feat(consent-tester): Phase B — named CMP library + plugin architecture

cmp_extractor.py refactored to thin coordinator (123 LOC, was 223). Discovers all CMP modules via cmp_library/_registry.py:load_all() at import time. Restart consent-tester to pick up new modules. New cmp_library/ folder: - _registry.py: auto-discovers all modules with MATCHER + reconstruct() - epaas.py: BMW Group ePaaS (extracted from cmp_extractor) - onetrust.py: cdn.cookielaw.org Groups/Cookies schema - cookiebot.py: consent.cookiebot.com Categories schema - usercentrics.py: api.usercentrics.eu services schema - didomi.py: sdk.privacy-center.org notice + vendors + purposes - trustarc.py: consent.trustarc.com categories + vendors Each module: - MATCHER: re.Pattern matching the CMP JSON endpoint URL - reconstruct(d: dict) -> str: builds German Markdown cookie-policy text Phase E (self-improving) will write auto_*.py files into the same folder; _registry already picks those up via pkgutil.iter_modules.
2026-05-16 22:59:48 +02:00
parent 4f19310130
commit 7e426c31f1
9 changed files with 427 additions and 144 deletions
@@ -0,0 +1,52 @@
+"""Usercentrics CMP.
+
+URLs:
+  - api.usercentrics.eu/settings/<id>/<lang>.json
+  - app.usercentrics.eu/api/...
+Schema: services[] with dataProcessor, dataPurpose, cookieMaxAgeSeconds
+"""
+
+import re
+
+MATCHER = re.compile(r"(?:api|app)\.usercentrics\.eu/.+\.json(?:\?|$)", re.I)
+
+
+def reconstruct(d: dict) -> str:
+    parts: list[str] = ["# Cookie-Richtlinie (Usercentrics)"]
+
+    services = d.get("services") or d.get("dataProcessingServices") or []
+    if not services and isinstance(d.get("settings"), dict):
+        services = d["settings"].get("services") or []
+
+    for s in services:
+        name = s.get("name") or s.get("dataProcessor") or ""
+        purpose = s.get("dataPurpose") or s.get("purpose") or ""
+        desc = s.get("description") or ""
+        country = s.get("processingCompanyCountry") or s.get("country") or ""
+        max_age = s.get("cookieMaxAgeSeconds")
+        retention = s.get("retentionPeriodDescription") or ""
+
+        parts.append("")
+        parts.append(f"## {name}")
+        if desc:
+            parts.append(desc)
+        if purpose:
+            parts.append(f"Zweck: {purpose}")
+        if country:
+            parts.append(f"Sitz: {country}")
+        if max_age:
+            days = max_age // 86400 if isinstance(max_age, int) else max_age
+            parts.append(f"Speicherdauer: {days} Tage")
+        if retention:
+            parts.append(f"Aufbewahrung: {retention}")
+
+    categories = d.get("categories") or []
+    for c in categories:
+        name = c.get("name") or ""
+        desc = c.get("description") or ""
+        parts.append("")
+        parts.append(f"## Kategorie: {name}")
+        if desc:
+            parts.append(desc)
+
+    return "\n".join(parts)