Java中对于doc、docx、xls、xlsx、pdf内容读取

一、引用所需要的jar包

 <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>4.0.1</version>
    </dependency>
    
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-scratchpad</artifactId>
        <version>4.0.1</version>
    </dependency>
    
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml-schemas</artifactId>
        <version>4.0.1</version>
    </dependency>

    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi</artifactId>
        <version>4.0.1</version>
    </dependency>
    
    <dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>2.0.23</version>
    </dependency>

二、进行进行导包

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.ss.usermodel.*;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;

三、读取文件内容

1、对于doc文件读取文件内容

    /**
     * doc读取文件内容
     * @param file       文件路径
     */
public String searchContent(File file) {
    String text = "";
    try (FileInputStream fis = new FileInputStream(file);
         HWPFDocument document = new HWPFDocument(fis)) {
        Range range = document.getRange();
        text = range.text();
        return text;
    } catch (Exception e) {
        return text;
    }
}

2、docx文件读取文件内容

   /**
     * 读取文件内容并搜索匹配的文本
     *
     * @param file       文件路径
     */
    public String docxSearchContent(File file) {
     	String s = "";
        try {
            FileInputStream fis = new FileInputStream(file);
            XWPFDocument document = new XWPFDocument(fis);
            List<XWPFParagraph> paragraphs = document.getParagraphs();
            for (XWPFParagraph paragraph : paragraphs) {
                String text = paragraph.getText();
                s += text;
            }
            document.close();
            fis.close();
            return s;
        } catch (Exception e) {
            return s;
        }
    }

3、pdf文件内容读取

/**
 * 读取pdf进行匹配
 *
 * @param file 文件
 */
private String pdfSearch(File file) {
    String info = "";
    try {
        //multipartFile为multipartFile文件类型，将文件转化为文件流被PDDocument加载
        PDDocument document = PDDocument.load(file);
        document.getClass();
        //使用PDFTextStripper 工具
        PDFTextStripper tStripper = new PDFTextStripper();
        //设置文本排序，有规则输出
        tStripper.setSortByPosition(true);
        //获取所有文字信息
        info = tStripper.getText(document);
        document.close();
        return info;
    } catch (Exception e) {
        return info;
    }
}

4、xlsx文件内容读取

 /**
 * @param file 文件
 * @return List<List<String>> 
 */
private List<List<String>>  xlsxSearch(File file) {
 List<List<String>> listAll = new ArrayList<>();
    try {
       
        // 1. 创建 Workbook 对象
        Workbook workbook = new XSSFWorkbook(new FileInputStream(file));

        // 2. 创建 Sheet 对象
        // 第一个工作表
        Sheet sheet = workbook.getSheetAt(0);

        // 3. 遍历每一行，获取单元格数据
        for (Row row : sheet) {
            List<String> list = new ArrayList<>();
            for (Cell cell : row) {
                String value;
                cell.setCellType(CellType.STRING);
                if (null == cell) {
                    value = "";
                } else {
                    value = cell.toString();
                }
                list.add(value);
            }
            listAll.add(list);
        }
        // 4. 关闭 Workbook 对象
        workbook.close();
        return listAll;
    } catch (Exception e) {
        log.info("xlsxSearch==[{}]", e);
         return listAll;
    }
}

5、xls文件内容读取

 /**
     * 
     * @param file 文件
     * @return List<List<String>>
     */
private List<List<String>> xlsSearch(File file) {
    List<List<String>> listAll = new ArrayList<>();
    boolean flag = false;
    try {
        // 1. 创建 Workbook 对象
        HSSFWorkbook workbook = new HSSFWorkbook(new FileInputStream(file));
        // 2. 创建 Sheet 对象
        // 第一个工作表
        HSSFSheet sheet = workbook.getSheetAt(0);
        // 3. 遍历每一行，获取单元格数据
        for (Row row : sheet) {
            List<String> list = new ArrayList<>();
            for (Cell cell : row) {
                String value;
                cell.setCellType(CellType.STRING);
                if (null == cell) {
                    value = "";
                } else {
                    value = cell.toString();
                }
                list.add(value);
            }
            listAll.add(list);
        }
        // 4. 关闭 Workbook 对象
        workbook.close();
        return listAll;
    } catch (Exception e) {
       return listAll;
    }
}