feat: initial implementation of website integrity scanner

Python-Package zur unabhängigen Überwachung statischer Websites gegen
SEO-Spam und unbefugte Manipulationen. Läuft außerhalb des Hosters.

Kernfunktionen:
- Reiner Python-Crawler (bs4+lxml), kein wget
- Baseline-Management mit manuellem Freigabe-Workflow (niemals automatisch)
- Text-/Link-/Meta-Diff mit Risiko-Scoring (grün/gelb/rot)
- Hidden-Content-Erkennung (CSS inline, noscript, Kommentar-Links)
- Whitelist für externe Domains und interne Pfade
- E-Mail + Webhook Alarmierung
- CLI: init, crawl, check, scan, approve, report, status
- 79 Unit-Tests (pytest), alle grün

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/test_baseline.py

@@ -0,0 +1,161 @@
+"""Tests for snapshot saving, baseline management and approval workflow."""
+import json
+import pytest
+from pathlib import Path
+from scanner.baseline import BaselineManager, url_key
+
+
+def _sample_page(url: str, text: str = "Inhalt") -> dict:
+    return {
+        "url": url,
+        "final_url": url,
+        "status": 200,
+        "content_type": "text/html",
+        "response_headers": {},
+        "text": text,
+        "links": {"a": [], "canonical": None, "meta_refresh": []},
+        "metadata": {"title": "T", "h1": [], "h2": []},
+        "hidden_content": [],
+        "inline_scripts": [],
+        "jsonld": [],
+        "comment_links": [],
+    }
+
+
+@pytest.fixture
+def bm(tmp_path: Path) -> BaselineManager:
+    return BaselineManager(tmp_path / "data")
+
+
+class TestUrlKey:
+    def test_deterministic(self):
+        assert url_key("https://example.com/") == url_key("https://example.com/")
+
+    def test_different_urls_different_keys(self):
+        assert url_key("https://a.com/") != url_key("https://b.com/")
+
+    def test_16_hex_chars(self):
+        k = url_key("https://example.com/")
+        assert len(k) == 16
+        assert all(c in "0123456789abcdef" for c in k)
+
+
+class TestSaveSnapshot:
+    def test_creates_manifest(self, bm, tmp_path):
+        pages = [_sample_page("https://b.info/")]
+        snap_dir = bm.save_snapshot(pages)
+        assert (snap_dir / "manifest.json").exists()
+
+    def test_manifest_content(self, bm):
+        pages = [_sample_page("https://b.info/"), _sample_page("https://b.info/p/")]
+        snap_dir = bm.save_snapshot(pages)
+        manifest = json.loads((snap_dir / "manifest.json").read_text())
+        assert manifest["page_count"] == 2
+        assert "https://b.info/" in manifest["urls"]
+
+    def test_creates_page_files(self, bm):
+        pages = [_sample_page("https://b.info/")]
+        snap_dir = bm.save_snapshot(pages)
+        page_files = list((snap_dir / "pages").glob("*.json"))
+        assert len(page_files) == 1
+
+    def test_latest_snapshot_dir(self, bm):
+        assert bm.latest_snapshot_dir() is None
+        bm.save_snapshot([_sample_page("https://b.info/")])
+        assert bm.latest_snapshot_dir() is not None
+
+
+class TestLoadSnapshot:
+    def test_loads_saved_snapshot(self, bm):
+        pages = [_sample_page("https://b.info/"), _sample_page("https://b.info/p/")]
+        bm.save_snapshot(pages)
+        snap = bm.load_snapshot()
+        assert "https://b.info/" in snap["pages"]
+        assert "https://b.info/p/" in snap["pages"]
+
+    def test_returns_empty_when_no_snapshot(self, bm):
+        result = bm.load_snapshot()
+        assert result == {}
+
+
+class TestBaselineExists:
+    def test_false_before_approve(self, bm):
+        assert not bm.baseline_exists()
+
+    def test_true_after_approve(self, bm):
+        bm.save_snapshot([_sample_page("https://b.info/")])
+        bm.approve_all(note="test")
+        assert bm.baseline_exists()
+
+
+class TestApproveAll:
+    def test_approve_all_creates_baseline(self, bm):
+        pages = [_sample_page("https://b.info/"), _sample_page("https://b.info/p/")]
+        bm.save_snapshot(pages)
+        approved = bm.approve_all(note="Initial baseline")
+        assert "https://b.info/" in approved
+        assert "https://b.info/p/" in approved
+        assert bm.baseline_exists()
+
+    def test_manifest_contains_approval_metadata(self, bm):
+        bm.save_snapshot([_sample_page("https://b.info/")])
+        bm.approve_all(note="test note", approved_by="testuser")
+        manifest = json.loads((bm.baseline_dir / "manifest.json").read_text())
+        assert manifest["note"] == "test note"
+        assert manifest["approved_by"] == "testuser"
+        assert "approved_at" in manifest
+
+    def test_approve_all_raises_without_snapshot(self, bm):
+        with pytest.raises(RuntimeError):
+            bm.approve_all()
+
+
+class TestApproveUrl:
+    def test_approve_single_url(self, bm):
+        pages = [_sample_page("https://b.info/"), _sample_page("https://b.info/p/")]
+        bm.save_snapshot(pages)
+        result = bm.approve_url("https://b.info/")
+        assert result is True
+        assert bm.baseline_exists()
+        baseline = bm.load_baseline()
+        assert "https://b.info/" in baseline["pages"]
+        assert "https://b.info/p/" not in baseline["pages"]
+
+    def test_approve_missing_url_returns_false(self, bm):
+        bm.save_snapshot([_sample_page("https://b.info/")])
+        result = bm.approve_url("https://b.info/does-not-exist/")
+        assert result is False
+
+
+class TestLoadBaseline:
+    def test_loads_approved_pages(self, bm):
+        pages = [_sample_page("https://b.info/", "Text A")]
+        bm.save_snapshot(pages)
+        bm.approve_all()
+        baseline = bm.load_baseline()
+        assert "https://b.info/" in baseline["pages"]
+        assert baseline["pages"]["https://b.info/"]["text"] == "Text A"
+
+    def test_never_auto_updates(self, bm):
+        """Baseline must not change unless approve is explicitly called."""
+        bm.save_snapshot([_sample_page("https://b.info/", "Original")])
+        bm.approve_all()
+
+        # Second snapshot with different content
+        bm.save_snapshot([_sample_page("https://b.info/", "Manipuliert")])
+
+        # Baseline must still contain original content
+        baseline = bm.load_baseline()
+        assert baseline["pages"]["https://b.info/"]["text"] == "Original"
+
+
+class TestRebuildBaseline:
+    def test_rebuild_replaces_baseline(self, bm):
+        bm.save_snapshot([_sample_page("https://b.info/", "Alt")])
+        bm.approve_all()
+
+        bm.save_snapshot([_sample_page("https://b.info/", "Neu")])
+        bm.rebuild_baseline(note="Major update")
+
+        baseline = bm.load_baseline()
+        assert baseline["pages"]["https://b.info/"]["text"] == "Neu"