Notebook

Τμήμα Πληροφορικής και Τηλεπικοινωνιών - Άρτα 
Πανεπιστήμιο Ιωαννίνων 

Γκόγκος Χρήστος 
http://chgogos.github.io/
Εαρινό εξάμηνο 2020-2021

XML¶

minidom και ElementTree (standard library)

xmltodict (3rd party library)

Parsing με το minidom¶

In [1]:

import xml.dom.minidom
print(dir(xml.dom.minidom))

['Attr', 'AttributeList', 'CDATASection', 'CharacterData', 'Childless', 'Comment', 'DOMImplementation', 'DOMImplementationLS', 'Document', 'DocumentFragment', 'DocumentLS', 'DocumentType', 'EMPTY_NAMESPACE', 'EMPTY_PREFIX', 'Element', 'ElementInfo', 'EmptyNodeList', 'Entity', 'Identified', 'NamedNodeMap', 'Node', 'NodeList', 'Notation', 'ProcessingInstruction', 'ReadOnlySequentialNamedNodeMap', 'StringTypes', 'Text', 'TypeInfo', 'XMLNS_NAMESPACE', '__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__spec__', '_append_child', '_clear_id_cache', '_clone_node', '_do_pulldom_parse', '_get_containing_element', '_get_containing_entref', '_get_elements_by_tagName_helper', '_get_elements_by_tagName_ns_helper', '_in_document', '_no_type', '_nodeTypes_with_children', '_nssplit', '_set_attribute_node', '_write_data', 'defproperty', 'domreg', 'getDOMImplementation', 'io', 'parse', 'parseString', 'xml']

In [2]:

# parsing του XML, εκτύπωση

path = "../../../datasets/person.xml"
xml_f = open(path, "r", encoding="utf-8")
xmlparse = xml.dom.minidom.parseString(xml_f.read())
prettyxml = xmlparse.toprettyxml()
print(prettyxml)

<?xml version="1.0" ?>
<root>
	
    
	<address>
		
        
		<city>Άρτα</city>
		
        
		<postalCode>45221</postalCode>
		
        
		<state>Ήπειρος</state>
		
        
		<streetAddress>Ανεξαρτησίας 33</streetAddress>
		
    
	</address>
	
    
	<age>30</age>
	
    
	<firstName>Γιάννης</firstName>
	
    
	<lastName>Παπαδόπουλος</lastName>
	
    
	<married>true</married>
	
    
	<phoneNumbers>
		
        
		<element>
			
            
			<number>00302681123456</number>
			
            
			<type>home</type>
			
        
		</element>
		
        
		<element>
			
            
			<number>00302681654321</number>
			
            
			<type>work</type>
			
        
		</element>
		
        
		<element>
			
            
			<number>00306971234567</number>
			
            
			<type>mobile</type>
			
        
		</element>
		
    
	</phoneNumbers>
	
    
	<email null="true"/>
	

</root>

In [3]:

# εμφάνιση της πληροφορίας lastName ως XML

xmlparse.getElementsByTagName('lastName')[0].toxml()

Out[3]:

'<lastName>Παπαδόπουλος</lastName>'

In [4]:

# εμφάνιση της πληροφορίας lastName

print(xmlparse.getElementsByTagName('lastName')[0].firstChild.data)
print(xmlparse.getElementsByTagName('lastName')[0].firstChild.nodeValue) # το nodeValue είναι ψευδώνυμο για το data

Παπαδόπουλος
Παπαδόπουλος

In [5]:

# εμφάνιση όλων των εμφωλευμένων πληροφοριών στην ετικέτα address

for node in xmlparse.getElementsByTagName('address')[0].childNodes:
    if node.nodeType == node.ELEMENT_NODE:
        print(f'{node.tagName}: {node.firstChild.data}')

city: Άρτα
postalCode: 45221
state: Ήπειρος
streetAddress: Ανεξαρτησίας 33

In [6]:

for node in xmlparse.getElementsByTagName('phoneNumbers'):
    i=0
    for node2 in node.childNodes:
        if node2.nodeType == node.ELEMENT_NODE:
            i+=1
            print(f'Phone{i}')
            for node3 in node2.childNodes:
                if node3.nodeType == node.ELEMENT_NODE:
                    print(f'{node3.tagName}: {node3.firstChild.data}')
            print("#"*30)
            

Phone1
number: 00302681123456
type: home
##############################
Phone2
number: 00302681654321
type: work
##############################
Phone3
number: 00306971234567
type: mobile
##############################

Parsing με το ElementTree¶

In [7]:

