reading xml data

[heiro]

I have an Xml w/c look like this:

<xml>
  <process name="proc1">
       <mkdir>directory</mkdir>
         <copyfile>src,dst</copyfile>
  </process>
 
  <process name="proc2">
       <copyfile>src,dst</copyfile>
  </process>
</xml>

then my problem is how can I get the child nodes of process w/c are "proc1" and "proc2"?
then i also need to get the value of these child nodes(example "src,dst" for <copyfile>)..
im using xml.dom.minidom module

Im hoping for your response guys...

[heiro]

anyone knows???pls help...

[bvdet]

You will need to create a parser, something like this:

from xml.dom.minidom import parse
 
fn = 'sample.xml'
 
dom1 = parse(fn)
# global variable required by handleData
nameList = ["proc1", "proc2"]
 
def getText(nodelist):
    rc = ""
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            rc = rc + node.data
    return rc
 
def handleData(nodelist, *args):
    resList = []
    for node in nodelist:
        if str(node.attributes["name"].value) in nameList:
            for arg in args:
                resList.append(node.getElementsByTagName(arg))
    return [item[0] for item in resList if item]
 
for item in dom1.getElementsByTagName("copyfile"):
    print getText(item.childNodes)
 
process_elements = dom1.getElementsByTagName('process')
print process_elements
 
print handleData(process_elements, "mkdir", "copyfile")
 
for item in handleData(process_elements, "mkdir", "copyfile"):
    print getText(item.childNodes)

Contents of sample.xml:

<xml>
<process name="proc1">
<mkdir>directory</mkdir>
<copyfile>src,dst</copyfile>
</process>

<process name="proc2">
<copyfile>src,dst</copyfile>
</process>
<process name="proc3">
<mkdir>directory</mkdir>
<copyfile>src,dst</copyfile>
</process>
<process name="proc4">
<mkdir>directory</mkdir>
<copyfile>src,dst</copyfile>
</process>
</xml>

Output from above code:

>>> src,dst
src,dst
src,dst
src,dst
[<DOM Element: process at 0xed2670>, <DOM Element: process at 0xed2f58>, <DOM Element: process at 0xedb4b8>, <DOM Element: process at 0xedb788>]
[<DOM Element: mkdir at 0xed2e68>, <DOM Element: copyfile at 0xed2e90>, <DOM Element: copyfile at 0xedb0a8>]
directory
src,dst
src,dst
>>>

[heiro]

You will need to create a parser, something like this:

from xml.dom.minidom import parse
 
fn = 'sample.xml'
 
dom1 = parse(fn)
# global variable required by handleData
nameList = ["proc1", "proc2"]
 
def getText(nodelist):
    rc = ""
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            rc = rc + node.data
    return rc
 
def handleData(nodelist, *args):
    resList = []
    for node in nodelist:
        if str(node.attributes["name"].value) in nameList:
            for arg in args:
                resList.append(node.getElementsByTagName(arg))
    return [item[0] for item in resList if item]
 
for item in dom1.getElementsByTagName("copyfile"):
    print getText(item.childNodes)
 
process_elements = dom1.getElementsByTagName('process')
print process_elements
 
print handleData(process_elements, "mkdir", "copyfile")
 
for item in handleData(process_elements, "mkdir", "copyfile"):
    print getText(item.childNodes)

Contents of sample.xml:

<xml>
<process name="proc1">
<mkdir>directory</mkdir>
<copyfile>src,dst</copyfile>
</process>

<process name="proc2">
<copyfile>src,dst</copyfile>
</process>
<process name="proc3">
<mkdir>directory</mkdir>
<copyfile>src,dst</copyfile>
</process>
<process name="proc4">
<mkdir>directory</mkdir>
<copyfile>src,dst</copyfile>
</process>
</xml>

Output from above code:

>>> src,dst
src,dst
src,dst
src,dst
[<DOM Element: process at 0xed2670>, <DOM Element: process at 0xed2f58>, <DOM Element: process at 0xedb4b8>, <DOM Element: process at 0xedb788>]
[<DOM Element: mkdir at 0xed2e68>, <DOM Element: copyfile at 0xed2e90>, <DOM Element: copyfile at 0xedb0a8>]
directory
src,dst
src,dst
>>>

thanks bvdet....i'll try this one..thanks

[bvdet]

thanks bvdet....i'll try this one..thanks

You are welcome. I am learning about XML and DOM also.

[heiro]

You are welcome. I am learning about XML and DOM also.

I know this is too much :-).
I want to ask another favor..What if i want the output should look like this:

process name="proc1"
mkdir: directory
copyfile: src,dst


process name="proc2"
copyfile: src,dst


process name="proc3"
mkdir: directory
copyfile>src,dst

and how can i parse an xml childnode w/c look like this:
<download ='ftp' user='username' password='password'>

thanks in advance bvdet..Hope you can help me with this in a second time...

[bvdet]

I know this is too much :-).
I want to ask another favor..What if i want the output should look like this:

process name="proc1"
mkdir: directory
copyfile: src,dst


process name="proc2"
copyfile: src,dst


process name="proc3"
mkdir: directory
copyfile>src,dst

and how can i parse an xml childnode w/c look like this:
<download ='ftp' user='username' password='password'>

thanks in advance bvdet..Hope you can help me with this in a second time...

