subjects.py

#!/usr/bin/env python3

# This program will fetch the first page of recently updated Library of Congress
# Subject Headings from id.loc.gov and print out the MARC records for them.
# 
# /// script
# dependencies = ["requests", "pymarc"]
# ///
#
# see PEP 723

import io
import pymarc
import requests

def print_marc(url):
    marc_xml = io.StringIO(requests.get(url).text)
    record = pymarc.marcxml.parse_xml_to_array(marc_xml)[0]
    print(str(record))

feed = requests.get('https://id.loc.gov/authorities/names/activitystreams/feed/1.json').json()
for item in feed['orderedItems']:
    for url in item['object']['url']:
        if url['mediaType'] == 'application/marc+xml':
            print_marc(url['href'])