Remove items that aren't from 2024 from a wordpress export.

trim_old.py

import xml.etree.ElementTree as ET

# Parse the XML file and get the root
tree = ET.parse('wordpress_export.xml')
root = tree.getroot()

# Find the <channel> element
channel = root.find('channel')

total = 0
skipped = 0
kept = 0

# Iterate over all <item> elements within the <channel>
for item in channel.findall('item'):
    # Find the <pubdate> element and get its text
    pubdate = item.find('pubDate')
    if pubdate is not None and isinstance(pubdate.text, str):
        try:
            if "2024" not in pubdate.text:
                channel.remove(item)
                print(f"\t{pubdate.text}")
                skipped += 1
            else:
                print(pubdate.text)
                kept += 1
        except:
            print("Error")

    total += 1

# Write the modified XML back to the file
tree.write('trimmed.xml')

print(f"\nKept {kept} items, and dropped {skipped} items out of {total} total items.")