Using xmllib

[Robert Roy]

On Wed, 12 Apr 2000 13:38:41 +0200, Pieter Claerhout
<PClaerhout at CREO.BE> wrote:

>Hello,
>
>does anyone has an example on how to use the xmllib to parse an xmlfile?
>I have an xml-file, which looks a bit like this:
>
><!-- a general comment -->
><COLLECTION VERSION="1">
>    <GENERAL PATH="S:\" />
>    <ITEM NAME="Item1">
>        <DESCRIPTION>Item 1 description.</DESCRIPTION>
>        <DATE>Thu Dec 16 16:35:05 1999</DATE>
>    </ITEM>
>    <ITEM NAME="Item2">
>        <DESCRIPTION>Item 2 description.</DESCRIPTION>
>        <DATE>Wed Mar 15 11:54:27 2000</DATE>
>    </ITEM>
></COLLECTION>
>
>I want to convert it to something like this:
>
>Collection from path s:\
>
>- Item 1 (Thu Dec 16 16:35:05 1999)
>  Item 1 description.
>- Item 2 (Wed Mar 15 11:54:27 2000)
>  Item 2 description.
>
>Anyone an idea on how to do that with XMLlib?
>
>Kind regards,
>
>
>Pieter
>Pieter_Claerhout at creoscitex.com
>

This is a fairly trivial example based on what you posted.

Bob
++++++++++

import xmllib, string

class myparser(xmllib.XMLParser):
    def __init__(self):
        xmllib.XMLParser.__init__(self)
        self.currentdescrip = ''
        self.currentdate = ''
        self.currentitem = ''
        self.currentdata = []
        
    def handle_data(self, data):
        self.currentdata.append(data)

    def start_COLLECTION(self, attrs):
        print "Collection from path",
                
    def end_COLLECTION(self):
        pass

    def start_GENERAL(self, attrs):
        print attrs['PATH']
                
    def end_GENERAL(self):
        pass

    def start_ITEM(self, attrs):
        self.currentitem = attrs['NAME']
                
    def end_ITEM(self):
        print '-%(currentitem)s (%(currentdate)s)\n
%(currentdescrip)s' % self.__dict__

    def start_DESCRIPTION(self, attrs):
        self.currentdata = []
                
    def end_DESCRIPTION(self):
        self.currentdescrip = string.join(self.currentdata,'')
        
    def start_DATE(self, attrs):
        self.currentdata = []
                
    def end_DATE(self):
        self.currentdate = string.join(self.currentdata,'')


### some test code
data= """\
<COLLECTION VERSION="1">
    <GENERAL PATH="S:\\" />
    <ITEM NAME="Item1">
        <DESCRIPTION>Item 1 description.</DESCRIPTION>
        <DATE>Thu Dec 16 16:35:05 1999</DATE>
    </ITEM>
    <ITEM NAME="Item2">
        <DESCRIPTION>Item 2 description.</DESCRIPTION>
        <DATE>Wed Mar 15 11:54:27 2000</DATE>
    </ITEM>
</COLLECTION>

"""

if __name__ == "__main__":
    p=myparser()
    p.feed(data)
    p.close()