feat: ingest site videos through raw pipeline

tests/test_source_adapters.py

@@ -28,11 +28,23 @@ class FakeResponse:
         }
 
 
+class FollowedPageResponse(FakeResponse):
+    async def json(self, **_kwargs):
+        data = await super().json(**_kwargs)
+        data["items"][0]["text"] = "Title\nAuthor"
+        return data
+
+
 class FakeSession:
     def post(self, *_args, **_kwargs):
         return FakeResponse()
 
 
+class FollowedPageSession(FakeSession):
+    def post(self, *_args, **_kwargs):
+        return FollowedPageResponse()
+
+
 class SourceAdapterTests(unittest.IsolatedAsyncioTestCase):
     async def test_worker_response_is_normalized(self) -> None:
         client = SiteParserClient(FakeSession(), "http://worker", "token", "captcha", 30)
@@ -46,10 +58,23 @@ class SourceAdapterTests(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(items[0].media[0].url, "https://example.test/1.jpg")
         self.assertEqual(state["browser_state"]["cookies"][0]["name"], "cf_clearance")
 
+    async def test_followed_page_does_not_repeat_title(self) -> None:
+        client = SiteParserClient(FollowedPageSession(), "http://worker", "token", "captcha", 30)
+        items, _ = await client.fetch({
+            "url": "https://example.test/rss.xml",
+            "settings_json": '{"format":"rss","follow_links":true,"content_selector":"article.full"}',
+            "runtime_state_json": "{}",
+        })
+        self.assertEqual(items[0].text, "Title\nAuthor")
+
     def test_site_config_is_required(self) -> None:
         with self.assertRaisesRegex(ValueError, "нужен конфиг"):
             validate_source_config("site", {})
 
+    def test_follow_links_requires_selector(self) -> None:
+        with self.assertRaisesRegex(ValueError, "content_selector"):
+            validate_source_config("site", {"format": "rss", "follow_links": True})
+
 
 if __name__ == "__main__":
     unittest.main()