probe_sections.py

"""Probe for section-level parquet files on Lex CDN."""
import httpx

base = "https://lexdownloads.blob.core.windows.net/downloads/latest"
patterns = [
    "legislation_section.parquet",
    "legislation_sections.parquet",
    "legislation_section_1983.parquet",
    "legislation_section/1983.parquet",
    "sections/1983.parquet",
    "legislation_sections/1983.parquet",
    "legislation_section_2005.parquet",
    "legislation_section_2014.parquet",
    "sections_1983.parquet",
    "legislation-section.parquet",
    "legislation-sections.parquet",
    "explanatory_note.parquet",
    "amendment.parquet",
]

for p in patterns:
    url = f"{base}/{p}"
    try:
        r = httpx.head(url, timeout=10, follow_redirects=True)
        size = r.headers.get("content-length", "?")
        mb = int(size) // 1024 // 1024 if size.isdigit() else "?"
        status = "FOUND" if r.status_code == 200 else str(r.status_code)
        print(f"{status}: {p} ({mb} MB)" if r.status_code == 200 else f"  {r.status_code}: {p}")
    except Exception as e:
        print(f"  ERROR: {p} -> {type(e).__name__}")