python Python.XML.ElementTree

Posted 2021-05-08

import os
import sys

try:
	import xml.etree.ElementTree as ET
except Exception as e:
	print(str(e))
else:
	print(dir(ET))

file_in = sys.argv[1]

# Parse xml file
tree = ET.parse(file_in)

# Get root element
root = tree.getroot()

# Iterate over all item and print attribute pairs
# Example of how to invoke a name value
print("All item attributes")
for elem in root:
	print("Handling element: ", str(elem))
	for subelem in elem:
		print("Handling subelement: " + str(subelem))
		print("Printing subelement attributes" + str(subelem.attrib))
		print(subelem.attrib['name'])


# Iterate over all item and print values and attribute pairs and text
print("\n\nAll item attributes - Data accessing")
for elem in root:
	print("Handling element: ", str(elem))
	for subelem in elem:
		print("Handling subelement: " + str(subelem))
		print("Printing subelement attributes: " + str(subelem.attrib))
		print("Printing subelement value: " + str(subelem.text))
		
		print(subelem.attrib['name'])
		

# In this module the XML file is represented by a connected graph.
# Here s[x][y] -> x = how many levels below root it is, with 0 it is one level.
#                 y = which item in grouping we want to fish
print(root[0][0].text)
print(root[0][1].text)
print(root[0][2].text)

print(root[0][0].attrib)
print(root[0][1].attrib)
print(root[0][2].attrib)


#############################################
#############################################

import os
import sys


# Insert subelement
from xml.etree import ElementTree
root = ElementTree.parse("sample.xml").getroot()
c = ElementTree.Element("c")
c.text = "3"

root.insert(1, c)
ElementTree.dump(root)


# Remove SubElement
root = ElementTree.parse("sample.xml").getroot()
b = root.getchildren()[1]

root.remove(b)
ElementTree.dump(root)

# Get the text 
from xml.etree import ElementTree
tree = ElementTree.parse("sample.xml")
root = tree.getroot()
print root.find("a").text

# Get the attribute 
from xml.etree import ElementTree
tree = ElementTree.parse("fruits.xml")
item = tree.getroot()[0]

print item.get("color")


# Get the root XML element of an 'ElementTree'
from xml.etree import ElementTree
tree = ElementTree.parse("sample.xml")
print tree.getroot()


# Get all child elements of an XML element 
from xml.etree import ElementTree
tree = ElementTree.parse("sample.xml")
root = tree.getroot()

children = root.getchildren()
for child in children:
    ElementTree.dump(child)
    

# Get the tag name of an XML element 
from xml.etree import ElementTree
element = ElementTree.Element("a")
print element.tag


# Get a descendant of an XML element using indices.
from xml.etree import ElementTree
tree = ElementTree.parse("fruits.xml")
root = tree.getroot()
print root[0][1].text


# Get the key/value pairs of the attrib dictionary (XML)
from xml.etree import ElementTree
tree = ElementTree.parse("fruits.xml")
item = tree.getroot()[0]

print item.keys()
print item.items()

# Retrieve the tag of an XML element with a namespace
from xml.etree import ElementTree
root = ElementTree.parse("namespaces.xml").getroot()

ElementTree.dump(root)
print root.tag

# Add element as last child of another XML element 
from xml.etree import ElementTree
root = ElementTree.parse("sample.xml").getroot()
c = ElementTree.Element("c")
c.text = "3"

root.append(c)
ElementTree.dump(root)


# Load XML from string 
from xml.etree import ElementTree
root = ElementTree.XML("<root><a>1</a></root>")
ElementTree.dump(root)

#Load XML from a string into an ElementTree

from xml.etree import ElementTree
root = ElementTree.fromstring("<root><a>1</a></root>")
ElementTree.dump(root)

# Load XML file into ElementTree 
from xml.etree import ElementTree
tree = ElementTree.parse("sample.xml")
ElementTree.dump(tree)


# Load XML file into an ElementTree more effieciently 
from xml.etree import cElementTree
tree = cElementTree.parse("sample.xml")
cElementTree.dump(tree)

