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 +1,46 @@
+"""Cookiebot (by Usercentrics A/S — separate product from Usercentrics CMP).
+
+URLs (multiple shapes observed):
+  - consent.cookiebot.com/<id>/cc.js     (JSONP-wrapped)
+  - consent.cookiebot.com/uc.js?...      (JSONP)
+  - consent.cookiebot.com/<id>/cd.js     (cookie declaration)
+We accept any URL on consent.cookiebot.com that returns JSON-like data.
+The capture pipeline JSON-decodes; if it's JSONP we'd need to strip the
+callback wrapper. For now we match only direct JSON responses.
+
+Schema (cookiedeclaration JSON):
+  Categories: list with name + cookies (each with name, vendor, expires)
+"""
+
+import re
+
+MATCHER = re.compile(r"consent\.cookiebot\.com/.*\.(?:json|js)(?:\?|$)", re.I)
+
+
+def reconstruct(d: dict) -> str:
+    parts: list[str] = ["# Cookie-Richtlinie (Cookiebot)"]
+
+    cats = d.get("Categories") or d.get("categories") or []
+    for cat in cats:
+        name = cat.get("Name") or cat.get("name") or ""
+        desc = cat.get("Description") or cat.get("description") or ""
+        parts.append("")
+        parts.append(f"## {name}")
+        if desc:
+            parts.append(desc)
+        cookies = cat.get("Cookies") or cat.get("cookies") or []
+        for c in cookies[:50]:
+            cn = c.get("Name") or c.get("name") or ""
+            vendor = c.get("Vendor") or c.get("vendor") or ""
+            expires = c.get("Expires") or c.get("expires") or ""
+            purpose = c.get("Purpose") or c.get("purpose") or ""
+            line = f"- {cn}"
+            if vendor:
+                line += f" ({vendor})"
+            if purpose:
+                line += f" — {purpose[:120]}"
+            if expires:
+                line += f" — Speicherdauer: {expires}"
+            parts.append(line)
+
+    return "\n".join(parts)