Section:

PDF2Office - Convert PDF to DOCX, XSLX - Java Sample Code

Requirements
Server SDK
Package: Office Conversion
Module: Structured Output

Sample code for using Apryse SDK to programmatically convert generic PDF documents to Word, Excel, PowerPoint; provided in Python, C++, C#, Go, Java, Node.js (JavaScript), PHP, Ruby and VB.

To convert files to Office with this Apryse Server SDK sample code:

  1. Complete the Get started with Server SDK process in your language/framework.
  2. After you complete the Get Started with Server SDK work in your language/framework from Step 1 above, next, download the Structured Output Module.
  3. Add sample code provided in this guide

To use this feature in production, your license key will need the Office Conversion Package. Trial keys already include all packages.

Learn more about our Server SDK and PDF to Office Conversion.

1//
2// Copyright (c) 2001-2024 by Apryse Software Inc. All Rights Reserved.
3// Consult legal.txt regarding legal and license information.
4//---------------------------------------------------------------------------------------
5
6import com.pdftron.common.PDFNetException;
7import com.pdftron.pdf.*;
8
9//---------------------------------------------------------------------------------------
10// The following sample illustrates how to use the PDF::Convert utility class to convert 
11// documents and files to Office.
12//
13// The Structured Output module is an optional PDFNet Add-on that can be used to convert PDF
14// and other documents into Word, Excel, PowerPoint and HTML format.
15//
16// The Apryse SDK Structured Output module can be downloaded from
17// https://docs.apryse.com/core/info/modules/
18//
19// Please contact us if you have any questions.
20//---------------------------------------------------------------------------------------
21
22public class PDF2OfficeTest 
23{
24    // Relative path to the folder containing test files.
25    static String inputPath = "../../TestFiles/";
26    static String outputPath = "../../TestFiles/Output/";
27
28    /// <summary>
29    /// The main entry point for the application.
30    /// </summary>
31    public static void main(String[] args) 
32    {
33        // The first step in every application using PDFNet is to initialize the 
34        // library. The library is usually initialized only once, but calling 
35        // Initialize() multiple times is also fine.
36        PDFNet.initialize(PDFTronLicense.Key());
37
38        PDFNet.addResourceSearchPath("../../../Lib/");
39
40        try {
41            if (!StructuredOutputModule.isModuleAvailable()) {
42                System.out.println();
43                System.out.println("Unable to run the sample: Apryse SDK Structured Output module not available.");
44                System.out.println("-----------------------------------------------------------------------------");
45                System.out.println("The Structured Output module is an optional add-on, available for download");
46                System.out.println("at https://docs.apryse.com/core/info/modules/. If you have already");
47                System.out.println("downloaded this module, ensure that the SDK is able to find the required files");
48                System.out.println("using the PDFNet::AddResourceSearchPath() function.");
49                System.out.println();
50                return;
51            }
52        } catch (PDFNetException e) {
53            System.out.println(e);
54            return;
55        }  catch (Exception e) {
56            System.out.println(e);
57            return;
58        }
59
60        boolean err = false;
61
62        //////////////////////////////////////////////////////////////////////////
63        // Word
64        //////////////////////////////////////////////////////////////////////////
65
66        try {
67            // Convert PDF document to Word
68            System.out.println("Converting PDF to Word");
69
70            String outputFile = outputPath + "paragraphs_and_tables.docx";
71
72            Convert.toWord(inputPath + "paragraphs_and_tables.pdf", outputFile);
73
74            System.out.println("Result saved in " + outputFile);
75        } catch (PDFNetException e) {
76            System.out.println("Unable to convert PDF document to Word, error: ");
77            System.out.println(e);
78            err = true;
79        }  catch (Exception e) {
80            System.out.println("Unknown Exception, error: ");
81            System.out.println(e);
82            err = true;
83        }
84
85        //////////////////////////////////////////////////////////////////////////
86
87        try {
88            // Convert PDF document to Word with options
89            System.out.println("Converting PDF to Word with options");
90
91            String outputFile = outputPath + "paragraphs_and_tables_first_page.docx";
92
93            Convert.WordOutputOptions wordOutputOptions = new Convert.WordOutputOptions();
94
95            // Convert only the first page
96            wordOutputOptions.setPages(1, 1);