# Clear an XML element 
from xml.etree import ElementTree
root = ElementTree.parse("fruits.xml").getroot()

root.clear()
ElementTree.dump(root
# Find the first subelement of an xml element that matches a condition
rom xml.etree import ElementTree
root = ElementTree.parse("fruits.xml").getroot()

for item in root.findall("item"):
    ElementTree.dump(item)


from xml.etree import ElementTree
root = ElementTree.parse("fruits.xml").getroot()

name = root.find("item/name")
ElementTree.dump(name)    
    
# Find all children of an XML element that match a tag 
from xml.etree import ElementTree
root = ElementTree.parse("fruits.xml").getroot()

for name in root.iter("name"):
    ElementTree.dump(name)

# Find all descendants of an XML element that match a tag
from xml.etree import ElementTree
root = ElementTree.parse("fruits.xml").getroot()

for name in root.iter("name"):
    ElementTree.dump(name)
    
    
# Set attributes of an XML element 
from xml.etree import ElementTree
item = ElementTree.Element("item")

item.set("color", "red")
item.set("flavor", "sweet")
ElementTree.dump(item)


# Check whether an object is an xml element 
from xml.etree import ElementTree
tree = ElementTree.parse("sample.xml")
root = tree.getroot()
a = root[0]

print ElementTree.iselement(root)
print ElementTree.iselement(a)
print ElementTree.iselement(tree)
print ElementTree.iselement(1)

# Generate a string representation of an XML element
from xml.etree import ElementTree
a = ElementTree.Element("a")
a.text = "1"
print ElementTree.tostring(a)


# Efficient ways to construct XML elements
from xml.etree import cElementTree
a = cElementTree.Element("a")
a.text = "1"
cElementTree.dump(a)

import os
import sys

try:
    import xml.etree.ElementTree as ET
except Exception as e:
    print(str(e))
else:
    print(dir(ET))

def pplist(list_in):
    import pprint
    pp = pprint.PrettyPrinter(indent=4)
    pp.pprint(list_in)



def MapXmlLvl2LoL(file_in):
    tree = ET.parse(file_in)
    root = tree.getroot()
    output = []

    for elem in root:
    
        if list(elem) == []:
            output.append(elem)
        else:
            innerlist = []
            for subelem in elem:
                innerlist.append(subelem)
            output.append(innerlist)

    return output



def MapXmlLvl2(file_in):
    tree = ET.parse(file_in)
    root = tree.getroot()
    print("Root element: " + str(root))

    for elem in root:
        print("First Level element: " + str(elem))

        if list(elem) == []:
            next
        else:
            for subelem in elem:
                print("Second Level element: " + str(subelem))



def MapXmlLvl2attrib(file_in):
    tree = ET.parse(file_in)
    root = tree.getroot()
    print("Root element: " + str(root.tag) + " : " + str(root.attrib))

    for elem in root:
        print("First Level element: " + str(elem.tag) + " : " + str(elem.attrib))

        if list(elem) == []:
            next
        else:
            for subelem in elem:
                print("Second Level element: " + str(subelem.tag) + " : " + str(subelem.attrib))



def MapXmlLvl2tag(file_in):
    tree = ET.parse(file_in)
    root = tree.getroot()
    print("Root element: " + str(root.tag))

    for elem in root:
        print("First Level element: " + str(elem.tag))

        if list(elem) == []:
            next
        else:
            for subelem in elem:
                print("Second Level element: " + str(subelem.tag))


def MapXmlLvl2full(file_in):
    tree = ET.parse(file_in)
    root = tree.getroot()
    print("Root element: " + str(root.tag) + " : " + str(root.attrib) + " : " + str(root.text))

    for elem in root:
        print("\tFirst Level element: " + str(elem.tag) + " : " + str(elem.attrib) + " : " + str(elem.text))

        if list(elem) == []:
            next
        else:
            for subelem in elem:
                print("\t\tSecond Level element: " + str(subelem.tag) + " : " + str(subelem.attrib) + " : " + str(subelem.text))
            print("\n")



def ExtractData2LevelIn(file_in, position):
    # These will work for xml with double nesting
    # ie <parent>
    #      <child>
    #        <subchild>
    # Note: For more nesting, add a 3/4/5 dimension to root. 
    # ie for triple nesting root would be [0][1][2]
    tree = ET.parse(file_in)
    root = tree.getroot()
    elements = len(root)
    for i in range(int(elements)):
        print("i is: " + str(i))
        print(root[i][position].text)
   

