【数据处理】xml的创建、读写问题

悠悠 2022-12-17 08:56 128阅读 0赞

### 文章目录 ###

*   *  一、VOC格式数据标注范例
     *  二、关于xml的创建、读写问题
     *   *  （1）xml的创建
         *  （2）在xml有根元素时写入
         *  （3）xml的读取
         *  （4）删除path节点
     *  参考

## 一、VOC格式数据标注范例 ##

<annotation>
        <folder>VOC2007</folder>
        <filename>DSC00142.JPG</filename>
        <source>
            <database>ezi</database>
        </source>
        <size>
            <width>760</width>
            <height>700</height>
            <depth>3</depth>
        </size>
        <segmented>0</segmented>
        <object>
            <name>mlc</name>
            <pose>Unspecified</pose>
            <truncated>0</truncated>
            <difficult>0</difficult>
            <bndbox>
                <xmin>483</xmin>
                <ymin>446</ymin>
                <xmax>582</xmax>
                <ymax>549</ymax>
            </bndbox>
        </object>
        <object>
            <name>mlc</name>
            <pose>Unspecified</pose>
            <truncated>0</truncated>
            <difficult>0</difficult>
            <bndbox>
                <xmin>131</xmin>
                <ymin>442</ymin>
                <xmax>221</xmax>
                <ymax>532</ymax>
            </bndbox>
        </object>
    </annotation>

## 二、关于xml的创建、读写问题 ##

### （1）xml的创建 ###

# -*- coding:utf-8 -*-
    # https://zhuanlan.zhihu.com/p/54269963
    
    
    # from xml.etree import ElementTree as etree
    from xml.etree.ElementTree import Element
    from xml.etree.ElementTree import SubElement
    from xml.etree.ElementTree import ElementTree
    from xml.dom import minidom
    
    # generate root node
    root = Element('root')
    
    # generate first child-node head
    head = SubElement(root, 'head')
    
    # child-node of head node
    title = SubElement(head, 'title')
    title.text = "Well Dola!"
    
    # generate second child-node body
    body = SubElement(root, 'body')
    body.text = "I Love Dola!"
    
    tree = ElementTree(root)
    
    # write out xml data
    tree.write('result.xml', encoding='utf-8')

*  结果 ：result.xml

### （2）在xml有根元素时写入 ###

*  customer.xml

<customer ID="C003">
        <name>kavin</name>
        <phone>32467</phone>
        <comments>
            <![CDATA[A small but healthy company.]]>
        </comments>
    </customer>

*  在 customer.xml 中写入的范例代码

from xml.dom.minidom import parse
    import xml.dom.minidom
    import os
    
    
    def writeXML():
        domTree = parse("./customer.xml")
        # 文档根元素
        rootNode = domTree.documentElement
    
        # 新建一个customer节点
        customer_node = domTree.createElement("customer")
        customer_node.setAttribute("ID", "C003")
    
        # 创建name节点,并设置textValue
        name_node = domTree.createElement("name")
        name_text_value = domTree.createTextNode("kavin")
        name_node.appendChild(name_text_value)  # 把文本节点挂到name_node节点
        customer_node.appendChild(name_node)
    
        # 创建phone节点,并设置textValue
        phone_node = domTree.createElement("phone")
        phone_text_value = domTree.createTextNode("32467")
        phone_node.appendChild(phone_text_value)  # 把文本节点挂到name_node节点
        customer_node.appendChild(phone_node)
    
        # 创建comments节点,这里是CDATA
        comments_node = domTree.createElement("comments")
        cdata_text_value = domTree.createCDATASection("A small but healthy company.")
        comments_node.appendChild(cdata_text_value)
        customer_node.appendChild(comments_node)
    
        rootNode.appendChild(customer_node)
    
        with open('added_customer.xml', 'w') as f:
            # 缩进 - 换行 - 编码
            domTree.writexml(f, addindent=' ', encoding='utf-8')
    
    
    if __name__ == '__main__':
        writeXML()

*  结果

<?xml version="1.0" encoding="utf-8"?>
    <customer ID="C003">
        <name>kavin</name>
        <phone>32467</phone>
        <comments>
            <![CDATA[A small but healthy company.]]>
        </comments>
        <customer ID="C003">
            <name>kavin</name>
            <phone>32467</phone>
            <comments><![CDATA[A small but healthy company.]]>    </comments>
        </customer>
    </customer>

