java通过poi解析word入门的操作方法

   <dependency>
       <groupId>org.apache.poi</groupId>
       <artifactId>poi</artifactId>
       <version>5.2.3</version>
   </dependency>
   <dependency>
       <groupId>org.apache.poi</groupId>
       <artifactId>poi-ooxml</artifactId>
       <version>5.2.3</version>
   </dependency>

FileInputStream fis = new FileInputStream("C:\\test.docx");
XWPFDocument document = new XWPFDocument(fis);

List<IBodyElement> bodyElements = document.getBodyElements();
for(int i=0;i<size;i++) {
    IBodyElement iBodyElement = bodyElements.get(i);
    if(iBodyElement instanceof XWPFParagraph){
        XWPFParagraph xwpParagraph=(XWPFParagraph)iBodyElement;
    }
    if(iBodyElement instanceof XWPFTable){
        XWPFTable xwpfTable=(XWPFTable)iBodyElement;
    }
    if(iBodyElement instanceof XWPFSDT){
        XWPFSDT xwpfSdt=(XWPFSDT)iBodyElement;
    }
}

// 获取所有段落
 List<XWPFParagraph> paragraphs = document.getParagraphs();

// 获取所有表格
 List<XWPFTable> xwpfTableList = xwpfDocument.getTables();

// 获取所有脚注
List<XWPFFootnote> footnotes = document.getFootnotes();

import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.List;
public class WordReader {
    public static void main(String[] args) {
        try {
            // 加载Word文档
            FileInputStream fis = new FileInputStream("C:\\Users\\Administrator\\Desktop\\test.docx");
            XWPFDocument document = new XWPFDocument(fis);
            // 获取所有段落
            List<XWPFParagraph> paragraphs = document.getParagraphs();
            int index=0;
            for (XWPFParagraph paragraph : paragraphs) {
                // 获取段落样式
                String style = paragraph.getStyle();
                System.out.println(index++);
                System.out.println("style "+style);
                System.out.println("getStyleID "+paragraph.getStyleID());
                System.out.println(paragraph.getText());
                if (paragraph.getStyleID() != null && paragraph.getStyleID().startsWith("Heading")) {
                    System.out.println("title:"+paragraph.getText());
                }
            }
            // 关闭文档
            document.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

import org.apache.poi.xwpf.usermodel.*;
import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTAnchor;
import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTInline;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDrawing;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.List;
public class WordPictureTest {
    public static void main(String[] args) {
        try {
            // 加载Word文档
            FileInputStream fis = new FileInputStream("C:\\Users\\Administrator\\Desktop\\pic.docx");
            XWPFDocument document = new XWPFDocument(fis);
            // 获取所有段落
            List<XWPFParagraph> paragraphs = document.getParagraphs();
            int index=0;
            for (XWPFParagraph paragraph : paragraphs) {
                parsePicture(paragraph);
            }
            // 关闭文档
            document.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    private static void parsePicture(XWPFParagraph paragraph){
        List<XWPFRun> runs = paragraph.getRuns();
        for (XWPFRun run:runs){
            List<XWPFPicture> embeddedPictures = run.getEmbeddedPictures();
            for(XWPFPicture picture:embeddedPictures){
                String fileName = picture.getPictureData().getFileName();
                System.out.println(fileName);
                CTDrawing drawing = run.getCTR().getDrawingArray(0);
                List<CTAnchor> anchorList = drawing.getAnchorList();
                List<CTInline> inlineList = drawing.getInlineList();
                System.out.println("anchorList "+anchorList.size());
                //inlineList.size>0 说明时嵌入式的布局
                System.out.println("inlineList "+inlineList.size());
                for (CTAnchor anchor :anchorList){
                    //文字环绕
                    boolean behindDoc = anchor.getBehindDoc();
                    boolean setWrapSquare = anchor.isSetWrapSquare();
                    boolean setWrapThrough = anchor.isSetWrapThrough();
                    boolean setWrapTight = anchor.isSetWrapTight();
                    boolean setWrapTopAndBottom = anchor.isSetWrapTopAndBottom();
                    boolean setWrapNone = anchor.isSetWrapNone();
                    System.out.println("setWrapNone "+setWrapNone +" behindDoc "+behindDoc);
                }
        }
    }
}