package com.dsideal.base.Tools.Test; import org.apache.poi.openxml4j.exceptions.InvalidFormatException; import org.dom4j.Document; import org.dom4j.DocumentException; import org.dom4j.Element; import org.dom4j.io.SAXReader; import org.xml.sax.SAXException; import javax.xml.parsers.ParserConfigurationException; import javax.xml.xpath.XPathExpressionException; import java.io.File; import java.io.FileInputStream; import java.io.FileOutputStream; import java.io.IOException; import java.util.List; import java.util.zip.ZipEntry; import java.util.zip.ZipInputStream; public class TestOutSideExcel { /** * 解压缩 * * @throws IOException */ public static void UnCompress(String wordPath, String workingPath) throws IOException { File file = new File(wordPath);//取得word文件 FileInputStream inputStream = new FileInputStream(file); ZipInputStream zipInputStream = new ZipInputStream(inputStream); ZipEntry entry; byte[] ch = new byte[256]; while ((entry = zipInputStream.getNextEntry()) != null) { File zFile = new File(workingPath + entry.getName()); if (entry.isDirectory()) { if (!zFile.exists()) { zFile.mkdirs(); } zipInputStream.closeEntry(); } else { File fpath = new File(zFile.getParent()); if (!fpath.exists()) { fpath.mkdirs(); } FileOutputStream outputStream = new FileOutputStream(zFile); int i; while ((i = zipInputStream.read(ch)) != -1) { outputStream.write(ch, 0, i); } zipInputStream.closeEntry(); outputStream.close(); } } inputStream.close(); } public static void main(String[] args) throws IOException, InvalidFormatException, InterruptedException, ParserConfigurationException, SAXException, XPathExpressionException, DocumentException { String sourceDoc = "c:/西双版纳州人口变化及其对教育的影响20240420.docx"; //1、将word文件解压缩 String workingPath = "C:\\zipFile"; UnCompress(sourceDoc, workingPath); //2、我们需要第几个图表 int chartNumber = 1; String xml = workingPath + "\\word\\charts\\chart" + chartNumber + ".xml"; if (!(new File(xml).exists())) { System.out.println("没有找到第" + chartNumber + "个图表"); return; } //3、开始读取 // 创建 SAXReader 对象,读取 XML 文件 SAXReader reader = new SAXReader(); Document document = reader.read(new File(xml)); // 获取根元素 Element root = document.getRootElement(); //折线图 //将xml用IDEA打开,搜索关键的数据值,然后右键查看XPATH完整路径可以获取到下面的路径 ///c:chartSpace/c:chart/c:plotArea/c:lineChart/c:ser/c:cat/c:numRef/c:numCache/c:pt/c:v List xList = root.element("chart").element("plotArea") .element("lineChart").element("ser").element("cat") .element("numRef").element("numCache").elements("pt"); for (Element e : xList) { System.out.println(e.element("v").getText()); } ///c:chartSpace/c:chart/c:plotArea/c:lineChart/c:ser/c:val/c:numRef/c:numCache List yList = root.element("chart").element("plotArea") .element("lineChart").element("ser").element("val") .element("numRef").element("numCache").elements("pt"); for (Element e : yList) { System.out.println(e.element("v").getText()); } } }