XML 到 Dataframe 解析时重复的值

Question

代码的目的是从 xml 文件中获取元素并将它们解析为 csv 文件。

最近我更新了代码，因此代码转到 Phones（ProjectData 的另一个子项）从 Set 获取元素，然后 Get 附加它们与下划线一起并将它们解析为标题名称为 Identify 的第一列 这是我的代码

from xml.etree import ElementTree as ET
from collections import defaultdict
from pathlib import Path
import csv
from pathlib import Path


directory = 'C:/Users/TRY/try.xml'

with open('try.csv', 'w', newline='') as f:
    writer = csv.writer(f, delimiter=';')
   #◙ writer = csv.writer(f)

    headers = ['identify','id', 'service_code', 'rational', 'qualify', 'description_num', 'description_txt','Counter', 'set_data_xin', 'set_data_xax', 'set_data_value', 'set_data_x']

    writer.writerow(headers)

    xml_files_list = list(map(str,Path(directory).glob('**/*.xml')))
    for xml_file in xml_files_list:
        tree = ET.parse(xml_file)
        root = tree.getroot()
        p_get = tree.find('.//Phones/Get').text
        p_set = tree.find('.//Phones/Set').text


        start_nodes = root.findall('.//START')
        for sn in start_nodes:
            row = defaultdict(str)

            # <<<<< Indentation was wrong here
            for k,v in sn.attrib.items():
                row[k] = v
            for rn in sn.findall('.//Rational'):
                row['Rational'] = rn.text

            for qu in sn.findall('.//Qualify'):
                row['Qualify'] = qu.text

            for ds in sn.findall('.//Description'):
                row['Description_txt'] = ds.text
                row['Description_text_id'] = ds.attrib['text_id']



            for counter, st in enumerate( sn.findall('.//SetData') ):
                for k,v in st.attrib.items():
                    if v.startswith("-"):
                        v = v.replace("-","",1)
                    v=v.replace(',', '.')
                    row['SetData_'+ str(k)] = v
                row["Counter"] = counter 
                row_data = [row[i] for i in headers]
                row_data[0]=p_get + '_' + p_set
                writer.writerow(row_data)
                row = defaultdict(str)

这是xml文件

<?xml version="1.0" encoding="utf-8"?>
<ProjectData>
 <Phones>
    <Date />
    <Prog />
    <Box />
    <Feature />
    <IN>MAFWDS</IN>
    <Set>234234</Set>
    <Pr>23423</Pr>
    <Number>afasfhrtv</Number>
    <Simple>dfasd</Simple>
    <Nr />
    <Get>6070106091</Get>
    <Reno>1233</Reno>
  </Phones>
<FINAL>
    <START id="B001" service_code="0x5196">
      <Docs Docs_type="START">
        <Rational>225196</Rational>
        <Qualify>6251960000A0DE</Qualify>
      </Docs>
      <Description num="1213f2312">The parameter</Description>
      <DataFile dg="12" dg_id="let">
        <SetData value="32" />
      </DataFile>
    </START>
    <START id="C003" service_code="0x517B">
      <Docs Docs_type="START">
        <Rational>23423</Rational>
        <Qualify>342342</Qualify>
      </Docs>
      <Description num="3423423f3423">The third</Description>
      <DataFile dg="55" dg_id="big">
        <SetData x="E1" value="21259" />
        <SetData x="E2" value="02" />
      </DataFile>
    </START>
    <START id="Z048" service_code="0x5198">
      <RawData rawdata_type="ASDS">
        <Rational>225198</Rational>
        <Qualify>3432433</Qualify>
      </RawData>
      <Description num="434234234">The forth</Description>
      <DataFile unit="21" unit_id="FEDS">
        <FileX unit="eg" discrete="false" axis_pts="19" name="Vsome" text_id="bx5" unit_id="GDFSD" />
        <SetData xin="5" xax="233" value="323" />
        <SetData xin="123" xax="77" value="555" />
        <SetData xin="17" xax="65" value="23" />
      </DataFile>
    </START>
</FINAL>
</ProjectData>

输出看起来像这样以及它应该是什么样子。

问题是 identify 列被重复。我想要它不会重复。 我尝试使用代码并在代码周围移动此变量但没有成功，发现很难解决这个问题，因为列是由 xml 文件的另一个子元素的元素组成的。

Answer 1

您的代码为每个写入 csv 文件的 row_data 设置 row_data[0]，因此它在 csv 文件的每一行中重复。

如果你想每原始行只看到一次，你必须在row内部循环之前直接设置它for counter, st in enumerate( sn.findall('.//SetData') ):

例如：

        row['identify']=p_get + '_' + p_set
        for counter, st in enumerate( sn.findall('.//SetData') ):
            for k,v in st.attrib.items():
                if v.startswith("-"):
                    v = v.replace("-","",1)
                v=v.replace(',', '.')
                row['SetData_'+ str(k)] = v
            row["Counter"] = counter 
            row_data = [row[i] for i in headers]
            writer.writerow(row_data)
            row = defaultdict(str)