        }
    }
}

To install with Maven, add a reference to the repository in pom.xml:

<repositories>
    <repository>
        <id>jitpack.io</id>
        <url>https://jitpack.io</url>
    </repository>
</repositories>

And add a reference to the dependency in pom.xml:

<dependencies>
<dependency>
    <groupId>com.github.Cloudmersive</groupId>
    <artifactId>Cloudmersive.APIClient.Java</artifactId>
    <version>v4.25</version>
</dependency>
</dependencies>

To install with Gradle, add it in your root build.gradle at the end of repositories:

allprojects {
	repositories {
		...
		maven { url 'https://jitpack.io' }
	}
}

And add the dependency in build.gradle:

dependencies {
        implementation 'com.github.Cloudmersive:Cloudmersive.APIClient.Java:v4.25'
}

// Import classes:
//import com.cloudmersive.client.invoker.ApiClient;
//import com.cloudmersive.client.invoker.ApiException;
//import com.cloudmersive.client.invoker.Configuration;
//import com.cloudmersive.client.invoker.auth.*;
//import com.cloudmersive.client.EditPdfApi;

ApiClient defaultClient = Configuration.getDefaultApiClient();

// Configure API key authorization: Apikey
ApiKeyAuth Apikey = (ApiKeyAuth) defaultClient.getAuthentication("Apikey");
Apikey.setApiKey("YOUR API KEY");
// Uncomment the following line to set a prefix for the API key, e.g. "Token" (defaults to null)
//Apikey.setApiKeyPrefix("Token");

EditPdfApi apiInstance = new EditPdfApi();
File inputFile = new File("/path/to/file"); // File | Input file to perform the operation on.
String textFormattingMode = "textFormattingMode_example"; // String | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'.
try {
    PdfTextByPageResult result = apiInstance.editPdfGetPdfTextByPages(inputFile, textFormattingMode);
    System.out.println(result);
} catch (ApiException e) {
    System.err.println("Exception when calling EditPdfApi#editPdfGetPdfTextByPages");
    e.printStackTrace();
}

Run this command to install the SDK:

composer require cloudmersive/cloudmersive_document_convert_api_client

<?php
require_once(__DIR__ . '/vendor/autoload.php');

// Configure API key authorization: Apikey
$config = Swagger\Client\Configuration::getDefaultConfiguration()->setApiKey('Apikey', 'YOUR_API_KEY');



$apiInstance = new Swagger\Client\Api\EditPdfApi(
    
    
    new GuzzleHttp\Client(),
    $config
);
$input_file = "/path/to/file"; // \SplFileObject | Input file to perform the operation on.
$text_formatting_mode = "text_formatting_mode_example"; // string | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'.

try {
    $result = $apiInstance->editPdfGetPdfTextByPages($input_file, $text_formatting_mode);
    print_r($result);
} catch (Exception $e) {
    echo 'Exception when calling EditPdfApi->editPdfGetPdfTextByPages: ', $e->getMessage(), PHP_EOL;
}
?>

Add the Objective-C client to your Podfile:

pod 'CloudmersiveDocumentAndDataConvertApiClient', '~> 1.0'

CMDefaultConfiguration *apiConfig = [CMDefaultConfiguration sharedConfig];

// Configure API key authorization: (authentication scheme: Apikey)
[apiConfig setApiKey:@"YOUR_API_KEY" forApiKeyIdentifier:@"Apikey"];




NSURL* inputFile = [NSURL fileURLWithPath:@"/path/to/file"]; // Input file to perform the operation on.
NSString* textFormattingMode = @"textFormattingMode_example"; // Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'. (optional)

CMEditPdfApi*apiInstance = [[CMEditPdfApi alloc] init];

// Get text in a PDF document by page
[apiInstance editPdfGetPdfTextByPagesWithInputFile:inputFile
              textFormattingMode:textFormattingMode
          completionHandler: ^(CMPdfTextByPageResult* output, NSError* error) {
                        if (output) {
                            NSLog(@"%@", output);
                        }
                        if (error) {
                            NSLog(@"Error calling CMEditPdfApi->editPdfGetPdfTextByPages: %@", error);
                        }
                    }];

Add the Ruby client to your Gemfile:

gem 'cloudmersive-convert-api-client', '~> 2.1.6'

