import json, os, sys, ssl, io, csv, urllib.request, urllib.error

BASE = "https://urlhaus.abuse.ch/downloads/"


def _cfg():
    return json.loads(os.environ.get("INTEGRATION_SECRETS", "{}"))


def _inputs():
    return json.loads(os.environ.get("INTEGRATION_INPUTS", "{}"))


def _ctx(cfg):
    if cfg.get("insecure"):
        c = ssl.create_default_context()
        c.check_hostname = False
        c.verify_mode = ssl.CERT_NONE
        return c
    return None


def _headers(cfg):
    h = {"User-Agent": "Riposte-SOAR"}
    k = cfg.get("api_key")
    if k:
        h["Auth-Key"] = str(k)
    return h


def _get(url, cfg):
    req = urllib.request.Request(url, headers=_headers(cfg))
    with urllib.request.urlopen(req, timeout=120, context=_ctx(cfg)) as r:
        return r.read()


def _run(fn):
    try:
        print(json.dumps(fn(_cfg(), _inputs())))
    except urllib.error.HTTPError as e:
        print(json.dumps({"error": "HTTP " + str(e.code), "detail": e.read().decode("utf-8", "replace")}))
        sys.exit(1)
    except Exception as e:
        print(json.dumps({"error": str(e)}))
        sys.exit(1)


def main(cfg, inputs):
    which = str(inputs.get("list") or cfg.get("list") or "recent").lower()
    fname = "csv_online" if which == "online" else "csv_recent"
    raw = _get(BASE + fname + "/", cfg).decode("utf-8", "replace")

    maxn = int(inputs.get("max_indicators") or 0)
    out = []
    for row in csv.reader(io.StringIO(raw)):
        if not row or row[0].lstrip().startswith("#"):
            continue
        if row[0].strip().strip('"') == "id":  # header row
            continue
        # columns: id,dateadded,url,url_status,last_online,threat,tags,urlhaus_link,reporter
        if len(row) < 3:
            continue
        url = row[2].strip()
        if not url:
            continue
        item = {"value": url, "type": "url"}
        if len(row) > 3:
            item["status"] = row[3].strip()
        if len(row) > 5:
            item["threat"] = row[5].strip()
        if len(row) > 6:
            item["tags"] = row[6].strip()
        out.append(item)
        if maxn and len(out) >= maxn:
            break

    return {"source": "urlhaus:" + fname, "count": len(out), "indicators": out}


_run(main)