Use logging instead of printing

This avoids poisoning STDOUT with log messages which really
should go to STDERR. In turn, this makes room for real output
on STDOUT originating from the upcoming CLI module.

python_dwd/data_collection.py

@@ -1,4 +1,5 @@
 """ Data collection pipeline """
+import logging
 from pathlib import Path
 from typing import List, Union
 import pandas as pd
@@ -12,6 +13,8 @@
 from python_dwd.parsing_data.parse_data_from_files import parse_dwd_data
 from python_dwd.data_storing import restore_dwd_data, store_dwd_data, _build_local_store_key
 
+log = logging.getLogger(__name__)
+
 
 def collect_dwd_data(station_ids: List[int],
                      parameter: Union[Parameter, str],
@@ -60,13 +63,13 @@ def collect_dwd_data(station_ids: List[int],
 
             # When successful append data and continue with next iteration
             if not station_data.empty:
-                print(f"Data for {request_string} restored from local.")
+                log.info(f"Data for {request_string} restored from local.")
 
                 data.append(station_data)
 
                 continue
 
-        print(f"Data for {request_string} will be collected from internet.")
+        log.info(f"Data for {request_string} will be collected from internet.")
 
         remote_files = create_file_list_for_dwd_server(
             [station_id], parameter, time_resolution, period_type, folder, create_new_filelist)

python_dwd/dwd_station_request.py

@@ -1,3 +1,4 @@
+import logging
 from pathlib import Path
 from typing import List, Union, Optional, Dict, Generator
 import pandas as pd
@@ -16,6 +17,8 @@
 from python_dwd.constants.access_credentials import DWD_FOLDER_MAIN
 from python_dwd.enumerations.column_names_enumeration import DWDColumns
 
+log = logging.getLogger(__name__)
+
 
 class DWDStationRequest:
     """
@@ -80,9 +83,9 @@ def __init__(self,
             if not check_parameters(parameter=self.parameter,
                                     time_resolution=self.time_resolution,
                                     period_type=period_type):
-                print(f"Combination of: parameter {self.parameter.value}, "
-                      f"time_resolution {self.time_resolution.value}, "
-                      f"period_type {period_type} not available and removed.")
+                log.info(f"Combination of: parameter {self.parameter.value}, "
+                         f"time_resolution {self.time_resolution.value}, "
+                         f"period_type {period_type} not available and removed.")
                 self.period_type.remove(period_type)
 
         # Use the clean up of self.period_type to identify if there's any data with those parameters

python_dwd/parsing_data/parse_data_from_files.py

@@ -1,4 +1,5 @@
 """ function to read data from dwd server """
+import logging
 from typing import List, Tuple
 from io import BytesIO
 import pandas as pd
@@ -7,6 +8,8 @@
 from python_dwd.constants.column_name_mapping import GERMAN_TO_ENGLISH_COLUMNS_MAPPING
 from python_dwd.constants.metadata import NA_STRING, STATIONDATA_SEP
 
+log = logging.getLogger(__name__)
+
 
 def parse_dwd_data(filenames_and_files: List[Tuple[str, BytesIO]]) -> pd.DataFrame:
     """
@@ -27,9 +30,9 @@ def parse_dwd_data(filenames_and_files: List[Tuple[str, BytesIO]]) -> pd.DataFra
     try:
         data = pd.concat(data).reset_index(drop=True)
     except ValueError:
-        print(f"An error occurred while concatenating the data for files "
-              f"{[filename for filename, file in filenames_and_files]}. "
-              f"An empty DataFrame will be returned.")
+        log.error(f"An error occurred while concatenating the data for files "
+                  f"{[filename for filename, file in filenames_and_files]}. "
+                  f"An empty DataFrame will be returned.")
         data = pd.DataFrame()
 
     return data
@@ -57,10 +60,10 @@ def _parse_dwd_data(filename_and_file: Tuple[str, BytesIO]) -> pd.DataFrame:
             dtype="str"  # dtypes are mapped manually to ensure expected dtypes
         )
     except pd.errors.ParserError:
-        print(f"The file representing {filename} could not be parsed and is skipped.")
+        log.warning(f"The file representing {filename} could not be parsed and is skipped.")
         return pd.DataFrame()
     except ValueError:
-        print(f"The file representing {filename} is None and is skipped.")
+        log.warning(f"The file representing {filename} is None and is skipped.")
         return pd.DataFrame()
 
     data = data.rename(columns=str.upper).rename(GERMAN_TO_ENGLISH_COLUMNS_MAPPING)