使用Python将CSV数据转换为XML文件的问题求助

输入数据（Input.csv） #

CustID,CardNo
A00001,C000000001  
A00001,C000000002  
A00002,C000000003  

尝试的Python代码 #

import csv
import io
import xml.etree.ElementTree as ET
from collections import defaultdict

def generate_xml(input_file, output_file):

    # Read input data from the file
    with open(input_file, 'r') as file:
        input_data = file.readlines()

    cards_per_custid = defaultdict(list)
    for line in csv.DictReader(input_data):
        cards_per_custid[line["CustID"]].append(line["CardNo"])

    root = ET.Element(
    "ReceivableAccounting",
    attrib={"xmlns": "http://www.sample.com/testing"},
    )
    for cust_id, cards in sorted(cards_per_custid.items()):
        card_el = ET.SubElement(root, "Card")
        header = ET.SubElement(card_el, "CustHolderHeader")
        ET.SubElement(header, "CustID").text = cust_id
    for card_no in cards:
        line = ET.SubElement(card_el, "CardLine")
        ET.SubElement(line, "CardDetail").text = card_no

    tree = ET.ElementTree(root)
    ET.indent(tree)
    tree.write(output_file)

# Example usage:
input_file = "Input.csv"
output_file = "output.xml"
generate_xml(input_file, output_file)

当前生成的XML结果 #

<ReceivableAccounting xmlns="http://www.sample.com/testing">
  <Card>
    <CustHolderHeader>
      <CustID>A00001</CustID>
    </CustHolderHeader>
  </Card>
  <Card>
    <CustHolderHeader>
      <CustID>A00003</CustID>
    </CustHolderHeader>
    <CardLine>
      <CardDetail>C000000003</CardDetail>
    </CardLine>
  </Card>

预期的XML结果 #

<?xml version="1.0" encoding="UTF-8"?>
<ReceivableAccounting xmlns=http://www.sample.com/testing>
  <Card>
     <CustHolderHeader>
        <CustID>A00001</CustID>
     </CustHolderHeader>
     <CardLine>
        <CardDetail>C000000001</CardDetail>
     </CardLine>
       <CardLine>
        <CardDetail>C000000002</CardDetail>
     </CardLine> 
  </Card>
  <Card>
     <CustHolderHeader>
        <CustID>A00002</CustID>
     </CustHolderHeader>
     <CardLine>
        <CardDetail>C000000003</CardDetail>
     </CardLine>  
     </Card>

问题分析与修复 #

原代码存在两个核心问题：

1. 缩进错误：生成CardLine的for循环未嵌套在遍历客户的外层循环中，导致仅最后一个客户的卡片被生成，其他客户的CardLine完全缺失。
2. XML输出配置缺失：未指定编码和XML声明，导致输出结果缺少<?xml version="1.0" encoding="UTF-8"?>头。

额外可处理CardNo的前后空白，避免输出带空格的卡号。

修正后的代码 #

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

def generate_xml(input_file, output_file):
    # 读取CSV数据
    cards_per_custid = defaultdict(list)
    with open(input_file, 'r') as file:
        for line in csv.DictReader(file):
            # 去除卡号前后空白
            cards_per_custid[line["CustID"]].append(line["CardNo"].strip())

    root = ET.Element(
        "ReceivableAccounting",
        attrib={"xmlns": "http://www.sample.com/testing"},
    )
    # 遍历每个客户，生成对应的Card节点
    for cust_id, cards in sorted(cards_per_custid.items()):
        card_el = ET.SubElement(root, "Card")
        # 添加客户头信息
        header = ET.SubElement(card_el, "CustHolderHeader")
        ET.SubElement(header, "CustID").text = cust_id
        # 为当前客户的每张卡生成CardLine
        for card_no in cards:
            line = ET.SubElement(card_el, "CardLine")
            ET.SubElement(line, "CardDetail").text = card_no

    tree = ET.ElementTree(root)
    ET.indent(tree)
    # 写入XML，指定编码和声明
    tree.write(output_file, encoding='UTF-8', xml_declaration=True)

# 执行转换
input_file = "Input.csv"
output_file = "output.xml"
generate_xml(input_file, output_file)

修正后输出结果 #

<?xml version='1.0' encoding='UTF-8'?>
<ReceivableAccounting xmlns="http://www.sample.com/testing">
  <Card>
    <CustHolderHeader>
      <CustID>A00001</CustID>
    </CustHolderHeader>
    <CardLine>
      <CardDetail>C000000001</CardDetail>
    </CardLine>
    <CardLine>
      <CardDetail>C000000002</CardDetail>
    </CardLine>
  </Card>
  <Card>
    <CustHolderHeader>
      <CustID>A00002</CustID>
    </CustHolderHeader>
    <CardLine>
      <CardDetail>C000000003</CardDetail>
    </CardLine>
  </Card>
</ReceivableAccounting>

内容的提问来源于stack exchange，提问作者vijay