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 +1,53 @@
+"""TrustArc / TRUSTe CMP.
+
+URLs:
+  - consent.trustarc.com/v2/notice/<id>
+  - cookie-pref.trustarc.com/...
+Schema varies; typically categories[] + vendors[]
+"""
+
+import re
+
+MATCHER = re.compile(
+    r"(?:consent|cookie-pref|tr-cdn)\.trustarc\.com/.+\.(?:json|js)(?:\?|$)", re.I,
+)
+
+
+def reconstruct(d: dict) -> str:
+    parts: list[str] = ["# Cookie-Richtlinie (TrustArc)"]
+
+    for key in ("title", "summary", "description", "intro"):
+        v = d.get(key)
+        if v:
+            parts.append("")
+            parts.append(str(v))
+
+    cats = d.get("categories") or d.get("Categories") or []
+    for c in cats:
+        name = c.get("name") or c.get("Name") or ""
+        desc = c.get("description") or c.get("Description") or ""
+        parts.append("")
+        parts.append(f"## {name}")
+        if desc:
+            parts.append(str(desc))
+        cookies = c.get("cookies") or c.get("Cookies") or []
+        for ck in cookies[:50]:
+            cn = ck.get("name") or ck.get("Name") or ""
+            cp = ck.get("purpose") or ck.get("Purpose") or ""
+            ce = ck.get("expires") or ck.get("Expires") or ""
+            line = f"- {cn}"
+            if cp:
+                line += f" — {cp[:120]}"
+            if ce:
+                line += f" — Speicherdauer: {ce}"
+            parts.append(line)
+
+    vendors = d.get("vendors") or d.get("Vendors") or []
+    if vendors:
+        parts.append("")
+        parts.append(f"## Anbieter ({len(vendors)})")
+        for v in vendors[:80]:
+            name = v.get("name") or v.get("Name") or ""
+            parts.append(f"- {name}")
+
+    return "\n".join(parts)