R11: Validate URL host before network I/O — prevent SSRF

- Add _validate_url_host() to check allowlist before urlopen()
- Validate both original URL and redirect target
- Reject localhost, internal IPs, and non-allowlisted hosts
- Add 2 unit tests for disallowed host rejection
- Prevents SSRF attacks via malicious source URLs

rf4_research/community_cli.py

@@ -93,13 +93,30 @@ def mark_fetch(source: str, *, state_file: Path, now: float | None = None) -> No
     _write_state(state_file, state)
 
 
+def _validate_url_host(url: str) -> str:
+    """Validate URL hostname is in allowlist before making network call."""
+    hostname = (urlsplit(url).hostname or "").lower()
+    if hostname.startswith("www."):
+        hostname = hostname[4:]
+    if not hostname:
+        raise ValueError("URL must include a valid hostname")
+    if hostname not in ALLOWED_HOSTS:
+        raise ValueError(f"URL hostname {hostname} not in allowlist")
+    return hostname
+
+
 def fetch_html(url: str, *, timeout: float = 30) -> str:
+    # Validate host BEFORE network I/O to prevent SSRF to internal endpoints
+    _validate_url_host(url)
     request = Request(url, headers={"User-Agent": USER_AGENT, "Accept": "text/html"})
     with urlopen(request, timeout=timeout) as response:
         final_url = response.url
-        hostname = (urlsplit(final_url).hostname or "").lower()
+        # Also validate redirect target
-        if hostname not in ALLOWED_HOSTS:
+        final_hostname = (urlsplit(final_url).hostname or "").lower()
-            raise ValueError(f"URL hostname {hostname} not in allowlist")
+        if final_hostname.startswith("www."):
+            final_hostname = final_hostname[4:]
+        if final_hostname not in ALLOWED_HOSTS:
+            raise ValueError(f"Redirect hostname {final_hostname} not in allowlist")
         if response.headers.get_content_type() != "text/html":
             raise ValueError(f"expected text/html, got {response.headers.get_content_type()}")
         data = response.read(MAX_RESPONSE_BYTES + 1)

tests/test_community_cli.py

@@ -31,3 +31,29 @@ def test_failed_fetch_still_reserves_site_cooldown(tmp_path: Path, monkeypatch:
     monkeypatch.setattr(community_cli, "fetch_html", fail)
     assert community_cli.main(["rf4db", "--state-file", str(state_file)]) == 1
     assert "download.rf4db.com" in json.loads(state_file.read_text(encoding="utf-8"))
+
+
+def test_validate_url_host_rejects_disallowed_hosts() -> None:
+    from rf4_research.community_cli import _validate_url_host
+
+    # Allowed hosts pass
+    assert _validate_url_host("https://download.rf4db.com/ru/catches") == "download.rf4db.com"
+    assert _validate_url_host("https://www.rf4-stat.ru/posts/") == "rf4-stat.ru"
+    assert _validate_url_host("https://rf4map.ru/point/123") == "rf4map.ru"
+
+    # Disallowed hosts raise ValueError before network I/O
+    with pytest.raises(ValueError, match="not in allowlist"):
+        _validate_url_host("http://localhost:8080/admin")
+    with pytest.raises(ValueError, match="not in allowlist"):
+        _validate_url_host("http://169.254.169.254/latest/meta-data/")
+    with pytest.raises(ValueError, match="not in allowlist"):
+        _validate_url_host("http://internal-service.corp/api")
+
+
+def test_validate_url_host_rejects_missing_hostname() -> None:
+    from rf4_research.community_cli import _validate_url_host
+
+    with pytest.raises(ValueError, match="valid hostname"):
+        _validate_url_host("not-a-valid-url")
+    with pytest.raises(ValueError, match="valid hostname"):
+        _validate_url_host("")