小编use*_*690的帖子

我正在将word文档转换为xml,以使用以下代码进行比较:

word = win32com.client.Dispatch('Word.Application')
wd = word.Documents.Open(inFile)
# Converts the word infile to xml outfile
wd.SaveAs(outFile,11)
wd.Close()
dom=parse(outFile)

我得到的xml文件看起来像:

<?xml version="1.0" encoding="utf-8"?>
<?mso-application progid="Word.Document"?>
<w:wordDocument w:embeddedObjPresent="no" w:macrosPresent="no" w:ocxPresent="no" xml:space="preserve" xmlns:aml="http://schemas.microsoft.com/aml/2001/core" xmlns:dt="uuid:C2F41010-65B3-11d1-A29F-00AA00C14882" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:sl="http://schemas.microsoft.com/schemaLibrary/2003/core" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:w="http://schemas.microsoft.com/office/word/2003/wordml" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:wsp="http://schemas.microsoft.com/office/word/2003/wordml/sp2" xmlns:wx="http://schemas.microsoft.com/office/word/2003/auxHint">
    <w:ignoreSubtree w:val="http://schemas.microsoft.com/office/word/2003/wordml/sp2"/>
    <w:shapeDefaults>
        <o:shapedefaults spidmax="1027" v:ext="edit"/>
        <o:shapelayout v:ext="edit">
            <o:idmap data="1" v:ext="edit"/>
        </o:shapelayout>
    </w:shapeDefaults>
    <w:body>
        <wx:sect>
            <w:tbl>

            <w:tblGrid>
                <w:gridCol w:w="200"/>
                                       ...
            </w:tblGrid>

                <w:pict>
                        <v:shapetype coordsize="21600,21600" filled="f" id="_x0000_t75" o:preferrelative="t" o:spt="75" path="m@4@5l@4@11@9@11@9@5xe" stroked="f">
                            <v:stroke joinstyle="miter"/>
                            <v:formulas>
                                <v:f eqn="if lineDrawn pixelLineWidth 0"/>
                                ... …