feat: ingest site videos through raw pipeline

src/vk_parser_app/source_adapters.py

@@ -55,6 +55,13 @@ def validate_source_config(platform: str, config: dict[str, Any]) -> None:
         raise ValueError("max_items должен быть целым числом") from exc
     if not 1 <= max_items <= 100:
         raise ValueError("max_items должен быть от 1 до 100")
+    follow_links = config.get("follow_links", False)
+    if not isinstance(follow_links, bool):
+        raise ValueError("follow_links должен быть true или false")
+    if follow_links and not str(config.get("content_selector") or "").strip():
+        raise ValueError("При follow_links=true нужен content_selector")
+
+
 def _posted_at(value: Any) -> datetime:
     try:
         parsed = datetime.fromisoformat(str(value).replace("Z", "+00:00"))
@@ -111,7 +118,11 @@ class SiteParserClient:
         for raw in data.get("items") or []:
             title = str(raw.get("title") or "").strip()
             body = str(raw.get("text") or "").strip()
-            text = "\n\n".join(part for part in (title, body) if part)
+            body_starts_with_title = title and (
+                body.casefold() == title.casefold()
+                or body.casefold().startswith(f"{title}\n".casefold())
+            )
+            text = body if body_starts_with_title else "\n\n".join(part for part in (title, body) if part)
             url = str(raw.get("url") or source["url"]).strip()
             external_id = str(raw.get("external_id") or url).strip()
             if not external_id: