Benjamin Admin
525038359a
When the user leaves some doc-type rows empty, the tool now actively searches the website for them — only marks 'not found' as last resort. Flow: 1. User submits N URLs (e.g. just DSI) 2. For each canonical doc_type with no submitted URL/text, the route identifies the most-common base (scheme://netloc) from submitted URLs 3. Calls consent-tester /dsi-discovery on the homepage with max_documents=15 (180s timeout) 4. Classifies every discovered doc into a canonical doc_type via title/URL keyword rules (_DISCOVERY_RULES — covers cookie/widerruf/ social_media/agb/nutzungsbedingungen/dsb/impressum/dse) 5. Fills matching empty entries with the discovered text, marks auto_discovered=True and discovery_attempted=True Padding now differentiates: - 'Auf der Website nicht gefunden' — discovery was attempted, no doc matched. Amber badge, friendly hint to add URL manually. - 'Nicht eingereicht — Quelle nicht angegeben' — user gave NO URLs at all, nothing to crawl from. Grey badge. Email + frontend: - Status labels: NICHT GEFUNDEN (amber) vs NICHT EINGEREICHT (grey) - 'Gepruefte Quellen' table tags auto-discovered URLs with a small blue 'auto-entdeckt' badge so GF sees what tool found vs user submitted. Implementation only runs when ≥1 URL was submitted (no base to crawl from otherwise). Adds 30-90s for unsubmitted types but avoids the 'just say nicht gefunden' anti-pattern.
233 lines
9.4 KiB
Python
233 lines
9.4 KiB
Python
"""
|
|
Extras for the agent doc-check email report.
|
|
|
|
Split out from agent_doc_check_report.py to keep both files under the
|
|
500-line hard cap. Contains:
|
|
- build_scanned_urls_html (list of fetched URLs + cross-domain notice)
|
|
- build_provider_list_html (cookie banner + TCF vendor table)
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
def build_scanned_urls_html(doc_entries: list[dict]) -> str:
|
|
"""Render the list of scanned URLs at the top of the report.
|
|
|
|
Transparent for the GF which sources were actually fetched/analysed.
|
|
Skips empty URLs (text-only uploads). Adds a cross-domain warning when
|
|
legal texts are distributed across multiple domains (e.g. BMW spreads
|
|
across bmw.de, bmwgroup.com, bmwgroup.jobs).
|
|
"""
|
|
from urllib.parse import urlparse
|
|
|
|
rows: list[str] = []
|
|
seen: set[str] = set()
|
|
domains: dict[str, list[str]] = {} # netloc -> list of doc_types
|
|
for entry in doc_entries:
|
|
url = (entry.get("url") or "").strip()
|
|
if not url or url in seen:
|
|
continue
|
|
seen.add(url)
|
|
label = _doc_type_label(entry.get("doc_type", ""))
|
|
words = entry.get("word_count") or 0
|
|
auto = entry.get("auto_discovered")
|
|
try:
|
|
netloc = urlparse(url).netloc.lower().lstrip("www.")
|
|
if netloc:
|
|
domains.setdefault(netloc, []).append(label)
|
|
except Exception:
|
|
pass
|
|
badge = ('<span style="display:inline-block;margin-left:6px;'
|
|
'background:#dbeafe;color:#1e40af;font-size:10px;'
|
|
'padding:1px 6px;border-radius:8px;font-family:sans-serif">'
|
|
'auto-entdeckt</span>') if auto else ""
|
|
rows.append(
|
|
f'<tr>'
|
|
f'<td style="padding:3px 12px 3px 0;color:#475569;font-size:12px">'
|
|
f'{label}{badge}</td>'
|
|
f'<td style="padding:3px 12px 3px 0;font-size:12px;'
|
|
f'font-family:ui-monospace,monospace;color:#1e293b;word-break:break-all">'
|
|
f'<a href="{url}" style="color:#2563eb;text-decoration:none">{url}</a></td>'
|
|
f'<td style="padding:3px 0;color:#94a3b8;font-size:11px;text-align:right;'
|
|
f'white-space:nowrap">{words} Woerter</td>'
|
|
f'</tr>'
|
|
)
|
|
if not rows:
|
|
return ""
|
|
|
|
cross_domain_html = _cross_domain_notice(domains) if len(domains) >= 2 else ""
|
|
|
|
return (
|
|
'<div style="font-family:-apple-system,BlinkMacSystemFont,sans-serif;'
|
|
'max-width:700px;margin:0 auto 16px;padding:12px 16px;'
|
|
'background:#fafafa;border:1px solid #e5e7eb;border-radius:8px">'
|
|
'<h3 style="margin:0 0 8px;font-size:14px;color:#334155">'
|
|
f'Gepruefte Quellen ({len(rows)})</h3>'
|
|
'<table style="width:100%;border-collapse:collapse">'
|
|
+ "".join(rows)
|
|
+ '</table>'
|
|
+ cross_domain_html
|
|
+ '</div>'
|
|
)
|
|
|
|
|
|
def _cross_domain_notice(domains: dict[str, list[str]]) -> str:
|
|
"""Warning box when legal texts are spread across multiple domains.