def ExtractDataSpecRecText(file_in, record_number):
    tree = ET.parse(file_in)
    root = tree.getroot()
    elements = len(root[int(record_number)])
    
    for i in range(int(elements)):
        print(root[record_number][i].text)
        

def ExtractDataSpecRecAttr(file_in, record_number):
    tree = ET.parse(file_in)
    root = tree.getroot()
    elements = len(root[int(record_number)])
    
    for i in range(int(elements)):
        print(root[record_number][i].attrib)



def ExtractDataSpecRecNode(file_in, record_number):
    tree = ET.parse(file_in)
    root = tree.getroot()
    elements = len(root[int(record_number)])
    
    for i in range(int(elements)):
        print(root[record_number][i])


file_in = sys.argv[1]

# Parse xml file
tree = ET.parse(file_in)

# Get root element
root = tree.getroot()

# Iterate over all item and print attribute pairs
# Example of how to invoke a name value

MapXmlLvl2(file_in)
MapXmlLvl2attrib(file_in)
MapXmlLvl2tag(file_in)
pplist(MapXmlLvl2LoL(file_in))
MapXmlLvl2full(file_in)

# element.attrib will place all attribute/value pairs in a dict.

print("All item attributes")
for elem in root:
    print("Handling element: ", str(elem))
    print("Handling element attribute: ", str(elem.attrib))
    for subelem in elem:
        print("Handling subelement: " + str(subelem))
        print("Printing subelement attributes" + str(subelem.attrib))
        
        # This will work only if the attrib 'name' is present in the attrib dict
        # of each node.
        #print(subelem.attrib['name'])


# Iterate over all item and print values and attribute pairs and text
print("\n\nAll item attributes - Data accessing")
for elem in root:
    print("Handling element: ", str(elem))
    for subelem in elem:
        print("Handling subelement: " + str(subelem))
        print("Printing subelement attributes: " + str(subelem.attrib))
        print("Printing subelement value: " + str(subelem.text))
        
        #print(subelem.attrib['name'])
        

# In this module the XML file is represented by a connected graph.
# Here s[x][y] -> x = how many levels below root it is, with 0 it is one level.
#                 y = which item in grouping we want to fish
print(root[0][0])
print(root[0][1])
print(root[0][2])


print(root[0][0].text)
print(root[0][1].text)
print(root[0][2].text)

print(root[0][0].attrib)
print(root[0][1].attrib)
print(root[0][2].attrib)

print(root[1][0].text)
print(root[2][0].text)


# for j in root[1][1]:
    # print(j.text)


ExtractData2LevelIn(file_in, 0)
ExtractData2LevelIn(file_in, 4)



ExtractDataSpecRecText(file_in, 1)
ExtractDataSpecRecAttr(file_in, 2)
ExtractDataSpecRecNode(file_in, 3)    

import os
import sys


import xml.etree.ElementTree as ET


def countxmlETsim(file_in):

    '''
    Name: countxmlETsim
    Description: Counts tags under the root tag. 
                 Counts xml "records" 
    Function: countxmlETsim(file_in)
    Input: <file_in>
    Output: <integer>
    Usage:
    Notes:
    
    
    '''


    import xml.etree.ElementTree as ET
    tree = ET.parse(file_in)
    
    try:
        root = tree.getroot()
    except Exception as e:
        return False
    else:
        return len(root)




file_in = sys.argv[1]
tree = ET.parse(file_in)
root = tree.getroot()




# total amount of items
print(len(root))
print(countxmlETsim(file_in))

# #########################################################
# This is an example of how to create an xml file by 
# declaring all elements one by one.
#
# Specific attributes are declared independently.

import os
import sys
import xml.etree.ElementTree as ET

file_in = sys.argv[1]

# create the file structure
data = ET.Element('data')
items = ET.SubElement(data, 'items')
item1 = ET.SubElement(items, 'item')
item2 = ET.SubElement(items, 'item')
#i_item1 = ET.SubElement(item1, 'gear')

