feat: add new search engine avaiability and new tests

Author: VinciGit00

examples/single_node/search_internet_node.py

@@ -0,0 +1,50 @@
+"""
+Example of custom graph using existing nodes
+"""
+
+from scrapegraphai.models import Ollama
+from scrapegraphai.nodes import SearchInternetNode
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+graph_config = {
+    "llm": {
+        "model": "llama3",
+        "temperature": 0,
+        "streaming": True
+    },
+    "search_engine": "google",
+    "max_results": 3,
+    "verbose": True
+}
+
+# ************************************************
+# Define the node
+# ************************************************
+
+llm_model = Ollama(graph_config["llm"])
+
+search_node = SearchInternetNode(
+    input="user_input",
+    output=["search_results"],
+    node_config={
+        "llm_model": llm_model,
+        "search_engine": graph_config["search_engine"],
+        "max_results": graph_config["max_results"],
+        "verbose": graph_config["verbose"]
+    }
+)
+
+# ************************************************
+# Test the node
+# ************************************************
+
+state = {
+    "user_input": "What is the capital of France?"
+}
+
+result = search_node.execute(state)
+
+print(result)

scrapegraphai/nodes/search_internet_node.py

@@ -43,6 +43,7 @@ def __init__(
         self.verbose = (
             False if node_config is None else node_config.get("verbose", False)
         )
+        self.search_engine = node_config.get("search_engine", "google")
         self.max_results = node_config.get("max_results", 3)
 
     def execute(self, state: dict) -> dict:
@@ -97,7 +98,8 @@ def execute(self, state: dict) -> dict:
 
         self.logger.info(f"Search Query: {search_query}")
 
-        answer = search_on_web(query=search_query, max_results=self.max_results)
+        answer = search_on_web(query=search_query, max_results=self.max_results,
+                               search_engine=self.search_engine)
 
         if len(answer) == 0:
             # raise an exception if no answer is found

scrapegraphai/utils/research_web.py

@@ -26,7 +26,8 @@ def search_on_web(query: str, search_engine: str = "Google", max_results: int =
         >>> search_on_web("example query", search_engine="Google", max_results=5)
         ['http://example.com', 'http://example.org', ...]
 
-    This function allows switching between Google and DuckDuckGo to perform internet searches, returning a list of result URLs.
+    This function allows switching between Google and DuckDuckGo to perform 
+    internet searches, returning a list of result URLs.
     """
 
     if search_engine.lower() == "google":

tests/nodes/search_internet_node_test.py

@@ -0,0 +1,58 @@
+import unittest
+from scrapegraphai.models import Ollama
+from scrapegraphai.nodes import SearchInternetNode
+
+class TestSearchInternetNode(unittest.TestCase):
+
+    def setUp(self):
+        # Configuration for the graph
+        self.graph_config = {
+            "llm": {
+                "model": "llama3",
+                "temperature": 0,
+                "streaming": True
+            },
+            "search_engine": "google",
+            "max_results": 3,
+            "verbose": True
+        }
+
+        # Define the model
+        self.llm_model = Ollama(self.graph_config["llm"])
+
+        # Initialize the SearchInternetNode
+        self.search_node = SearchInternetNode(
+            input="user_input",
+            output=["search_results"],
+            node_config={
+                "llm_model": self.llm_model,
+                "search_engine": self.graph_config["search_engine"],
+                "max_results": self.graph_config["max_results"],
+                "verbose": self.graph_config["verbose"]
+            }
+        )
+
+    def test_execute_search_node(self):
+        # Initial state
+        state = {
+            "user_input": "What is the capital of France?"
+        }
+
+        # Expected output
+        expected_output = {
+            "user_input": "What is the capital of France?",
+            "search_results": [
+                "https://en.wikipedia.org/wiki/Paris",
+                "https://en.wikipedia.org/wiki/France",
+                "https://en.wikipedia.org/wiki/%C3%8Ele-de-France"
+            ]
+        }
+
+        # Execute the node
+        result = self.search_node.execute(state)
+
+        # Assert the results
+        self.assertEqual(result, expected_output)
+
+if __name__ == "__main__":
+    unittest.main()