Java操作Word文档的全攻略(读取doc与docx文件)

# docx文件解压后结构
unzip -l document.docx

<dependency>  
  <groupId>org.apache.poi</groupId>  
  <artifactId>poi-ooxml</artifactId>  
  <version>5.2.3</version>  
</dependency>  

implementation 'org.apache.poi:poi-ooxml:5.2.3'

getParagraphs()  // 获取所有段落
getTables()      // 获取所有表格
getFootnotes()   // 获取脚注

getFontSize()  // 字号
isBold()       // 加粗状态
getColor()     // 颜色值

getRows()       // 获取行
getCell(row,col)// 定位单元格

import org.apache.poi.xwpf.usermodel.*;

public class DocxReader {
    public static void main(String[] args) throws Exception {
        // 1. 加载文档
        XWPFDocument doc = new XWPFDocument(
            new FileInputStream("report.docx"));
        
        // 2. 段落处理
        System.out.println("==== 段落内容 ====");
        doc.getParagraphs().forEach(p -> {
            System.out.println(p.getText());
            
            // 获取文本样式
            p.getRuns().forEach(run -> {
                System.out.printf("[字体:%s 大小:%d]%n", 
                    run.getFontName(), run.getFontSize());
            });
        });
        
        // 3. 表格处理
        System.out.println("==== 表格数据 ====");
        for (XWPFTable table : doc.getTables()) {
            for (XWPFTableRow row : table.getRows()) {
                for (XWPFTableCell cell : row.getTableCells()) {
                    System.out.print(cell.getText() + " | ");
                }
                System.out.println();
            }
        }
        
        // 4. 释放资源
        doc.close();
    }
}

<dependency>  
  <groupId>org.apache.poi</groupId>  
  <artifactId>poi-scratchpad</artifactId>  
  <version>5.2.3</version>  
</dependency>  

getRange()            // 获取文档内容范围
getSummaryInformation() // 元数据（作者、标题等）

numParagraphs()      // 段落总数
getParagraph(index)  // 获取特定段落

isBold()
isItalic()
getFontSize()

import org.apache.poi.hwpf.*;
import org.apache.poi.hwpf.usermodel.*;

public class DocReader {
    public static void main(String[] args) throws Exception {
        // 1. 加载文档
        HWPFDocument doc = new HWPFDocument(
            new FileInputStream("legacy.doc"));
        
        // 2. 获取文档范围
        Range range = doc.getRange();
        
        // 3. 读取段落
        System.out.println("==== 文本内容 ====");
        for (int i = 0; i < range.numParagraphs(); i++) {
            Paragraph para = range.getParagraph(i);
            System.out.println(para.text());
        }
        
        // 4. 读取表格（需要特殊处理）
        TableIterator it = new TableIterator(range);
        while (it.hasNext()) {
            Table table = it.next();
            for (int r = 0; r < table.numRows(); r++) {
                TableRow row = table.getRow(r);
                for (int c = 0; c < row.numCells(); c++) {
                    TableCell cell = row.getCell(c);
                    System.out.print(cell.text().trim() + "\t");
                }
                System.out.println();
            }
        }
        
        // 5. 释放资源
        doc.close();
    }
}

XWPFParagraph paragraph = doc.getParagraphArray(0);
for (XWPFRun run : paragraph.getRuns()) {
    CTRPr pr = run.getCTR().getRPr();
    if (pr != null) {
        System.out.println("加粗: " + pr.isSetB());
        System.out.println("字体: " + run.getFontName());
    }
}

import org.apache.poi.openxml4j.opc.*;
import org.apache.poi.xwpf.eventusermodel.*;

public class LargeDocxReader {
    public static void main(String[] args) throws Exception {
        OPCPackage pkg = OPCPackage.open("huge.docx");
        XWPFReader reader = new XWPFReader(pkg);
        
        // 自定义内容处理器
        XWPFReader.SAXParser parser = reader.getSAXParser();
        parser.parse(new XWPFVisitor() {
            @Override
            public void visitParagraph(XWPFParagraph paragraph) {
                System.out.println(paragraph.getText());
            }
        });
        
        pkg.close();
    }
}

public void processDocument(File file) throws Exception {
    String name = file.getName().toLowerCase();
    
    if (name.endsWith(".docx")) {
        try (XWPFDocument doc = new XWPFDocument(new FileInputStream(file))) {
            // docx处理逻辑
        }
    } else if (name.endsWith(".doc")) {
        try (HWPFDocument doc = new HWPFDocument(new FileInputStream(file))) {
            // doc处理逻辑
        }
    } else {
        throw new IllegalArgumentException("Unsupported format");
    }
}

// 尝试不同编码方案
String[] encodings = {"GBK", "UTF-8", "ISO-8859-1"};
for (String enc : encodings) {
    try {
        String text = new String(paragraph.getBytes(), enc);
        System.out.println(enc + ": " + text);
        break;
    } catch (Exception e) {
        continue;
    }
}