legislation.gov.uk

python -m pip install pandas requests

import xml.etree.ElementTree as ET
import pandas as pd
import requests

response = requests.get(
    "https://www.legislation.gov.uk/ukpga/2018/12/data.xml",
    timeout=30,
)
response.raise_for_status()
root = ET.fromstring(response.content)
ns = {"a": "http://www.legislation.gov.uk/namespaces/legislation"}
title = root.findtext(".//a:Title", default="", namespaces=ns)
sections = [
    {
        "number": item.findtext("a:Number", default="", namespaces=ns),
        "title": item.findtext("a:Title", default="", namespaces=ns),
    }
    for item in root.findall(".//a:P1group", ns)[:20]
]
print(title)
print(pd.DataFrame(sections).head())