python - 如何有条件地从带有 ElementTree 的 XML 中获取值？

Question

我有 XML，我需要提取一些值，如果这些值不存在，我想要“N/A”。

<?xml version="1.0" encoding="utf-8"?>
<DEF xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="FF.xsd">
    <FOLD SERV="TRYING" VERSION="918" PLATFORM="UNIX" GROUP_NAME="UNIX" MODIFIED="False" LAST_UPLOAD="20220117145134UTC" TYPE="1" USED_BY_CODE="0">
        <JOB JOBID="835" APP="TRY" JOBNAME="JOBA" DESC="Extrac607" TYPE="db" FORM="Databases" CM_VER="N/A" MULTY_AGENT="N" VERSION_SERIAL="1" PARENT_FOLDER="UNIX">
            <VARIABLE NAME="%%TYPE_DB" VALUE="Open Query" />
            <VARIABLE NAME="%%APPLOG" VALUE="N" />
            <VARIABLE NAME="%%ACCOUNT" VALUE="ONLINE" />
            <VARIABLE NAME="%%TYPE" VALUE="Oracle" />
            <VARIABLE NAME="%%VERS" VALUE="11g" />
            <VARIABLE NAME="%%LENGHT" VALUE="16" />
        </JOB>
        <JOB JOBID="839" APP="TRY" JOBNAME="JOBB" DESC="Extrac617" TYPE="db" FORM="Databases" CM_VER="N/A" MULTY_AGENT="N" VERSION_SERIAL="1" PARENT_FOLDER="UNIX">
            <VARIABLE NAME="%%TYPEDB" VALUE="Open Query" />
            <VARIABLE NAME="%%ACCOUNT" VALUE="ONLINE" />
            <VARIABLE NAME="%%TYPE" VALUE="Oracle" />
            <VARIABLE NAME="%%VERS" VALUE="11g" />
            <VARIABLE NAME="%%LENGHT" VALUE="16" />
        </JOB>
    </FOLD>
</DEF>

这是我的代码:

from xml.etree import ElementTree
from contextlib import redirect_stdout
from collections import Counter

import xlsxwriter
import pprint
import os
import datetime

begin_time = datetime.datetime.now()
print(datetime.datetime.now())
    
###VARIABLES RUTASL   
fileXML= 'C:\\xxxx\\completa.xml'
cont=0
path= 'C:\\xxxxxx\\todo.csv'
outputExcel = 'C:\\xxxxxxx\\salida.xlsx'
file2 = 'C:\\xxxxxxxx\\todo.csv'




try:
    os.remove(path)
except OSError as e:  ## if failed, report it back to the user ##
    print ("Error: %s - %s." % (e.filename, e.strerror))

try:
    os.remove(outputExcel)
except OSError as e:  ## if failed, report it back to the user ##
    print ("Error: %s - %s." % (e.filename, e.strerror))




with open(fileXML, encoding="utf8") as f:
    tree = ElementTree.parse(f)

    
# using getchildren() within root and check if tag starts with keyword 
#print [node.text for node in root.getchildren() if node.tag.startswith('%%FTP-LPATH')]
root = tree.getroot()
set_tipos= set()
lista_tipos = list()

for node in tree.iter('JOB'):


    name = node.attrib.get('JOBNAME')
    appl_type = node.attrib.get('TYPE')
    appl_form = node.attrib.get('FORM')
    

    if appl_form:
        set_tipos.add(appl_form)
        lista_tipos.append(appl_form)
    else:
        set_tipos.add(appl_type)
        lista_tipos.append(appl_type)
        
     
    
print('#####################################')


cuenta1 = Counter(lista_tipos)
print(cuenta1)

workbook = xlsxwriter.Workbook(outputExcel)
worksheet = workbook.add_worksheet('Resumen')
bold =workbook.add_format({'bold':1})
centrado =workbook.add_format({'center_across':1})
centrado = workbook.add_format({'bold': True, 'center_across': True})

headings = list()
datos = list()
listaBD = list()
pointDB=1

for key, value in cuenta1.items():
    # scores = 0
    print(key)
    headings.append(key)
    datos.append(value)



if 'Databases' in headings:
    print('Existe base de datos')
    
    for node4 in tree.iterfind(".//JOB[@TYPE = 'db']"): 
        listaBD.clear()
        name = node4.attrib.get('JOBNAME')
        appl_type = node4.attrib.get('TYPE')
        listaBD.append(name)
        listaBD.append(appl_type)
        for node4 in tree.iterfind(".//JOB/VARIABLE[@NAME='%%TYPE_DB']"):
            a=0 

        value = node4.attrib.get('VALUE', 'N/A')
        listaBD.append(value) 


        worksheet.write_row('A'+str(pointDB),listaBD)
        pointDB += 1


        node4.clear()

else:
    print('Don't exists')

print(datetime.datetime.now() - begin_time)

workbook.close()

                ...................

这行得通，但我在每种情况下都有 6 个 if(s)，而且程序非常慢。我已经编辑了主要代码。看来问题是 xml 的大小。 XML 有 50 MB。输出是: 我还能如何有条件地获取这些值？

Answer 1

我看到至少有两件事可以更改以删除 if block 。

更具体的 X 路径

我看到这个“如果类型匹配就做所有事情，否则跳过”分支:

appl_type = node4.attrib.get('TYPE')
if appl_type == 'db':

您可以通过将对 @TYPE 的检查放入您的顶级 X-Path 来避免这种情况:

for node4 in tree.iterfind(".//JOB[@TYPE = 'db']"):

默认 setter/getter

您将获得一个属性值并根据它是否为 None 来决定要做什么:

if node4.attrib.get('VALUE') is None:
    print("don't exists")
    listaBD.append('N/A')
else:
    print("Existe")
    listaBD.append(node4.attrib.get('VALUE'))

在 get() 方法中使用 默认值 如果它是 None 并避免检查:

value = node4.attrib.get('VALUE', 'N/A')
listaBD.append(value)

杂项

这不会删除 if block ，但会重组并使代码更容易理解:

if 'DB' not in headings:
    quit()  # or `return` from a function/method... don't go on

print('DB Exists')

不删除 if，但现在所有内容都没有嵌套在它下面。

这是我对你的原始代码的完整编辑

from xml.etree import ElementTree as ET

tree = ET.parse('input.xml')
headings = ['DB']
listaBD = []

if 'DB' not in headings:
    quit()  # or `return` from a function/method... don't go on

print('DB Exists')

for node4 in tree.iterfind(".//JOB[@TYPE = 'db']"):
    print('//////////////////////////')
    print(node4.tag, node4.attrib)
    name = node4.attrib.get('JOBNAME')
    appl_type = node4.attrib.get('TYPE')
    
    print(name + " " + appl_type)
    for node4 in tree.iterfind(".//JOB/VARIABLE[@NAME='%%TYPE_DB']"):
        print('TIPO')
        print(node4.attrib.get('VALUE'))

    value = node4.attrib.get('VALUE', 'N/A')
    listaBD.append(value)

    node4.clear()
    for node4 in tree.iterfind(".//JOB/VARIABLE[@NAME='%%DBSCHEMA']"):
        print(node4)