make output nicer

etl/pdfReader/sitenotes.py

@@ -201,7 +201,6 @@ class QuidosSiteNotesExtractor(SiteNotesExtractor):
         door = self.get_door()
 
         windows = self.get_windows()
-        print(windows["main_property"])
 
         # Section 12
         ventilationAndCooling = self.get_ventilation_and_cooling()

etl/scraper/scraper.py

@@ -216,6 +216,7 @@ class SharePointScraper():
                                         if any(file["name"].endswith(ext) for ext in only_pdf):
                                             file_names_to_download.update({file["name"]: file['@microsoft.graph.downloadUrl']})
                                 for file_name, url in file_names_to_download.items():
+                                    print(pformat(file_names_to_download))
                                     content = self.get_file_content(url)
                                     path = self.create_temp_file(content, f"{name}/{WEEK_COMMENCING}/{house_ass}/{address}/{file_name}")
                                     if DomnaSharePointValidator.is_quidos_presite(path):
@@ -224,6 +225,7 @@ class SharePointScraper():
                                         else:
                                             self.surveyor_work_completed.update({name: 1})
                                         break
+                                    print("trololol")
 
         return self.surveyor_work_completed
 

etl/validator/validator.py

@@ -13,6 +13,8 @@ class DomnaSharePointValidator():
     def __init__(self):
         self.logger = Logger(name='DomnaSharePointValidator', level=logging.DEBUG).get_logger()
 
+    
+    @staticmethod
     def valid_dates(list_of_dates_to_check):
         # Patten Nic wants: W.C. DD.MM.YYYY
         # TODO: Ideally split the date and W.C. and use a datatime library so its more standardised
@@ -23,14 +25,15 @@ class DomnaSharePointValidator():
             if not re.match(pattern, date):
                 return False
         return True
-    
+
+    @staticmethod   
     def is_quidos_presite(file_path):
         file = pdfReaderToText(file_path)
         type = file.get_file_type()
-        print(type)
         return type == ReportType.QUIDOS_PRESITE_NOTE
 
 
+    @staticmethod
     def valid_social_housing_associations(list_):
         """
         Nic gave me a list of housing association names, will most likely use in future so leaving it here