# load the gem
require 'cloudmersive-convert-api-client'
# setup authorization
CloudmersiveConvertApiClient.configure do |config|
  # Configure API key authorization: Apikey
  config.api_key['Apikey'] = 'YOUR API KEY'
  # Uncomment the following line to set a prefix for the API key, e.g. 'Bearer' (defaults to nil)
  #config.api_key_prefix['Apikey'] = 'Bearer'
end

api_instance = CloudmersiveConvertApiClient::EditPdfApi.new

input_file = File.new('/path/to/inputfile') # File | Input file to perform the operation on.

opts = { 
  text_formatting_mode: 'text_formatting_mode_example' # String | Optional; specify how whitespace should be handled when converting the document to text.  Possible values are 'preserveWhitespace' which will attempt to preserve whitespace in the document and relative positioning of text within the document, and 'minimizeWhitespace' which will not insert additional spaces into the document in most cases.  Default is 'preserveWhitespace'.
}

begin
  #Get text in a PDF document by page
  result = api_instance.edit_pdf_get_pdf_text_by_pages(input_file, opts)
  p result
rescue CloudmersiveConvertApiClient::ApiError => e
  puts "Exception when calling EditPdfApi->edit_pdf_get_pdf_text_by_pages: #{e}"
end

Download and copy the /client folder into your Apex project:

Download Apex Client

SwagEditPdfApi api = new SwagEditPdfApi();
SwagClient client = api.getClient();

// Configure API key authorization: Apikey
ApiKeyAuth Apikey = (ApiKeyAuth) client.getAuthentication('Apikey');
Apikey.setApiKey('YOUR API KEY');

Map<String, Object> params = new Map<String, Object>{
    'inputFile' => Blob.valueOf('Sample text file\nContents'),
    'textFormattingMode' => 'textFormattingMode_example'
};

try {
    // cross your fingers
    SwagPdfTextByPageResult result = api.editPdfGetPdfTextByPages(params);
    System.debug(result);
} catch (Swagger.ApiException e) {
    // ...handle your exceptions
}

Install libcurl in your C/C++ project:

libcurl/7.75.0

CURL *curl;
CURLcode res;
curl = curl_easy_init();
if(curl) {
     curl_easy_setopt(curl, CURLOPT_CUSTOMREQUEST, "POST");
     curl_easy_setopt(curl, CURLOPT_URL, "https://api.cloudmersive.com/convert/edit/pdf/pages/get-text");
     curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
     curl_easy_setopt(curl, CURLOPT_DEFAULT_PROTOCOL, "https");
     struct curl_slist *headers = NULL;
     headers = curl_slist_append(headers, "textFormattingMode: <string>");
     headers = curl_slist_append(headers, "Content-Type: multipart/form-data");
     headers = curl_slist_append(headers, "Apikey: YOUR-API-KEY-HERE");
     curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
     curl_mime *mime;
     curl_mimepart *part;
     mime = curl_mime_init(curl);
     part = curl_mime_addpart(mime);
     curl_mime_name(part, "inputFile");
     curl_mime_filedata(part, "/path/to/file");
     curl_easy_setopt(curl, CURLOPT_MIMEPOST, mime);
     res = curl_easy_perform(curl);
     curl_mime_free(mime);
}
curl_easy_cleanup(curl);

curl --location --request POST 'https://api.cloudmersive.com/convert/edit/pdf/pages/get-text' \
--header 'textFormattingMode: <string>' \
--header 'Content-Type: multipart/form-data' \
--header 'Apikey: YOUR-API-KEY-HERE' \
--form 'inputFile=@"/path/to/file"'

import Foundation
#if canImport(FoundationNetworking)
import FoundationNetworking
#endif

var semaphore = DispatchSemaphore (value: 0)

let parameters = [
     [
          "key": "inputFile",
          "src": "/path/to/file",
          "type": "file"
     ]] as [[String : Any]]

