python - 使用 Python 优化 XML 解析为 CSV

Question

我有大约 10,000 个具有类似结构的 XML 文件，我希望将它们转换为单个 CSV 文件。每个 XML 文件如下所示:

<?xml version='1.0' encoding='UTF-8'?>
<S:Envelope xmlns:S="http://schemas.xmlsoap.org/soap/envelope/">
    <S:Body>
        <ns7:GetStopMonitoringServiceResponse xmlns:ns3="http://www.siri.org.uk/siri" xmlns:ns4="http://www.ifopt.org.uk/acsb" xmlns:ns5="http://www.ifopt.org.uk/ifopt" xmlns:ns6="http://datex2.eu/schema/1_0/1_0" xmlns:ns7="http://new.webservice.namespace">
            <Answer>
                <ns3:ResponseTimestamp>2019-03-31T09:00:52.912+03:00</ns3:ResponseTimestamp>
                <ns3:ProducerRef>ISR Siri Server (141.10)</ns3:ProducerRef>
                <ns3:ResponseMessageIdentifier>276480603</ns3:ResponseMessageIdentifier>
                <ns3:RequestMessageRef>0100700:1351669188:4684</ns3:RequestMessageRef>
                <ns3:Status>true</ns3:Status>
                <ns3:StopMonitoringDelivery version="IL2.71">
                    <ns3:ResponseTimestamp>2019-03-31T09:00:52.912+03:00</ns3:ResponseTimestamp>
                    <ns3:Status>true</ns3:Status>
                    <ns3:MonitoredStopVisit>
                        <ns3:RecordedAtTime>2019-03-31T09:00:52.000+03:00</ns3:RecordedAtTime>
                        <ns3:ItemIdentifier>-881202701</ns3:ItemIdentifier>
                        <ns3:MonitoringRef>20902</ns3:MonitoringRef>
                        <ns3:MonitoredVehicleJourney>
                            <ns3:LineRef>23925</ns3:LineRef>
                            <ns3:DirectionRef>2</ns3:DirectionRef>
                            <ns3:FramedVehicleJourneyRef>
                                <ns3:DataFrameRef>2019-03-31</ns3:DataFrameRef>
                                <ns3:DatedVehicleJourneyRef>36962685</ns3:DatedVehicleJourneyRef>
                            </ns3:FramedVehicleJourneyRef>
                            <ns3:PublishedLineName>15</ns3:PublishedLineName>
                            <ns3:OperatorRef>15</ns3:OperatorRef>
                            <ns3:DestinationRef>26020</ns3:DestinationRef>
                            <ns3:OriginAimedDepartureTime>2019-03-31T08:35:00.000+03:00</ns3:OriginAimedDepartureTime>
                            <ns3:VehicleLocation>
                                <ns3:Longitude>34.78000259399414</ns3:Longitude>
                                <ns3:Latitude>32.042293548583984</ns3:Latitude>
                            </ns3:VehicleLocation>
                            <ns3:VehicleRef>37629301</ns3:VehicleRef>
                            <ns3:MonitoredCall>
                                <ns3:StopPointRef>20902</ns3:StopPointRef>
                                <ns3:ExpectedArrivalTime>2019-03-31T09:03:00.000+03:00</ns3:ExpectedArrivalTime>
                            </ns3:MonitoredCall>
                        </ns3:MonitoredVehicleJourney>
                    </ns3:MonitoredStopVisit>
                </ns3:StopMonitoringDelivery>
            </Answer>
        </ns7:GetStopMonitoringServiceResponse>
    </S:Body>
</S:Envelope>

上面的示例显示了一个 MonitoredStopVisit 嵌套标记，但每个 XML 大约有 4,000 个。完整的 XML 作为示例可以找到 here .

我想将所有 10K 文件转换为一个 CSV，其中每条记录对应一个 MonitoredStopVisit 标记，因此 CSV 应如下所示:

目前这是我的架构:

• 将 10K 文件分成 8 个 block (根据我的 PC 内核)。
• 每个子流程都会迭代其 xml 文件并对象化 xml。
• 然后迭代该对象，并针对每个元素使用数组的条件来排除/包含数据。
• 当标记为/ns3:MonitoredStopVisit 时，该数组将作为一个序列附加到 pandas 数据帧。
• 完成所有子流程后，数据帧将合并并保存为 CSV。

这是 xml 到 df 的代码:

def xml_to_df(xml_file):
    from lxml import objectify
    xml_content = xml_file.read()
    obj = objectify.fromstring(xml_content)
    df_cols=[
        'RecordedAtTime',
        'MonitoringRef',
        'LineRef',
        'DirectionRef',
        'PublishedLineName',
        'OperatorRef',
        'DestinationRef',
        'OriginAimedDepartureTime',
        'Longitude',
        'Latitude',
        'VehicleRef',
        'StopPointRef',
        'ExpectedArrivalTime',
        'AimedArrivalTime'
        ]
    tempdf = pd.DataFrame(columns=df_cols)
    arr_of_vals = [""] * 14

    for i in obj.getiterator():
        if "MonitoredStopVisit" in i.tag or "Status" in i.tag and "false" in str(i):
            if arr_of_vals[0] != "" and (arr_of_vals[8] and arr_of_vals[9]):
                s = pd.Series(arr_of_vals, index=df_cols)
                if tempdf[(tempdf==s).all(axis=1)].empty:
                    tempdf = tempdf.append(s, ignore_index=True)
                    arr_of_vals =  [""] * 14
        elif "RecordedAtTime" in i.tag:
            arr_of_vals[0] = str(i)
        elif "MonitoringRef" in i.tag:
            arr_of_vals[1] = str(i)
        elif "LineRef" in i.tag:
            arr_of_vals[2] = str(i)
        elif "DestinationRef" in i.tag:
            arr_of_vals[6] = str(i)
        elif "OriginAimedDepartureTime" in i.tag:
            arr_of_vals[7] = str(i)
        elif "Longitude" in i.tag:
            if str(i) == "345353":
                print("Lon: " + str(i))
            arr_of_vals[8] = str(i)
        elif "Latitude" in i.tag:
            arr_of_vals[9] = str(i)
        elif "VehicleRef" in i.tag:
            arr_of_vals[10] = str(i)
        elif "ExpectedArrivalTime" in i.tag:
            arr_of_vals[12] = str(i)

