Learn XML - parsing in python with simple examples

Learn XML - parsing in python with simple examples.py

# 1. How to read and XML file using Python ?
# For example purpose, kindly save the above XML content into a file named as 'data.xml'
# import a class named xml.etree.ElementTree

import xml.etree.ElementTree as element_tree

# Before reading we should parse the whole XML file content as tree
tree = element_tree.parse('data.xml')

# Now with tree we have to fetch the root
root = tree.getroot()

# if you print the root.tag, it will print as data
print "Root of the XML is ", root.tag

# if you print the root.attrib, it will print be a empty dict
print "Root attrib is ", root.attrib

# 2. How to print the country name out of it?
for child in root:
    # print "Country Name = ", child.attrib['name']
    print "Country Name = ", child.attrib.get('name')

print '~' * 127

# 2. How to print the neighbor and  country name alone out of it?
for child in root:
    print child.tag, " is  ",  child.attrib.get('name')
    for neighbor in child.findall('neighbor'):
        print neighbor.tag, " is ", neighbor.attrib

print '*' * 127

# 3. How to print all the content out of the XML file ?
for child in root:
    print child.tag, " is  ",  child.attrib['name']
    for grand_child in child:
            print grand_child.tag, grand_child.text, grand_child.attrib

print "=" * 127

# 3. How to print only neighbor out of the XML file ?
for neighbor in root.iter('neighbor'):
    print neighbor.tag, neighbor.attrib

print "-" * 127

# 4. How to print the rank and year of the country?
for country in root.iter('country'):
    rank = country.find('rank').text
    year = country.find('year').text
    name = country.attrib.get('name')
    print name, "rank is ", rank, " on ", year

print '~' * 127

# 5. How to set the attribute for the root ?
root.set('location', 'world')
print "Now the Root attrib is ", root.attrib

# 6. How to write the output.xml file
tree.write('output.xml', xml_declaration=True, encoding='utf-8')

# 7. How to modify the values of rank or year particular country?
for country in root:
    if country.attrib.get('name') == 'Panama':
        for grand_child in country:
            if grand_child.tag == 'year' or grand_child.tag == 'rank':
                new_value = int(grand_child.text) + 1
                grand_child.text = str(new_value)
                grand_child.set('Updated', 'yes')

# To print the dump
element_tree.dump(tree)

tree.write('output.xml', xml_declaration=True, encoding="us-ascii")

# 8. How to remove the country or a child from the xml file?
for country in root.findall('country'):
        rank = int(country.find('rank').text)
        if rank > 50:
            print "Removing the Country ", country.attrib.get('name')
            root.remove(country)

# To print the dump
element_tree.dump(tree)

print '=' * 127
# xml.etree.ElementTree.tostring(element, encoding="us-ascii", method="xml")
# 9. How to convert the XML file as string?
xml_content = element_tree.tostring(root, method="xml", encoding="us-ascii")  # Don't use tree
print xml_content

print '=' * 127

# 10. How to Parse the XML content form the string ?
string_root = element_tree.fromstring(xml_content)  # Don't consider as tree

print "New string tree root is ", string_root.tag