c#/vb.net 根据分节符和分页符拆分 word 文档-ag凯发旗舰厅

在word文档中，我们可以通过最简单的方法来拆分word文档，那就是打开一个是需要拆分的文档的副本，删除我们不需要的内容然后将剩余内容保存为新文档到本地。虽然操作简单，但是一节一节的删除是个相当繁琐且枯燥的过程。利用spire.doc，我们可以程序化的根据分节符和分页符来拆分word文档，这避免了手动冗杂的操作。本文将对此做详细介绍。

根据分节符拆分文档

//加载测试文档
            document document = new document();
            document.loadfromfile("测试文档.docx");
            //拆分
            document newword;
            for (int i = 0; i < document.sections.count;i   )
            {
                newword = new document();
                newword.sections.add(document.sections[i].clone());
                newword.savetofile(string.format("拆分结果/分节符拆分的结果文档_{0}.docx", i));
                i = (i   1);
            }

dim document as document = new document
document.loadfromfile("测试文档.docx")
dim newword as document
dim i as integer = 0
do while (i < document.sections.count)
    newword = new document
    newword.sections.add(document.sections(i).clone)
    newword.savetofile(string.format("拆分结果\分节符拆分的结果文档_{0}.docx", i))
    i = (i   1)
loop

原文档如图，其中有两个分节符：

运行程序得到如下结果：

根据分页符拆分文档

//加载源文档
            document original = new document();
            original.loadfromfile("c:/users/administrator/desktop/template.docx");
            //创建一个新的文档并给它添加一个section
            document newword = new document();
            section section = newword.addsection();
            int index = 0;
            //遍历源文档的所有section，检测page break并根据page break拆分文档
            foreach (section sec in original.sections)
            {
                foreach (documentobject obj in sec.body.childobjects)
                {
                    if (obj is paragraph)
                    {
                        paragraph para = obj as paragraph;
                        section.body.childobjects.add(para.clone());
                        foreach (documentobject parobj in para.childobjects)
                        {
                            if (parobj is break && (parobj as break).breaktype == breaktype.pagebreak)
                            {
                                int i = para.childobjects.indexof(parobj);
                                for (int j = i; j < para.childobjects.count; j  )
                                {
                                    section.body.lastparagraph.childobjects.removeat(i);
                                }
                                newword.savetofile(string.format("c:/users/administrator/desktop/拆分结果/分页符拆分的结果文档-{0}.docx", index), fileformat.docx);
                                index  ;
                                newword = new document();
                                section = newword.addsection();
                                section.body.childobjects.add(para.clone());
                                while (i >= 0)
                                {
                                    section.paragraphs[0].childobjects.removeat(i);
                                    i--;
                                }
                                if (section.paragraphs[0].childobjects.count == 0)
                                {
                                    section.body.childobjects.removeat(0);
                                }
                            }
                        }
                    }
                    if (obj is table)
                    {
                        section.body.childobjects.add(obj.clone());
                    }
                }
            }
            newword.savetofile(string.format("c:/users/administrator/desktop/拆分结果/分页符拆分的结果文档-{0}.docx", index), fileformat.docx);

dim original as document = new document
original.loadfromfile("c:\users\administrator\desktop\template.docx")
dim newword as document = new document
dim section as section = newword.addsection
dim index as integer = 0
for each sec as section in original.sections
    for each obj as documentobject in sec.body.childobjects
        if (typeof obj is paragraph) then
            dim para as paragraph = ctype(obj,paragraph)
            section.body.childobjects.add(para.clone)
            for each parobj as documentobject in para.childobjects
                if (typeof parobj is (break  _
                            andalso (ctype(parobj,break).breaktype = breaktype.pagebreak))) then
                    dim i as integer = para.childobjects.indexof(parobj)
                    section.body.lastparagraph.childobjects.removeat(i)
                    newword.savetofile(string.format("c:\users\administrator\desktop\拆分结果\分页符拆分的结果文档_{0}.docx", index), fileformat.docx)
                    index = (index   1)
                    newword = new document
                    section = newword.addsection
                    section.body.childobjects.add(para.clone)
                    if (section.paragraphs(0).childobjects.count = 0) then
                        section.body.childobjects.removeat(0)
                    else
                        
                        while (i >= 0)
                            section.paragraphs(0).childobjects.removeat(i)
                            i = (i - 1)
                            
                        end while
                        
                    end if
                    
                end if
                
            next
        end if
        
        if (typeof obj is table) then
            section.body.childobjects.add(obj.clone)
        end if
        
    next
next
newword.savetofile(string.format("c:\users\administrator\desktop\拆分结果\分页符拆分的结果文档_{0}.docx", index), fileformat.docx)

原文档如图，其中有一个分页符：

运行程序得到如下结果：