feat: filter site bodies before media upload

src/vk_parser_app/source_adapters.py

@@ -37,6 +37,10 @@ class SourceItem:
     media: list[SourceMedia] = field(default_factory=list)
     raw: dict[str, Any] = field(default_factory=dict)
 
+    @property
+    def body_text(self) -> str:
+        return str(self.raw.get("text") or "").strip()
+
 
 def validate_source_config(platform: str, config: dict[str, Any]) -> None:
     if platform == PLATFORM_VK:
@@ -60,6 +64,12 @@ def validate_source_config(platform: str, config: dict[str, Any]) -> None:
         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")
+    try:
+        min_text_length = int(config.get("min_text_length", 0))
+    except (TypeError, ValueError) as exc:
+        raise ValueError("min_text_length должен быть целым числом") from exc
+    if not 0 <= min_text_length <= 100_000:
+        raise ValueError("min_text_length должен быть от 0 до 100000")
 
 
 def _posted_at(value: Any) -> datetime: