使用python拆分XML字符串并解析字段属性文件名

使用python拆分XML字符串并解析字段属性文件名

提示：以下是本篇文章正文内容，下面案例可供参考

一、XML源数据

多段XML使用’=========='字符拼接

<?xml version="1.0" encoding="utf-8"?>
<PPO_COMPLETE>
    <HEADER>
        <CONTROLNO>563</CONTROLNO>
        <TASK_ORDER>BPLHBL000000001</TASK_ORDER>
        <TASK_REVISION>00</TASK_REVISION>
        <SUPPLIER_NUMBER>124124</SUPPLIER_NUMBER>
        <DROP_SHIP>N</DROP_SHIP>
        <HEADER_ATTRIBUTE1/>
        <HEADER_ATTRIBUTE2/>
        <HEADER_ATTRIBUTE3/>
        <HEADER_ATTRIBUTE4/>
        <HEADER_ATTRIBUTE5/>
        <HEADER_ATTRIBUTE6/>
        <HEADER_ATTRIBUTE7/>
        <HEADER_ATTRIBUTE8/>
        <LINE>
            <LINEITEM>12431ASFQ</LINEITEM>
            <LINE_QTY>600</LINE_QTY>
            <ERP_LINE_ID>29074326</ERP_LINE_ID>
            <ITEM_REVISION/>
            <NEEDBY_DATE/>
            <TRANSACTION_DATE/>
            <SUBINVENTORY_CODE/>
            <LINE_ATTRIBUTE1>25490</LINE_ATTRIBUTE1>
            <LINE_ATTRIBUTE2/>
            <LINE_ATTRIBUTE3></LINE_ATTRIBUTE3>
            <LINE_ATTRIBUTE4>ASD</LINE_ATTRIBUTE4>
            <LINE_ATTRIBUTE5>2574479-2574481-2574496-2614852</LINE_ATTRIBUTE5>
            <LINE_ATTRIBUTE6/>
            <LINE_ATTRIBUTE7/>
            <LINE_ATTRIBUTE8/>
        </LINE>
    </HEADER>
</PPO_COMPLETE>
==========
<?xml version="1.0" encoding="utf-8"?>
<PPO_COMPLETE>
    <HEADER>
        <CONTROLNO>563</CONTROLNO>
        <TASK_ORDER>BPLHBL000000002</TASK_ORDER>
        <TASK_REVISION>00</TASK_REVISION>
        <SUPPLIER_NUMBER>124124</SUPPLIER_NUMBER>
        <DROP_SHIP>N</DROP_SHIP>
        <HEADER_ATTRIBUTE1/>
        <HEADER_ATTRIBUTE2/>
        <HEADER_ATTRIBUTE3/>
        <HEADER_ATTRIBUTE4/>
        <HEADER_ATTRIBUTE5/>
        <HEADER_ATTRIBUTE6/>
        <HEADER_ATTRIBUTE7/>
        <HEADER_ATTRIBUTE8/>
        <LINE>
            <LINEITEM>12431ASFA</LINEITEM>
            <LINE_QTY>600</LINE_QTY>
            <ERP_LINE_ID>29074326</ERP_LINE_ID>
            <ITEM_REVISION/>
            <NEEDBY_DATE/>
            <TRANSACTION_DATE/>
            <SUBINVENTORY_CODE/>
            <LINE_ATTRIBUTE1>25490</LINE_ATTRIBUTE1>
            <LINE_ATTRIBUTE2/>
            <LINE_ATTRIBUTE3></LINE_ATTRIBUTE3>
            <LINE_ATTRIBUTE4>QWEI</LINE_ATTRIBUTE4>
            <LINE_ATTRIBUTE5>2574479-2574481-2574496-2614852</LINE_ATTRIBUTE5>
            <LINE_ATTRIBUTE6/>
            <LINE_ATTRIBUTE7/>
            <LINE_ATTRIBUTE8/>
        </LINE>
    </HEADER>
</PPO_COMPLETE>

二、第一版

split拆分生成文件，再从文件中解析xml属性，（没必要这么，直接看第二版就行）

# coding=utf-8
from xml.etree.ElementTree import parse
from lxml import etree
import xml.etree.ElementTree as ET
import os

xml_list = []
xml = ''
name_list = []

print('读取EDI08_FILE.xml文件开始')
try:
    with open('EDI08_FILE.xml', encoding='utf-8') as f:
        xml = f.read()
        # print(xml)
        xml_list = xml.split('==========\n')
        # print(xml_list)
        a = 0
        for i in xml_list:
            with open(str(a) + '.xml', 'w', encoding='utf-8') as x:
                x.write(i)
            a = a + 1
    f.close()
except Exception as result:
    print(f'获取EDI08_FILE.xml文件失败，ERROR:{result}')
finally:
    print('读取EDI08_FILE.xml文件结束')

print('开始拆分xml文件')
try:
    for i in range(0, len(xml_list)):
        # 解析XML文件
        f = open(str(i) + '.xml', encoding='utf-8')
        tree = ET.parse(f)  # 解析XML
        root = tree.getroot()  # 获取XML根节点
        # print(list(root))
        for obj in root.iter('HEADER'):  # 获取XML子节点
            # print(obj)
            # 找到指定节点
            if obj.find('TASK_ORDER').text:  # XML子节点中找到需要的属性的内容
                node = obj.find('TASK_ORDER').text
            else:
                node = 'i'
            # 获取节点的值
            print(node)  # 输出该属性的内容
        f.close()
        os.replace(str(i) + '.xml',
                   'PPO_COMPLETE_' + node + '.xml')  # 对文件重命名
        # os.remove('C:/Users/32566/Desktop/WORK/EDI08_FILE/' + str(i) + '.xml')  # 删除文件
except Exception as result:
    print(f'拆分xml文件失败，ERROR:{result}')
finally:
    print('拆分xml文件文件结束')

二、第二版

拆分xml字符串，直接解析拆分结果生成XML文件

# coding=utf-8
import xml.etree.ElementTree as ET

xml_list = []
xml = ''
name_list = []

print('读取EDI08_FILE.xml文件开始')
try:
    with open('EDI08_FILE.xml', encoding='utf-8') as f:
        print(type(f))
        xml = f.read()
        xml_list = xml.split('==========\n')  # 将拆分结果写入列表
    f.close()

    print('开始拆分xml文件')
    for xml_text in xml_list:  # 列表中XML逐个解析生成XML文件
        # print(xml_text)
        try:
            # 解析XML文件
            # tree = ET.parse(xml_text)
            # root = tree.getroot()
            # print(list(root))

            # 解析XML字符串
            root = ET.fromstring(xml_text)  # 将字符串转换为XML格式
            print(list(root))
            for obj in root.iter('HEADER'):
                # print(obj)
                # 找到指定节点
                if obj.find('TASK_ORDER').text:  # 获取需要的属性字段值
                    node = obj.find('TASK_ORDER').text
                else:
                    node = 'i'
                # 获取节点的值
                print(node)
            f.close()
            with open('PPO_COMPLETE_' + node + '.xml', 'w', encoding='utf-8') as x:
                x.write(xml_text)  # 将获取到的字段值作为文件名并生成XML文件
        except Exception as result:
            print(f'拆分xml文件失败，ERROR:{result}')
        finally:
            print('拆分xml文件文件结束')
except Exception as result:
    print(f'EDI08_FILE.xml文件拆分失败，ERROR:{result}')
finally:
    print('EDI08_FILE.xml拆分文件结束')