|
|
|
|
Relevant for big corporate groups (BMW Group: bmw.de / bmwgroup.com /
|
|
bmwgroup.jobs). Affects findability for data subjects and may indicate
|
|
incomplete disclosure on the main site.
|
|
"""
|
|
items = []
|
|
for netloc, labels in sorted(domains.items()):
|
|
labels_str = ", ".join(sorted(set(labels)))
|
|
items.append(
|
|
f'<li style="margin-bottom:2px"><strong>{netloc}</strong> '
|
|
f'<span style="color:#92400e;font-size:11px">→ {labels_str}</span></li>'
|
|
)
|
|
return (
|
|
'<div style="margin-top:12px;padding:10px 12px;background:#fffbeb;'
|
|
'border-left:3px solid #f59e0b;border-radius:4px;font-size:12px;'
|
|
'color:#78350f">'
|
|
'<strong>Hinweis: Rechtstexte verteilt auf '
|
|
f'{len(domains)} Domains.</strong> '
|
|
'Erschwert die Auffindbarkeit fuer Betroffene (Art. 12 Abs. 1 DSGVO — '
|
|
'transparente Information). Pruefen Sie, ob alle Texte auch von der '
|
|
'Hauptdomain aus klar verlinkt sind.'
|
|
'<ul style="margin:6px 0 0 16px;padding-left:0">'
|
|
+ "".join(items) +
|
|
'</ul></div>'
|
|
)
|
|
|
|
|
|
def _doc_type_label(doc_type: str) -> str:
|
|
"""Lazy resolver — avoids circular import with agent_compliance_check_routes."""
|
|
labels = {
|
|
"dse": "Datenschutzerklaerung",
|
|
"datenschutz": "Datenschutzerklaerung",
|
|
"privacy": "Datenschutzerklaerung",
|
|
"impressum": "Impressum",
|
|
"agb": "AGB",
|
|
"widerruf": "Widerrufsbelehrung",
|
|
"cookie": "Cookie-Richtlinie",
|
|
"avv": "Auftragsverarbeitung",
|
|
"loeschkonzept": "Loeschkonzept",
|
|
"dsfa": "Datenschutz-Folgenabschaetzung",
|
|
"social_media": "Social Media Datenschutz",
|
|
"nutzungsbedingungen": "Nutzungsbedingungen",
|
|
"dsb": "DSB-Kontakt",
|
|
}
|
|
return labels.get(doc_type, doc_type.upper() if doc_type else "Dokument")
|
|
|
|
|
|
def build_provider_list_html(
|
|
banner_result: dict | None,
|
|
vvt_entries: list[dict] | None,
|
|
) -> str:
|
|
"""Render the cookie banner result + TCF vendor table for the email.
