require url

tool.py

@@ -223,6 +223,12 @@ class BrightDataDatasetTool(Tool):
                 return self._ensure_scheme(raw)
 
         if isinstance(raw, dict):
+            file_path = raw.get("path")
+            if isinstance(file_path, str) and os.path.isfile(file_path):
+                text = self._read_text_file(file_path)
+                if text:
+                    return self._ensure_scheme(text)
+
             orig_name = raw.get("orig_name")
             if (
                 isinstance(orig_name, str)
@@ -237,14 +243,9 @@ class BrightDataDatasetTool(Tool):
                     return url_value
                 if url_value.startswith("/gradio_api/file="):
                     file_path = url_value.split("=", 1)[-1]
-                    if os.path.isfile(file_path):
-                        try:
-                            with open(file_path, "r", encoding="utf-8", errors="ignore") as fh:
-                                text = fh.read().strip()
-                                if text and not text.lstrip().startswith("<"):
-                                    return self._ensure_scheme(text)
-                        except OSError:
-                            pass
+                    text = self._read_text_file(file_path)
+                    if text:
+                        return self._ensure_scheme(text)
                 return None
 
         return None
@@ -261,6 +262,19 @@ class BrightDataDatasetTool(Tool):
         except (ValueError, SyntaxError):
             return None
 
+    def _read_text_file(self, path: str) -> Optional[str]:
+        if not os.path.isfile(path):
+            return None
+        try:
+            with open(path, "r", encoding="utf-8", errors="ignore") as fh:
+                for line in fh:
+                    text = line.strip()
+                    if text and not text.startswith("<"):
+                        return text
+        except OSError:
+            return None
+        return None
+
     def _get_gradio_app_code(self, tool_module_name: str = "tool") -> str:
         choices = sorted(self.datasets.keys())
         dataset_fields = {key: value["inputs"] for key, value in self.datasets.items()}