def has_children(e):
''' Check if element, e, has children'''
return(len(list(e)) > 0)
def has_attrib(e):
''' Check if element, e, has attributes'''
return(len(e.attrib)>0)
def get_uniqe_key(mydict, key):
''' Generate unique key if already exists in mydict'''
if key in mydict:
while key in mydict:
key = key + '*'
return(key)
tree = ET.parse('input2.xml')
root = tree.getroot()
# Get first level:
lvl_one = list(root)
myList = [];
for e in lvl_one:
mydict = {}
# Iterate over each node in level one element
for node in e.iter():
if (not has_children(node)) & (node.text != None):
uniqe_key = get_uniqe_key(mydict, node.tag)
mydict[uniqe_key] = node.text
if has_attrib(node):
for key in node.attrib:
uniqe_key = get_uniqe_key(mydict, key)
mydict[uniqe_key] = node.attrib[key]
myList.append(mydict)
print(pd.DataFrame(myList))
def has_children(e):
''' Check if element, e, has children'''
return(len(list(e)) > 0)
def has_attrib(e):
''' Check if element, e, has attributes'''
return(len(e.attrib)>0)
def get_uniqe_key(mydict, key):
''' Generate unique key if already exists in mydict'''
if key in mydict:
while key in mydict:
key = key + '*'
return(key)
tree = ET.parse('input2.xml')
root = tree.getroot()
# Get first level:
lvl_one = list(root)
myList = [];
for e in lvl_one:
mydict = {}
# Iterate over each node in level one element
for node in e.iter():
if (not has_children(node)) & (node.text != None):
uniqe_key = get_uniqe_key(mydict, node.tag)
mydict[uniqe_key] = node.text
if has_attrib(node):
for key in node.attrib:
uniqe_key = get_uniqe_key(mydict, key)
mydict[uniqe_key] = node.attrib[key]
myList.append(mydict)
print(pd.DataFrame(myList))