# assign labels
item1.set('name', 'item1')
item2.set('name', 'item2')
#i_item1.set('name', 'gear1')

# assign values to the label tags
item1.text = 'item1abc'
item2.text = 'item2abc'
#i_item1.text = 'wheel'

# create the file with the results
mydata = ET.tostring(data)
myfile = open(file_in, 'w')
myfile.write(mydata.decode('utf8'))

import os
import sys

file_in = sys.argv[1]

try:
	import xml.etree.ElementTree as ET
except Exception as e:
	print(str(e))

tree = ET.parse(file_in)
root = tree.getroot()

# find the first root object
# find(match, namespaces=None)
for elem in root:
	print(elem.find('item').get('name'))

# find all item objects and iterate to print
# findall(match, namespaces=None)
for elem in root:
	for subelem in elem.findall('item'):

		# if we dont know the name of the attribute - get the dict
		print(subelem.attrib)

		# if we know the name of the attribute, access it directly
		print(subelem.get('name'))
		# Similarly we access the value of the attribute
		print(subelem.text)

import os
import sys

file_in = sys.argv[1]

from xml.dom import minidom

def prettify(elem):
    """Return a pretty-printed XML string for the Element.
    """
    from xml.dom import minidom
    import xml.etree.ElementTree as ET
    rough_string = ET.tostring(elem, 'utf-8')
    reparsed = minidom.parseString(rough_string)
    return reparsed.toprettyxml(indent="  ")

def indent(elem, level=0):
    i = os.linesep + level*"  "
    #i = "\n" + level*"  "
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + "  "
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for elem in elem:
            indent(elem, level+1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i

try:
	import xml.etree.ElementTree as ET
except Exception as e:
	print(str(e))
    
    
tree = ET.parse(file_in)
root = tree.getroot()

# changing a field text
for elem in root.iter('item'):
        elem.text = 'new text'
    
# changing an attribute
for elem in root.iter('item'):
    elem.set('name', 'newitem')
    
# adding an extra attribute 
for elem in root.iter('item'):
    elem.set('name2', 'newitem2')
    
    
# Conditionally changing a field text
for elem in root.iter('item'):
    #print(elem.attrib, elem.text)
    if elem.attrib['name']=='item2':
        elem.text = 'new text'   

# Conditionally Remove an attribute 
for elem in root.iter('item'):
    if elem.text == 'new text':
        elem.attrib = {}
        # or we could set the new mapping.
    
# Using tree.write to write xml adds extra formatting and indentation    
tree.write('newitems3.xml')


# Creating XML Sub-Elements 
# makeelement()
# SubElement()

# To add element to ROOT NODE we need to do:

# 1. declare the attrib dictionary
attrib = {}
# 2. Construct the element 
element = root.makeelement('seconditems', attrib)
# 3. Append to root 
root.append(element)


# To add element to the second subnode of root 
attrib = {'name2': 'secondname2'}
subelement = root[0][1].makeelement('seconditem', attrib)
ET.SubElement(root[1], 'seconditem', attrib)
root[1][0].text = 'seconditemabc'

indent(root)

# create a new xml file with the new element 
tree.write('newitems_v1.xml')



# how to prettify xml 
# check func as well 
print(prettify(root))

print (minidom.parseString(
            ET.tostring(
              tree.getroot(),
              'utf-8')).toprettyxml(indent=" "))




# Deleting XML Elements 
# Deleting an attrib
# Deleting text
# Deleting one sub element 
# Deleting all subelements

tree = ET.parse(file_in)
root = tree.getroot()
# removing the name attribute from the first node of root. [0][0]
root[0][0].attrib.pop('name', None)
tree.write('newitems_v2_del.xml')

tree = ET.parse(file_in)
root = tree.getroot()
root[0].remove(root[0][0])
tree.write('newitems_v2_sub.xml')
# write with declaration
tree.write("newitems_v2_sub2.xml", encoding="utf-8", xml_declaration=True)


tree = ET.parse(file_in)
root = tree.getroot()
root[0].clear()
tree.write('newitems_v2_clr.xml')

import os
import sys

file_in = sys.argv[1]

from xml.dom import minidom

def prettify(elem):
    """Return a pretty-printed XML string for the Element.
    """
    from xml.dom import minidom
    import xml.etree.ElementTree as ET
    rough_string = ET.tostring(elem, 'utf-8')
    reparsed = minidom.parseString(rough_string)
    return reparsed.toprettyxml(indent="  ")

def indent(elem, level=0):
    i = os.linesep + level*"  "
    #i = "\n" + level*"  "
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + "  "
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for elem in elem:
            indent(elem, level+1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i

try:
	import xml.etree.ElementTree as ET
except Exception as e:
	print(str(e))
    
    
tree = ET.parse(file_in)
root = tree.getroot()

