利用java从docx文档中提取文本内容

利用java从docx文档中提取文本内容

使用Apache的第三方jar包，地址为https://poi.apache.org/

docx文档内容如图：



目录结构：



每个文件夹的名称为日期加上来源，例如：20180618医院，每个docx文档的名称是被试的姓名和来源地，例如：小明-xx社区。

代码如下：

MriReportService.java

package services;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.regex.Pattern;

public class MriReportService {

    public static String[] findYearAndSource(File file) {
        String[] result = new String[2];
        // 日期
        String dateStr = file.getParentFile().getName();
//        System.out.println(dateStr);
        if (Pattern.compile("\\d").matcher(dateStr).find()) {
            dateStr = Pattern.compile("-").matcher(dateStr).replaceAll("");
            result[0] = dateStr.substring(0, 8);
        } else {
            result[0] = "";
        }

        // 社区
        String fileName = file.getName();
        if (fileName.indexOf("-") < 0) {
            fileName = Pattern.compile("\\.").matcher(fileName).replaceAll("-.");
        }
        fileName = Pattern.compile("--+").matcher(fileName).replaceAll("-");
        result[1] = fileName.substring(fileName.indexOf("-") + 1, fileName.indexOf("."));

        return result;
    }

    public static LinkedList<File> findAllFile(String rootPath) {
        File file = new File(rootPath);
        LinkedList<File> list = new LinkedList<>();
        if (file.exists()) {
            File[] subDirs = file.listFiles();
            for (File tmpDir : subDirs) {
//                System.out.println(tmpDir);
                for (File tmpFile : tmpDir.listFiles()) {
                    if (tmpFile.isFile() && tmpFile.getName().indexOf("~$") < 0) {
                        list.add(tmpFile);
                    }
                }
            }
        }

        return list;
    }

    public static ArrayList<String> findSub(String docx) {
        String name = "";
        String gender = "";
        String age = "";
        String MRICheck = "";
        String MRIMem = "";

        if (!Pattern.compile("性别：").matcher(docx).find() || !Pattern.compile("年龄：").matcher(docx).find()) {
            try {
                name = docx.substring(docx.indexOf("姓名：") + 3, docx.indexOf("检查项目："));
                MRICheck = docx.substring(docx.indexOf("MRI检查描述：") + 8, docx.indexOf("MRI印象："));
                MRIMem = docx.substring(docx.indexOf("MRI印象：") + 6, docx.indexOf("报告医师："));
            } catch (StringIndexOutOfBoundsException e) {
//                name = "";
            }
        } else {
            name = docx.substring(docx.indexOf("姓名：") + 3, docx.indexOf("性别："));
            gender = docx.substring(docx.indexOf("性别：") + 3, docx.indexOf("年龄："));
            age = docx.substring(docx.indexOf("年龄：") + 3, docx.indexOf("检查项目："));
            MRICheck = docx.substring(docx.indexOf("MRI检查描述：") + 8, docx.indexOf("MRI印象："));
            MRIMem = docx.substring(docx.indexOf("MRI印象：") + 6, docx.indexOf("报告医师："));
        }

        ArrayList<String> result = new ArrayList<>();
        result.add(name);
        result.add(gender);
        result.add(age);
        result.add(MRICheck);
        result.add(MRIMem);
        return result;
    }
}

Main.java

import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

import java.io.*;
import java.util.ArrayList;
import java.util.regex.*;

import static services.MriReportService.findAllFile;
import static services.MriReportService.findSub;
import static services.MriReportService.findYearAndSource;

public class Main {

    public static void main(String[] args) throws Exception {

        if (args.length < 2) {
            System.out.println("请输入源文件和目标文件的完整路径！");
            System.out.println("举个例子：java -jar docx2csv.jar d:\\核磁报告 d:\\result.csv");
            System.exit(-1);
        }

        String srcPath = args[0];
        String outPath = args[1];
        ArrayList<ArrayList<String>> result = new ArrayList<>();
        for (File tmpFile : findAllFile(srcPath)) {

            String[] yearAndSrc = findYearAndSource(tmpFile);

            FileInputStream fis = new FileInputStream(tmpFile);
            XWPFDocument xdoc = new XWPFDocument(fis);
            XWPFWordExtractor extractor = new XWPFWordExtractor(xdoc);
            String docx = extractor.getText();

            docx = Pattern.compile("\\s").matcher(docx).replaceAll("");
            ArrayList<String> tmpRe = findSub(docx);
            tmpRe.add(yearAndSrc[0]);
            tmpRe.add(yearAndSrc[1]);
            result.add(tmpRe);
            fis.close();
        }
        write(result, outPath);
    }

    public static void write(ArrayList<ArrayList<String>> result, String outPath) throws IOException {
        BufferedWriter bufferedWriter = new BufferedWriter(new OutputStreamWriter(
                new FileOutputStream(outPath), "GBK"));
        for (ArrayList<String> tmpStrs : result) {
//            System.out.println();
            bufferedWriter.write(tmpStrs.get(0) + "," + tmpStrs.get(1) + ","
                    + tmpStrs.get(2) + "," + tmpStrs.get(3) + ","
                    + tmpStrs.get(4) + "," + tmpStrs.get(5) + ","
                    + tmpStrs.get(6));
            bufferedWriter.newLine();
        }
        bufferedWriter.close();
    }
}