Files
school_compare/integrator/scripts/sources/ees.py

54 lines
1.7 KiB
Python
Raw Normal View History

"""
Shared EES (Explore Education Statistics) API client.
Base URL: https://api.education.gov.uk/statistics/v1
"""
import sys
from pathlib import Path
from typing import Optional
import requests
API_BASE = "https://api.education.gov.uk/statistics/v1"
TIMEOUT = 60
def get_publication_files(publication_slug: str) -> list[dict]:
"""Return list of data-set file descriptors for a publication."""
url = f"{API_BASE}/publications/{publication_slug}/data-set-files"
resp = requests.get(url, timeout=TIMEOUT)
resp.raise_for_status()
return resp.json().get("results", [])
def get_latest_csv_url(publication_slug: str, keyword: str = "") -> Optional[str]:
"""
Find the most recent CSV download URL for a publication.
Optionally filter by a keyword in the file name.
"""
files = get_publication_files(publication_slug)
for entry in files:
name = entry.get("name", "").lower()
if keyword and keyword.lower() not in name:
continue
csv_url = entry.get("csvDownloadUrl") or entry.get("file", {}).get("url")
if csv_url:
return csv_url
return None
def download_csv(url: str, dest_path: Path) -> Path:
"""Download a CSV from EES to dest_path."""
if dest_path.exists():
print(f" EES: {dest_path.name} already exists, skipping.")
return dest_path
print(f" EES: downloading {url} ...")
resp = requests.get(url, timeout=300, stream=True)
resp.raise_for_status()
dest_path.parent.mkdir(parents=True, exist_ok=True)
with open(dest_path, "wb") as f:
for chunk in resp.iter_content(chunk_size=65536):
f.write(chunk)
print(f" EES: saved {dest_path} ({dest_path.stat().st_size // 1024} KB)")
return dest_path