Fix: str not int cast for ESP id downloader.

Author: diamant-x

source/data/interim/esp_PfdParserToCsvInterim.py

@@ -21,7 +21,7 @@
 
 #%% Import metadata to use
 dfMetadataAll = pd.read_csv(metadataFile, sep=";", header=0, dtype={"area":str})
-dfMetadataAll["CoreFileName"] = dfMetadataAll["File"].str.replace(startFileName,"").str.replace(endFileName,"")
+dfMetadataAll["CoreFileName"] = dfMetadataAll["File"].str.replace(startFileName,"").str.replace(endFileName,"").astype('int32')
 rawFiles = glob.glob(os.path.join(pathInputFile, startFileName+"*"+endFileName))
 
 #%% Process Data Structure
@@ -41,7 +41,7 @@
 
     if dfMetadata.size == 0:
         #Try to find the previous file metadata identified and apply same settings, if none, then skip file.
-        coreFileName = fileName.replace(startFileName,"").replace(endFileName,"")
+        coreFileName = int(fileName.replace(startFileName,"").replace(endFileName,""))
         if coreFileName < dfMetadataAll["CoreFileName"].min():
             print("Skipping file due to no metadata defined.")
             continue

source/data/raw/esp_PfdDownloader.py

@@ -31,14 +31,15 @@
 
 countFiles = 0
 
-for fileId in range(numberOfDays+1): #We assume 360 reports maximum may be issued.
+for fileId in range(numberOfDays+1): 
     #Get official file name to store it.
     fileName = startFileName+str(fileId+31)+endFileName
 
     if "Error 404" in requests.get(rootURL+fileName, verify = False).text:
+        print("Error File not Found:\t"+ fileName)
         continue
     else:
-        print("Downloading file "+fileName)
+        print("Downloading file:\t"+fileName)
         # https://stackoverflow.com/a/7244263
         with open(pathOutputFiles+fileName, 'wb') as out_file:
             out_file.write(requests.get(rootURL+fileName, verify = False).content)