python xml解析和生成

解析使用xml.etree.ElementTree 模塊，生成使用xml.dom.minidom模塊，  ElementTree比dom快，dom生成簡單且會自動格式化。

 

<?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>

 

解析為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'}}

將上述字典再還原xml


執行代碼：

# coding = 'utf-8'
import time
import xml.etree.ElementTree as ET
import xml.dom.minidom as minidom
start = time.clock()  # 記錄處理開始時間；與最后一行一起使用，來判斷輸出運行時間。

def read_xml(in_path):
    """讀取並解析xml文件
       in_path: xml路徑
       return: tree"""
    tree = ET.parse(in_path)
    return tree

def creat_dict(root):
    """xml生成為dict：，
    將tree中個節點添加到list中，將list轉換為字典dict_init
    疊加生成多層字典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):
    """ 定義根節點root_tag，定義第二層節點node_tag
    第三層中將字典中鍵值對對應參數名和值
       return: xml的tree結構 """
    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轉換為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="\n", encoding="utf-8")
    return True

if __name__ == '__main__':
    in_files = r"D:\baspool_read.xml"
    out_file = r"D:\baspool_out.xml"
    tree = read_xml(in_files)
    node_new = creat_dict(tree.getroot())  # 將xml轉換為dict
    root = dict_to_xml(node_new, "baspools", "bas")  # 將dict轉換為xml
    out_xml(root)     # 輸出xml到out_files
end = time.clock()
print("read: %f s" % (end - start))

 

 

解決 字典無順序導致生成的xml文件參數位置不固定，對dict_to_xml()函數進行修正：

def dict_to_xml(input_dict,root_tag,node_tag):
    """ 定義根節點root_tag，定義第二層節點node_tag
    第三層中將字典中鍵值對對應參數名和值
       return: xml的tree結構 """
    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