    if arr_of_vals[0] != "" and (arr_of_vals[8] and arr_of_vals[9]):  
        s = pd.Series(arr_of_vals, index=df_cols)
        if tempdf[(tempdf == s).all(axis=1)].empty:
            tempdf = tempdf.append(s, ignore_index=True)
    return tempdf

问题是，对于 10K 文件，使用 8 个子处理器大约需要 10 个小时。在检查 CPU/Mem 使用情况时，我可以看到没有充分利用。

知道如何改进吗？我的下一步是线程化，但也许还有其他适用的方法。请注意，记录的顺序并不重要 - 我可以稍后对其进行排序。

Answer 1

这是我使用 pandas 的解决方案:

每个5Mb文件的计算时间约为0.4s

import xml.etree.ElementTree as ET
import re
import pandas as pd
import os



def collect_data(xml_file):
    # create xml object
    root = ET.parse(xml_file).getroot()

    # collect raw data
    out_data = []
    for element in root.iter():
        # get tag name
        tag = re.sub('{.*?}', '', element.tag)
        # add break segment element
        if tag == 'RecordedAtTime':
            out_data.append('break')

        if tag in tag_list:
            out_data.append((tag, element.text))

    # get break indexes
    break_index = [i for i, x in enumerate(out_data) if x == 'break']

    # break list into parts
    list_data = []
    for i in range(len(break_index) - 1):
        list_data.append(out_data[break_index[i]:break_index[i + 1]])

    # check for each value in data
    final_data = []
    for item in list_data:
        # delete bleak element ad convert list into dictionary
        del item[item.index('break')]
        data_dictionary = dict(item)

        if 'RecordedAtTime' in data_dictionary.keys():
            recorded_at_time = data_dictionary.get('RecordedAtTime')
        else:
            recorded_at_time = ''

        if 'MonitoringRef' in data_dictionary.keys():
            monitoring_ref = data_dictionary.get('MonitoringRef')
        else:
            monitoring_ref = ''

        if 'LineRef' in data_dictionary.keys():
            line_ref = data_dictionary.get('LineRef')
        else:
            line_ref = ''

        if 'DirectionRef' in data_dictionary.keys():
            direction_ref = data_dictionary.get('DirectionReff')
        else:
            direction_ref = ''

        if 'PublishedLineName' in data_dictionary.keys():
            published_line_name = data_dictionary.get('PublishedLineName')
        else:
            published_line_name = ''

        if 'OperatorRef' in data_dictionary.keys():
            operator_ref = data_dictionary.get('OperatorRef')
        else:
            operator_ref = ''

        if 'DestinationRef' in data_dictionary.keys():
            destination_ref = data_dictionary.get('DestinationRef')
        else:
            destination_ref = ''

        if 'OriginAimedDepartureTime' in data_dictionary.keys():
            origin_aimed_departure_time = data_dictionary.get('OriginAimedDepartureTime')
        else:
            origin_aimed_departure_time = ''

        if 'Longitude' in data_dictionary.keys():
            longitude = data_dictionary.get('Longitude')
        else:
            longitude = ''

        if 'Latitude' in data_dictionary.keys():
            latitude = data_dictionary.get('Latitude')
        else:
            latitude = ''

        if 'VehicleRef' in data_dictionary.keys():
            vehicle_ref = data_dictionary.get('VehicleRef')
        else:
            vehicle_ref = ''

        if 'StopPointRef' in data_dictionary.keys():
            stop_point_ref = data_dictionary.get('StopPointRef')
        else:
            stop_point_ref = ''

        if 'ExpectedArrivalTime' in data_dictionary.keys():
            expected_arrival_time = data_dictionary.get('ExpectedArrivalTime')
        else:
            expected_arrival_time = ''

        if 'AimedArrivalTime' in data_dictionary.keys():
            aimed_arrival_time = data_dictionary.get('AimedArrivalTime')
        else:
            aimed_arrival_time = ''

        final_data.append((recorded_at_time, monitoring_ref, line_ref, direction_ref, published_line_name, operator_ref,
                       destination_ref, origin_aimed_departure_time, longitude, latitude, vehicle_ref,
                       stop_point_ref,
                       expected_arrival_time, aimed_arrival_time))

     return final_data


# setup tags list for checking
tag_list = ['RecordedAtTime', 'MonitoringRef', 'LineRef', 'DirectionRef', 'PublishedLineName', 'OperatorRef',
            'DestinationRef', 'OriginAimedDepartureTime', 'Longitude', 'Latitude', 'VehicleRef', 'StopPointRef',
            'ExpectedArrivalTime', 'AimedArrivalTime']

# collect data from each file
save_data = []
for file_name in os.listdir(os.getcwd()):
    if file_name.endswith('.xml'):
        save_data.append(collect_data(file_name))
    else:
        pass

# merge list of lists
flat_list = []
for sublist in save_data:
    for item in sublist:
        flat_list.append(item)

# load data into data frame
data = pd.DataFrame(flat_list, columns=tag_list)

# save data to file
data.to_csv('data.csv', index=False)