fix(subscribestar): match gallery-dl's generic post delimiter (live-feed drift)

The native client split the feed on `<div class="post is-shown`, but `is-shown` is added by SubscribeStar's infinite-scroll JS when a post scrolls into view — present in a browser-SAVED page (what the Step-0 characterization used) but ABSENT from the raw server HTML we and gallery-dl actually fetch. So the live feed (cheunart) parsed to zero posts and raised a false SubscribeStarDriftError. Align with gallery-dl's proven `_pagination`: split on the generic `<div class="post ` (trailing space rules out the hyphenated post-content/ post-date/post-body siblings). Also mirror gallery-dl's redirect-based gating detection (/verify_subscriber, /age_confirmation_warning => auth, not drift). Regression tests: raw server markup without is-shown now parses; an age-wall redirect raises SubscribeStarAuthError. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-17 15:04:05 -04:00
parent 9201b7b539
commit 204d341a99
2 changed files with 73 additions and 1 deletions
@@ -127,6 +127,56 @@ def test_iter_posts_parses_and_paginates(monkeypatch):
    assert out[0][0]["_base"] == "https://subscribestar.adult"


+def test_iter_posts_parses_raw_server_html_without_is_shown(monkeypatch):
+    # Regression (cheunart, 2026-06-17): the RAW server HTML opens posts as
+    # `<div class="post ...">` WITHOUT the `is-shown` class — that class is added
+    # by SubscribeStar's infinite-scroll JS when a post scrolls into view, so it's
+    # present in a browser-SAVED page but absent from the feed we actually fetch.
+    # The delimiter must match the generic `<div class="post ` (gallery-dl parity),
+    # else the live feed parses to zero posts → false drift.
+    client = SubscribeStarClient(None)
+    raw_post = (
+        '<div class="post for-subscribers" data-id="555" '
+        'data-infinite-scroll-id="555">'
+        '<div class="post-date">May 01, 2026 12:00 pm</div>'
+        '<div class="post-body" data-role="post-body">'
+        '<div class="post-content" data-role="post_content-text">'
+        '<div class="trix-content"><p>raw</p></div></div></div></div>'
+    )
+    page = (
+        '<html><body><div data-role="posts_container-list">'
+        f'{raw_post}</div></body></html>'
+    )
+    monkeypatch.setattr(client, "_feed_html", lambda url: page)
+    out = list(client.iter_posts("https://subscribestar.adult/x"))
+    assert [p["id"] for p, _inc, _cur in out] == ["555"]
+
+
+def test_redirect_to_age_wall_is_auth_error():
+    # gallery-dl parity: SubscribeStar redirects an unauthenticated / age-
+    # unconfirmed request to /age_confirmation_warning (or /verify_subscriber).
+    # That's auth, not drift — rotate cookies / set the age cookie.
+    client = SubscribeStarClient(None)
+
+    class _Resp:
+        status_code = 200
+        url = "https://subscribestar.adult/age_confirmation_warning"
+        history = [object()]
+        text = ""
+        headers: dict = {}
+
+    class _Session:
+        def get(self, url, timeout=None, headers=None):
+            return _Resp()
+
+    client._session = _Session()
+    try:
+        client._get("https://subscribestar.adult/x")
+    except SubscribeStarAuthError:
+        return
+    raise AssertionError("expected SubscribeStarAuthError")
+
+
 def test_iter_posts_drift_when_no_container(monkeypatch):
    client = SubscribeStarClient(None)
    monkeypatch.setattr(client, "_feed_html", lambda url: "<html>nothing</html>")