modify fetch node with no cut mode

Author: VinciGit00

examples/extras/no_cut.py

@@ -0,0 +1,43 @@
+""" 
+This example shows how to do not process the html code in the fetch phase
+"""
+
+import os, json
+from scrapegraphai.graphs import SmartScraperGraph
+from scrapegraphai.utils import prettify_exec_info
+
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+
+graph_config = {
+    "llm": {
+        "api_key": "s",
+        "model": "gpt-3.5-turbo",
+    },
+    "cut": False,
+    "verbose": True,
+    "headless": False,
+}
+
+# ************************************************
+# Create the SmartScraperGraph instance and run it
+# ************************************************
+
+smart_scraper_graph = SmartScraperGraph(
+    prompt="Extract me the python code inside the page",
+    source="https://www.exploit-db.com/exploits/51447",
+    config=graph_config
+)
+
+result = smart_scraper_graph.run()
+print(json.dumps(result, indent=4))
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = smart_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))

scrapegraphai/graphs/smart_scraper_graph.py

@@ -66,6 +66,8 @@ def _create_graph(self) -> BaseGraph:
             output=["doc", "link_urls", "img_urls"],
             node_config={
                 "llm_model": self.llm_model,
+                "force": self.config.get("force", False),
+                "cut": self.config.get("cut", True),
                 "loader_kwargs": self.config.get("loader_kwargs", {}),
             }
         )

scrapegraphai/nodes/fetch_node.py

@@ -71,6 +71,10 @@ def __init__(
             False if node_config is None else node_config.get("script_creator", False)
         )
 
+        self.cut = (
+            False if node_config is None else node_config.get("cut", True)
+        )
+
     def execute(self, state):
         """
         Executes the node's logic to fetch HTML content from a specified URL and
@@ -105,7 +109,7 @@ def execute(self, state):
             compressed_document = [
                 source
             ]
-  
+
             state.update({self.output[0]: compressed_document})
             return state
         # handling pdf
@@ -165,10 +169,13 @@ def execute(self, state):
             if response.status_code == 200:
                 if not response.text.strip():
                     raise ValueError("No HTML body content found in the response.")
+                
+                parsed_content = response
+   
+                if not self.cut:
+                    parsed_content = cleanup_html(response, source)
 
-                parsed_content = cleanup_html(response, source)
-
-                if  isinstance(self.llm_model, OpenAI) and not self.script_creator or self.force and not self.script_creator and not:
+                if  (isinstance(self.llm_model, OpenAI) and not self.script_creator) or (self.force and not self.script_creator):
                     parsed_content = convert_to_md(source)
                 compressed_document = [Document(page_content=parsed_content)]
             else: