integrity_scanner_fuer_stat.../scanner/alerter.py
Your Name 98e8d11eb5 feat: initial implementation of website integrity scanner
Python-Package zur unabhängigen Überwachung statischer Websites gegen
SEO-Spam und unbefugte Manipulationen. Läuft außerhalb des Hosters.

Kernfunktionen:
- Reiner Python-Crawler (bs4+lxml), kein wget
- Baseline-Management mit manuellem Freigabe-Workflow (niemals automatisch)
- Text-/Link-/Meta-Diff mit Risiko-Scoring (grün/gelb/rot)
- Hidden-Content-Erkennung (CSS inline, noscript, Kommentar-Links)
- Whitelist für externe Domains und interne Pfade
- E-Mail + Webhook Alarmierung
- CLI: init, crawl, check, scan, approve, report, status
- 79 Unit-Tests (pytest), alle grün

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-12 00:51:41 +02:00

183 lines
6.4 KiB
Python

"""
Alert dispatch: e-mail (smtplib) and HTTP webhook.
Alerts are only sent when the assessment level meets or exceeds min_level.
"""
import logging
import os
import smtplib
from datetime import datetime, timezone
from email.message import EmailMessage
import requests
logger = logging.getLogger(__name__)
_LEVEL_ORDER = {"green": 0, "yellow": 1, "red": 2}
def send_alert(report: dict, cfg: dict) -> None:
"""Send alert if the report's level is at or above min_level."""
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
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)
# ---------------------------------------------------------------------------
# Formatting
# ---------------------------------------------------------------------------
def _make_subject(report: dict) -> str:
level = report.get("assessment", {}).get("level", "?").upper()
target = report.get("target", "?")
ts = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
return f"[{level}] Integrity Alert: {target}{ts}"
def _format_body(report: dict) -> str:
lines = [
"=" * 60,
"WEBSITE INTEGRITY ALERT",
"=" * 60,
f"Ziel: {report.get('target', '?')}",
f"Zeitpunkt: {datetime.now(timezone.utc).isoformat()}",
]
assessment = report.get("assessment", {})
level = assessment.get("level", "?").upper()
score = assessment.get("score", "?")
lines += [
f"Level: {level}",
f"Score: {score}",
"",
"--- Gruende ---",
]
for reason in assessment.get("reasons", []):
lines.append(f" * {reason}")
diff = report.get("diff", {})
_section(lines, "Neue externe Domains", diff.get("new_external_domains", []), "+")
_section(lines, "Neue interne URLs", diff.get("new_internal_urls", []), "+")
_section(lines, "Fehlende URLs", diff.get("missing_internal_urls", []), "-")
for pd in diff.get("page_diffs", [])[:10]:
lines += ["", f"--- Aenderung: {pd['url']} ---"]
if pd.get("text_diff"):
lines.append(f" Text-Diff: {pd['added_chars']} Zeichen zugefügt")
lines += [f" {l}" for l in pd["text_diff"][:30]]
if pd.get("new_hidden_content"):
lines.append(f" Hidden Content: {len(pd['new_hidden_content'])} neue(r) Fund(e)")
if pd.get("new_meta_refresh"):
lines.append(f" Meta-Refresh: {pd['new_meta_refresh']}")
if pd.get("canonical_changed"):
lines.append(f" Canonical geaendert: {pd.get('old_canonical')} -> {pd.get('new_canonical')}")
if pd.get("new_comment_links"):
lines.append(f" Kommentar-Links: {pd['new_comment_links']}")
lines += [
"",
"--- Empfehlung ---",
]
level_lower = assessment.get("level", "green")
if level_lower == "red":
lines += [
" SOFORT HANDELN: Website moeglicherweise kompromittiert.",
" Zugriff auf Hosting-Backend prüfen, Dateien vergleichen.",
]
elif level_lower == "yellow":
lines += [
" PRÜFEN: Unerwartete Aenderungen gefunden.",
" Alle markierten URLs manuell kontrollieren.",
" Falls legitim: python -m scanner approve --all",
]
else:
lines.append(" OK — nur zur Information.")
lines += [
"",
"--- Workflow ---",
" Details: python -m scanner report",
" Freigabe: python -m scanner approve --url <URL>",
" Rebuild: python -m scanner approve --rebuild",
"=" * 60,
]
return "\n".join(lines)
def _section(lines: list, title: str, items: list, prefix: str) -> None:
if not items:
return
lines += ["", f"--- {title} ---"]
for item in items[:50]:
lines.append(f" {prefix} {item}")
if len(items) > 50:
lines.append(f" ... und {len(items) - 50} weitere")
# ---------------------------------------------------------------------------
# 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)