97
98            Convert.toWord(inputPath + "paragraphs_and_tables.pdf", outputFile, wordOutputOptions);
99
100            System.out.println("Result saved in " + outputFile);
101        } catch (PDFNetException e) {
102            System.out.println("Unable to convert PDF document to Word, error: ");
103            System.out.println(e);
104            err = true;
105        }  catch (Exception e) {
106            System.out.println("Unknown Exception, error: ");
107            System.out.println(e);
108            err = true;
109        }
110
111        //////////////////////////////////////////////////////////////////////////
112        // Excel
113        //////////////////////////////////////////////////////////////////////////
114
115        try {
116            // Convert PDF document to Excel
117            System.out.println("Converting PDF to Excel");
118
119            String outputFile = outputPath + "paragraphs_and_tables.xlsx";
120
121            Convert.toExcel(inputPath + "paragraphs_and_tables.pdf", outputFile);
122
123            System.out.println("Result saved in " + outputFile);
124        } catch (PDFNetException e) {
125            System.out.println("Unable to convert PDF document to Excel, error: ");
126            System.out.println(e);
127            err = true;
128        }  catch (Exception e) {
129            System.out.println("Unknown Exception, error: ");
130            System.out.println(e);
131            err = true;
132        }
133
134        //////////////////////////////////////////////////////////////////////////
135
136        try (PDFDoc doc = new PDFDoc()) {
137            // Convert PDF document to Excel with options
138            System.out.println("Converting PDF to Excel with options");
139
140            String outputFile = outputPath + "paragraphs_and_tables_second_page.xlsx";
141
142            Convert.ExcelOutputOptions excelOutputOptions = new Convert.ExcelOutputOptions();
143
144            // Convert only the second page
145            excelOutputOptions.setPages(2, 2);
146
147            Convert.toExcel(inputPath + "paragraphs_and_tables.pdf", outputFile, excelOutputOptions);
148
149            System.out.println("Result saved in " + outputFile);
150        } catch (PDFNetException e) {
151            System.out.println("Unable to convert PDF document to Excel, error: ");
152            System.out.println(e);
153            err = true;
154        }  catch (Exception e) {
155            System.out.println("Unknown Exception, error: ");
156            System.out.println(e);
157            err = true;
158        }
159
160        //////////////////////////////////////////////////////////////////////////
161        // PowerPoint
162        //////////////////////////////////////////////////////////////////////////
163
164        try {
165            // Convert PDF document to PowerPoint
166            System.out.println("Converting PDF to PowerPoint");
167
168            String outputFile = outputPath + "paragraphs_and_tables.pptx";
169
170            Convert.toPowerPoint(inputPath + "paragraphs_and_tables.pdf", outputFile);
171
172            System.out.println("Result saved in " + outputFile);
173        } catch (PDFNetException e) {
174            System.out.println("Unable to convert PDF document to PowerPoint, error: ");
175            System.out.println(e);
176            err = true;
177        }  catch (Exception e) {
178            System.out.println("Unknown Exception, error: ");
179            System.out.println(e);
180            err = true;
181        }
182
183        //////////////////////////////////////////////////////////////////////////
184
185        try {
186            // Convert PDF document to PowerPoint with options
187            System.out.println("Converting PDF to PowerPoint with options");
188
189            String outputFile = outputPath + "paragraphs_and_tables_first_page.pptx";
190
191            Convert.PowerPointOutputOptions powerPointOutputOptions = new Convert.PowerPointOutputOptions();
192
193            // Convert only the first page
194            powerPointOutputOptions.setPages(1, 1);
195
196            Convert.toPowerPoint(inputPath + "paragraphs_and_tables.pdf", outputFile, powerPointOutputOptions);
197
198            System.out.println("Result saved in " + outputFile);
199        } catch (PDFNetException e) {
200            System.out.println("Unable to convert PDF document to PowerPoint, error: ");
201            System.out.println(e);
202            err = true;
203        }  catch (Exception e) {
204            System.out.println("Unknown Exception, error: ");
205            System.out.println(e);
206            err = true;
207        }
208
209        //////////////////////////////////////////////////////////////////////////
210
211        PDFNet.terminate();
212        System.out.println("Done.");        
213    }
214}

Did you find this helpful?

Trial setup questions?

Ask experts on Discord

Need other help?

Contact Support

Pricing or product questions?

Contact Sales