add filter feature

README.md

@@ -72,6 +72,10 @@ postprocessor = 'pandoc -f html -t markdown_strict-raw_html --reference-links --
 # Fileending for the article files.
 fileending = 'md'
 
+# List of regular expression strings. If any of these matches an lowercase article title, the article won't be saved.
+# E.g. if you wan't to skip news about RSS explicitly, add '(\W|^)rss(\W|$)'.
+filters = []
+
 # Date and time format as strftime to be included in the articles.
 datetime_format = '%d.%m.%Y %H:%M'
 
@@ -153,6 +157,6 @@ Just synchronize the base_directory with [Syncthing](https://syncthing.net/), [r
 
 ## Acknowledgements
 
-Thanks to all the people, who created the nice libraries this project in based on.
+Thanks to all the people who created the nice software, this project in based on.
 And also thanks to Dieter Steffmann who created the Canterbury font, which is used for the logo.
 You can find it in the `fonts/` directory.

config.toml

@@ -13,6 +13,10 @@ postprocessor = 'pandoc -f html -t markdown_strict-raw_html+pipe_tables --refere
 # Fileending for the article files.
 fileending = 'md'
 
+# List of regular expression strings. If any of these matches an lowercase article title, the article won't be saved.
+# E.g. if you wan't to skip news about RSS explicitly, add '(\W|^)rss(\W|$)'.
+filters = []
+
 # Feeds
 # The category can be empty (''). The feed fill then be stored in the base_directory.
 # The category can also be a path, which will result in subdirectories (e.g. 'technology/hardware').

spiderss.py

@@ -249,6 +249,15 @@ def update_feed(feed):
 
             if date > threshold_date:
 
+                # Check if article should be filtered
+                filter = False
+                for f in filters:
+                    if re.search(f, a.title.lower()):
+                        filter = True
+                        log('    filtered article "{}"'.format(a.title))
+
+                if not filter:
+
                     # Construct filename
                     filename_prefix = date.strftime('%Y%m%d%H%M')
                     filename_postfix = get_filename_postfix(a.title)
@@ -294,7 +303,7 @@ def remove_old_articles():
 # Parse config file
 def load_config(filepath):
 
-    global base_directory, max_age, datetime_format, postprocessor, fileending, feeds
+    global base_directory, max_age, datetime_format, postprocessor, fileending, filters, feeds
 
     try:
         config = toml.load(filepath)
@@ -303,6 +312,7 @@ def load_config(filepath):
         datetime_format = config['datetime_format']
         postprocessor = config['postprocessor']
         fileending = config['fileending']
+        filters = config['filters']
         feeds = config['feed']
     except Exception as e:
         error('while parsing config: {}'.format(e))