• python xml解析和生成


    解析使用xml.etree.ElementTree 模块,生成使用xml.dom.minidom模块,  ElementTree比dom快,dom生成简单且会自动格式化。

    <?xml version='1.0' encoding='utf-8'?>
    <baspools>
            <bas>
                    <basprovider>0</basprovider>
                    <portal_version>1</portal_version>
                    <timeout>111</timeout>
                    <retry>111</retry>
                    <auth_type>111</auth_type>
            </bas>
            <bas>
                    <basprovider>0</basprovider>
                    <portal_version>1</portal_version>
                    <timeout>5000</timeout>
                    <retry>3</retry>
                    <auth_type>0</auth_type>
            </bas>
    </baspools>
    解析为dict:
    {0: {'retry': '111', 'auth_type': '111', 'portal_version': '1', 'timeout': '111', 'basprovider': '0'}, 1: {'retry': '3', 'auth_type': '0', 'portal_version': '1', 'timeout': '5000', 'basprovider': '0'}}
    将上述字典再还原xml


    执行代码:
    # coding = 'utf-8'
    import time
    import xml.etree.ElementTree as ET
    import xml.dom.minidom as minidom
    start = time.clock()  # 记录处理开始时间;与最后一行一起使用,来判断输出运行时间。
    
    def read_xml(in_path):
        """读取并解析xml文件
           in_path: xml路径
           return: tree"""
        tree = ET.parse(in_path)
        return tree
    
    def creat_dict(root):
        """xml生成为dict:,
        将tree中个节点添加到list中,将list转换为字典dict_init
        叠加生成多层字典dict_new"""
        dict_new = {}
        for key, valu in enumerate(root):
            dict_init = {}
            list_init = []
            for item in valu:
                list_init.append([item.tag, item.text])
                for lists in list_init:
                    dict_init[lists[0]] = lists[1]
            dict_new[key] = dict_init
        return dict_new
    
    def dict_to_xml(input_dict, root_tag, node_tag):
        """ 定义根节点root_tag,定义第二层节点node_tag
        第三层中将字典中键值对对应参数名和值
           return: xml的tree结构 """
        root_name = ET.Element(root_tag)
        for (k, v) in input_dict.items():
            node_name = ET.SubElement(root_name, node_tag)
            for key, val in v.items():
                key = ET.SubElement(node_name, key)
                key.text = val
        return root_name
    
    def out_xml(root):
        """格式化root转换为xml文件"""
        rough_string = ET.tostring(root, 'utf-8')
        reared_content = minidom.parseString(rough_string)
        with open(out_file, 'w+') as fs:
            reared_content.writexml(fs, addindent=" ", newl="
    ", encoding="utf-8")
        return True
    
    if __name__ == '__main__':
        in_files = r"D:aspool_read.xml"
        out_file = r"D:aspool_out.xml"
        tree = read_xml(in_files)
        node_new = creat_dict(tree.getroot())  # 将xml转换为dict
        root = dict_to_xml(node_new, "baspools", "bas")  # 将dict转换为xml
        out_xml(root)     # 输出xml到out_files
    end = time.clock()
    print("read: %f s" % (end - start))

    解决 字典无顺序导致生成的xml文件参数位置不固定,对dict_to_xml()函数进行修正:

    def dict_to_xml(input_dict,root_tag,node_tag):
        """ 定义根节点root_tag,定义第二层节点node_tag
        第三层中将字典中键值对对应参数名和值
           return: xml的tree结构 """
        root_name = ET.Element(root_tag)
        for (k, v) in input_dict.items():
            node_name = ET.SubElement(root_name, node_tag)
            for (key, val) in sorted(v.items(), key=lambda e:e[0], reverse=True):
                key = ET.SubElement(node_name, key)
                key.text = val
        return root_name
     
  • 相关阅读:
    吐槽下博客园
    关于爱情
    CCD 驱动 时序理解
    写在博客的第一天
    51单片机最小系统
    swing之登陆功能
    TDSQL | 在整个技术解决方案中HTAP对应的混合交易以及分析系统应该如何实现?
    TDSQL | 深度解读HTAP系统的问题与主义之争
    硬核干货!TDSQL全局一致性读技术详解|
    35w奖金池,腾讯云TDSQL精英挑战赛等你来战!
  • 原文地址:https://www.cnblogs.com/jonyq/p/5929073.html
Copyright © 2020-2023  润新知