Question

这是我试图整理的脚本片段，让我的生活更轻松。我有一堆来自不同API源的XML文件。他们有不同的项目和不同的领域。他们所做的共同点是像“clientid”这样的共同领域。

我想要做的是最终得到一个CSV，它包含所有XML的组合标题及其相应的数据。所以我需要能够确保12345的“clientid”中的所有信息都添加到行的末尾，用于“itemid”中的同名客户端ID

项目数据：

<item>
<id>99899</id>
<client-id>12345</client-id>

脚本的一部分：

def parseXML():
    ### Parse XML and convert to CSV ###
    #Get XML Source #
    tree = ET.fromstring(getdata)
    # open a file for writing
    xmlTest01 = open('xmlTest01.csv', 'w')
    # create the csv writer object
    csvwriter = csv.writer(xmlTest01)
    item_head = []

    count = 0
    for member in tree.findall('item'):
                    item = []
                    if count == 0:
                                    id = member.find('id').tag
                                    item_head.append(id)
                                    clientid = member.find('client-id').tag
                                    item_head.append(clientid)

                    id = member.find('id').text
                    item.append(id)
                    clientid = member.find('client-id').text
                    item.append(clientid)
                    csvwriter.writerow(item)
    xmlTest01.close()

下一组数据包括：

<client>
<id>12345</id>
<name>Clients name</name>
<current type="boolean">true</current>
<status>good</status>

所以我想检查上一组数据中的行，查看相同的clientid，然后将名称，当前和状态添加到该行的末尾。

有关最佳方法的任何想法吗？我有大约5-7种这类文件要合并。在将文件转换为CSV之前，我是否应首先尝试合并文件？如果他们都有相似的内容但是他们不这样做可能没问题。

所需的输出结合了两个xml文件的值：

id,clientid,name,current,status
99899,12345,Clients name,true,good

Answer 1

考虑迭代这三个文件并有条件地检查客户端ID。将xml值解析为您写入csv文件的列表：

import csv
import xml.etree.ElementTree as ET 

def parseXML():
    projecttree = ET.parse('projects.xml')
    clienttree = ET.parse('clients.xml')
    teamtasktree = ET.parse('teammembers.xml')

    projectroot = projecttree.getroot()
    clientroot = clienttree.getroot()
    teamtaskroot = teamtasktree.getroot()

    data = []
    for i in projectroot.iter('project'):
        for j in clientroot.iter('client'):
            clientid = i.find('client-id').text
            if clientid == j.find('id').text:
                data.append(i.find('id').text)
                data.append(j.find('id').text)
                data.append(j.find('name').text)
                data.append(j.find('active').text)
                data.append(i.find('name').text)
                data.append(i.find('active').text)
                data.append(i.find('billable').text)
                data.append(i.find('bill-by').text)
                data.append(i.find('hourly-rate').text)
                data.append(i.find('budget').text)
                data.append(i.find('over-budget-notification-percentage').text)
                data.append(i.find('created-at').text)
                data.append(i.find('updated-at').text)
                data.append(i.find('starts-on').text)
                data.append(i.find('ends-on').text)
                data.append(i.find('estimate').text)
                data.append(i.find('estimate-by').text)
                data.append(i.find('notes').text)
                data.append(i.find('cost-budget').text)

        cnt = 1     
        for tm in teamtaskroot.iter('team_members'):
            for item in tm.iter('item'):                
                if item.find('cid').text == clientid and cnt <= 3:
                    data.append(item.find('full_name').text)
                    data.append(item.find('cost_rate').text)
                cnt += 1

        cnt = 1
        for tk in teamtaskroot.iter('tasks'):
            for item in tk.iter('item'):                
                if item.find('cid').text == clientid and cnt <= 2:
                    data.append(item.find('task_id').text)
                    data.append(item.find('total_hours').text)
                cnt += 1

    with open('Output.csv', 'w') as f:
        csvwriter = csv.writer(f, lineterminator = '\n')
        csvwriter.writerow(['Pid', 'Clientid', 'ClientName', 'ClientActive', 'ProjectName', 'ProjectActive',
                            'Billable', 'BillBy', 'HourlyRate', 'Budget', 'OverbudgetNotificationPercentage',
                            'CreatedAt', 'UpdatedAt', 'StartsOn', 'EndsOn', 'Estimate', 'EstimateBy',
                            'Notes', 'CostBudget', 'TeammemberName1', 'CostRate1', 'TeammemberName2', 'CostRate2',
                            'TeammemberName3', 'CostRate3', 'TaskId1', 'TotalHours1', 'TaskId2', 'TotalHours2'])
        csvwriter.writerow(data)

if __name__ == "__main__":
    parseXML()

