Das deutsche Python-Forum

Code: Alles auswählen

#!/usr/bin/env python
#-*- coding: iso-8859-1 -*-

import xml.dom.minidom

def getUglyString(fname): 

    fh = file(fname, "r")
    a = fh.readlines()
    fh.close()

    b = ""

    for i in a: 
        i = i.strip()
        b += i

    return b

dom = xml.dom.minidom.parseString(getUglyString("file.xml"))

lines = []

def getLine(merkmalnode):

    line = merkmalnode.attributes["ID"].nodeValue

    for node in merkmalnode.childNodes:

        if node.nodeType == node.ELEMENT_NODE and node.nodeName == "Name":
            for u in node.childNodes:
                if u.nodeType == u.TEXT_NODE:
                    line += ";" + u.nodeValue.strip()

        if node.nodeType == node.ELEMENT_NODE and node.nodeName == "AddData":
            for u in node.childNodes:

                if u.nodeType == node.ELEMENT_NODE and u.nodeName == "Wert" and u.attributes["MerkmalID"].nodeValue == "Kurzbezeichnung":
                    for u2 in u.childNodes:
                        if u2.nodeType == u.TEXT_NODE:
                            line += ";" + u2.nodeValue.strip()

                if u.nodeType == node.ELEMENT_NODE and u.nodeName == "Wert" and u.attributes["MerkmalID"].nodeValue == "Beschreibung":
                    for u2 in u.childNodes:
                        if u2.nodeType == u.TEXT_NODE:
                            line += ";" + u2.nodeValue.strip()
    return line

def walkOver(domina):

    for node in domina.childNodes:

        if node.nodeType == node.ELEMENT_NODE and node.nodeName == "Merkmal" and node.attributes.has_key("ID"):

            lines.append(getLine(node))

        walkOver(node)

walkOver(dom)

for i in lines:
    print i

Code: Alles auswählen

import csv
import sys
from lxml import etree


def parse(filename):
    root = etree.parse(filename)
    xpath_template = 'AddData/Wert[@MerkmalID="%s"]/text()'
    short_description = xpath_template % 'Kurzbezeichnung'
    description = xpath_template % 'Beschreibung'
    for merkmal in root.xpath('//Merkmal'):
        yield [merkmal.attrib['ID'],
               merkmal.find('Name').text,
               merkmal.xpath(short_description)[0],
               merkmal.xpath(description)[0]]


def main():
    writer = csv.writer(sys.stdout, delimiter=';')
    writer.writerows(parse('test.xml'))

Code: Alles auswählen

import csv
from lxml import objectify

def main(xml_file, csv_file):

    tree = objectify.parse(xml_file)

    writer = csv.DictWriter(csv_file, ("ID", "Name", "Kurzbezeichnung", "Beschreibung", "Noch_ein_Wert"))

    for m in tree.xpath("//Merkmal"):
        row = dict()
        row.update({"ID": m.get("ID")})
        row.update({"Name": m.Name})
        for wert in m.AddData.xpath("Wert"):
            row.update({wert.get("MerkmalID") : wert})
        writer.writerow(row)


if __name__ == "__main__":
    
    import StringIO
    
    xml_file = StringIO.StringIO("""
        <root>
            <Merkmal ID="34747"> 
                <Name>Volumen</Name> 
                <AddData> 
                    <Wert MerkmalID="Kurzbezeichnung">Volumen</Wert> 
                    <Wert MerkmalID="Beschreibung">= Inhalt einer Verpackung in Liter</Wert> 
                </AddData> 
            </Merkmal>
            <Merkmal ID="4711"> 
                <Name>Gewicht</Name> 
                <AddData> 
                    <Wert MerkmalID="Kurzbezeichnung">Gewicht</Wert> 
                    <Wert MerkmalID="Beschreibung">= Inhalt einer Verpackung in kg</Wert> 
                    <Wert MerkmalID="Noch_ein_Wert">Hallo, Welt!</Wert> 
                </AddData> 
            </Merkmal>
        </root>""")
    
    csv_file = StringIO.StringIO()
    
    main(xml_file, csv_file)
    
    print csv_file.getvalue()

Code: Alles auswählen

34747,Volumen,Volumen,= Inhalt einer Verpackung in Liter,
4711,Gewicht,Gewicht,= Inhalt einer Verpackung in kg,"Hallo, Welt!"

Code: Alles auswählen

 l = [list(chain(*[
	    (m.get("ID"), m.Name), [wert for wert in m.AddData.xpath("Wert")]
	    	      ])) for m in tree.xpath("//Merkmal")]

Code: Alles auswählen

In [23]: w.writerow("hallo")

In [24]: w.writerow( ("hallo",) )

In [25]: print o.getvalue()
h,a,l,l,o
hallo

Code: Alles auswählen

stringliteral   ::=  [stringprefix](shortstring | longstring)
stringprefix    ::=  "r" | "u" | "ur" | "R" | "U" | "UR" | "Ur" | "uR"
shortstring     ::=  "'" shortstringitem* "'" | '"' shortstringitem* '"'
longstring      ::=  "'''" longstringitem* "'''"
                     | '"""' longstringitem* '"""'
shortstringitem ::=  shortstringchar | escapeseq
longstringitem  ::=  longstringchar | escapeseq
shortstringchar ::=  <any source character except "\" or newline or the quote>
longstringchar  ::=  <any source character except "\">
escapeseq       ::=  "\" <any ASCII character>

Code: Alles auswählen

class DictWriter:
    def __init__(self, f, fieldnames, restval="", extrasaction="raise",
                 dialect="excel", *args, **kwds):
        self.fieldnames = fieldnames    # list of keys for the dict
        self.restval = restval          # for writing short dicts
        if extrasaction.lower() not in ("raise", "ignore"):
            raise ValueError, \
                  ("extrasaction (%s) must be 'raise' or 'ignore'" %
                   extrasaction)
        self.extrasaction = extrasaction
        self.writer = writer(f, dialect, *args, **kwds)
        self.writer.writerow(fieldnames)

    def _dict_to_list(self, rowdict):
        if self.extrasaction == "raise":
            for k in rowdict.keys():
                if k not in self.fieldnames:
                    raise ValueError, "dict contains fields not in fieldnames"
        return [rowdict.get(key, self.restval) for key in self.fieldnames]

    def writerow(self, rowdict):
        return self.writer.writerow(self._dict_to_list(rowdict))

    def writerows(self, rowdicts):
        rows = []
        for rowdict in rowdicts:
            rows.append(self._dict_to_list(rowdict))
        return self.writer.writerows(rows)

Code: Alles auswählen

fieldnames=['A1','A2', 'A3', 'A4', 'A5']
csv.DictWriter((csv_file, 'w'), fieldnames, restval="", extrasaction="raise", dialect="excel", *args, **kwds)