Get PDF Document Word Count

Introduction

This example allows you to get word count per page from PDF document using Aspose.PDF Cloud API in your applications. The API has the following properties

API	Type	Description
/pdf/{name}/pages/wordCount	GET	Get word count for a particular page in a PDF Document
The API has the following parameters

Parameter	Required	Description	Type	Data Type
name	Yes	The name of the PDF Document	Path	String

Resource

The following Aspose.PDF Cloud REST API resource has been used in the examples: GetWordsPerPage.

cURL Example

Request

Get Authentication Header


curl -v "https://api.aspose.cloud/connect/token" \
-X POST \
-d "grant_type=client_credentials&client_id=xxxx&client_secret=xxxx" \
-H "Content-Type: application/x-www-form-urlencoded" \
-H "Accept: application/json"

Create cURL Request


curl -X GET "https://api.aspose.cloud/v3.0/pdf/4pages.pdf/pages/wordCount" \
-H "accept: application/json" \
-H "authorization: Bearer <jwt token>"

Response


{

  "WordsPerPage": {

    "List": [

      {

        "PageNumber": 1,

        "Count": 6

      },

      {

        "PageNumber": 2,

        "Count": 6

      }

    ]

  },

  "Code": 200,

  "Status": "OK"

}

SDK Source

The Aspose for Cloud SDKs can be downloaded from the following page: Available SDKs

SDK Examples

	// For complete examples and data files, please go to https://github.com/aspose-pdf/Aspose.Pdf-for-Cloud
	PdfApi pdfApi = new PdfApi("API_KEY", "APP_SID");

	String fileName = "sample-input.pdf";
	String storage = "";
	String folder = "";

	try
	{
	// Upload source file to aspose cloud storage
	pdfApi.UploadFile(fileName, System.IO.File.ReadAllBytes(Common.GetDataDir() + fileName));

	// Invoke Aspose.PDF Cloud SDK API to get words count per page from pdf document
	WordCountResponse apiResponse = pdfApi.GetWordsPerPage(fileName, storage, folder);

	if (apiResponse != null && apiResponse.Status.Equals("OK"))
	{
	foreach (PageWordCount PageWordCount in apiResponse.WordsPerPage.List)
	{
	Console.WriteLine("Page Number :: " + PageWordCount.PageNumber + " Total Words :: " + PageWordCount.Count);
	}
	Console.ReadKey();
	}
	}
	catch (Exception ex)
	{
	System.Diagnostics.Debug.WriteLine("error:" + ex.Message + "\n" + ex.StackTrace);
	}

view raw Examples-DotNet-CSharp-Pages-GetWordsCount-1.cs hosted with ❤ by GitHub

Node.js

	For complete examples and data files, please go to https://github.com/aspose-pdf/Aspose.Pdf-for-Cloud
	var fs = require('fs');
	var assert = require('assert');
	var PdfApi = require('asposepdfcloud');
	var StorageApi = require('asposestoragecloud');
	var configProps = require('../config/config.json');
	var data_path = '../../../Data/';

	var AppSID = configProps.app_sid;
	var AppKey = configProps.api_key;
	var config = {'appSid':AppSID,'apiKey':AppKey , 'debug' : true};

	// Instantiate Aspose Storage API SDK
	var storageApi = new StorageApi(config);
	// Instantiate Aspose.Pdf API SDK
	var pdfApi = new PdfApi(config);

	// Set input file name
	var name = "sample-input.pdf";

	try {
	// Upload source file to aspose cloud storage
	storageApi.PutCreate(name, null, null, data_path + name , function(responseMessage) {

	assert.equal(responseMessage.status, 'OK', '');

	pdfApi.GetWordsPerPage(name, null, null, function(responseMessage) {
	assert.equal(responseMessage.status, 'OK');


	// Display the annotation info
	responseMessage.body.WordsPerPage.List.forEach(function(PageWordCount) {
	console.log("Page Number :: " + PageWordCount.PageNumber + " Total Words :: " + PageWordCount.Count);
	});

	});
	});

	}
	catch (e)
	{
	console.log("exception in example");
	console.log(e);
	}

view raw Examples-Node.js-Pages-GetWordsCount-1.js hosted with ❤ by GitHub

Java

	// For complete examples and data files, please go to https://github.com/aspose-pdf/Aspose.PDF-for-Cloud
	String fileName = "sample-input.pdf";
	String storage = "";
	String folder = "";
	Path inputFile = Utils.getPath(ApendPDFFileExample.class, fileName);
	try
	{
	// Instantiate Aspose Words API SDK
	PdfApi pdfApi = new PdfApi(Configuration.apiKey, Configuration.appSID, true);
	// Upload source file to aspose cloud storage
	pdfApi.uploadFile(templateFile, inputFile.toFile(),null);
	// Invoke Aspose.PDF Cloud SDK API to get all annotations from pdf page
	WordCountResponse apiResponse = pdfApi.GetWordsPerPage(fileName, storage, folder);
	if (apiResponse != null && apiResponse.getStatus().equals("OK"))
	{
	for (PageWordCount PageWordCount : apiResponse.getWordsPerPage().getList())
	{
	System.out.println("Page Number :: " + PageWordCount.getPageNumber() + " Total Words :: " + PageWordCount.getCount());
	}
	}
	}
	catch (Exception ex)
	{
	ex.printStackTrace();
	}

view raw Examples-JAVA-SDK-src-main-java-com-aspose-pdf-cloud-examples-documents-GetWordsPerPageExample-create-pdf-svg.java hosted with ❤ by GitHub