<强>输出

Pid,Clientid,ClientName,ClientActive,ProjectName,ProjectActive,Billable,
BillBy,HourlyRate,Budget,OverbudgetNotificationPercentage,CreatedAt,
UpdatedAt,StartsOn,EndsOn,Estimate,EstimateBy,Notes,CostBudget,TeammemberName
1,CostRate1,TeammemberName2,CostRate2,TeammemberName3,CostRate3,
TaskId1,TotalHours1,TaskId2,TotalHours2
11493770,4708336,AFB,true,Services - Consulting - AH,true,true,Project,
421.28,16.0,80.0,2016-08-16T03:22:51Z,
2016-08-16T03:22:51Z,,,16.0,project,Random 
notes,,BobR,76.0,BobR,76.0,BobR,76.0,6357137,0.0,6357138,0.0

Answer 2

此外，考虑XSLT，这是一种特殊用途的转换语言，它可以直接将XML转换为CSV，甚至可以使用其document()函数从其他XML文件解析。 Python的lxml模块可以处理XSLT 1.0脚本。确保所有三个xml都位于同一目录中。

XSLT 脚本（另存为.xsl文件 - 一个特殊的.xml文件 - 在Python下面调用）

<xsl:transform xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="2.0">
<xsl:output version="1.0" encoding="UTF-8" method="text" indent="yes" omit-xml-declaration="yes"/>
<xsl:strip-space elements="*"/>

  <xsl:template match="/projects">
    <xsl:copy>
      <xsl:text>Pid,Clientid,ClientName,ClientActive,ProjectName,ProjectActive,Billable,BillBy,HourlyRate,</xsl:text>
      <xsl:text>Budget,OverbudgetNotificationPercentage,CreatedAt,UpdatedAt,StartsOn,EndsOn,Estimate,EstimateBy,</xsl:text>
      <xsl:text>Notes,CostBudget,TeammemberName1,CostRate1,TeammemberName2,CostRate2,TeammemberName3,CostRate3,</xsl:text>
      <xsl:text>TaskId1,TotalHours1,TaskId2,TotalHours2&#xa;</xsl:text>      
      <xsl:apply-templates select="project"/>      
    </xsl:copy>
  </xsl:template>

  <xsl:template match="project">    
    <xsl:variable name="clientid" select="client-id"/>
    <xsl:value-of select="concat(id, ',')"/>
    <xsl:variable name="delimiter"><xsl:text>&quot;,&quot;</xsl:text></xsl:variable>

    <xsl:for-each select="document('clients.xml')/clients/client[id=$clientid]/*
                                   [local-name()='id' or local-name()='name' or local-name()='active']">
      <xsl:value-of select="." />
      <xsl:if test="position() != last()">
        <xsl:text>,</xsl:text>
      </xsl:if>      
    </xsl:for-each>

    <xsl:value-of select="concat(',',name,',',active,',',billable,',',bill-by,',',hourly-rate,',',budget,',',
                                 over-budget-notification-percentage,',',created-at,',',updated-at,',',starts-on,',',ends-on,',',
                                 estimate,',',estimate-by,',',notes,',',cost-budget,',')"/>        

    <xsl:for-each select="document('teammembers.xml')/root/team_members/item[cid=$clientid]/*
                                   [local-name()='full_name' or local-name()='cost_rate']">
      <xsl:if test="position() &lt; 5">
        <xsl:value-of select="." />      
        <xsl:text>,</xsl:text>
      </xsl:if>
    </xsl:for-each>

    <xsl:for-each select="document('ClientItems_teammembers.xml')/root/tasks/item[cid=$clientid]/*
                                   [local-name()='task_id' or local-name()='total_hours']">
      <xsl:if test="position() &lt; 5">
        <xsl:value-of select="." />
        <xsl:if test="position() != last()">
          <xsl:text>,</xsl:text>
        </xsl:if>
      </xsl:if>
    </xsl:for-each>

    <xsl:text>&#xa;</xsl:text>
  </xsl:template>

</xsl:transform>

Python 脚本（转换projects.xml并在XSLT中读取其他两个）

import lxml.etree as ET

def transformXML():
    dom = ET.parse('projects.xml')
    xslt = ET.parse('XSLTscript.xsl')

    transform = ET.XSLT(xslt)
    newdom = transform(dom)

    with open('Output.csv'),'w') as f:
        f.write(str(newdom))

if __name__ == "__main__":
    transformXML()

<强>输出

Pid,Clientid,ClientName,ClientActive,ProjectName,ProjectActive,Billable,
BillBy,HourlyRate,Budget,OverbudgetNotificationPercentage,CreatedAt,
UpdatedAt,StartsOn,EndsOn,Estimate,EstimateBy,Notes,CostBudget,TeammemberName
1,CostRate1,TeammemberName2,CostRate2,TeammemberName3,CostRate3,
TaskId1,TotalHours1,TaskId2,TotalHours2
11493770,4708336,AFB,true,Services - Consulting - AH,true,true,Project,
421.28,16.0,80.0,2016-08-16T03:22:51Z,
2016-08-16T03:22:51Z,,,16.0,project,Random 
notes,,BobR,76.0,BobR,76.0,BobR,76.0,6357137,0.0,6357138,0.0,

python将多个xmls合并为单个CSV

2 个答案: