java读取word文档,提取标题和内容的实例

<dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi</artifactId>
      <version>3.17</version>
    </dependency>
    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-ooxml</artifactId>
      <version>3.17</version>
    </dependency>
    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-scratchpad</artifactId>
      <version>3.17</version>
    </dependency>
    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>ooxml-schemas</artifactId>
      <version>1.1</version>
    </dependency>
    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-ooxml-schemas</artifactId>
      <version>3.17</version>
    </dependency>

package com.w.test;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hwpf.usermodel.CharacterRun;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import com.example.model.Policy_content;
public class GetWord {
  public static void main(String[] args) {
    // TODO Auto-generated method stub
    try {
      List<Policy_content> list = new ArrayList<>();
      InputStream is = new FileInputStream(new File("文件路径")); //需要将文件路更改为word文档所在路径。
      POIFSFileSystem fs = new POIFSFileSystem(is);
      HWPFDocument document = new HWPFDocument(fs);
      Range range = document.getRange();
      CharacterRun run1 = null;//用来存储第一行内容的属性
      CharacterRun run2 = null;//用来存储第二行内容的属性
      int q=1;
      for (int i = 0; i < range.numParagraphs()-1; i++) {
        Paragraph para1 = range.getParagraph(i);// 获取第i段
        Paragraph para2 = range.getParagraph(i+1);// 获取第i段
        int t=i;       //记录当前分析的段落数
        
        String paratext1 = para1.text().trim().replaceAll("\r\n", "");  //当前段落和下一段
        String paratext2 = para2.text().trim().replaceAll("\r\n", "");
        run1=para1.getCharacterRun(0);
        run2=para2.getCharacterRun(0);
        if (paratext1.length() > 0&&paratext2.length() > 0) {
            //这个if语句为的是去除大标题，连续三个段落字体大小递减就跳过
            if(run1.getFontSize()>run2.getFontSize()&&run2.getFontSize()>range.getParagraph(i+2).getCharacterRun(0).getFontSize()) {
              continue;
            }            
            //连续两段字体格式不同
            if(run1.getFontSize()>run2.getFontSize()) {
              
              String content=paratext2;
              run1=run2; //从新定位run1 run2
              run2=range.getParagraph(t+2).getCharacterRun(0);
              t=t+1;
              while(run1.getFontSize()==run2.getFontSize()) {
                //连续的相同
                content+=range.getParagraph(t+1).text().trim().replaceAll("\r\n", "");
                run1=run2;
                run2=range.getParagraph(t+2).getCharacterRun(0);
                t++;
              }
              
              if(paratext1.indexOf("HYPERLINK")==-1&&content.indexOf("HYPERLINK")==-1) {
                System.out.println(q+"标题"+paratext1+"\t内容"+content);
                i=t;
                q++;
              }
                
            }
        }
      }
      
      
    } catch (Exception e) {
      e.printStackTrace();
    }
  }
  
}

  /**
   * 提取word文件内容
   * @param file
   * @param request
   * @return
   * @throws IOException 
   * @throws IllegalStateException 
   */
  @RequestMapping(value = "/getPapers", method = RequestMethod.POST, produces = { "text/html;charset=utf-8" })
  @ResponseBody
  private Object getPapers(@RequestParam("file") MultipartFile multfile，HttpServletRequest request) throws IllegalStateException, IOException {
    // 获取文件名
    String fileName = multfile.getOriginalFilename();
    //判断是否为word类型文件
    if (!fileName.endsWith(".doc") && !fileName.endsWith(".docx")) {
      System.out.println("此文件不是word文件！");
    }
    //当前系统的临时文件地址
    String realPath = request.getSession().getServletContext().getRealPath("/static/app/appkmbgszh/uploadFile");
    // 用uuid作为文件名，防止生成的临时文件重复
    String fileAdd = UUID.randomUUID().toString() + ".docx";
    // 构建一个临时文件
    File uploadFile = new File(realPath, fileAdd);
    //将上传的MultipartFile格式文件转换为创建的新文件
    multfile.transferTo(uploadFile);
    //获取新文件的绝对路径
    String filePath = uploadFile.getAbsolutePath();
 
    String buffer = "";
    JSONObject msg = new JSONObject();
    try {
      InputStream inIo = new FileInputStream(uploadFile);
      //提取文本内容
      if (fileName.endsWith(".doc")) {
        WordExtractor ex = new WordExtractor(inIo);
        buffer = ex.getText();
        ex.close();
      } else if (fileName.endsWith(".docx")) {
        OPCPackage opcPackage = POIXMLDocument.openPackage(filePath);
        POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
        buffer = extractor.getText();
        extractor.close();
      }
      //删除上传存放的临时文件
      uploadFile.delete();
      msg.put("status", true);
      msg.put("msg", buffer);
    } catch (Exception e) {
      e.printStackTrace();
      msg.put("status", false);
      msg.put("msg", "文件内容提取失败");
    }
    return retString(msg);
  }
 
  /**
   * json格式化;
   * @param ret
   * @return
   */
  private String retString(JSONObject ret) {
    String jsoStr = "";
    try {
      jsoStr = JSON.json(ret);
    } catch (IOException e) {
      e.printStackTrace();
      return jsoStr;
    }
    return jsoStr;
  }