From 7f0c5ce8d366417fb59921c7edcb5d0f8742ea5d Mon Sep 17 00:00:00 2001
From: Christian Risi <75698846+CnF-Gris@users.noreply.github.com>
Date: Thu, 18 Sep 2025 17:23:56 +0200
Subject: [PATCH] Updated File for fetching

---
 Script/fetchdata.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/Script/fetchdata.py b/Script/fetchdata.py
index 7573751..e1cbf7a 100644
--- a/Script/fetchdata.py
+++ b/Script/fetchdata.py
@@ -1,3 +1,4 @@
+from math import floor
 from time import sleep
 import SPARQLWrapper
 import requests
@@ -8,9 +9,11 @@ TYPE = SPARQLWrapper.CSV
 TIMEOUT_SECONDS = 1.5
 LIMIT = int(1E4)
 OFFSET = LIMIT
-INITIAL_OFFSET = 0
+INITIAL_OFFSET =  15200000
 MAX_PAGES = int(1E9)
 
+# Missing page 13220000
+
 FILE_URI = "./Assets/Dataset/1-hop/dataset.csv"
 
 QUERY = """
@@ -35,13 +38,13 @@ WHERE {
 def main():
 
     exit = False
-    page = INITIAL_OFFSET
+    page = int(floor(INITIAL_OFFSET / LIMIT)) -1
 
     while not exit:
 
         print(f"Starting to get page {page}")
 
-        CURRENT_OFFSET = OFFSET * page
+        CURRENT_OFFSET = int(OFFSET + (page * LIMIT))
         sparql = SPARQLWrapper.SPARQLWrapper(BASE_URL)
 
         sparql.setReturnFormat(TYPE)