Java对word和pdf抽取文字

冷不防 2022-05-17 05:53 577阅读 0赞

##### 前言： #####

本文用常见的java工具包对word和pdf进行文字提取

1.首先声明一下依赖的包  
注意，Word 03和Word 07是两种不同类型的文件，  
一种以.doc结尾，另一种以.docx结尾，依赖的包不一样。

<dependency>
                <groupId>org.apache.poi</groupId>
                <artifactId>poi</artifactId>
                <version>3.15</version>
            </dependency>
    
            
            <dependency>
                <groupId>org.apache.poi</groupId>
                <artifactId>poi-ooxml</artifactId>
                <version>3.15</version>
            </dependency>
            
            <dependency>
                <groupId>org.apache.poi</groupId>
                <artifactId>poi-scratchpad</artifactId>
                <version>3.15</version>
            </dependency>
            
            <dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>pdfbox</artifactId>
                <version>2.0.4</version>
            </dependency>
            
            <dependency>
                <groupId>junit</groupId>
                <artifactId>junit</artifactId>
                <version>4.12</version>
                <scope>test</scope>
            </dependency>

2.把三种类型的文件抽取都写到一个类里面，如下

package com.chinamobile.cmss.i3.ba.extractText;
    
    import org.apache.pdfbox.pdmodel.PDDocument;
    import org.apache.pdfbox.text.PDFTextStripper;
    import org.apache.poi.POIXMLDocument;
    import org.apache.poi.POIXMLTextExtractor;
    import org.apache.poi.hwpf.extractor.WordExtractor;
    import org.apache.poi.openxml4j.opc.OPCPackage;
    import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
    
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.InputStream;
    
    public class FileExtract {
        public String fileExtractText(String filePath) throws Exception {
            String text;
            if(filePath.isEmpty()){
                return "";
            }
            if(filePath.toLowerCase().endsWith("doc")){
                InputStream file = new FileInputStream(new File(filePath));
                WordExtractor wordExtractor = new WordExtractor(file);
                text = wordExtractor.getText();
                file.close();
                wordExtractor.close();
            }
            else if(filePath.toLowerCase().endsWith("docx")){
                OPCPackage opcPackage = POIXMLDocument.openPackage(filePath);
                POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
                text = extractor.getText();
                opcPackage.close();
                extractor.close();
            }
            else if(filePath.toLowerCase().endsWith("pdf")){
                PDDocument pdDocument;
                InputStream file = new FileInputStream(new File(filePath));
                pdDocument = PDDocument.load(file);
                PDFTextStripper stripper = new PDFTextStripper();
                text = stripper.getText(pdDocument);
                file.close();
                pdDocument.close();
            }else {
                return "error file";
            }
            return text;
        }
    }

3.写一个测试文件，如下

import org.junit.Test;
    
    public class ExtractTest {
        @Test
        public void FileExtractTest(){
            String filePath = "D:\\baoxiao.docx";
            FileExtract fileExtract = new FileExtract();
            String text = null;
            try {
                text = fileExtract.fileExtractText(filePath);
            } catch (Exception e) {
                e.printStackTrace();
            }
            System.out.println(text);
        }
    }

4.测试结果  
无论是word还是pdf都无法识别图片，程序会自动过滤掉图片  
可以抽取包括表格在内的word和pdf中的文字