integrity_scanner_fuer_stat.../scanner/config.py
Your Name bed20db8bd feat: Laientauglichkeit — Auto-Modus, Klartext-Ausgabe, einfachere Doku
Ziel: ein einziger täglicher Befehl genügt, jede Meldung ist auch ohne
IT-Wissen verständlich.

Auto-Modus (ein Cron-Job genügt für alles):
- data/state.json merkt sich, wann die Wochen-Prüfungen zuletzt liefen
  (baseline.py: load_state/save_state/is_check_due/mark_check_run)
- `scan` führt fällige Zusatzprüfungen (Tarnung/externe Links/Dateien)
  automatisch mit aus; Gesamt-Ampel = schlechtestes Teilergebnis;
  EIN kombinierter Report + EIN Alert
- neuer Config-Abschnitt periodic_checks (Default: wöchentlich, an)

Klartext (scanner/plain.py):
- Ampel 🟢/🟡/🔴 + Sätze ohne Fachbegriffe, aus den strukturierten Befunden
- Report: Klartext oben, "Technische Details (für Ihren Dienstleister)" unten
- Terminal-Ausgabe und E-Mail (alerter.py) ebenso umgestellt

Komfort:
- approve --all/--rebuild legt die Datei-Überwachung automatisch mit an
  (Opt-out: --skip-assets); approve-assets bleibt für den Sonderfall
- status zeigt Ampel zuoberst + wann die Wochen-Prüfungen zuletzt liefen
- Onboarding-Text in einfacher Sprache, wenn noch kein Vergleichsstand existiert

Doku: README + BEDIENUNGSANLEITUNG mit "In 3 Schritten"-Einstieg.

Tests: test_state.py, test_plain.py (Fachbegriff-Assertion), Auto-Asset-
Baseline-Test. 165 Tests grün.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-12 11:14:05 +02:00

123 lines
3.6 KiB
Python

"""Config loading with deep-merge against defaults."""
from pathlib import Path
import yaml
DEFAULT_CONFIG: dict = {
"target": "https://bredelar.info",
"user_agent": "integrity-scanner/1.0 (+security-monitoring)",
"request_timeout": 20,
"data_dir": "data",
"reports_dir": "reports",
"logs_dir": "logs",
"config_dir": "config",
"crawl": {
"max_pages": 200,
"delay_seconds": 1.0,
"respect_robots_txt": False,
"skip_extensions": [
".jpg", ".jpeg", ".png", ".gif", ".webp", ".svg", ".ico",
".pdf", ".zip", ".woff", ".woff2", ".ttf", ".otf", ".eot",
".mp4", ".mp3", ".webm", ".avi", ".mov",
],
},
"scoring": {
"new_external_domain": 50,
"new_internal_url": 30,
"missing_internal_url": 20,
"hidden_content": 40,
"unexpected_canonical": 35,
"meta_refresh": 40,
"unexpected_jsonld": 35,
"large_text_addition": 20,
"new_inline_script_suspicious": 30,
"comment_links": 25,
"new_broken_link": 20,
"suspicious_filename": 60,
"cloaking_extra_link": 60,
"cloaking_extra_text": 40,
"cloaking_vary_ua": 25,
"changed_script": 40,
"changed_stylesheet": 30,
"changed_asset": 20,
},
"thresholds": {
"yellow": 20,
"red": 60,
"large_text_block_chars": 200,
},
"periodic_checks": {
"enabled": True,
"interval_days": 7,
"cloak_check": True,
"ext_links": True,
"assets": True,
},
"alerting": {
"min_level": "yellow",
"email": {
"enabled": False,
"smtp_host": "localhost",
"smtp_port": 587,
"smtp_tls": True,
"smtp_user": "",
"smtp_password_env": "SCANNER_SMTP_PASSWORD",
"from": "scanner@example.com",
"to": [],
},
"webhook": {
"enabled": False,
"url": "",
},
},
"normalization": {
"strip_html_comments": True,
"collapse_whitespace": True,
"ignore_selectors": [],
"ignore_patterns": [],
},
"allowed_jsonld_types": [
"Organization", "WebSite", "WebPage", "Article", "BreadcrumbList",
"ItemList", "LocalBusiness", "Place", "Person", "Event",
"FAQPage", "Question", "Answer", "ImageObject", "SiteLinksSearchBox",
"ContactPage", "AboutPage",
],
"security_headers": [
"Content-Security-Policy",
"Strict-Transport-Security",
"X-Content-Type-Options",
"Referrer-Policy",
],
}
def load_config(config_file: str = "config.yaml") -> dict:
"""Load config from YAML, deep-merged on top of defaults."""
cfg = _deep_copy(DEFAULT_CONFIG)
p = Path(config_file)
if p.exists():
with p.open(encoding="utf-8") as f:
user_cfg = yaml.safe_load(f) or {}
_deep_update(cfg, user_cfg)
return cfg
def resolve_paths(cfg: dict, base_dir: Path) -> dict:
"""Resolve relative paths in config against base_dir."""
for key in ("data_dir", "reports_dir", "logs_dir", "config_dir"):
cfg[key] = str(base_dir / cfg[key])
return cfg
def _deep_copy(d: dict) -> dict:
import copy
return copy.deepcopy(d)
def _deep_update(base: dict, override: dict) -> None:
for k, v in override.items():
if isinstance(v, dict) and isinstance(base.get(k), dict):
_deep_update(base[k], v)
elif v is None and isinstance(base.get(k), list):
pass # YAML null on a list field = "not set" → keep default
else:
base[k] = v