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:[code=Python]from xml.dom.minidom import parse

fn = 'sample.xml'

dom1 = parse(fn)
# global variable required by handleData
nameList = ["proc1", "proc2"]

def getText(nodelis t):
rc = ""
for node in nodelist:
if node.nodeType == node.TEXT_NODE:
rc = rc + node.data
return rc

def handleData(node list, *args):
resList = []
for node in nodelist:
if str(node.attrib utes["name"].value) in nameList:
for arg in args:
resList.append( node.getElement sByTagName(arg) )
return [item[0] for item in resList if item]

for item in dom1.getElement sByTagName("cop yfile"):
print getText(item.ch ildNodes)

process_element s = dom1.getElement sByTagName('pro cess')
print process_element s

print handleData(proc ess_elements, "mkdir", "copyfile")

for item in handleData(proc ess_elements, "mkdir", "copyfile") :
print getText(item.ch ildNodes)[/code]Contents of sample.xml:

<xml>
<process name="proc1">
<mkdir>director y</mkdir>
<copyfile>src,d st</copyfile>
</process>

<process name="proc2">
<copyfile>src,d st</copyfile>
</process>
<process name="proc3">
<mkdir>director y</mkdir>
<copyfile>src,d st</copyfile>
</process>
<process name="proc4">
<mkdir>director y</mkdir>
<copyfile>src,d st</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:[code=Python]from xml.dom.minidom import parse

fn = 'sample.xml'

dom1 = parse(fn)
# global variable required by handleData
nameList = ["proc1", "proc2"]

def getText(nodelis t):
rc = ""
for node in nodelist:
if node.nodeType == node.TEXT_NODE:
rc = rc + node.data
return rc

def handleData(node list, *args):
resList = []
for node in nodelist:
if str(node.attrib utes["name"].value) in nameList:
for arg in args:
resList.append( node.getElement sByTagName(arg) )
return [item[0] for item in resList if item]

for item in dom1.getElement sByTagName("cop yfile"):
print getText(item.ch ildNodes)

process_element s = dom1.getElement sByTagName('pro cess')
print process_element s

print handleData(proc ess_elements, "mkdir", "copyfile")

for item in handleData(proc ess_elements, "mkdir", "copyfile") :
print getText(item.ch ildNodes)[/code]Contents of sample.xml:

<xml>
<process name="proc1">
<mkdir>director y</mkdir>
<copyfile>src,d st</copyfile>
</process>

<process name="proc2">
<copyfile>src,d st</copyfile>
</process>
<process name="proc3">
<mkdir>director y</mkdir>
<copyfile>src,d st</copyfile>
</process>
<process name="proc4">
<mkdir>director y</mkdir>
<copyfile>src,d st</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,ds t

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

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,ds t

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

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

Create a function to format the data:[code=Python]from xml.dom.minidom import parse

# global variables required by formatData
nameList = ["proc1", "proc2"]
nodeIDlist = ['name',]

def formatData(node list, *args):
resList = []
for node in nodelist:
for id in nodeIDlist:
try:
s = str(node.attrib utes[id].value)
if s in nameList:
resList.append( '%s name=%s' % (repr(elem.pare ntNode).split(' :')[1].split()[0], s))
for arg in args:
try:
resList.append( ' %s: %s' % (arg, getText(node.ge tElementsByTagN ame(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(resLi st)

dom1 = parse('sample.x ml')[/code][code=Python]>>> process_element s = dom1.getElement sByTagName('pro cess')
>>> process_element s
[<DOM Element: process at 0xf8bb98>, <DOM Element: process at 0xf8b918>, <DOM Element: process at 0xf8b710>, <DOM Element: process at 0xf87490>]
>>> print formatData(proc ess_elements, "mkdir", "copyfile")
process name=proc1
mkdir: directory1
copyfile: src1,dst1
process name=proc2
copyfile: src2,dst2
>>> [/code]The string <download ='ftp' user='username' password='passw ord'> 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:[code=Python]from xml.dom.minidom import parse

# global variables required by formatData
nameList = ["proc1", "proc2"]
nodeIDlist = ['name',]

def formatData(node list, *args):
resList = []
for node in nodelist:
for id in nodeIDlist:
try:
s = str(node.attrib utes[id].value)
if s in nameList:
resList.append( '%s name=%s' % (repr(elem.pare ntNode).split(' :')[1].split()[0], s))
for arg in args:
try:
resList.append( ' %s: %s' % (arg, getText(node.ge tElementsByTagN ame(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(resLi st)

dom1 = parse('sample.x ml')[/code][code=Python]>>> process_element s = dom1.getElement sByTagName('pro cess')
>>> process_element s
[<DOM Element: process at 0xf8bb98>, <DOM Element: process at 0xf8b918>, <DOM Element: process at 0xf8b710>, <DOM Element: process at 0xf87490>]
>>> print formatData(proc ess_elements, "mkdir", "copyfile")
process name=proc1
mkdir: directory1
copyfile: src1,dst1
process name=proc2
copyfile: src2,dst2
>>> [/code]The string <download ='ftp' user='username' password='passw ord'> 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>pa th</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:[code=Python]from xml.dom.minidom import parse

def getText(nodelis t):
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).spli t(':')[1].split()[0]
except: return ''

def getDataList(nod elist, **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.attrib utes[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_NO DE:
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.c hildNodes)))
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\temsy s\sampleXML.txt '

dom1 = parse(fn)

process_element s = dom1.getElement sByTagName('pro cess')
download_elemen ts = dom1.getElement sByTagName('dow nload')

elemDict = {'process': {'name': ["proc1", "proc2"]}, 'download': {'server': ['ftp', ]}}
x = getDataList(pro cess_elements, **elemDict)
y = getDataList(dow nload_elements, **elemDict)

print
print x
print y[/code]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']
>>>