# changing a field text
for elem in root.iter('item'):
        elem.text = 'new text'
    
# changing an attribute
for elem in root.iter('item'):
    elem.set('name', 'newitem')
    
# adding an extra attribute 
for elem in root.iter('item'):
    elem.set('name2', 'newitem2')
    
    
# Conditionally changing a field text
for elem in root.iter('item'):
    #print(elem.attrib, elem.text)
    if elem.attrib['name']=='item2':
        elem.text = 'new text'   

# Conditionally Remove an attribute 
for elem in root.iter('item'):
    if elem.text == 'new text':
        elem.attrib = {}
        # or we could set the new mapping.
    
# Using tree.write to write xml adds extra formatting and indentation    
tree.write('newitems3.xml')


# Creating XML Sub-Elements 
# makeelement()
# SubElement()

# To add element to ROOT NODE we need to do:

# 1. declare the attrib dictionary
attrib = {}
# 2. Construct the element 
element = root.makeelement('seconditems', attrib)
# 3. Append to root 
root.append(element)


# To add element to the second subnode of root 
attrib = {'name2': 'secondname2'}
subelement = root[0][1].makeelement('seconditem', attrib)
ET.SubElement(root[1], 'seconditem', attrib)
root[1][0].text = 'seconditemabc'

indent(root)

# create a new xml file with the new element 
tree.write('newitems_v1.xml')



# how to prettify xml 
# check func as well 
print(prettify(root))

print (minidom.parseString(
            ET.tostring(
              tree.getroot(),
              'utf-8')).toprettyxml(indent=" "))




# Deleting XML Elements 
# Deleting an attrib
# Deleting text
# Deleting one sub element 
# Deleting all subelements

tree = ET.parse(file_in)
root = tree.getroot()
# removing the name attribute from the first node of root. [0][0]
root[0][0].attrib.pop('name', None)
tree.write('newitems_v2_del.xml')

tree = ET.parse(file_in)
root = tree.getroot()
root[0].remove(root[0][0])
tree.write('newitems_v2_sub.xml')
# write with declaration
tree.write("newitems_v2_sub2.xml", encoding="utf-8", xml_declaration=True)


tree = ET.parse(file_in)
root = tree.getroot()
root[0].clear()
tree.write('newitems_v2_clr.xml')

import os
import sys

try:
	import xml.etree.ElementTree as ET
except Exception as e:
	print(str(e))
else:
	pass


file_in = sys.argv[1]


def pplist(list_in):
	import pprint
	pp = pprint.PrettyPrinter(indent=4)
	pp.pprint(list_in)


def MapXmlLvl3(file_in):
	tree = ET.parse(file_in)
	root = tree.getroot()
	print("Root element: " + str(root))

	for elem in root:
		print("First Level element: " + str(elem))

		if list(elem) == []:
			next
		else:
			for subelem in elem:
				print("Second Level element: " + str(subelem))
				if list(subelem) == []:
					next
				else:
					for thirdlevel in subelem:
						print("Third level element: " + str(thirdlevel))


def MapXmlLvl3attrib(file_in):
	tree = ET.parse(file_in)
	root = tree.getroot()
	print("Root element: " + str(root) + " : " + str(root.attrib))

	for elem in root:
		print("First Level element: " + str(elem) + " : " + str(elem.attrib))

		if list(elem) == []:
			next
		else:
			for subelem in elem:
				print("Second Level element: " + str(subelem) + " : " + str(subelem.attrib))
				if list(subelem) == []:
					next
				else:
					for thirdlevel in subelem:
						print("Third level element: " + str(thirdlevel) + " : " + str(thirdlevel.attrib))

