Java开发中读取与解析Word文档的实践教学

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.doc</artifactId>
        <version>14.5.3</version>
    </dependency>
</dependencies>

import com.spire.doc.Document;

public class ReadAllText {
    public static void main(String[] args) {
        Document doc = new Document();
        doc.loadFromFile("sample.docx");

        // 获取文档的完整文本内容
        String allText = doc.getText();
        System.out.println(allText);

        doc.close();
    }
}

import com.spire.doc.Document;
import com.spire.doc.documents.Paragraph;

public class ReadParagraphs {
    public static void main(String[] args) {
        Document doc = new Document();
        doc.loadFromFile("sample.docx");

        // 遍历文档中的节
        for (int i = 0; i < doc.getSections().getCount(); i++) {
            // 遍历每个节中的段落
            for (int j = 0; j < doc.getSections().get(i).getParagraphs().getCount(); j++) {
                Paragraph paragraph = doc.getSections().get(i).getParagraphs().get(j);

                String text = paragraph.getText();
                String styleName = paragraph.getStyleName();

                System.out.println("样式: " + styleName);
                System.out.println("内容: " + text);
                System.out.println("---");
            }
        }
        doc.close();
    }
}

import com.spire.doc.Document;
import com.spire.doc.Section;
import com.spire.doc.Table;
import com.spire.doc.TableRow;
import com.spire.doc.TableCell;

public class ReadTable {
    public static void main(String[] args) {
        Document doc = new Document();
        doc.loadFromFile("sample.docx");

        // 遍历所有节
        for (int i = 0; i < doc.getSections().getCount(); i++) {
            Section section = doc.getSections().get(i);

            // 遍历当前节中的表格
            for (int j = 0; j < section.getTables().getCount(); j++) {
                Table table = section.getTables().get(j);
                System.out.println("表格 " + (j + 1) + ":");

                // 按行读取
                for (int k = 0; k < table.getRows().getCount(); k++) {
                    TableRow row = table.getRows().get(k);
                    // 按单元格读取
                    for (int l = 0; l < row.getCells().getCount(); l++) {
                        TableCell cell = row.getCells().get(l);
                        System.out.print(cell.getText() + "\t");
                    }
                    System.out.println();
                }
                System.out.println("============");
            }
        }
        doc.close();
    }
}

import com.spire.doc.Document;
import com.spire.doc.fields.DocPicture;
import com.spire.doc.interfaces.IDocumentObject;

public class ExtractImages {
    public static void main(String[] args) throws Exception {
        Document doc = new Document();
        doc.loadFromFile("sample.docx");

        int imageIndex = 0;
        // 遍历文档中的子对象
        for (int i = 0; i < doc.getSections().getCount(); i++) {
            for (int j = 0; j < doc.getSections().get(i).getBody().getChildObjects().getCount(); j++) {
                IDocumentObject obj = doc.getSections().get(i).getBody().getChildObjects().get(j);

                // 判断是否为图片对象
                if (obj instanceof DocPicture) {
                    DocPicture picture = (DocPicture) obj;
                    // 保存为 PNG 文件
                    picture.getImage().save("output/image_" + imageIndex + ".png", null);
                    imageIndex++;
                }
            }
        }
        System.out.println("共提取 " + imageIndex + " 张图片");
        doc.close();
    }
}