Added parse_html option in parse_node

Author: epage480

scrapegraphai/nodes/parse_node.py

@@ -30,6 +30,7 @@ def __init__(self, input: str, output: List[str], node_config: dict, node_name:
         super().__init__(node_name, "node", input, output, 1, node_config)
 
         self.verbose = True if node_config is None else node_config.get("verbose", False)
+        self.parse_html = True if node_config is None else node_config.get("parse_html", True)
 
     def execute(self,  state: dict) -> dict:
         """
@@ -62,8 +63,11 @@ def execute(self,  state: dict) -> dict:
         )
 
         # Parse the document
-        docs_transformed = Html2TextTransformer(
-        ).transform_documents(input_data[0])[0]
+        docs_transformed = input_data[0]
+        if self.parse_html:
+            docs_transformed = Html2TextTransformer(
+            ).transform_documents(input_data[0])
+        docs_transformed = docs_transformed[0]
 
         chunks = text_splitter.split_text(docs_transformed.page_content)