GitHub Advisory Database

git clone --filter=blob:none https://github.com/github/advisory-database.git

"""One recently changed GitHub advisory -> pandas -> Parquet. No key."""
import requests
import pandas as pd

API = "https://api.github.com/repos/github/advisory-database"
headers = {"Accept": "application/vnd.github+json", "User-Agent": "signal-lab-catalog-check"}
commits = requests.get(f"{API}/commits", params={"path": "advisories", "per_page": 10}, headers=headers, timeout=60)
commits.raise_for_status()
advisory = None
for commit in commits.json():
    detail = requests.get(f"{API}/commits/{commit['sha']}", headers=headers, timeout=60)
    detail.raise_for_status()
    files = [f for f in detail.json().get("files", []) if f["filename"].startswith("advisories/") and f["filename"].endswith(".json") and f.get("raw_url")]
    if files:
        data = requests.get(files[0]["raw_url"], headers=headers, timeout=60)
        data.raise_for_status()
        advisory = data.json()
        break
if advisory is None:
    raise RuntimeError("No changed advisory found")
row = {"id": advisory["id"], "published": advisory.get("published"), "modified": advisory.get("modified"), "summary": advisory.get("summary"), "aliases": ";".join(advisory.get("aliases", []))}
pd.DataFrame([row]).to_parquet("github_advisory_sample.parquet", index=False)
ecosystems = sorted({a.get("package", {}).get("ecosystem", "") for a in advisory.get("affected", [])})
print(advisory["id"], "modified", advisory.get("modified"), "ecosystems", ",".join(ecosystems))