Das deutsche Python-Forum

Code: Alles auswählen

from xml.sax import make_parser, handler
import sqlite3
import time

class OmdsHeader(handler.ContentHandler):

    def __init__(self) -> None:
        self.header_list = []
        self.vu_list = []    

    def startElement(self, name, attrs):
        if name == 'PAKET':
            self.header_list.append(attrs['MaklerID'])
            self.header_list.append(attrs['PaketZpktErstell'])
            self.header_list.append(attrs['PaketZpktLetztErstell'])
            self.header_list.append(attrs['PaketInhCd'])
            self.header_list.append(attrs['PaketUmfCd'])
            self.header_list.append(attrs['OMDSVersion'])
            self.header_list.append(attrs['VUVersion'])
            self.header_list.append(attrs['DVRNrAbs'])
            self.header_list.append(attrs['PaketKommentar'])

            self.vu_list.append(self.header_list)

    def characters(self, content):
        pass

        
    def endElement(self, name):
        pass

    def getVuNr(self):              
        return self.vu_list
        
parser = make_parser()
b = OmdsHeader()
parser.setContentHandler(b)
parser.parse("muki.xml")
print(b.getVuNr())

Code: Alles auswählen

<?xml version="1.0" encoding="utf-8"?>
<OMDS xmlns="urn:omds20" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="urn:omds20 .\omds211-00.xsd">
  <PAKET VUNr="063" MaklerID="7016281" PaketZpktErstell="2021-08-23T04:56:11.515" PaketZpktLetztErstell="2021-08-23T04:56:11.515" PaketInhCd="VV" PaketUmfCd="G" OMDSVersion="211-00" VUVersion="211-00" DVRNrAbs="2110857" PaketKommentar="muki Bestandsdaten erstellt am 23.08.2021">
</PAKET>
<PAKET VUNr="063" MaklerID="7016282" PaketZpktErstell="2021-08-23T04:56:11.515" PaketZpktLetztErstell="2021-08-23T04:56:11.515" PaketInhCd="VV" PaketUmfCd="G" OMDSVersion="211-00" VUVersion="211-00" DVRNrAbs="2110857" PaketKommentar="muki Bestandsdaten erstellt am 23.08.2021">
  </PAKET>
</OMDS>

Code: Alles auswählen

In [17]: xs = []                                                                

In [18]: ys = []                                                                

In [19]: xs.append(1); xs.append(2)                                             

In [20]: ys.append(xs)                                                          

In [21]: xs                                                                     
Out[21]: [1, 2]

In [22]: ys                                                                     
Out[22]: [[1, 2]]

In [23]: xs.append(4); xs.append(5)                                             

In [24]: xs                                                                     
Out[24]: [1, 2, 4, 5]

In [25]: ys.append(xs)                                                          

In [26]: ys                                                                     
Out[26]: [[1, 2, 4, 5], [1, 2, 4, 5]]

In [27]: xs.append(42)                                                          

In [28]: ys                                                                     
Out[28]: [[1, 2, 4, 5, 42], [1, 2, 4, 5, 42]]

Code: Alles auswählen

#!/usr/bin/env python3
from operator import itemgetter
from pprint import pprint
from xml.sax import make_parser
from xml.sax.handler import ContentHandler

get_paket_values = itemgetter(
    "MaklerID",
    "PaketZpktErstell",
    "PaketZpktLetztErstell",
    "PaketInhCd",
    "PaketUmfCd",
    "OMDSVersion",
    "VUVersion",
    "DVRNrAbs",
    "PaketKommentar",
)


class OmdsHandler(ContentHandler):
    def __init__(self):
        ContentHandler.__init__(self)
        self.pakete = []

    def startElement(self, name, attrs):
        if name == "PAKET":
            self.pakete.append(get_paket_values(attrs))


def main():
    parser = make_parser()
    omds_handler = OmdsHandler()
    parser.setContentHandler(omds_handler)
    parser.parse("muki.xml")
    pprint(omds_handler.pakete)


if __name__ == "__main__":
    main()

Code: Alles auswählen

[('7016281',
  '2021-08-23T04:56:11.515',
  '2021-08-23T04:56:11.515',
  'VV',
  'G',
  '211-00',
  '211-00',
  '2110857',
  'muki Bestandsdaten erstellt am 23.08.2021'),
 ('7016282',
  '2021-08-23T04:56:11.515',
  '2021-08-23T04:56:11.515',
  'VV',
  'G',
  '211-00',
  '211-00',
  '2110857',
  'muki Bestandsdaten erstellt am 23.08.2021')]

Code: Alles auswählen

#!/usr/bin/env python3
from operator import itemgetter
from pprint import pprint
from xml.etree.ElementTree import iterparse

get_paket_values = itemgetter(
    "MaklerID",
    "PaketZpktErstell",
    "PaketZpktLetztErstell",
    "PaketInhCd",
    "PaketUmfCd",
    "OMDSVersion",
    "VUVersion",
    "DVRNrAbs",
    "PaketKommentar",
)


def iter_pakete(xml_source):
    for event_type, element in iterparse(xml_source, events=["start", "end"]):
        if event_type == "start":
            if element.tag == "{urn:omds20}PAKET":
                yield get_paket_values(element.attrib)
        elif event_type == "end":
            element.attrib.clear()
            element.clear()
        else:
            assert False, f"unexpected event type {event_type!r}"


def main():
    pprint(list(iter_pakete("muki.xml")))


if __name__ == "__main__":
    main()