### （3）xml的读取 ###

*  movie.xml

<collection shelf="New Arrivals">
        <movie title="Enemy Behind">
            <type>War, Thriller</type>
            <format>DVD</format>
            <year>2003</year>
            <rating>PG</rating>
            <stars>10</stars>
            <description>Talk about a US-Japan war</description>
        </movie>
        <movie title="Transformers">
            <type>Anime, Science Fiction</type>
            <format>DVD</format>
            <year>1989</year>
            <rating>R</rating>
            <stars>8</stars>
            <description>A schientific fiction</description>
        </movie>
        <movie title="Trigun">
            <type>Anime, Action</type>
            <format>DVD</format>
            <episodes>4</episodes>
            <rating>PG</rating>
            <stars>10</stars>
            <description>Vash the Stampede!</description>
        </movie>
        <movie title="Ishtar">
            <type>Comedy</type>
            <format>VHS</format>
            <rating>PG</rating>
            <stars>2</stars>
            <description>Viewable boredom</description>
        </movie>
    </collection>

*  读取代码

# https://www.cnblogs.com/smart-zihan/p/12015192.html
    
    from xml.dom.minidom import parse
    import xml.dom.minidom
    import os
    
    
    def is_xml_exist(xml_path):
        xml_exist = os.path.exists(xml_path)
        if not xml_exist:
            return False
        return True
    
    
    def read_movie_xml():
        path = "movie.xml"
        if not is_xml_exist(path):
            print("%s is not exist" % path)
        else:
            # 使用minidom解析器打开XML文档
    
            open_xml = parse(path)
            root_node = open_xml.documentElement
    
            shelf_attrib = "shelf"
            if root_node.hasAttribute(shelf_attrib):
                print("Lable: %s\tAttrib: %s\t\tValue: %s" % (
                    root_node.nodeName, shelf_attrib, root_node.getAttribute(shelf_attrib)))
            print("")
            # 在集合中获取所有电影
            movie_node = "movie"
            movies = root_node.getElementsByTagName(movie_node)
    
            # 打印每部电影的详细信息
            for movie in movies:
                print("**** Movie ****")
                if movie.hasAttribute("title"):
                    print("Title: %s" % movie.getAttribute("title"))
    
                type_movie = movie.getElementsByTagName('type')[0]
                print("Type: %s" % type_movie.childNodes[0].data)
    
                format_movie = movie.getElementsByTagName('format')[0]
                print("Format: %s" % format_movie.childNodes[0].data)
    
                rating_movie = movie.getElementsByTagName('rating')[0]
                print("Rating: %s" % rating_movie.childNodes[0].data)
    
                descrip_movie = movie.getElementsByTagName('description')[0]
                print("Rating: %s" % descrip_movie.childNodes[0].data)
    
                print("")
    
    
    if __name__ == "__main__":
        read_movie_xml()

### （4）删除path节点 ###

*  原xml

<annotation>
    	<folder>117_PANA</folder>
    	<filename>P1160997.JPG</filename>
    	<path>E:\样本库\0814草地贪夜蛾\117_PANA\P1160997.JPG</path>
    	<source>
    		<database>Unknown</database>
    	</source>
    	<size>
    		<width>4608</width>
    		<height>3456</height>
    		<depth>3</depth>
    	</size>
    	<segmented>0</segmented>
    	<object>
    		<name>cdtye</name>
    		<pose>Unspecified</pose>
    		<truncated>0</truncated>
    		<difficult>0</difficult>
    		<bndbox>
    			<xmin>1832</xmin>
    			<ymin>2196</ymin>
    			<xmax>2258</xmax>
    			<ymax>2628</ymax>
    		</bndbox>
    	</object>
    </annotation>

*  删除path节点代码

# -*- coding=utf-8 -*-
    import xml.etree.cElementTree as ET
    import os
    
    
    def deal_xml(xml_path):
        tree = ET.parse(xml_path)
        root = tree.getroot()
        for i in root:
            if i.tag == 'path':
                root.remove(i)
        tree.write(xml_path)
    
    
    if __name__ == '__main__':
        path = r"D:\pycharm\test\处理xml\xml"
        for i in os.listdir(path):
            xml_path = os.path.join(path, i)
            deal_xml(xml_path)

*  处理后

<annotation>
    	<folder>117_PANA</folder>
    	<filename>P1160997.JPG</filename>
    	<source>
    		<database>Unknown</database>
    	</source>
    	<size>
    		<width>4608</width>
    		<height>3456</height>
    		<depth>3</depth>
    	</size>
    	<segmented>0</segmented>
    	<object>
    		<name>cdtye</name>
    		<pose>Unspecified</pose>
    		<truncated>0</truncated>
    		<difficult>0</difficult>
    		<bndbox>
    			<xmin>1832</xmin>
    			<ymin>2196</ymin>
    			<xmax>2258</xmax>
    			<ymax>2628</ymax>
    		</bndbox>
    	</object>
    </annotation>

## 参考 ##

[Python创建、修改、保存XML文件——xml.etree.ElementTree模块][Python_XML_xml.etree.ElementTree]

[Python_XML_xml.etree.ElementTree]: https://blog.csdn.net/weixin_42782150/article/details/106219001