java解析word示例（支持docx、doc，wps格式）

1.导入pom.xml
需要先导入解析插件包

  <!-- POI-word文件处理需要 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.1.2</version>
        </dependency>

2.代码示例：

package com.common.utils;

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.slf4j.Logger;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

/**
 * @ClassName WordAlansis
 * @Description:  java解析word代码示例
 * @Author: mischen
 * @date: 14:57 2022/11/25
 * @Version 1.0
 */
public class WordAlansis {

    public static void main(String[] args) {
        String path ="C:\\Users\\Administrator\\Desktop\\公司资料\\面试\\1.docx";
       // Map<String, String> getContentWps = getContentWps(path);
       // System.out.println(getContentWps);
        Map<String, String> getContentWps = getContentDocx(new File(path));
        System.out.println(getContentWps);
    }

    /**
     * 获取正文文件内容，docx方法
     *
     * @param file
     * @return
     */
    public static Map<String, String> getContentDocx(File file) {
        Map<String, String> map = new HashMap();
        StringBuffer content = new StringBuffer("");
        String result = "0";  // 0表示获取正常，1表示获取异常
        InputStream is = null;
        Logger logger = null;
        try {
            //根据需求入参也可以改为文件路径，对应的输入流部分改为new File(路径)即可
            is = new FileInputStream(file);
            // 2007版本的word
            XWPFDocument xwpf = new XWPFDocument(is);    // 2007版本，仅支持docx文件处理
            List<XWPFParagraph> paragraphs = xwpf.getParagraphs();
            if (paragraphs != null && paragraphs.size() > 0) {
                for (XWPFParagraph paragraph : paragraphs) {
                    if (!paragraph.getParagraphText().startsWith("    ")) {
                        content.append(paragraph.getParagraphText().trim()).append("\r\n");
                    } else {
                        content.append(paragraph.getParagraphText());
                    }
                }
            }
        } catch (Exception e) {
            logger.error("docx解析正文异常:" + e);
            result = "1"; // 出现异常
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    logger.error("" + e);
                }
            }
            map.put("result", result);
            map.put("content", String.valueOf(content));
        }
        return map;
    }

    /**
     * 获取正文文件内容，doc方法
     *
     * @param path
     * @return
     */
    public static Map<String, String> getContentDoc(String path) {
        Map<String, String> map = new HashMap();
        StringBuffer content = new StringBuffer("");
        String result = "0";  // 0表示获取正常，1表示获取异常
        InputStream is = null;
        Logger logger = null;
        try {
            is = new FileInputStream(new File(path));
            // 2003版本的word
            WordExtractor extractor = new WordExtractor(is);  // 2003版本 仅doc格式文件可处理，docx文件不可处理
            String[] paragraphText = extractor.getParagraphText();   // 获取段落，段落缩进无法获取，可以在前添加空格填充
            if (paragraphText != null && paragraphText.length > 0) {
                for (String paragraph : paragraphText) {
                    if (!paragraph.startsWith("    ")) {
                        content.append(paragraph.trim()).append("\r\n");
                    } else {
                        content.append(paragraph);
                    }
                }
            }
        } catch (Exception e) {
            logger.error("doc解析正文异常:" + e);
            result = "1"; // 出现异常
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    logger.error("" + e);
                }
            }
            map.put("result", result);
            map.put("content", content.toString());
        }
        return map;
    }

    /**
     * 获取正文文件内容，wps方法
     *
     * @param path
     * @return
     */
    public static Map<String, String> getContentWps(String path) {
        Map<String, String> map = new HashMap();
        StringBuffer content = new StringBuffer("");
        String result = "0";  // 0表示获取正常，1表示获取异常
        InputStream is = null;
        Logger logger = null;
        try {
            is = new FileInputStream(new File(path));
            // wps版本word
            HWPFDocument hwpf = new HWPFDocument(is);
            WordExtractor wordExtractor = new WordExtractor(hwpf);
            // 文档文本内容
            String[] paragraphText1 = wordExtractor.getParagraphText();
            if (paragraphText1 != null && paragraphText1.length > 0) {
                for (String paragraph : paragraphText1) {
                    if (!paragraph.startsWith("    ")) {
                        content.append(paragraph.trim()).append("\r\n");
                    } else {
                        content.append(paragraph);
                    }
                }
            }
        } catch (Exception e) {
            logger.error("wps解析正文异常:" + e);
            result = "1"; // 出现异常
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    logger.error("" + e);
                }
            }
            map.put("result", result);
            map.put("content", content.toString());
        }
        return map;
    }
}