# διάσχιση XML χρησιμοποιώντας τη συνάρτηση list(elem)

import xml.etree.ElementTree as ET 

path = "../../../datasets/person.xml"
xml_f = open(path, "r", encoding="utf-8")
tree = ET.ElementTree(file=xml_f)

root = tree.getroot()
print(root)
print("#" * 30)

for elem in list(root):
    if elem.tag == 'address': 
        for elem2 in list(elem):
            print(elem2.tag, elem2.text)
    elif elem.tag == 'phoneNumbers':
        for elem2 in list(elem):
            print(list(elem2)[0].tag, list(elem2)[0].text)
            print(list(elem2)[1].tag, list(elem2)[1].text)
    else:
        print(elem.tag, elem.text)

<Element 'root' at 0x00000251EDCACCC0>
##############################
city Άρτα
postalCode 45221
state Ήπειρος
streetAddress Ανεξαρτησίας 33
age 30
firstName Γιάννης
lastName Παπαδόπουλος
married true
number 00302681123456
type home
number 00302681654321
type work
number 00306971234567
type mobile
email None

In [8]:

# διάσχιση XML με iterator 

for elem in tree.iter():
    if elem.tag == 'root':
        continue
    elif elem.tag == 'address':
        print('ADDRESS')
    elif elem.tag == 'phoneNumbers':
        print('PHONENUMBERS')
    elif elem.tag == 'element':
        continue
    else: 
        print(f'{elem.tag} {elem.text}')

ADDRESS
city Άρτα
postalCode 45221
state Ήπειρος
streetAddress Ανεξαρτησίας 33
age 30
firstName Γιάννης
lastName Παπαδόπουλος
married true
PHONENUMBERS
number 00302681123456
type home
number 00302681654321
type work
number 00306971234567
type mobile
email None

Εγγραφή δεδομένων σε αρχείο XML με το ElementTree¶

In [9]:

# εγγραφή αρχείου XML που περιέχει attributes και elements

import xml.etree.ElementTree as ET 

xml_doc = ET.Element("messages")
note1 = ET.SubElement(xml_doc, "note")
note1.set('id', '501')
note1_to = ET.SubElement(note1, "to")
note1_to.text = 'Tove'
note1_from = ET.SubElement(note1, "from")
note1_from.text = 'Jani'
note1_heading = ET.SubElement(note1, "heading")
note1_heading.text = 'Reminder'
note1_body = ET.SubElement(note1, "body")
note1_body.text = "Don't forget me the weekend!"

note2 = ET.SubElement(xml_doc, "note")
note2.set('id', '502')
note2_to = ET.SubElement(note2, "to")
note2_to.text = 'Jani'
note2_from = ET.SubElement(note2, "from")
note2_from.text = 'Tove'
note2_heading = ET.SubElement(note2, "heading")
note2_heading.text = 'Re: Reminder'
note2_body = ET.SubElement(note2, "body")
note2_body.text = "I will not"

# https://stackoverflow.com/questions/749796/pretty-printing-xml-in-python
def prettify(element, indent="  "):
    queue = [(0, element)]  # (level, element)
    while queue:
        level, element = queue.pop(0)
        children = [(level + 1, child) for child in list(element)]
        if children:
            element.text = "\n" + indent * (level + 1)  # for child open
        if queue:
            element.tail = "\n" + indent * queue[0][0]  # for sibling open
        else:
            element.tail = "\n" + indent * (level - 1)  # for parent close
        queue[0:0] = children  # prepend so children come before siblings

prettify(xml_doc)
tree = ET.ElementTree(xml_doc)
tree.write('../../../datasets/notes.xml')

xmltodict¶

Μετατρέπει XML δεδομένα σε λεξικό

$ pip install xmltodict

In [10]:

import xmltodict

path = "../../../datasets/person.xml"
xml_f = open(path, "r", encoding="utf-8")

xmldict = xmltodict.parse(xml_f.read())
xmldict

Out[10]:

OrderedDict([('root',
              OrderedDict([('address',
                            OrderedDict([('city', 'Άρτα'),
                                         ('postalCode', '45221'),
                                         ('state', 'Ήπειρος'),
                                         ('streetAddress',
                                          'Ανεξαρτησίας 33')])),
                           ('age', '30'),
                           ('firstName', 'Γιάννης'),
                           ('lastName', 'Παπαδόπουλος'),
                           ('married', 'true'),
                           ('phoneNumbers',
                            OrderedDict([('element',
                                          [OrderedDict([('number',
                                                         '00302681123456'),
                                                        ('type', 'home')]),
                                           OrderedDict([('number',
                                                         '00302681654321'),
                                                        ('type', 'work')]),
                                           OrderedDict([('number',
                                                         '00306971234567'),
                                                        ('type',
                                                         'mobile')])])])),
                           ('email', OrderedDict([('@null', 'true')]))]))])

In [11]:

print(xmldict['root']['lastName'])
print(xmldict['root']['address']['city'])
print(xmldict['root']['phoneNumbers']['element'][0]['number'])

Παπαδόπουλος
Άρτα
00302681123456

In [ ]: