java实现抽取word和pdf文件中的内容

本文使用POI来实现功能：

导入依赖

导入POI主要的依赖：

<!-- 用于对文件操作，例如写操作 -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.15</version>
</dependency>

<!-- .docx解析依赖 -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.15</version>
</dependency>
<!-- .doc解析依赖 -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.15</version>
</dependency>
<!-- .pdf解析依赖 -->
<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.4</version>
</dependency>
<!-- 单元测试依赖，也可以自己写一个测试类，这个无关紧要 -->
<dependency>
    <groupId>junit</groupId>
    <artifactId>junit</artifactId>
    <version>4.12</version>
    <scope>test</scope>
</dependency>

需要保持上面的依赖的版本的一致性。不然会报各种莫名其妙的错！

工具类

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;

/**
 * @Author: 勇哥
 * @Date: 2021/7/8 14:25
 */
public class FileExtract {
    public static String fileExtractText(String filePath) throws Exception {
        String text;
        if (filePath == null || "".equals(filePath)) {
            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;
    }
}

测试

public static void main(String[] args) throws XmlException, OpenXML4JException, IOException {
//        String filePath = "F:\\extract\\20181226163749u1xcw.pdf";
        String filePath = "F:\\extract\\12.docx";
        try {
            String s = FileExtract.fileExtractText(filePath);
            System.out.println(s);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

结果分析：
通过工具扫描出来的PDF不能提取出文字。