survery data processor

etl/pdfReader/pdfReaderToText.py

@@ -31,10 +31,9 @@ class pdfReaderToText():
         if len(self.text_list) > 1:
             if  "Quidos Ltd using Argyle software BRE approved calculator".lower() in self.text_list[0].lower():
                 self.type = ReportType.QUIDOS_PRESITE_NOTE
-                return self.type
             else:
-                return None
-                # raise NotImplementedError("New type of file - please contact Jun-te Kim")
+                pass
+            return self.type
     
     def get_reader(self):
         self.get_file_type()

etl/scis_invoice.py

@@ -1,5 +1,7 @@
 from etl.scraper.scraper import SharePointScraper, SharePointInstaller
 from pprint import pformat
+from etl.pdfReader.pdfReaderToText import pdfReaderToText
+from etl.surveyedData.surveryedData import surveyedDataProcessor
 
 
 def get_type_of_file(path):
@@ -9,12 +11,8 @@ def main():
     south_coast_scraper = SharePointScraper(SharePointInstaller.SOUTH_COAST_INSULATION, development=True)
     file_paths = south_coast_scraper.download_file_for_each_address()
 
-    print(pformat(file_paths))
-
     for eachAddress in file_paths:
-        print(eachAddress)
-
-    # Download presite notes and add it to pdf reader class
+            survey = surveyedDataProcessor(eachAddress)
 
 
 if __name__ == "__main__":

etl/scraper/scraper.py

@@ -243,9 +243,9 @@ class SharePointScraper():
                             if 'file' not in address:
                                 # Only directories
                                 allAddress.append(address['name'])
-                        address_paths = {} 
-                        for address in allAddress:
+                        for i, address in enumerate(allAddress):
                             path = f"/{name}/{WEEK_COMMENCING}/{house_ass}/{address}"
+                            address_paths = {} 
                             files_to_download_sharepoint_info  = self.get_folders_in_path(path)
                             if 'value' not in files_to_download_sharepoint_info:
                                 raise RuntimeError("Failed to get files to download")

etl/surveyedData/surveryedData.py

@@ -0,0 +1,6 @@
+class surveyedDataProcessor():
+    def __init__(self, address_to_files):
+        for key, value in address_to_files.items():
+            self.address = key
+            self.files = value
+            print(f"Address is {self.address}, with all files at location {self.files}")