OCSGE téléchargement IGN flux Atom

get-ocs-data-filtered.py

import xml.etree.ElementTree as ET
import requests

base_url_ocsge = "https://data.geopf.fr/telechargement/resource/OCSGE"
limit = 50
first_page = f'{base_url_ocsge}?page=1&limit={limit}'
r_first_page = requests.get(first_page)

root = ET.fromstring(r_first_page.text)

print(root.attrib)

pages = int(root.attrib['{https://data.geopf.fr/annexes/ressources/xsd/gpf_dl.xsd}pagecount'])

keys_entries = [[j.tag for j in i] for i in root.findall('{http://www.w3.org/2005/Atom}entry')]

unique_keys_for_entry = list(set([element for sublist in keys_entries for element in sublist]))

all_entries = []

for page in range(1, pages + 1):
    url = f'{base_url_ocsge}?page={page}&limit={limit}'
    res = requests.get(url)
    root = ET.fromstring(res.text)
    for i in root.findall('{http://www.w3.org/2005/Atom}entry'):
        entry_dicts = []
        for j in unique_keys_for_entry:
            tag_no_ns = j.split('}')[1]
            if i.find(j) is not None:
                if 'label' in i.find(j).attrib:
                    entry_dicts.append([tag_no_ns, i.find(j).attrib['label']])
                else:
                    entry_dicts.append([tag_no_ns, i.find(j).text])
            else:
                entry_dicts.append([tag_no_ns, ''])
        all_entries.append(dict(entry_dicts))

filtered_entries = []
for i in all_entries:
    if ('2021' in i['id'] or '2022' in i['id'] or '2023' in i['id']) and 'DIFF' not in i['id']:
        filtered_entries.append(i)