本文介绍如何使用Spire.Doc for Java获取Word文档中书签包含的文本。

import com.spire.doc.Document;
import com.spire.doc.documents.BookmarksNavigator;
import com.spire.doc.documents.Paragraph;
import com.spire.doc.documents.TextBodyPart;
import com.spire.doc.fields.TextRange;

import java.io.FileNotFoundException;
import java.io.PrintWriter;

public class GetBookmarkText {

    public static void main(String[] args) throws FileNotFoundException {

        //创建Document对象
        Document doc = new Document();

        //加载Word文档
        doc.loadFromFile("C:\\Users\\Administrator\\Desktop\\sample.docx");

        //获取指定书签
        BookmarksNavigator navigator = new BookmarksNavigator(doc);
        navigator.moveToBookmark("MyBookmark");

        //获取书签内容
        TextBodyPart textBodyPart = navigator.getBookmarkContent();

        //创建String变量
        String text = "";

        //遍历书签内容的项目
        for (Object item : textBodyPart.getBodyItems()) {

            //判断项目是否为段落
            if (item instanceof Paragraph) {
                Paragraph paragraph = (Paragraph) item;

                //遍历段落中的子对象
                for (Object childObj : paragraph.getChildObjects()) {

                    //判断子对象是否为TextRange
                    if (childObj instanceof TextRange) {

                        //获取TextRange中的文本
                        TextRange textRange = (TextRange) childObj;
                        text = text + textRange.getText();
                    }
                }
            }
        }

        //将获取到的文本写入Txt文件
        PrintWriter printWriter = new PrintWriter("output/BookmarkText.txt");
        printWriter.println(text);
        printWriter.close();
    }
}