Java拆分Word文档的两种实用方案详解

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <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.*;
import com.spire.doc.documents.*;
import com.spire.doc.fields.Table;

public class SplitByPageBreak {

    public static void main(String[] args) throws Exception {
        // 加载源文档
        Document originalDoc = new Document();
        originalDoc.loadFromFile("大型文档.docx");

        Document newDoc = new Document();
        newDoc.addSection();
        int fileIndex = 0;
        boolean hasContent = false;

        for (int s = 0; s < originalDoc.getSections().getCount(); s++) {
            Section section = originalDoc.getSections().get(s);

            for (int c = 0; c < section.getBody().getChildObjects().getCount(); c++) {
                DocumentObject obj = section.getBody().getChildObjects().get(c);

                if (obj instanceof Paragraph) {
                    Paragraph para = (Paragraph) obj;
                    boolean hasPageBreak = false;

                    // 检测段落中是否含有分页符
                    for (int i = 0; i < para.getChildObjects().getCount(); i++) {
                        if (para.getChildObjects().get(i) instanceof Break) {
                            Break breakObj = (Break) para.getChildObjects().get(i);
                            if (breakObj.getBreakType() == BreakType.Page_Break) {
                                hasPageBreak = true;
                                break;
                            }
                        }
                    }

                    if (hasPageBreak) {
                        // 遇到分页符，保存当前文档
                        if (hasContent) {
                            String outputFile = String.format("page_split_%d.docx", fileIndex++);
                            newDoc.saveToFile(outputFile, FileFormat.Docx);
                            newDoc.close();

                            newDoc = new Document();
                            newDoc.addSection();
                            hasContent = false;
                        }

                        // 克隆段落并移除分页符
                        Paragraph clonedPara = (Paragraph) para.deepClone();
                        for (int i = clonedPara.getChildObjects().getCount() - 1; i >= 0; i--) {
                            if (clonedPara.getChildObjects().get(i) instanceof Break) {
                                Break breakObj = (Break) clonedPara.getChildObjects().get(i);
                                if (breakObj.getBreakType() == BreakType.Page_Break) {
                                    clonedPara.getChildObjects().removeAt(i);
                                }
                            }
                        }
                        if (clonedPara.getText().trim().length() > 0 || clonedPara.getChildObjects().getCount() > 0) {
                            newDoc.getSections().get(0).getBody().getChildObjects().add(clonedPara);
                            hasContent = true;
                        }
                    } else {
                        // 普通段落直接复制
                        newDoc.getSections().get(0).getBody().getChildObjects().add(para.deepClone());
                        hasContent = true;
                    }
                } else if (obj instanceof Table) {
                    // 表格直接复制
                    newDoc.getSections().get(0).getBody().getChildObjects().add(obj.deepClone());
                    hasContent = true;
                }
            }
        }

        // 保存最后一部分
        if (hasContent) {
            newDoc.saveToFile(String.format("page_split_%d.docx", fileIndex), FileFormat.Docx);
            fileIndex++;
        }

        originalDoc.close();
        newDoc.close();
        System.out.println("按分页符拆分完成，共生成 " + fileIndex + " 个文件");
    }
}

import com.spire.doc.Document;
import com.spire.doc.FileFormat;

public class SplitBySection {

    public static void main(String[] args) {
        Document document = new Document();
        document.loadFromFile("带分节符的文档.docx");

        for (int i = 0; i < document.getSections().getCount(); i++) {
            Document newDoc = new Document();
            // 将原文档的第 i 节复制到新文档
            newDoc.getSections().add(document.getSections().get(i).deepClone());

            String outputFile = String.format("section_%d.docx", i + 1);
            newDoc.saveToFile(outputFile, FileFormat.Docx);
            newDoc.close();
        }

        document.close();
        System.out.println("按分节符拆分完成，共 " + document.getSections().getCount() + " 个节");
    }
}