|
|
|
|
Sections:
|
|
1. Banner summary (provider, violations count)
|
|
2. Vendor table: Name | Kategorie | Zweck | Drittland | Rechtsgrundlage
|
|
"""
|
|
if not banner_result and not vvt_entries:
|
|
return ""
|
|
|
|
parts: list[str] = [
|
|
'<div style="font-family:-apple-system,BlinkMacSystemFont,sans-serif;'
|
|
'max-width:700px;margin:0 auto 16px;padding:12px 16px;'
|
|
'background:#fafafa;border:1px solid #e5e7eb;border-radius:8px">'
|
|
'<h3 style="margin:0 0 10px;font-size:14px;color:#334155">'
|
|
'Cookie-Banner & Verarbeiter</h3>'
|
|
]
|
|
|
|
if banner_result:
|
|
detected = banner_result.get("banner_detected", False)
|
|
provider = banner_result.get("banner_provider") or "unbekannt"
|
|
violations = banner_result.get("banner_checks", {}).get("violations", [])
|
|
n_viol = len(violations) if isinstance(violations, list) else int(violations or 0)
|
|
|
|
status_color = "#16a34a" if detected and n_viol == 0 else (
|
|
"#d97706" if detected else "#6b7280"
|
|
)
|
|
parts.append(
|
|
f'<div style="font-size:13px;color:#374151;margin-bottom:10px">'
|
|
f'<span style="display:inline-block;width:8px;height:8px;'
|
|
f'border-radius:50%;background:{status_color};margin-right:8px"></span>'
|
|
f'Banner erkannt: <strong>{"Ja" if detected else "Nein"}</strong>'
|
|
f' · Anbieter: <strong>{provider}</strong>'
|
|
f' · Auffaelligkeiten: <strong>{n_viol}</strong>'
|
|
f'</div>'
|
|
)
|
|
|
|
vendors = vvt_entries or []
|
|
if vendors:
|
|
parts.append(
|
|
f'<div style="font-size:12px;color:#475569;margin:8px 0 6px">'
|
|
f'<strong>{len(vendors)} TCF-Verarbeiter ueber das Banner eingebunden:</strong>'
|
|
f'</div>'
|
|
'<table style="width:100%;border-collapse:collapse;font-size:11px">'
|
|
'<thead><tr style="background:#f1f5f9;color:#475569;text-align:left">'
|
|
'<th style="padding:5px 8px">Name</th>'
|
|
'<th style="padding:5px 8px">Kategorie</th>'
|
|
'<th style="padding:5px 8px">Zweck</th>'
|
|
'<th style="padding:5px 8px">Drittland</th>'
|
|
'<th style="padding:5px 8px">Rechtsgrundlage</th>'
|
|
'</tr></thead><tbody>'
|
|
)
|
|
for v in vendors[:50]:
|
|
parts.append(_render_vendor_row(v))
|
|
parts.append('</tbody></table>')
|
|
if len(vendors) > 50:
|
|
parts.append(
|
|
f'<div style="font-size:11px;color:#94a3b8;margin-top:4px">'
|
|
f'... und {len(vendors) - 50} weitere</div>'
|
|
)
|
|
elif banner_result and banner_result.get("banner_detected"):
|
|
parts.append(
|
|
'<div style="font-size:11px;color:#94a3b8">'
|
|
'Keine TCF-Verarbeiter erkannt (Banner nutzt kein TCF v2 Framework '
|
|
'oder Vendor-Liste konnte nicht ausgelesen werden).</div>'
|
|
)
|
|
|
|
parts.append('</div>')
|
|
return "".join(parts)
|
|
|
|
|
|
def _render_vendor_row(v: dict) -> str:
|
|
name = v.get("name") or "Unbekannt"
|
|
kategorie = _category_label(v.get("kategorie", ""))
|
|
zweck = v.get("zweck_kurz") or ", ".join((v.get("zweck") or [])[:2])
|
|
drittland = v.get("drittland")
|
|
land = v.get("land") or ""
|
|
if drittland is True:
|
|
drittland_str = (f'<span style="color:#dc2626">Ja ({land})</span>'
|
|
if land else '<span style="color:#dc2626">Ja</span>')
|
|
elif drittland is False:
|
|
drittland_str = (f'<span style="color:#16a34a">Nein ({land})</span>'
|
|
if land else '<span style="color:#16a34a">Nein</span>')
|
|
else:
|
|
drittland_str = '<span style="color:#94a3b8">unbekannt</span>'
|
|
rg = v.get("rechtsgrundlage", "")
|
|
rg_short = "Einwilligung" if "Einwilligung" in rg else (
|
|
"Berechtigtes Interesse" if "Berechtigtes" in rg else rg[:40]
|
|
)
|
|
return (
|
|
f'<tr style="border-top:1px solid #e2e8f0">'
|
|
f'<td style="padding:4px 8px;color:#1e293b">{name}</td>'
|
|
f'<td style="padding:4px 8px;color:#475569">{kategorie}</td>'
|
|
f'<td style="padding:4px 8px;color:#475569">{zweck}</td>'
|
|
f'<td style="padding:4px 8px">{drittland_str}</td>'
|
|
f'<td style="padding:4px 8px;color:#475569">{rg_short}</td>'
|
|
f'</tr>'
|
|
)
|
|
|
|
|
|
def _category_label(kat: str) -> str:
|
|
return {
|
|
"necessary": "Notwendig",
|
|
"functional": "Funktional",
|
|
"statistics": "Statistik",
|
|
"marketing": "Marketing",
|
|
}.get(kat, kat or "—")
|