Poi的Word文档结构介绍
1、poi之word文档结构介绍之正文段落 一个文档包含多个段落，一个段落包含多个Runs，一个Runs包含多个Run，Run是文档的最小单元 获取所有段落：List paragraphs = word.getParagraphs(); 获取一个段落中的所有Runs：List xwpfRuns = xwpfParagraph.getRuns(); 获取一个Runs中的一个Run：XWPFRun run = xwpfRuns.get(index);
2、poi之word文档结构介绍之正文表格 一个文档包含多个表格，一个表格包含多行，一行包含多列（格），每一格的内容相当于一个完整的文档 获取所有表格：List xwpfTables = doc.getTables(); 获取一个表格中的所有行：List xwpfTableRows = xwpfTable.getRows(); 获取一行中的所有列：List xwpfTableCells = xwpfTableRow.getTableCells(); 获取一格里的内容：List paragraphs = xwpfTableCell.getParagraphs(); 之后和正文段落一样
注： 表格的一格相当于一个完整的docx文档，只是没有页眉和页脚。里面可以有表格，使用xwpfTableCell.getTables()获取，and so on 在poi文档中段落和表格是完全分开的，如果在两个段落中有一个表格，在poi中是没办法确定表格在段落中间的。（当然除非你本来知道了，这句是废话）。只有文档的格式固定，才能正确的得到文档的结构
3、poi之word文档结构介绍之页眉： 一个文档可以有多个页眉(不知道怎么会有多个页眉。。。),页眉里面可以包含段落和表格 获取文档的页眉：List headerList = doc.getHeaderList(); 获取页眉里的所有段落：List paras = header.getParagraphs(); 获取页眉里的所有表格：List tables = header.getTables(); 之后就一样了
4、poi之word文档结构介绍之页脚： 页脚和页眉基本类似，可以获取表示页数的角标
IBodyElement -------------------迭代器（段落和表格） XWPFComment -------------------评论（个人理解应该是批注） XWPFSDT XWPFFooter -------------------页脚 XWPFFootnotes -------------------脚注 XWPFHeader -------------------页眉 XWPFHyperlink -------------------超链接 XWPFNumbering -------------------编号 XWPFParagraph -------------------段落 XWPFPictureData -------------------图片 XWPFStyles -------------------样式（设置多级标题的时候用） XWPFTable -------------------表格
pom 依赖
<dependencies>
<!--解析doc文档HWPFDocument-->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>springframework</groupId>
<artifactId>spring-core</artifactId>
<version>1.2.6</version>
</dependency>
</dependencies>
maven依赖
import org.apache.poi.xwpf.usermodel.*;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDocument1;
import java.io.*;
import java.util.List;
public class poi3 {
public static void main(String[] args) throws IOException {
// 获取文件输入流
FileInputStream fileInputStream = getFileInputStream("666.docx");
dealDocx(fileInputStream, "副本.docx");
}
private static FileInputStream getFileInputStream(String name) throws FileNotFoundException {
String dir = poi3.class.getResource("").getPath() + name;
FileInputStream fileInputStream = new FileInputStream(dir);
return fileInputStream;
}
private static void dealDocx(InputStream inputStream, String newFileName) throws IOException {
// 创建输出文件
File file = new File(poi3.class.getResource("").getPath() + newFileName);
// 获取文件输出流
FileOutputStream fileOutputStream = new FileOutputStream(file);
// 创建操作word的对象
XWPFDocument wordInput = new XWPFDocument(inputStream);
XWPFDocument wordOutput = new XWPFDocument();
// 获取所有段落
List<XWPFParagraph> xwpfParagraphs = wordInput.getParagraphs();
// 迭代每一个段落
for (XWPFParagraph xwpfParagraph : xwpfParagraphs) {
// 原文档有多少个段落 我就创建多少个
XWPFParagraph wordOutputParagraph = wordOutput.createParagraph();
// 获取当前段落的所有run
List<XWPFRun> runs = xwpfParagraph.getRuns();
for (XWPFRun run : runs) {
XWPFRun wordOutputParagraphRun = wordOutputParagraph.createRun();
// 赋值
//wordOutputParagraphRun.setText("哈哈哈哈~我修改过了");
// 添加回车 硬回车
//wordOutputParagraphRun.addCarriageReturn();
//wordOutputParagraphRun.addBreak(); // 软回车
wordOutputParagraphRun.setText(run.getText(run.getCharacterSpacing()));