Create a function to format the data:

from xml.dom.minidom import parse
 
# global variables required by formatData
nameList = ["proc1", "proc2"]
nodeIDlist = ['name',]
 
def formatData(nodelist, *args):
    resList = []
    for node in nodelist:
        for id in nodeIDlist:
            try:
                s = str(node.attributes[id].value)
                if s in nameList:
                    resList.append('%s name=%s' % (repr(elem.parentNode).split(':')[1].split()[0], s))
                    for arg in args:
                        try:
                            resList.append('  %s: %s' % (arg, getText(node.getElementsByTagName(arg)[0].childNodes)))
                        except IndexError, e:
                            # print 'Invalid element tag: %s' % arg
                            pass
            except KeyError, e:
                # print 'Invalid node atribute:', e
                pass
    return '\n'.join(resList)
 
dom1 = parse('sample.xml')

>>> process_elements = dom1.getElementsByTagName('process')
>>> process_elements
[<DOM Element: process at 0xf8bb98>, <DOM Element: process at 0xf8b918>, <DOM Element: process at 0xf8b710>, <DOM Element: process at 0xf87490>]
>>> print formatData(process_elements, "mkdir", "copyfile")
process name=proc1
  mkdir: directory1
  copyfile: src1,dst1
process name=proc2
  copyfile: src2,dst2
>>> 

The string <download ='ftp' user='username' password='password'> does not appear to be valid XML. Should not there be an attribute name to the left of the equal sign after 'download'?

[heiro]

Create a function to format the data:

from xml.dom.minidom import parse
 
# global variables required by formatData
nameList = ["proc1", "proc2"]
nodeIDlist = ['name',]
 
def formatData(nodelist, *args):
    resList = []
    for node in nodelist:
        for id in nodeIDlist:
            try:
                s = str(node.attributes[id].value)
                if s in nameList:
                    resList.append('%s name=%s' % (repr(elem.parentNode).split(':')[1].split()[0], s))
                    for arg in args:
                        try:
                            resList.append('  %s: %s' % (arg, getText(node.getElementsByTagName(arg)[0].childNodes)))
                        except IndexError, e:
                            # print 'Invalid element tag: %s' % arg
                            pass
            except KeyError, e:
                # print 'Invalid node atribute:', e
                pass
    return '\n'.join(resList)
 
dom1 = parse('sample.xml')

>>> process_elements = dom1.getElementsByTagName('process')
>>> process_elements
[<DOM Element: process at 0xf8bb98>, <DOM Element: process at 0xf8b918>, <DOM Element: process at 0xf8b710>, <DOM Element: process at 0xf87490>]
>>> print formatData(process_elements, "mkdir", "copyfile")
process name=proc1
  mkdir: directory1
  copyfile: src1,dst1
process name=proc2
  copyfile: src2,dst2
>>> 

The string <download ='ftp' user='username' password='password'> does not appear to be valid XML. Should not there be an attribute name to the left of the equal sign after 'download'?

it actually look like this..

<process name='download'>
<download server='ftp' user='username' password='******'>
<destination>path</destination>
<unzip>*.jpg, *.doc, *.pdf</unzip>
</download>
</process>

Actually I'm making a program right now and its output depends on the xml.
You help a me a lot bvdet..Thanks man

[bvdet]

I have played around with XML parsing, and I made a new function. It is kind of ugly and does not work exactly the way I want, so maybe someone can improve it. Following is the complete code:

from xml.dom.minidom import parse
 
def getText(nodelist):
    rc = []
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            s = node.data.strip()
            if s:
                rc.append(node.data)
    return '\n'.join(rc)
 
def nodeName(node):
    try: return repr(node).split(':')[1].split()[0]
    except: return ''
 
def getDataList(nodelist, **kargs):
    resList = []
    for node in nodelist:
        node_name = nodeName(node)
        if node_name in kargs:
            keys = kargs[node_name].keys()
            for id in keys:
                try:
                    s = str(node.attributes[id].value)
                    v = kargs[node_name][id]
                    if not v or s in kargs[node_name][id]:
                        resList.append('%s %s=%s' % (node_name, id, s))
 
                        if node.nodeType == node.ELEMENT_NODE:
                            nodes = node.childNodes
                            name = node.nodeName
                            print 'DOM element = %s' % name
                            s = []
                            for elem in nodes:
                                nm = nodeName(elem)
                                s.append('  %s%s' % (['', nm+': '][len(nm)>0 or 0],getText(elem.childNodes)))
                            print '\n'.join([i for i in s if i.strip()])
                        elif node.nodeType == node.TEXT_NODE:
                            s = getText(node)
                            print 'Text Node Text = %s' % s
 
                except KeyError, e:
                    print 'Invalid node atribute:', e
                    pass
    return resList
 
fn = r'H:\TEMP\temsys\sampleXML.txt'
 
dom1 = parse(fn)
 
process_elements = dom1.getElementsByTagName('process')
download_elements = dom1.getElementsByTagName('download')
 
elemDict = {'process': {'name': ["proc1", "proc2"]}, 'download': {'server': ['ftp', ]}}
x = getDataList(process_elements, **elemDict)
y = getDataList(download_elements, **elemDict)
 
print
print x
print y

Output:

>>> DOM element = process
mkdir: directory1
mkdir: directory11
mkdir: directory111
copyfile: src1,dst1
DOM element = process
copyfile: src2,dst2
DOM element = download
destination: path
unzip: *.jpg, *.doc, *.pdf

['process name=proc1', 'process name=proc2']
['download server=ftp']
>>>