load db to hubspot

etl/db/load.py

@@ -1,12 +1,43 @@
 from etl.hubSpotClient.hubspot import HubSpotClient, DealStage
 from etl.surveyPrice.surveyPrice import SurveyPrice
+from etl.surveyedData.surveryedData import surveyedDataProcessor
+from urllib.parse import unquote
+
 
 class HubspotTodb():
     def __init__(self):
         self.hubspot = HubSpotClient()
         self.deals_in_hubspot = None
+        self.data_in_sharepoint = []
 
     def get_all_deals(self):
         sp = SurveyPrice()
         self.deals_in_hubspot = sp.get_all_surveys_from_hubspot()
         return self.deals_in_hubspot
+    
+    def get_sharepoint_path(self, url):
+        url_parts = url.split('/')
+        # Find the index of 'Forms'
+        forms_index = url_parts.index('Forms')
+        # Get the part after 'Forms'
+        after_forms = url_parts[forms_index + 1]
+        
+        # Find 'id=' and extract after it
+        if 'id=' in after_forms:
+            id_part = after_forms.split('id=')[1]
+            # Only keep the path before '&' (to ignore other parameters)
+            id_path = id_part.split('&')[0]
+            # Decode the path
+            decoded_path = unquote(id_path)
+            # Now, remove the leading '/sites/xxx/Shared Documents/' part
+            parts = decoded_path.split('Shared Documents')
+            if len(parts) > 1:
+                final_path = parts[1].strip('/')
+                return final_path
+            else:
+                return decoded_path.strip('/')
+
+    def gather_data_from_each_sharepoint(self):
+        self.get_all_deals()
+        for _, row in self.deals_in_hubspot.iterrows():
+            print(self.get_sharepoint_path(row["HUBSPOT_SHAREPOINT_PATH"]))

etl/hubspot_to_db.py

@@ -10,4 +10,4 @@ from etl.db.load import HubspotTodb
 
 dbLoader = HubspotTodb()
 
-dbLoader.get_all_deals()
+dbLoader.gather_data_from_each_sharepoint()