python使用ElementTree操作xml

前言:

在web数据传输过程中,用到最多的两种数据传输格式分别是json和xml,现记录一下如何使用python的ElementTree库来操作xml,实现对xml的增删查改!

这里通过以下方式来操作xml

  • 标签节点的CRUD
  • 标签属性的CRUD
  • 标签值的CRUD
  • xml数据样例:
    <?xml version='1.0' encoding='utf-8'?>
    <root name="test" msg="测试">
            <uid>6taE112M48343D7QaP452o29</uid>
            <fileType>Other</fileType>
            <sum>100</sum>
            <createTime>2018-11-28 15:10:02</createTime>
        </head>
        <datas>
                <id>1530</id>
                <osId>UNIX1001</osId>
                <ip>192.168.1.2</ip>
                <groupId>275</groupId>
                <secrity>安全</secrity>
                <securityManager>张三</securityManager>
                <port>22</port>
                <protocol>ssh</protocol>
                <upPriv>su -</upPriv>
            </data>
                <id>1531</id>
                <osId>UNIX1002</osId>
                <ip>192.168.1.3</ip>
                <groupId>276</groupId>
                <secrity>安全</secrity>
                <securityManager>李四</securityManager>
                <port>25</port>
                <protocol>ssh</protocol>
                <upPriv>insert</upPriv>
            </data>
        </datas>
    </root>
    
    标签节点的CRUD
    1.查询标签节点

    1.findall(标签名):查找所有标签节点,返回一个可迭代对象
    2.find(标签名):查找满足条件的第一个标签节点,返回该节点对象

    #coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def select_node():
        """查询节点"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # findall():查找并迭代标签
        for data in root.findall('.//data'):  # xpath语法
            print data
        # find(): 查找满足条件的第一个标签
        data = root.find('.//data')
        print data
    
    2.删除标签节点

    1.remove(节点对象):删除指定的节点
    2.clear():清空本节点下的所有子节点

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def del_node():
        """添加节点"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # 获取datas节点
        datas_node = root.find(".//datas")
        # 获取datas的第一个子节点
        data_node = root.find('.//datas/data')
        # 1.remove(节点对象):删除指定的节点
        datas_node.remove(data_node)
        # 2.clear(): 清空datas下的所有子节点
        # datas_node.clear()
        # 回写xml数据
        tree.write("test2.xml", encoding='utf-8', xml_declaration=True)
    
    3.添加标签节点:(需要两步:创建标签节点,添加标签)

    1.创建标签节点:
    Element(标签名):创建标签节点对象
    2.添加标签:
    1.append(标签节点):在标签的末尾添加新标签
    2.insert(索引号,标签节点):在指定的索引位置添加新标签

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def add_node():
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # Element(标签名):创建标签节点对象
        new_node = ET.Element("node")
        # 添加标签值
        new_node.text = "newNode"
        # 添加标签
        root.append(new_node)
        # 回写xml数据
        tree.write("test2.xml", encoding='utf-8', xml_declaration=True)
    
    标签属性的CRUD
    1.获取标签属性:

    1.attrib:以字典形式返回标签属性
    2.keys():返回标签属性名称列表
    3.items():返回标签属性项列表
    4.get(key, default=None):根据标签属性名称获取标签属性值

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def select_attrib():
        """查询标签属性"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # 获取标签属性
        attr_dict = root.attrib  # {'msg': '测试', 'name': 'test'}
        attr_key = root.keys()  # ['msg', 'name']
        attr_item = root.items()  # [('msg', u'测试'), ('name', 'test')]
        attr_get = root.get('name')  # test
    
    2.添加/修改标签属性:

    set(key, value):添加/修改标签属性

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def update_attrib():
        """添加/修改标签属性"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # 不存在则添加
        root.set("age", "30")
        # 存在则修改
        root.set("name", "mytest")
        # 回写xml数据
        tree.write("test2.xml", encoding='utf-8', xml_declaration=True)
    
    3.删除标签属性:

    del node.attrib[key]

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def del_attrib():
        """删除节点属性"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # 删除名为name的属性
        del root.attrib["name"]
        # 回写xml数据
        tree.write("test2.xml", encoding='utf-8', xml_declaration=True)
    
    标签值的CRUD
    1.获取标签值

    node.text

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def select_node_value():
        """查询节点值"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # 获取第一个ip节点
        ip_node = root.find(".//ip")
        # 获取节点值
        node_value = ip_node.text
        print node_value
    
    2.添加/修改标签值

    node.text = value :存在就修改,不存在就添加

    # coding:utf-8
        import xml.etree.cElementTree as ET
    except ImportError:
        import xml.etree.ElementTree as ET
    def update_node_value():
        """添加/修改标签属性"""
        xml_path = "test.xml"
        # 通过获取tree对象
        tree = ET.parse(xml_path)
        # 获取根节点
        root = tree.getroot()
        # 获取第一个ip节点
        ip_node = root.find(".//ip")