python Python.XML.Minidom

Posted 2021-05-08

import os
import sys

# using minidom
try:
	from xml.dom import minidom
except Exception as e:
	print(str(e))
else:
	print("Xml dom loaded")


file_in = sys.argv[1]

# parse xml file by name
try:
	mydoc = minidom.parse(file_in)
except Exception as e:
	print(str(e))
else:
	print("Xml file parsed")
finally:
	print(str(mydoc))




# Get all elements by specific tag into a list
try:
	items = mydoc.getElementsByTagName('item')
except Exception as e:
	print(str(e))
else:
	print("Parsed specific tag name")
finally:
	print(str(items))
	#print(dir(items.attributes))


# Access values of the elements in the previous list
try:
	print(items[0].attributes['name'].value)
	print(items[1].attributes['name'].value)
	print(items[2].attributes['name'].value)
except Exception as e:
	print(str(e))


# Alternatively, iterate to print all values
try:
	for item in items:
		print(item.attributes['name'].value)
except Exception as e:
	print(str(e))


# Access data of child elements from parent element
try:
	print(items[0].firstChild.data)
	print(items[0].childNodes[0].data)
	print(items[1].firstChild.data)
	print(items[1].childNodes[0].data)
	print(items[2].firstChild.data)
	print(items[2].childNodes[0].data)
except Exception as e:
	print(str(e))


# Various ways of accessing data using minidom interface
try:
	print(items[0])
	print(items[0].firstChild)
	print(items[0].firstChild.data)
	print(items[0].childNodes)
	print(items[0].childNodes[0])
	print(items[0].childNodes[0].data)	
except Exception as e:
	print(str(e))

# Using firstchild and iteration to print all children data.
try:
	for elem in items:
		print(elem.firstChild.data)
except Exception as e:
	print(str(e))

try:
	for elem in items:
		print(elem.firstChild)
except Exception as e:
	print(str(e))


# different way to open the file
try:
	datasource = open(file_in)
	mydoc2 = minidom.parse(datasource)
except Exception as e:
	print(str(e))

import os
import sys


# Using this functions we can count the amount of items of a specific tag
def countxmldomsim(file_in, tag_name):
	
    '''
    Name        : countxmldomsim
    Function    : countxmldomsim(file_in, tag_name)
    Description : Counts number of tags in an XML document.
                  Returns the integer count, or false.
    Input       : <file_in> -> Xml File (.xml)
                  <tag_name> -> String: ie 'item'    
    Output      : <integer> -> count | boolean False
    Usage       : countxmldomsim(file_in, 'item')
    Notes       : In case the parser fails to load the 
                  xml file this function will return false. 
    '''
   
	import sys

	try:
		from xml.dom import minidom
	except Exception as e:
		print("Failed to load necessary modules")
		return False
	else:
		mydoc = minidom.parse(file_in)
	

	try:
		items = mydoc.getElementsByTagName(str(tag_name))
	except Exception as e:
		print("Failed to parse items")
		return False
	else:
		return len(items)


from xml.dom import minidom
file_in = sys.argv[1]
mydoc = minidom.parse(file_in)
items = mydoc.getElementsByTagName('item')
print(len(items))
print(str(countxmldomsim(file_in, 'item')))

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="  ")