download_sections.py

"""
Download all sections for key nursing Acts from the Lex API.
Saves as nursing_sections.json for offline use.
"""
import httpx
import json
import time

BASE = "https://lex.lab.i.ai.gov.uk"

NURSING_ACTS = {
    "Mental Health Act 1983": "ukpga/1983/20",
    "Mental Capacity Act 2005": "ukpga/2005/9",
    "Care Act 2014": "ukpga/2014/23",
    "Human Rights Act 1998": "ukpga/1998/42",
    "Equality Act 2010": "ukpga/2010/15",
    "Health and Social Care Act 2012": "ukpga/2012/7",
    "Mental Health Units (Use of Force) Act 2018": "ukpga/2018/27",
    "Autism Act 2009": "ukpga/2009/15",
    "Children Act 1989": "ukpga/1989/41",
    "Children Act 2004": "ukpga/2004/31",
    "Safeguarding Vulnerable Groups Act 2006": "ukpga/2006/47",
}

all_sections = []
client = httpx.Client(timeout=60.0)

for act_name, leg_id in NURSING_ACTS.items():
    print(f"\n--- {act_name} ({leg_id}) ---")

    # Try searching for all sections of this Act
    try:
        # Use section search endpoint
        resp = client.post(
            f"{BASE}/legislation/section/search",
            json={
                "query": act_name,
                "legislation_id": leg_id,
                "size": 200,
                "include_text": True,
            },
        )
        resp.raise_for_status()
        data = resp.json()

        sections = data if isinstance(data, list) else data.get("results", data.get("sections", []))
        print(f"  Got {len(sections)} sections")

        for section in sections:
            section["act_name"] = act_name
            section["legislation_id"] = leg_id
            all_sections.append(section)

        time.sleep(1)  # Rate limiting

    except Exception as e:
        print(f"  ERROR: {type(e).__name__}: {e}")

        # Fallback: try getting sections one by one using browse
        try:
            resp2 = client.get(
                f"{BASE}/legislation/{leg_id}/sections",
                params={"limit": 200},
            )
            resp2.raise_for_status()
            data2 = resp2.json()
            sections2 = data2 if isinstance(data2, list) else data2.get("sections", [])
            print(f"  Fallback got {len(sections2)} sections")

            for section in sections2:
                section["act_name"] = act_name
                section["legislation_id"] = leg_id
                all_sections.append(section)

        except Exception as e2:
            print(f"  Fallback also failed: {type(e2).__name__}: {e2}")

        time.sleep(1)

client.close()

print(f"\n=== TOTAL: {len(all_sections)} sections ===")

# Save
output_path = r"c:\Users\g0226\Downloads\Ai Education\NurseLex\nursing_sections.json"
with open(output_path, "w", encoding="utf-8") as f:
    json.dump(all_sections, f, indent=2, ensure_ascii=False)

print(f"Saved to {output_path}")
print(f"File size: {len(json.dumps(all_sections)) // 1024} KB")

# Show sample
if all_sections:
    s = all_sections[0]
    print(f"\nSample keys: {list(s.keys())}")
    print(f"Sample title: {s.get('title', '?')}")
    print(f"Sample text preview: {str(s.get('text', ''))[:200]}")