added validation for content type

omniread/html/scraper.py

@@ -25,6 +25,21 @@ class HTMLScraper(BaseScraper):
             headers=headers,
             follow_redirects=follow_redirects,
         )
+        self.content_type = ContentType.HTML
+
+    def validate_content_type(
+        self,
+        response: httpx.Response,
+    ):
+        raw_ct = response.headers.get("Content-Type")
+        if not raw_ct:
+            raise ValueError("Missing Content-Type header")
+
+        base_ct = raw_ct.split(";", 1)[0].strip().lower()
+        if base_ct != self.content_type.value:
+            raise ValueError(
+                f"Expected HTML content, got '{raw_ct}'"
+            )
 
     def fetch(
         self,
@@ -34,11 +49,12 @@ class HTMLScraper(BaseScraper):
     ) -> Content:
         response = self._client.get(source)
         response.raise_for_status()
+        self.validate_content_type(response)
 
         return Content(
             raw=response.content,
             source=source,
-            content_type=ContentType.HTML,
+            content_type=self.content_type,
             metadata={
                 "status_code": response.status_code,
                 "headers": dict(response.headers),