MapXmlLvl3(file_in)
MapXmlLvl3attrib(file_in)

def indent(elem, level=0):
    i = os.linesep + level*"  "
    #i = "\n" + level*"  "
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + "  "
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for elem in elem:
            indent(elem, level+1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i

try:
	import xml.etree.ElementTree as ET
except Exception as e:
	print(str(e))

import os
import sys

from xml.etree import ElementTree

with open('podcasts.opml', 'rt') as f:
    tree = ElementTree.parse(f)


# Printing the Tree will return an ElementTreeObject
print (tree)

# Iterate over all notes with .iter()
for node in tree.iter():
    print(node.tag, node.attrib)
    
# Iteraver over all .outline nodes (specific)
# Limits iter to only nodes with the given tag.
for node in tree.iter('outline'):
    name = node.attrib.get('text')
    url = node.attrib.get('xmlUrl')
    if name and url:
        print(" %s :: %s " % (name, url))
    else:
        print(name)
        
# Use findall to look for nodes with more descriptive search
# characteristics.        
for node in tree.findall('.//outline'):
    url = node.attrib.get('xmlUrl')
    if url:
        print(url)
        
# We could limit it even further, by having it iterate over 
# all the inner outline nodes only.
for node in tree.findall('.//outline/outline'):
    url = node.attrib.get('xmlUrl')
    print(url)
    


# Parsing specific node attributes 

with open('data.xml', 'rt') as f:
    tree = ElementTree.parse(f)

# Set a specific node into a variable    
node = tree.find('/with_attributes')
print (node.tag)

# Parsing attrivute key/value pairs
for name, value in sorted(node.attrib.items()):
    print(' %-4s = "%s"' % (name, value))

# Parsing text and tail text   
for path in [ './child', './child_with_tail' ]:
    node = tree.find(path)
    print(node.tag)
    print('Child node text: ', node.text)
    print('and tail text  : ', node.tail)
    
# If we are dealing with XML entity references embedded
# in an xml document those are converted to chars before
# values are returned. 

node = tree.find('entity_expansion')
print(node.tag)
print(' in attribute:', node.attrib['attribute'])
print(' in text     :', node.text)

import os
import sys

# A different way of parsing XML is by using "events"
# The parser generates "start" events for opening tags and "end"
# events for closing tags. 

# Data can be extracted from the document during the parsing phase
# by iterating over the event stream, that way the document does not
# need to be maintained in memory.

# iterparse() returns an iterable that produces tuples
# containing the name of the event and the node triggering the event. 
# Events can be:
#   "start"   : new tag has been encountered. 
#   "end"     : Closing angle tag has been processed. All of the children were already processed.
#   "start-ns": Start a namespace declaration
#   "end-ns   : End a namespace declaration


from xml.etree.ElementTree import iterparse

depth = 0
prefix_width = 8
prefix_dots = '.' * prefix_width
line_template = '{prefix:<0.{prefix_len}}{event:<8}{suffix:<{suffix_len}} {node.tag:<12} {node_id}'

for (event, node) in iterparse('podcasts.opml', ['start', 'end', 'start-ns', 'end-ns']):
    if event == 'end':
        depth -= 1

    prefix_len = depth * 2
    
    print (line_template.format(prefix=prefix_dots,
                               prefix_len=prefix_len,
                               suffix='',
                               suffix_len=(prefix_width - prefix_len),
                               node=node,
                               node_id=id(node),
                               event=event,
                               ))
    
    if event == 'start':
        depth += 1
        
        
# This can be used in a "line by line" fashion ie 
# when converting XML input to some other format. 
# ie XML TO CSV

import csv
from xml.etree.ElementTree import iterparse
import sys

writer = csv.writer(sys.stdout, quoting=csv.QUOTE_NONNUMERIC)

group_name = ''


# This is how we can convert XML to csv
for (event, node) in iterparse('podcasts.opml', events=['start']):
    if node.tag != 'outline':
        # Ignore anything not part of the outline
        continue
    if not node.attrib.get('xmlUrl'):
        # Remember the current group
        group_name = node.attrib['text']
    else:
        # Output a podcast entry
        writer.writerow( (group_name, node.attrib['text'],
                          node.attrib['xmlUrl'],
                          node.attrib.get('htmlUrl', ''),
                          )
                         )