let boundary = "Boundary-\(UUID().uuidString)"
var body = ""
var error: Error? = nil
for param in parameters {
     if param["disabled"] == nil {
          let paramName = param["key"]!
          body += "--\(boundary)\r\n"
          body += "Content-Disposition:form-data; name=\"\(paramName)\""
          if param["contentType"] != nil {
               body += "\r\nContent-Type: \(param["contentType"] as! String)"
          }
          let paramType = param["type"] as! String
          if paramType == "text" {
               let paramValue = param["value"] as! String
               body += "\r\n\r\n\(paramValue)\r\n"
          } else {
               let paramSrc = param["src"] as! String
               let fileData = try NSData(contentsOfFile:paramSrc, options:[]) as Data
               let fileContent = String(data: fileData, encoding: .utf8)!
               body += "; filename=\"\(paramSrc)\"\r\n"
                 + "Content-Type: \"content-type header\"\r\n\r\n\(fileContent)\r\n"
          }
     }
}
body += "--\(boundary)--\r\n";
let postData = body.data(using: .utf8)

var request = URLRequest(url: URL(string: "https://api.cloudmersive.com/convert/edit/pdf/pages/get-text")!,timeoutInterval: Double.infinity)
request.addValue("<string>", forHTTPHeaderField: "textFormattingMode")
request.addValue("multipart/form-data", forHTTPHeaderField: "Content-Type")
request.addValue("YOUR-API-KEY-HERE", forHTTPHeaderField: "Apikey")
request.addValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")

request.httpMethod = "POST"
request.httpBody = postData

let task = URLSession.shared.dataTask(with: request) { data, response, error in 
     guard let data = data else {
          print(String(describing: error))
          semaphore.signal()
          return
     }
     print(String(data: data, encoding: .utf8)!)
     semaphore.signal()
}

task.resume()
semaphore.wait()

XHR | jQuery

This code snippet uses the built-in JavaScript XHR request capability

var data = new FormData();
data.append("inputFile", fileInput.files[0], "file");
 
var xhr = new XMLHttpRequest();
xhr.withCredentials = true;

xhr.addEventListener("readystatechange", function() {
     if(this.readyState === 4) {
          console.log(this.responseText);
     }
});

xhr.open("POST", "https://api.cloudmersive.com/convert/edit/pdf/pages/get-text");
xhr.setRequestHeader("textFormattingMode", "<string>");

xhr.setRequestHeader("Apikey", "YOUR-API-KEY-HERE");

xhr.send(data);

var form = new FormData();
form.append("inputFile", fileInput.files[0], "file");

var settings = {
     "url": "https://api.cloudmersive.com/convert/edit/pdf/pages/get-text",
     "method": "POST",
     "timeout": 0,
     "headers": {
          "textFormattingMode": "<string>",
          "Content-Type": "multipart/form-data",
          "Apikey": "YOUR-API-KEY-HERE"
     },
     "processData": false,
     "mimeType": "multipart/form-data",
     "contentType": false,
     "data": form
};

$.ajax(settings).done(function (response) {
     console.log(response);
});

package main

import (
     "fmt"
     "bytes"
     "mime/multipart"
     "os"
     "path/filepath"
     "io"
     "net/http"
     "io/ioutil"
)

func main() {

     url := "https://api.cloudmersive.com/convert/edit/pdf/pages/get-text"
     method := "POST"

     payload := &bytes.Buffer{}
     writer := multipart.NewWriter(payload)
     file, errFile1 := os.Open("/path/to/file")
     defer file.Close()
     part1,
         errFile1 := writer.CreateFormFile("inputFile",filepath.Base("/path/to/file"))
     _, errFile1 = io.Copy(part1, file)
     if errFile1 != nil {
          fmt.Println(errFile1)
          return
     }
     err := writer.Close()
     if err != nil {
          fmt.Println(err)
          return
     }


     client := &http.Client {
     }
     req, err := http.NewRequest(method, url, payload)

     if err != nil {
          fmt.Println(err)
          return
     }
     req.Header.Add("textFormattingMode", "<string>")
     req.Header.Add("Content-Type", "multipart/form-data")
     req.Header.Add("Apikey", "YOUR-API-KEY-HERE")

     req.Header.Set("Content-Type", writer.FormDataContentType())
     res, err := client.Do(req)
     if err != nil {
          fmt.Println(err)
          return
     }
     defer res.Body.Close()

     body, err := ioutil.ReadAll(res.Body)
     if err != nil {
          fmt.Println(err)
          return
     }
     fmt.Println(string(body))
}

Walkthrough Video