From 0ab31c3fdbd56652ed306e60109301f60e8042d3 Mon Sep 17 00:00:00 2001
From: VinciGit00 <mvincig11@gmail.com>
Date: Thu, 9 May 2024 21:07:07 +0200
Subject: [PATCH] fix: add json integration

---
 scrapegraphai/graphs/json_scraper_graph.py |  4 ++--
 scrapegraphai/nodes/fetch_node.py          | 10 ++++++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/scrapegraphai/graphs/json_scraper_graph.py b/scrapegraphai/graphs/json_scraper_graph.py
index aec41195..dc341eae 100644
--- a/scrapegraphai/graphs/json_scraper_graph.py
+++ b/scrapegraphai/graphs/json_scraper_graph.py
@@ -54,7 +54,7 @@ class JSONScraperGraph(AbstractGraph):
         """
 
         fetch_node = FetchNode(
-            input="json_dir",
+            input="json",
             output=["doc"],
         )
         parse_node = ParseNode(
@@ -106,4 +106,4 @@ class JSONScraperGraph(AbstractGraph):
         inputs = {"user_prompt": self.prompt, self.input_key: self.source}
         self.final_state, self.execution_info = self.graph.execute(inputs)
 
-        return self.final_state.get("answer", "No answer found.")
\ No newline at end of file
+        return self.final_state.get("answer", "No answer found.")
diff --git a/scrapegraphai/nodes/fetch_node.py b/scrapegraphai/nodes/fetch_node.py
index dfaf8bb6..52266b42 100644
--- a/scrapegraphai/nodes/fetch_node.py
+++ b/scrapegraphai/nodes/fetch_node.py
@@ -2,6 +2,7 @@
 FetchNode Module
 """
 import pandas as pd
+import json
 from typing import List, Optional
 from langchain_community.document_loaders import AsyncChromiumLoader
 from langchain_core.documents import Document
@@ -75,8 +76,13 @@ class FetchNode(BaseNode):
             compressed_document = loader.load()
 
         elif self.input == "csv":
-            compressed_document = [Document(page_content=pd.read_csv(source), metadata={
-                "source": "xml"
+            compressed_document = [Document(page_content=str(pd.read_csv(source)), metadata={
+                "source": "csv"
+            })]
+        elif self.input == "json":
+            f = open(source)
+            compressed_document = [Document(page_content=str(json.load(f)), metadata={
+                "source": "json"
             })]
         elif self.input == "xml":
             with open(source, 'r', encoding='utf-8') as f: