python生成xml文件时进行格式美化

python生成xml文件时进行格式美化

遇到的问题

在使用python的ElementTree生成xml文件时，xml属性会被重新排序，xml文件默认无缩进，影响xml文件的可读性。

解决办法

重定向xml序列化方法。

import xml.etree.ElementTree as ET

def _serialize_xml(write, elem, qnames, namespaces,
                   short_empty_elements, level=0, **kwargs):
    tag = elem.tag
    text = elem.text
    if tag is ET.Comment:
        write("\t" * level + "<!--%s-->\n" % text)
    elif tag is ET.ProcessingInstruction:
        write("<?%s?>" % text)
    else:
        tag = qnames[tag]
        if tag is None:
            if text:
                write(ET._escape_cdata(text))
            for e in elem:
                _serialize_xml(write, e, qnames, None, short_empty_elements=short_empty_elements, level=level+1)
        else:
            write("\t" * level + "<" + tag)
            items = list(elem.items())
            if items or namespaces:
                if namespaces:
                    for v, k in sorted(namespaces.items(), key=lambda x: x[1]):  # sort on prefix
                        if k:
                            k = ":" + k
                        write(" xmlns%s=\"%s\"" % (k, ET._escape_attrib(v)))
                for k, v in items:
                    if isinstance(k, ET.QName):
                        k = k.text
                    if isinstance(v, ET.QName):
                        v = qnames[v.text]
                    else:
                        v = ET._escape_attrib(v)
                    write(" %s=\"%s\"" % (qnames[k], v))
            if text or len(elem) or not short_empty_elements:
                write(">\n")
                if text:
                    write(ET._escape_cdata(text))
                for e in elem:
                    _serialize_xml(write, e, qnames, None, short_empty_elements=short_empty_elements, level=level+1)
                write("\t" * level + "</" + tag + ">\n")
            else:
                write(" />\n")
    if elem.tail:
        write(ET._escape_cdata(elem.tail))

# 重定向xml序列化方法, 以下重定向方法2选1
ET._serialize_xml = _serialize_xml
ET._serialize["xml"] = _serialize_xml

示例：

# 重定向xml序列化方法
ET._serialize_xml = _serialize_xml

def xml_test():
    root = ET.Element("Root", {"level":"0"})
    comment = ET.Comment("This is a test")
    root.append(comment)

    element = ET.Element("Element")
    element.attrib = {"name":"Element", "level":"1"}
    element.append(comment)
    subelement = ET.SubElement(element, "SubElement")
    subelement.attrib = {"name":"SubElement", "level":"2"}
    root.append(element)

    tree = ET.ElementTree(root)
    tree.write("test.xml", encoding="utf-8", xml_declaration=True)

if __name__ == "__main__":
    xml_test()

结果：

<?xml version='1.0' encoding='utf-8'?>
<Root level="0">
        <!--This is a test-->
        <Element name="Element" level="1">
                <!--This is a test-->
                <SubElement name="SubElement" level="2" />
        </Element>
</Root>

未作美化时：

<?xml version='1.0' encoding='utf-8'?>
<Root level="0"><!--This is a test--><Element level="1" name="Element"><!--This is a test--><SubElement level="2" name="SubElement" /></Element></Root>