Profanity filter, please.

[kiosk.git] / wsj_rss_renderer.py

diff --git a/wsj_rss_renderer.py b/wsj_rss_renderer.py
index 8e2b0ccbe2dede11b3c82d73ed45b9e4dde1d005..15eee9f88e1a1e6b633d8817d2adcea1e72d31d7 100644 (file)
--- a/wsj_rss_renderer.py
+++ b/wsj_rss_renderer.py
@@ -1,41 +1,61 @@
-import generic_news_rss_renderer
+#!/usr/bin/env python3
 
-class wsj_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
-    def __init__(self, name_to_timeout_dict, feed_site, feed_uris, page_title):
-        super(wsj_rss_renderer, self).__init__(
-            name_to_timeout_dict,
-            feed_site,
-            feed_uris,
-            page_title)
-        self.debug = 1
+import xml
+from typing import Dict, List, Optional
 
-    def debug_prefix(self):
-        return "wsj(%s)" % (self.page_title)
+import generic_news_rss_renderer as gnrssr
 
-    def get_headlines_page_prefix(self):
-        return "wsj-%s" % (self.page_title)
 
-    def get_details_page_prefix(self):
-        return "wsj-details-%s" % (self.page_title)
+class wsj_rss_renderer(gnrssr.generic_news_rss_renderer):
+    def __init__(
+        self,
+        name_to_timeout_dict: Dict[str, int],
+        feed_site: str,
+        feed_uris: List[str],
+        page_title: str,
+    ):
+        super().__init__(
+            name_to_timeout_dict, feed_site, feed_uris, page_title
+        )
+        self.debug = True
 
-    def should_use_https(self):
+    def debug_prefix(self) -> str:
+        return f"wsj({self.page_title})"
+
+    def get_headlines_page_prefix(self) -> str:
+        return f"wsj-{self.page_title}"
+
+    def get_details_page_prefix(self) -> str:
+        return f"wsj-details-{self.page_title}"
+
+    def find_image(self, item: xml.etree.ElementTree.Element) -> Optional[str]:
+        return None
+
+    def should_use_https(self) -> bool:
         return True
 
-    def item_is_interesting_for_headlines(self, title, description, item):
-        return ("WSJ.com" not in title and
-                "WSJ.com" not in description)
+    def item_is_interesting_for_headlines(
+        self, title: str, description: str, item: xml.etree.ElementTree.Element
+    ) -> bool:
+        if self.is_item_older_than_n_days(item, 7):
+            return False
+        return "WSJ.com" not in title and "WSJ.com" not in description
+
+    def item_is_interesting_for_article(
+        self, title: str, description: str, item: xml.etree.ElementTree.Element
+    ) -> bool:
+        if self.is_item_older_than_n_days(item, 7):
+            return False
+        return "WSJ.com" not in title and "WSJ.com" not in description
 
-    def item_is_interesting_for_article(self, title, description, item):
-        return ("WSJ.com" not in title and
-                "WSJ.com" not in description)
 
 # Test
-#x = wsj_rss_renderer(
+# x = wsj_rss_renderer(
 #    {"Fetch News" : 1,
 #     "Shuffle News" : 1},
 #    "feeds.a.dj.com",
 #    [ "/rss/RSSWorldNews.xml" ],
 #    "Test" )
-#if x.fetch_news() == 0:
-#    print "Error fetching news, no items fetched."
-#x.shuffle_news()
+# if x.fetch_news() == 0:
+#    print("Error fetching news, no items fetched.")
+# x.shuffle_news()