java如何利用poi解析doc和docx中的数据

		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-scratchpad</artifactId>
			<version>3.17</version>
		</dependency>
		<!--POI包 -->
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>3.17</version>
		</dependency>

File file = new File(FileUtils.getUserDirectoryPath() + "/" + multipartFile.getOriginalFilename());
FileUtils.copyInputStreamToFile(multipartFile.getInputStream(), file);

		String fileName = file.getName().toLowerCase();
        FileInputStream in = new FileInputStream(file);
        if (fileName.endsWith(".doc")) {
            // 处理doc格式 即office2003版本
            handlerDoc(in);
        }
        if (fileName.endsWith(".docx")) {
            handlerDocx(in);
        }

	/**
     * doc 格式解析
     *
     * @param in
     * @throws IOException
     */
    private void handlerDoc(FileInputStream in) throws IOException {
        POIFSFileSystem pfs = new POIFSFileSystem(in);
        HWPFDocument hwpf = new HWPFDocument(pfs);

        //得到文档的读取范围
        Range range = hwpf.getRange();
        for (int i = 0; i < range.numParagraphs(); i++) {
            //段落
            Paragraph p = range.getParagraph(i);
            //段落文本
            String paragraphText = p.text().replace("\r", "");
            log.info("paragraphText = {}", paragraphText );
            if (paragraphText.contains(VALUE_YLYC)) {
                analyze = false;
            }
        }

        TableIterator it = new TableIterator(range);
        // 迭代文档中的表格
        // 如果有多个表格只读取需要的一个 set是设置需要读取的第几个表格，total是文件中表格的总数
        int set = 1, total = 1;
        int num = set;
        for (int i = 0; i < set - 1; i++) {
            it.hasNext();
            it.next();
        }
        while (it.hasNext()) {
            Map<String, List<String>> tabelText = DocUtils.getTabelDocText((Table) it.next());
            log.info("tabelText = {}", tabelText);
        }
        // 过滤多余的表格
        while (num < total) {
            it.hasNext();
            it.next();
            num += 1;
        }
    }

    /**
     * docx 格式解析
     *
     * @param in
     * @throws IOException
     */
    private void handlerDocx(FileInputStream in) throws IOException {
        XWPFDocument xwpf = new XWPFDocument(in);
        // 获取word中的所有段落与表格
        List<IBodyElement> elements = xwpf.getBodyElements();
        // 解析表格后续不解析
        for (IBodyElement element : elements) {
            // 段落
            if (element instanceof XWPFParagraph) {
                String paragraphText = DocUtils.getParagraphText((XWPFParagraph) element);
                log.info("paragraphText = {}", paragraphText);
            } else if (element instanceof XWPFTable) {
                // 表格 
                Map<String, List<String>> tabelText = DocUtils.getTabelText((XWPFTable) element);
                log.info("tabelText = {}", tabelText);
            } else {
                log.info("其他内容");
            }
        }
    }

package com.hundsun.fais.innerreport.utils;

import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Table;
import org.apache.poi.hwpf.usermodel.TableCell;
import org.apache.poi.hwpf.usermodel.TableRow;
import org.apache.poi.xwpf.usermodel.*;

import java.util.*;

/**
 * @author lvbaolin
 * @date 2021/4/2 10:39
 */
public class DocUtils {


    /**
     * docx 格式获取表格内容
     *
     * @param table
     */
    public static Map<String, List<String>> getTabelText(XWPFTable table) {
        Map<String, List<String>> result = new LinkedHashMap<>();
        List<XWPFTableRow> rows = table.getRows();
        for (XWPFTableRow row : rows) {
            String key = null;
            List<String> list = new ArrayList<>(16);
            int i = 0;
            List<XWPFTableCell> cells = row.getTableCells();
            for (XWPFTableCell cell : cells) {
                // 简单获取内容（简单方式是不能获取字体对齐方式的）
                StringBuffer sb = new StringBuffer();
                // 一个单元格可以理解为一个word文档，单元格里也可以加段落与表格
                List<XWPFParagraph> paragraphs = cell.getParagraphs();
                for (XWPFParagraph paragraph : paragraphs) {
                    sb.append(DocUtils.getParagraphText(paragraph));
                }
                if (i == 0) {
                    key = sb.toString();
                } else {
                    String value = sb.toString();
                    list.add(value == null || Objects.deepEquals(value, "") ? null : value.replace(",", ""));
                }
                i++;
            }
            result.put(key, list);
        }
        return result;
    }

    /**
     * docx 获取段落字符串
     * 获取段落内容
     *
     * @param paragraph
     */
    public static String getParagraphText(XWPFParagraph paragraph) {
        StringBuffer runText = new StringBuffer();
        // 获取段落中所有内容
        List<XWPFRun> runs = paragraph.getRuns();
        if (runs.size() == 0) {
            return runText.toString();
        }
        for (XWPFRun run : runs) {
            runText.append(run.text());
        }
        return runText.toString();
    }

    /**
     * doc 格式的字段解析表格
     * @param tb
     * @return
     */
    public static Map<String, List<String>> getTabelDocText(Table tb) {
        Map<String, List<String>> result = new HashMap<>(16);
        //迭代行，默认从0开始,可以依据需要设置i的值,改变起始行数，也可设置读取到那行，只需修改循环的判断条件即可
        for (int i = 0; i < tb.numRows(); i++) {
            List<String> list = new ArrayList<>(16);
            int x = 0;
            TableRow tr = tb.getRow(i);
            String key = null;
            //迭代列，默认从0开始
            for (int j = 0; j < tr.numCells(); j++) {
                //取得单元格
                TableCell td = tr.getCell(j);
                StringBuffer sb = new StringBuffer();

                //取得单元格的内容
                for (int k = 0; k < td.numParagraphs(); k++) {
                    Paragraph paragraph = td.getParagraph(k);
                    String s = paragraph.text();
                    //去除后面的特殊符号
                    if (null != s && !"".equals(s)) {
                        s = s.substring(0, s.length() - 1);
                    }
                    sb.append(s);
                }
                if (x == 0) {
                    key = sb.toString();
                } else {
                    String value = sb.toString();
                    list.add(value == null || Objects.deepEquals(value, "") ? null : value.replace(",", ""));
                }
                x++;
            }
            result.put(key, list);
        }
        return result;
    }
}