}
}
// 获取所有表格
List<XWPFTable> xwpfTables = wordInput.getTables();
for (XWPFTable xwpfTable : xwpfTables) {
XWPFTable wordOutputTable = wordOutput.createTable();
// 获取一个表格中的所有行
List<XWPFTableRow> xwpfTableRows = xwpfTable.getRows();
System.out.println("xwpfTableRows个数"+xwpfTableRows.size());
for (XWPFTableRow xwpfTableRow : xwpfTableRows) {
XWPFTableRow wordOutputTableRow = wordOutputTable.createRow();
// 获取一行的所有列
List<XWPFTableCell> xwpfTableCell = xwpfTableRow.getTableCells();
System.out.println("xwpfTableCell个数"+xwpfTableCell.size());
int index = 0;
for (XWPFTableCell tableCell : xwpfTableCell) {
index++;
XWPFTableCell wordOutputTableRowCell = wordOutputTableRow.createCell();
// 获取单个列
//wordOutputTableRowCell.setText("哈哈哈哈~我修改过了");
System.out.println(tableCell.getText());
wordOutputTableRowCell.setText(tableCell.getText());
System.out.println("index:"+index);
}
wordOutputTable.removeRow(0);
}
//wordOutputTable.removeBorders(); 虚线边框
}
CTDocument1 document = wordInput.getDocument();
System.out.println();
wordOutput.write(fileOutputStream);
wordInput.close();
wordOutput.close();
inputStream.close();
fileOutputStream.close();
}
}
获取文档中的所有图片代码
private void getPictureImage(String filepath) throws IOException {
XWPFDocument doc = new XWPFDocument(new FileInputStream(filepath));
List<ImageInfo> result = Lists.newArrayList();
Pattern pattern = Pattern.compile(PICTURE_IMG_PATTERN);
for (XWPFParagraph paragraph : doc.getParagraphs()) {
for (XWPFRun run : paragraph.getRuns()) {
System.out.println("............................." + paragraph.getRuns());
for (XWPFPicture embeddedPicture : run.getEmbeddedPictures()) {
System.out.println("............................." + embeddedPicture.getDescription());
Matcher matcher = pattern.matcher(embeddedPicture.getDescription());
while (matcher.find()) {
String source = matcher.group();
ImageInfo imageInfo = new ImageInfo();
imageInfo.setSource(source);
imageInfo.setImageField(getImageField(imageInfo.getSource()));
imageInfo.setFiled(getField(imageInfo.getSource()));
result.add(imageInfo);
}
}
}
}
List<XWPFTable> xwpfTables = doc.getTables();
for (XWPFTable xwpfTable : xwpfTables) {
List<XWPFTableRow> xwpfTableRows = xwpfTable.getRows();
for (XWPFTableRow xwpfTableRow : xwpfTableRows) {
List<XWPFTableCell> xwpfTableCells = xwpfTableRow.getTableCells();
for (XWPFTableCell xwpfTableCell : xwpfTableCells) {
for (XWPFParagraph paragraph : xwpfTableCell.getParagraphs()) {
for (XWPFRun run : paragraph.getRuns()) {
for (XWPFPicture embeddedPicture : run.getEmbeddedPictures()) {
Matcher matcher = pattern.matcher(embeddedPicture.getDescription());
while (matcher.find()) {
String source = matcher.group();
ImageInfo imageInfo = new ImageInfo();
imageInfo.setSource(source);
imageInfo.setImageField(getImageField(imageInfo.getSource()));
imageInfo.setFiled(getField(imageInfo.getSource()));
result.add(imageInfo);
}
}
}
}
}
}
}
}
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
原文链接：https://blog.csdn.net/weixin_43702146/article/details/116159448
标签：word,表格,imageInfo,List,XWPFDocument,获取,文档,poi From： https://www.cnblogs.com/abel-he/p/18192089