- M1: Removed '/' from jamulix.de exclude_paths (blockaded ALL paths via startswith) - M2: Seed URLs now pass through should_crawl() in crawler.py - M3: Alert deduplication via last_alert.json (hash of reasons+level+score) - Added 11 tests for alert deduplication (277 total, all green)
174 lines
6.2 KiB
Python
174 lines
6.2 KiB
Python
"""
|
|
Alert dispatch: e-mail (smtplib) and HTTP webhook.
|
|
|
|
Alerts are only sent when the assessment level meets or exceeds min_level.
|
|
Duplicate alerts (identical reasons since last send) are suppressed.
|
|
"""
|
|
import hashlib
|
|
import json
|
|
import logging
|
|
import os
|
|
import smtplib
|
|
from email.message import EmailMessage
|
|
from pathlib import Path
|
|
|
|
import requests
|
|
|
|
from .plain import ampel
|
|
from .report import render_markdown
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_LEVEL_ORDER = {"green": 0, "yellow": 1, "red": 2}
|
|
_ALERT_STATE_FILE = "last_alert.json"
|
|
|
|
|
|
def send_alert(report: dict, cfg: dict) -> None:
|
|
"""Send alert if the report's level is at or above min_level.
|
|
|
|
Duplicate alerts (identical assessment reasons since last send) are suppressed.
|
|
The dedup state is persisted in data_dir/last_alert.json per site.
|
|
"""
|
|
alerting = cfg.get("alerting", {})
|
|
level = report.get("assessment", {}).get("level", "green")
|
|
min_level = alerting.get("min_level", "yellow")
|
|
|
|
if _LEVEL_ORDER.get(level, 0) < _LEVEL_ORDER.get(min_level, 1):
|
|
logger.debug("Alert suppressed: level=%s < min_level=%s", level, min_level)
|
|
return
|
|
|
|
# --- Deduplizierung: nur senden wenn sich die Alarm-Gründe geändert haben ---
|
|
alert_key = _compute_alert_key(report)
|
|
data_dir = cfg.get("data_dir")
|
|
if data_dir:
|
|
last = _load_last_alert(Path(data_dir))
|
|
if last and last.get("key") == alert_key:
|
|
logger.info("Alert suppressed (duplicate, reasons unchanged since %s)",
|
|
last.get("sent_at", "unknown"))
|
|
return
|
|
|
|
subject = _make_subject(report)
|
|
body = _format_body(report)
|
|
|
|
email_cfg = alerting.get("email", {})
|
|
if email_cfg.get("enabled"):
|
|
_send_email(subject, body, email_cfg)
|
|
|
|
webhook_cfg = alerting.get("webhook", {})
|
|
if webhook_cfg.get("enabled") and webhook_cfg.get("url"):
|
|
_send_webhook(webhook_cfg["url"], report, subject)
|
|
|
|
# Zustand speichern — für nächste Dedup-Runde
|
|
if data_dir:
|
|
_save_last_alert(Path(data_dir), alert_key)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Formatting
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _make_subject(report: dict) -> str:
|
|
level = report.get("assessment", {}).get("level", "green")
|
|
target = report.get("target", "?")
|
|
symbol, _ = ampel(level)
|
|
if level == "red":
|
|
return f"{symbol} Ihre Website {target} braucht Aufmerksamkeit"
|
|
if level == "yellow":
|
|
return f"{symbol} Bitte einmal auf Ihrer Website {target} nachschauen"
|
|
return f"{symbol} Ihre Website {target}: alles in Ordnung"
|
|
|
|
|
|
def _format_body(report: dict) -> str:
|
|
"""E-Mail-Body = derselbe Renderer wie der Dateibericht (eine Quelle der
|
|
Wahrheit). So enthalten Report und Mail garantiert denselben Inhalt."""
|
|
return render_markdown(report)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Transport
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _send_email(subject: str, body: str, cfg: dict) -> None:
|
|
password = os.environ.get(cfg.get("smtp_password_env", "SCANNER_SMTP_PASSWORD"), "")
|
|
recipients = cfg.get("to", [])
|
|
if not recipients:
|
|
logger.warning("E-Mail alert enabled but no recipients configured.")
|
|
return
|
|
|
|
msg = EmailMessage()
|
|
msg["Subject"] = subject
|
|
msg["From"] = cfg.get("from", "scanner@localhost")
|
|
msg["To"] = ", ".join(recipients)
|
|
msg.set_content(body)
|
|
|
|
host = cfg.get("smtp_host", "localhost")
|
|
port = cfg.get("smtp_port", 587)
|
|
use_tls = cfg.get("smtp_tls", True)
|
|
|
|
try:
|
|
with smtplib.SMTP(host, port) as server:
|
|
if use_tls:
|
|
server.starttls()
|
|
user = cfg.get("smtp_user", "")
|
|
if user and password:
|
|
server.login(user, password)
|
|
server.send_message(msg)
|
|
logger.info("Alert e-mail sent to %s", recipients)
|
|
except Exception as exc:
|
|
logger.error("E-mail alert failed: %s", exc)
|
|
|
|
|
|
def _send_webhook(url: str, report: dict, subject: str) -> None:
|
|
payload = {
|
|
"text": subject,
|
|
"target": report.get("target"),
|
|
"level": report.get("assessment", {}).get("level"),
|
|
"score": report.get("assessment", {}).get("score"),
|
|
"reasons": report.get("assessment", {}).get("reasons", []),
|
|
"new_external_domains": report.get("diff", {}).get("new_external_domains", []),
|
|
"new_internal_urls": report.get("diff", {}).get("new_internal_urls", []),
|
|
"missing_internal_urls": report.get("diff", {}).get("missing_internal_urls", []),
|
|
"changed_pages": report.get("diff", {}).get("changed_pages", 0),
|
|
}
|
|
try:
|
|
resp = requests.post(url, json=payload, timeout=10)
|
|
logger.info("Webhook delivered: HTTP %s", resp.status_code)
|
|
except Exception as exc:
|
|
logger.error("Webhook alert failed: %s", exc)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Deduplication state (last_alert.json in data_dir)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _compute_alert_key(report: dict) -> str:
|
|
"""Stable hash of the assessment reasons + level for deduplication."""
|
|
payload = {
|
|
"level": report.get("assessment", {}).get("level", "green"),
|
|
"score": report.get("assessment", {}).get("score", 0),
|
|
"reasons": sorted(report.get("assessment", {}).get("reasons", [])),
|
|
}
|
|
return hashlib.sha256(json.dumps(payload, sort_keys=True).encode()).hexdigest()
|
|
|
|
|
|
def _load_last_alert(data_dir: Path) -> dict:
|
|
"""Load previous alert state. Returns {} on missing/corrupt file."""
|
|
path = data_dir / _ALERT_STATE_FILE
|
|
try:
|
|
return json.loads(path.read_text())
|
|
except (FileNotFoundError, json.JSONDecodeError, OSError):
|
|
return {}
|
|
|
|
|
|
def _save_last_alert(data_dir: Path, alert_key: str) -> None:
|
|
"""Persist current alert state for next dedup round."""
|
|
from datetime import datetime, timezone
|
|
path = data_dir / _ALERT_STATE_FILE
|
|
state = {
|
|
"key": alert_key,
|
|
"sent_at": datetime.now(timezone.utc).isoformat(),
|
|
}
|
|
try:
|
|
path.write_text(json.dumps(state))
|
|
except OSError as exc:
|
|
logger.debug("Alert state write failed: %s", exc)
|