Python

	import asposepdfcloud
	from asposepdfcloud.PdfApi import PdfApi
	from asposepdfcloud.PdfApi import ApiException
	from asposepdfcloud.models import TextReplaceListRequest
	from asposepdfcloud.models import TextReplace


	import asposestoragecloud
	from asposestoragecloud.StorageApi import StorageApi
	from asposestoragecloud.StorageApi import ResponseMessage

	apiKey = "XXXXX" #sepcify App Key
	appSid = "XXXXX" #sepcify App SID
	apiServer = "http://api.aspose.com/v1.1"
	data_folder = "../../data/"

	#Instantiate Aspose Storage API SDK
	storage_apiClient = asposestoragecloud.ApiClient.ApiClient(apiKey, appSid, True)
	storageApi = StorageApi(storage_apiClient)
	#Instantiate Aspose Pdf API SDK
	api_client = asposepdfcloud.ApiClient.ApiClient(apiKey, appSid, True)
	pdfApi = PdfApi(api_client);
	# set input file name
	fileName = "sample-input.pdf"
	data_folde = ""
	name = "new-sample.pdf"
	try:
	# Instantiate Aspose Storage API SDK
	storage_apiClient = asposestoragecloud.ApiClient.ApiClient(apiKey, appSid, True)
	storageApi = StorageApi(storage_apiClient)

	# Instantiate Aspose Pdf API SDK
	api_client = asposepdfcloud.ApiClient.ApiClient(apiKey, appSid, True)
	pdfApi = PdfApi(api_client);


	# upload file to aspose cloud storage
	response = storageApi.PutCreate(fileName, data_folder + name)


	# invoke Aspose.Pdf Cloud SDK API to insert watermark image as stamp to a PDF page
	response = pdfApi.GetWordsPerPage(fileName)

	if response.Status == "OK":
	print("Words per page done")


	except ApiException as ex:
	print ("ApiException:")
	print ("Code:" + str(ex.code))
	print ("Message:" +ex.message)

view raw GetWordCountFromDocument.py hosted with ❤ by GitHub

Android

	// For complete examples and data files, please go to https://github.com/aspose-pdf/Aspose.PDF-for-Cloud
	String fileName = "sample-input.pdf";
	String storage = "";
	String folder = "";
	Path inputFile = Utils.getPath(ApendPDFFileExample.class, fileName);
	try
	{
	StorageApi storageApi = new StorageApi(Configuration.apiKey, Configuration.appSID, true);
	// Instantiate Aspose Words API SDK
	PdfApi pdfApi = new PdfApi(Configuration.apiKey, Configuration.appSID, true);
	// Upload source file to aspose cloud storage
	storageApi.PutCreate(fileName, "", "",inputFile.toFile());
	// Invoke Aspose.PDF Cloud SDK API to get all annotations from pdf page
	WordCountResponse apiResponse = pdfApi.GetWordsPerPage(fileName, storage, folder);
	if (apiResponse != null && apiResponse.getStatus().equals("OK"))
	{
	for (PageWordCount PageWordCount : apiResponse.getWordsPerPage().getList())
	{
	System.out.println("Page Number :: " + PageWordCount.getPageNumber() + " Total Words :: " + PageWordCount.getCount());
	}
	}
	}
	catch (Exception ex)
	{
	ex.printStackTrace();
	}

view raw Examples-JAVA-SDK-src-main-java-com-aspose-pdf-cloud-examples-documents-GetWordsPerPageExample-create-pdf-svg.java hosted with ❤ by GitHub

	// For complete examples and data files, please go to https://github.com/aspose-pdf/Aspose.Pdf-for-Cloud
	fileName := "4pages.pdf"
	filePath := "data/4pages.pdf"

	// init words cloud api
	config := asposepdfcloud.NewConfiguration(AppSid, AppKey, BaseURL)
	client := asposepdfcloud.NewAPIClient(config)

	// Upload 1st document
	file, _ := os.Open(filePath)
	_, _, err1 := client.PdfApi.UploadFile(fileName, file, nil)
	if err1 != nil {
	fmt.Println(err1)
	}

	options := map[string]interface{}{
	"storage": "First Storage",
	}

	//Get words per page
	wordCountResponse, response, _ := client.PdfApi.GetWordsPerPage(fileName, options)

	fmt.Println(response.Status)
	fmt.Println("1st page words count:", wordCountResponse.WordsPerPage.List[0].Count)

view raw Examples-Go-GetWordsPerPage.go hosted with ❤ by GitHub

Get PDF Document Page Count Retrieve PDF Page Information