Hi guys,
Following code will enable us to read Microsoft Word Document file using JAVA API.
| /* | |
| * To change this license header, choose License Headers in Project Properties. | |
| * To change this template file, choose Tools | Templates | |
| * and open the template in the editor. | |
| */ | |
| package com.milind.mr.doc.test; | |
| /** | |
| * | |
| * @author milind | |
| */ | |
| import java.io.File; | |
| import java.io.FileInputStream; | |
| import java.util.List; | |
| import org.apache.commons.io.FilenameUtils; | |
| import org.apache.poi.hwpf.HWPFDocument; | |
| import org.apache.poi.hwpf.extractor.WordExtractor; | |
| import org.apache.poi.xwpf.usermodel.XWPFDocument; | |
| import org.apache.poi.xwpf.usermodel.XWPFParagraph; | |
| public class MicrosoftWordDocReader { | |
| public static void readDocFile(String fileName) { | |
| try { | |
| File file = new File(fileName); | |
| FileInputStream fis = new FileInputStream(file.getAbsolutePath()); | |
| HWPFDocument doc = new HWPFDocument(fis); | |
| WordExtractor we = new WordExtractor(doc); | |
| String[] paragraphs = we.getParagraphText(); | |
| System.out.println("Total no of paragraph " + paragraphs.length); | |
| for (String para : paragraphs) { | |
| System.out.println(para.toString()); | |
| } | |
| fis.close(); | |
| } catch (Exception e) { | |
| e.printStackTrace(); | |
| } | |
| } | |
| public static void readDocxFile(String fileName) { | |
| try { | |
| File file = new File(fileName); | |
| FileInputStream fis = new FileInputStream(file.getAbsolutePath()); | |
| XWPFDocument document = new XWPFDocument(fis); | |
| List<XWPFParagraph> paragraphs = document.getParagraphs(); | |
| System.out.println("Total no of paragraph " + paragraphs.size()); | |
| for (XWPFParagraph para : paragraphs) { | |
| System.out.println(para.getText()); | |
| } | |
| fis.close(); | |
| } catch (Exception e) { | |
| e.printStackTrace(); | |
| } | |
| } | |
| public static void main(String[] args) { | |
| String ext = FilenameUtils.getExtension("D:\\test.docx"); | |
| System.out.println("extension : " + ext); | |
| if ("docx".equalsIgnoreCase(ext)) { | |
| readDocxFile("D:\\Test.docx"); | |
| } else if ("doc".equalsIgnoreCase(ext)) { | |
| readDocFile("D:\\Test.doc"); | |
| } else { | |
| System.out.println("INVALID FILE TYPE. ONLY .doc and .docx are permitted."); | |
| } | |
| } | |
| } |
Following is the pom.xml contents
| <?xml version="1.0" encoding="UTF-8"?> | |
| <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> | |
| <modelVersion>4.0.0</modelVersion> | |
| <groupId>com.milind</groupId> | |
| <artifactId>mr-doc</artifactId> | |
| <version>1.0</version> | |
| <packaging>jar</packaging> | |
| <properties> | |
| <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | |
| <maven.compiler.source>1.7</maven.compiler.source> | |
| <maven.compiler.target>1.7</maven.compiler.target> | |
| </properties> | |
| <dependencies> | |
| <dependency> | |
| <groupId>org.apache.poi</groupId> | |
| <artifactId>poi-scratchpad</artifactId> | |
| <version>3.0.1-FINAL</version> | |
| </dependency> | |
| <dependency> | |
| <groupId>org.apache.poi</groupId> | |
| <artifactId>poi-ooxml</artifactId> | |
| <version>3.9</version> | |
| </dependency> | |
| <dependency> | |
| <groupId>commons-io</groupId> | |
| <artifactId>commons-io</artifactId> | |
| <version>2.4</version> | |
| <type>jar</type> | |
| </dependency> | |
| </dependencies> | |
| </project> |
Following is the word file contents
Following is the output of code.
Thanks for having a read.
Do comment below for your queries.
how to extract data from specific page
Did you mean a specific page in the word document?
IF YES, I have not explored page specific data extraction.
Please let me know if you found the solution for this.
Appreciate it.