如何格式化路径中所有文件的 XML 结构

Question

我想转换此 XML:

<soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:bsvc="urn:com.workday/bsvc">
   <soapenv:Header>
      <bsvc:Workday_Common_Header>
         <!--Optional:-->
         <bsvc:Include_Reference_Descriptors_In_Response>?</bsvc:Include_Reference_Descriptors_In_Response>
      </bsvc:Workday_Common_Header>
   </soapenv:Header>
   <soapenv:Body>
      <bsvc:Gender_Data bsvc:version="?">
         <!--Optional:-->
         <bsvc:Country_Reference bsvc:Descriptor="?">
            <!--Zero or more repetitions:-->
            <bsvc:ID bsvc:type="?">?</bsvc:ID>
         </bsvc:Country_Reference>
         <!--You have a CHOICE of the next 2 items at this level-->
         <!--Optional:-->
         <bsvc:Is_Female>?</bsvc:Is_Female>
         <!--Optional:-->
         <bsvc:Is_Male>?</bsvc:Is_Male>
         <bsvc:Gender_Description>?</bsvc:Gender_Description>
         <bsvc:Gender_Code>?</bsvc:Gender_Code>
         <!--Optional:-->
         <bsvc:Inactive>?</bsvc:Inactive>
      </bsvc:Gender_Data>
   </soapenv:Body>
</soapenv:Envelope>

至：

<bsvc:Gender_Data bsvc:version="?" xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:bsvc="urn:com.workday/bsvc">
    
    <bsvc:Country_Reference bsvc:Descriptor="?">

        <bsvc:ID bsvc:type="?">?</bsvc:ID>
    </bsvc:Country_Reference>

    <bsvc:Is_Female>?</bsvc:Is_Female>

    <bsvc:Is_Male>?</bsvc:Is_Male>
    <bsvc:Gender_Description>?</bsvc:Gender_Description>
    <bsvc:Gender_Code>?</bsvc:Gender_Code>

    <bsvc:Inactive>?</bsvc:Inactive>
</bsvc:Gender_Data>

基本上删除前8行和后2行。删除所有注释的节点并将属性

xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/"

和

xmlns:bsvc="urn:com.workday/bsvc"

附加到第一个节点/根节点。

我尝试了这段代码，但遇到了前缀问题。

import os
import xml.etree.ElementTree as ET

# Specify the directory path where your XML files are located
directory_path = '/Users/File_Path/'

# Define the namespace mappings
namespaces = {
    'soapenv': 'http://schemas.xmlsoap.org/soap/envelope/',
    'bsvc': 'urn:com.workday/bsvc'
}

# Iterate through the XML files in the directory and process them
for filename in os.listdir(directory_path):
    if filename.endswith('.xml'):
        # Construct the full file path
        file_path = os.path.join(directory_path, filename)

        # Read the XML content from the file
        with open(file_path, 'r') as file:
            xml_lines = file.readlines()

        # Remove the first 8 lines and last 2 lines
        modified_lines = xml_lines[8:-2]

        # Join the modified lines back into a string
        modified_xml = ''.join(modified_lines)

        # Create a new root element with namespace declarations
        root = ET.Element('{http://schemas.xmlsoap.org/soap/envelope/}Envelope', nsmap=namespaces)

        # Parse the modified XML content and append it to the new root
        modified_root = ET.fromstring(modified_xml)
        root.extend(modified_root)

        # Remove all commented nodes
        for elem in root.iter():
            for child in elem:
                if child.tag == ET.Comment:
                    elem.remove(child)

        # Convert the modified XML back to a string
        modified_xml = ET.tostring(root, encoding='utf8').decode()

        # Overwrite the original file with the modified content
        with open(file_path, 'w') as file:
            file.write(modified_xml)

        print(f"Processed and overwritten: {file_path}")

Answer 1

为什么不查找性别数据，只将结果提取到文件中：

import xml.etree.ElementTree as ET
from io import StringIO

xml_tree = """<soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:bsvc="urn:com.workday/bsvc">
   <soapenv:Header>
      <bsvc:Workday_Common_Header>
         <!--Optional:-->
         <bsvc:Include_Reference_Descriptors_In_Response>?</bsvc:Include_Reference_Descriptors_In_Response>
      </bsvc:Workday_Common_Header>
   </soapenv:Header>
   <soapenv:Body>
      <bsvc:Gender_Data bsvc:version="?">
         <!--Optional:-->
         <bsvc:Country_Reference bsvc:Descriptor="?">
            <!--Zero or more repetitions:-->
            <bsvc:ID bsvc:type="?">?</bsvc:ID>
         </bsvc:Country_Reference>
         <!--You have a CHOICE of the next 2 items at this level-->
         <!--Optional:-->
         <bsvc:Is_Female>?</bsvc:Is_Female>
         <!--Optional:-->
         <bsvc:Is_Male>?</bsvc:Is_Male>
         <bsvc:Gender_Description>?</bsvc:Gender_Description>
         <bsvc:Gender_Code>?</bsvc:Gender_Code>
         <!--Optional:-->
         <bsvc:Inactive>?</bsvc:Inactive>
      </bsvc:Gender_Data>
   </soapenv:Body>
</soapenv:Envelope>"""

f = StringIO(xml_tree)

tree = ET.parse(f)
root = tree.getroot()

nsmap= {'soapenv': 'http://schemas.xmlsoap.org/soap/envelope/', 'bsvc': 'urn:com.workday/bsvc'}

ET.register_namespace("soapenv", "http://schemas.xmlsoap.org/soap/envelope/")
ET.register_namespace("bsvc", "urn:com.workday/bsvc")

new_root = ET.Element("root")
Envelope = ET.SubElement(new_root, ET.QName(nsmap['soapenv'], 'Envelope'))

gen = root.find(".//bsvc:Gender_Data", nsmap)

Envelope.append(gen)

# Pretty Print acnd write to file
tree = ET.ElementTree(new_root)
ET.indent(tree, space="  ")
tree.write("test.xml", xml_declaration=True, encoding="utf-8")

ET.dump(tree) 

输出：

<root xmlns:bsvc="urn:com.workday/bsvc" xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/">
  <soapenv:Envelope>
    <bsvc:Gender_Data bsvc:version="?">
      <bsvc:Country_Reference bsvc:Descriptor="?">
        <bsvc:ID bsvc:type="?">?</bsvc:ID>
      </bsvc:Country_Reference>
      <bsvc:Is_Female>?</bsvc:Is_Female>
      <bsvc:Is_Male>?</bsvc:Is_Male>
      <bsvc:Gender_Description>?</bsvc:Gender_Description>
      <bsvc:Gender_Code>?</bsvc:Gender_Code>
      <bsvc:Inactive>?</bsvc:Inactive>
    </bsvc:Gender_Data>
  </soapenv:Envelope>
</root>