Merge branch 'dev' into main

example_config.yaml

@@ -11,9 +11,10 @@ download_format: "pdf"
 # Where should the downloaded files be stored?
 download_folder: "/path/to/download/folder"
 
-# Use a lock file that indicates whether tomorrow's newspaper has already been downloaded to limit the number of times
-# the taz.de website is queried for new editions
-use_lock_file: True
+# Before the program searches for new download candidates, it checks whether tomorrow's newspaper has already been
+# downloaded by the number of queries on the taz.de website.
+# If you want to download all available newspaper missing in the download_history.csv, set this value to False.
+limit_requests: True
 
 # Set the log level.
 # Valid formats are: notset, debug, info, warning, error, critical

main.py

@@ -23,22 +23,6 @@ def main(config: dict):
     except ValueError as e:
         logging.error(f"Could not set log level.\n{e}", exc_info=True)
 
-    # If 'use_lock_file' configuration is set, check if lockfile exists for tomorrow's newspaper
-    if config['use_lock_file']:
-        try:
-            lock_files = [entry for entry in os.listdir(dir_path) if os.path.isfile(entry) and entry.endswith('.lock')]
-            # Delete all lock files that do not refer to tomorrow's date
-            for file in lock_files:
-                if not file.startswith('.' + tomorrow):
-                    os.remove(dir_path + file)
-            # If there is a lock file for tomorrow, exit the program
-            for file in lock_files:
-                if file.startswith('.' + tomorrow):
-                    logging.info('Tomorrow\'s newspaper was already downloaded. Execution canceled.')
-                    sys.exit(0)
-        except Exception as e:
-            logging.error(f"Could not check for lock files.\n{e}", exc_info=True)
-
     # Read download history from csv file
     try:
         df = pd.read_csv(dir_path + 'download_history.csv', header=0)
@@ -51,6 +35,16 @@ def main(config: dict):
             ]
         )
 
+    # If the 'limit_requests' argument is specified, check whether tomorrow's newspaper has already been downloaded
+    if config['limit_requests']:
+        try:
+            if any(df.file.str.contains(pat=tomorrow)):
+                logging.info('Tomorrow\'s newspaper was already downloaded. Execution canceled.')
+                sys.exit(0)
+        except Exception as e:
+            logging.error(f"Could not check whether tomorrow's newspaper has already been downloaded.\n{e}",
+                          exc_info=True)
+
     # Instantiate downloader object
     try:
         taz_dl = TazDownloader(config['id'], config['password'], config['download_format'])
@@ -59,7 +53,7 @@ def main(config: dict):
         sys.exit(1)
 
     try:
-        # Get newspapers available for download
+        # Get newspaper available for download
         newspaper_available = taz_dl.scrape_newspaper()
 
         # Remove outdated newspaper from download_history.csv
@@ -80,16 +74,6 @@ def main(config: dict):
         except Exception as e:
             logging.error(f"Could not download {n}\n{e}", exc_info=True)
 
-    # Create lock file for tomorrow
-    if config['use_lock_file']:
-        try:
-            lock_file = '.' + tomorrow + '.lock'
-            for n in newspaper_downloaded:
-                if n.startswith('taz_' + tomorrow):
-                    os.mknod(dir_path + lock_file)
-        except Exception as e:
-            logging.error(f"Could not download create lock file \"{lock_file}\"\n{e}", exc_info=True)
-
     # Add downloaded newspaper to download_history.csv
     try:
         for n in newspaper_downloaded:

models.py

@@ -25,7 +25,7 @@ class TazConfiguration:
         ('password', True),
         ('download_format', False),
         ('download_folder', True),
-        ('use_lock_file', False),
+        ('limit_requests', False),
         ('log_level', False),
     ]
 
@@ -65,19 +65,21 @@ class TazConfiguration:
         Parse command line arguments.
         """
         argparser = argparse.ArgumentParser(
-            description='Download taz e-paper'
+            description='Download taz e-paper',
         )
         argparser.add_argument(
             '-i',
             '--id',
             action='store',
             type=str,
+            help='Your taz-ID',
         )
         argparser.add_argument(
             '-p',
             '--password',
             action='store',
             type=str,
+            help='Your password',
         )
         argparser.add_argument(
             '-f',
@@ -85,23 +87,27 @@ class TazConfiguration:
             action='store',
             type=str,
             choices=['pdf', 'epub', 'epubt', 'html', 'ascii', 'mobi', 'mobit'],
+            help='The e-paper format',
         )
         argparser.add_argument(
             '-d',
             '--download_folder',
             action='store',
             type=str,
+            help='The path to a folder where the e-paper should be stored',
         )
         argparser.add_argument(
             '-l',
-            '--use_lock_file',
+            '--limit-requests',
             action='store_true',
-            default=None
+            default=None,
+            help='Only query website for available newspaper if tomorrow\'s newspaper has not already been downloaded',
         )
         argparser.add_argument(
             '--log_level',
             action='store',
             choices=['notset', 'debug', 'info', 'warning', 'error', 'critical'],
+            help='Set the log level',
         )
         return argparser.parse_args()