Edit XML file text based on path

Question

I have an XML file (e.g. jerry.xml) which contains some data as given below.

    2<         


        

Answer 1

I've altered your extractNumbers function and other code to generate a relative xpath based on the read in file.

import xml.etree.ElementTree as ET

def extractNumbers(path, node):
    nums = []
    # You'll want to store a relative, rather than an absolute path.
    if not path: # This is the root node, store the // Predicate to look at all root's children.
        path = ".//"
    else: # This is not the root node
        if 'month' in node.attrib:
            if node.attrib['month'] in ['05', '06']:
                return nums

        path += node.tag
        if 'name' in node.keys():
            path += '[@name="{:s}"]/'.format(node.attrib['name'])
        elif 'year' in node.keys():
            path += '[@month="{:s}"]/'.format(node.attrib['month'])
        try:
            num = float(node.text)
            nums.append((path, num) )
        except (ValueError, TypeError):
            pass
    # Descend into the node's child nodes
    for e in list(node):
        nums.extend( extractNumbers(path, e) )
    return nums

tree = ET.parse('jerry.xml')
nums = extractNumbers('', tree.getroot())

At this point you have a nums list populated with tuples of "path, num". You'll want to write the path into your csv. In the following, I've assumed that you know the Text1, Text2, and Text3 values before hand, and so I've written 'foo', 'bar', 'baz' into each row.

import csv
# Write the CSV file with the data found from extractNumbers
with open('records.csv', 'w') as records:
    writer = csv.writer(records, delimiter=';')
    writer.writerow(['Path', 'Text1', 'Text2', 'Text3'])
    for entry in nums:
        # Ensure that you're writing a relative xpath
        rel_path = entry[0]
        # you will want to "Text1", 'foo' below, to be an appropriate value, as it will be written into the xml below
        writer.writerow([rel_path, 'foo', 'bar', 'baz'])

You will now have the following CSV file

Path;Text1;Text2;Text3
".//country[@name=""Peru""]/rank";foo;bar;baz
".//country[@name=""Peru""]/gdpnp";foo;bar;baz
".//country[@name=""Singapore""]/rank";foo;bar;baz
".//country[@name=""Singapore""]/gdpnp";foo;bar;baz

In the following code, you will read the csv file Read the CSV file, and use the PATH column to alter the appropriate values

import csv
import xml.etree.ElementTree as ET
with open('records.csv', 'r') as records:
    reader = csv.reader(records, delimiter=';')
    for row in reader:
        if reader.line_num == 1: continue # skip the row of headers
        for data in tree.findall(row[0]):
            data.text = row[1]
tree.write('jerry_new.xml')

You'll have the following results in jerry_new.xml

<data>
    <country name="Peru">
        <rank updated="yes">foo</rank>
        <language>english</language>
        <currency>1.21$/kg</currency>
        <gdppc month="06">141100</gdppc>
        <gdpnp month="10">foo</gdpnp>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
    <country name="Singapore">
        <rank updated="yes">foo</rank>
        <language>english</language>
        <currency>4.1$/kg</currency>
        <gdppc month="05">59900</gdppc>
        <gdpnp month="08">foo</gdpnp>
        <neighbor direction="N" name="Malaysia" />
    </country>
</data>

Answer 2

FIrst of all, documentation of how to modify an XML. Now, here is my own example:

import xml.etree.ElementTree as ET

s = """
<root>
    <parent attribute="value">
        <child_1 other_attr="other_value">child text</child_1>
        <child_2 yet_another_attr="another_value">more child text</child_2>
    </parent>
</root>
"""

root = ET.fromstring(s)

for parent in root.getchildren():
    parent.attrib['attribute'] = 'new value'
    for child in parent.getchildren():
        child.attrib['new_attrib'] = 'new attribute for {}'.format(child.tag)
        child.text += ', appended text!'

>>> ET.dump(root)
<root>
    <parent attribute="new value">
        <child_1 new_attrib="new attribute for child_1" other_attr="other_value">child text, appended text!</child_1>
        <child_2 new_attrib="new attribute for child_2" yet_another_attr="another_value">more child text, appended text!</child_2>
    </parent>
</root>

And you can do this with Xpath as well.

>>> root.find('parent/child_1[@other_attr]').attrib['other_attr'] = 'found it!'
>>> ET.dump(root)
<root>
    <parent attribute="new value">
        <child_1 new_attrib="new attribute for child_1" other_attr="found it!">child text, appended text!</child_1>
        <child_2 new_attrib="new attribute for child_2" yet_another_attr="another_value">more child text, appended text!</child_2>
    </parent>
</root>

Answer 3

You should be able to use the XPath capabilities of the module to do this:

import xml.etree.ElementTree as ET
tree = ET.parse('jerry.xml')
root = tree.getroot()
for data in root.findall(".//country[@name='singapore']/gdpnp[@month='08']"):
    data.text = csv_value

tree.write("filename.xml")

So you need to rewrite the path in the csv to match the XPath rules defined for the module (see Supported XPath rules).