将动态 XML 文件转换为 CSV 文件 - Python

Question

我想转换这个 XML 文件：

<record id="idOne">
    <ts date="2019-07-03" time="15:28:41.720440">5</ts>
    <ts date="2019-07-03" time="15:28:42.629959">10</ts>
    <ts date="2019-07-03" time="15:28:43.552677">15</ts>
    <ts date="2019-07-03" time="15:28:43.855345">20</ts>
</record>

<record id="idOne">
    <ts date="2019-07-03" time="15:28:45.072922">30</ts>
    <ts date="2019-07-03" time="15:28:45.377087">35</ts>
    <ts date="2019-07-03" time="15:28:46.316321">40</ts>
    <ts date="2019-07-03" time="15:28:47.527960">45</ts>
</record>

到这个 CSV 文件：

ID, date, time, value
idOne, 2019-07-03, 15:28:41.720440, 5
idOne, 2019-07-03, 15:28:42.629959, 10
idOne, 2019-07-03, 15:28:43.552677, 15
idOne, 2019-07-03, 15:28:43.855345, 20
idOne, 2019-07-03, 15:28:45.072922, 30
idOne, 2019-07-03, 15:28:45.377087, 35
idOne, 2019-07-03, 15:28:46.316321, 40
idOne, 2019-07-03, 15:28:47.527960, 45

我可以拥有多个 ID 结构体。

我使用 lxml 库。

我尝试使用 xpath 方法和 for 循环，但我只能获取 ID，而不能获取其余部分。问题是第二个for循环，但是我不知道如何处理“日期”和“时间”的值...

with open(args.input, "r") as f:
    # add root balises to parse the xml file
    records = itertools.chain('<root>', f, '</root>')
    root = etree.fromstringlist(records)

    #root = etree.fromstring(records)
    # count the number of records
    NumberRecords = int(root.xpath('count(//record)'))

    RecordsGrid = [[] for __ in range(NumberRecords)]
    tss = ["id","date", "time", "value"]
    paths = root.xpath('//record')
    #print(paths)
    Counter = 0
    for path in paths:

        for ts in tss[:1]:
            target = f'(./@{ts})'  # using f-strings to populate the full path
            if path.xpath(target):
                # we start populating our current sublist with the relevant info
                RecordsGrid[Counter].append(path.xpath(target)[0])
            else:
                RecordsGrid[Counter].append('NA')

        for ts in tss[1:]:  
            target = f'(./ts[@name="{ts}"]/text())'
            if path.xpath(target):
                RecordsGrid[Counter].append(path.xpath(target)[0])
            else:
                RecordsGrid[Counter].append('NA')
        Counter += 1

    # now that we have our lists, create a df
    df = pd.DataFrame(RecordsGrid, columns=tss)
    df.to_csv(args.output, sep=',', encoding='utf-8', index=False)

结果如下：

id,date,time,value
idOne,NA,NA,NA

感谢您的宝贵时间。

Answer 1

为了解决您的问题，我编写了以下脚本

from bs4 import BeautifulSoup as bs

data = list()

with open("data.xml") as xml:
    data_xml = bs(xml, "html.parser")
    for record in data_xml.find_all("record"):
        for ts in record.find_all("ts"):
            id_, date, time, value = record.get("id"), ts.get("date"), ts.get("time"), ts.text
            data.append(", ".join([id_, date, time, value]) + "\n")

with open("data.csv", "w") as csv:
    csv.write("ID, date, time, value\n")
    csv.writelines(data)

Answer 2

要使用 lxml，您可以简单地将字符串作为 html() 传递。通过使用 xpath //record/ts（以双反斜杠开头），您可以获取所有 ts 结果。可以通过调用 .getparent() 然后调用属性来访问主 id。

要将 xml 转换为 csv，我建议使用 python 包 csv。您可以使用普通的文件编写器。但是 csv write 处理了很多问题，而且更干净。

一般来说，您有一种方法可以处理所有事情。我建议将逻辑拆分为函数。想想Single Responsibility。下面的解决方案我已经将 xml 节点转换为 NamedTupple，然后将 namedTupple 写入 csv。维护/阅读要容易得多。 （即有一处设置标题文本，一处填充数据）。

from lxml import etree
import csv #py -m pip install python-csv
import collections
from collections import namedtuple

Record = namedtuple('Record', ['id', 'date', 'time', 'value']) # Model to store records.

def CreateCsvFile(results):
    with open('results.csv', 'w', newline='') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=list(Record._fields)) # use the namedtuple fields for the headers 
        writer.writeheader()
        writer.writerows([x._asdict() for x in results]) # To use DictWriter, the namedtuple has to be converted to dictionary

def FormatRecord(xmlNode):
    return Record(xmlNode.getparent().attrib['id'], xmlNode.attrib["date"], xmlNode.attrib["time"], xmlNode.text)

def Main(html):
    xmlTree = etree.HTML(html)
    results = [FormatRecord(xmlNode) for xmlNode in xmlTree.xpath('//record/ts')] # the double backslash will retrieve all nodes for record.
    CreateCsvFile(results)

if __name__ == '__main__':
    Main("""<record id="idOne">
            <ts date="2019-07-03" time="15:28:41.720440">5</ts>
            <ts date="2019-07-03" time="15:28:42.629959">10</ts>
            <ts date="2019-07-03" time="15:28:43.552677">15</ts>
            <ts date="2019-07-03" time="15:28:43.855345">20</ts>
        </record>

        <record id="idTwo">
            <ts date="2019-07-03" time="15:28:45.072922">30</ts>
            <ts date="2019-07-03" time="15:28:45.377087">35</ts>
            <ts date="2019-07-03" time="15:28:46.316321">40</ts>
            <ts date="2019-07-03" time="15:28:47.527960">45</ts>
        </record>""")