diagbotcloud/knowledgeman-service/src/main/java/com/diagbot/api/ImportWord.java

package com.diagbot.api;

import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.poi.xwpf.usermodel.XWPFTableCell;
import org.apache.poi.xwpf.usermodel.XWPFTableRow;

import java.io.FileInputStream;
import java.util.Iterator;
import java.util.List;

public class ImportWord {
    public static void main(String[] args) {
        String filepath = "E:\\危重病人APACHE II评分表量表.docx";
        parseWord(filepath);
    }

    /**
     * 读取文档中表格
     * @param filePath
     */
    public static void parseWord(String filePath){
        try{
            FileInputStream in = new FileInputStream(filePath);//载入文档
            // 处理docx格式 即office2007以后版本
            if(filePath.toLowerCase().endsWith("docx")){
                //word 2007 图片不会被读取， 表格中的数据会被放在字符串的最后
                XWPFDocument xwpf = new XWPFDocument(in);//得到word文档的信息
                Iterator<XWPFTable> it = xwpf.getTablesIterator();//得到word中的表格
                // 设置需要读取的表格  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 = 4;
                int num = set;
                // 过滤前面不需要的表格
//                for (int i = 0; i < set-1; i++) {
//                    it.hasNext();
//                    it.next();
//                }
                while(it.hasNext()){
                    XWPFTable table = it.next();
                    System.out.println("这是第" + num + "个表的数据");
                    List<XWPFTableRow> rows = table.getRows();
                    //读取每一行数据
                    for (int i = 0; i < rows.size(); i++) {
                        XWPFTableRow  row = rows.get(i);
                        //读取每一列数据
                        List<XWPFTableCell> cells = row.getTableCells();
                        for (int j = 0; j < cells.size(); j++) {
                            XWPFTableCell cell = cells.get(j);
                            //输出当前的单元格的数据
                            System.out.print(cell.getText() + "\t");
                        }
                        System.out.println();
                    }
                    // 过滤多余的表格
                    while (num < total) {
                        it.hasNext();
                        it.next();
                        num += 1;
                    }
                }
            }
        }catch(Exception e){
            e.printStackTrace();
        }
    }

}