Add default to item_older_than_n_days.

[kiosk.git] / cnn_rss_renderer.py

diff --git a/cnn_rss_renderer.py b/cnn_rss_renderer.py
index a93b4917d97ac169165fe7fc21f1c16bc2ec677b..2628bd58975f0bb9b4f2614961b28377a68daf74 100644 (file)
--- a/cnn_rss_renderer.py
+++ b/cnn_rss_renderer.py
@@ -1,41 +1,64 @@
+#!/usr/bin/env python3
+
 import generic_news_rss_renderer
 import re
+from typing import Dict, List, Optional
+import xml
+
 
 class cnn_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
-    def __init__(self, name_to_timeout_dict, feed_site, feed_uris, page_title):
-        super(cnn_rss_renderer, self).__init__(
-            name_to_timeout_dict,
-            feed_site,
-            feed_uris,
-            page_title)
-        self.debug = 1
-
-    def debug_prefix(self):
-        return "cnn(%s)" % (self.page_title)
-
-    def get_headlines_page_prefix(self):
-        return "cnn-%s" % (self.page_title)
-
-    def get_details_page_prefix(self):
-        return "cnn-details-%s" % (self.page_title)
-
-    def munge_description(self, description):
-        description = re.sub('[Rr]ead full story for latest details.', '', description)
-        description = re.sub('<[^>]+>', '', description)
+    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)
+
+    def get_headlines_page_prefix(self) -> str:
+        return f"cnn-{self.page_title}"
+
+    def get_details_page_prefix(self) -> str:
+        return f"cnn-details-{self.page_title}"
+
+    def munge_description(
+        self, description: str, item: xml.etree.ElementTree.Element
+    ) -> str:
+        description = re.sub("[Rr]ead full story for latest details.", "", description)
+        description = re.sub("<[^>]+>", "", description)
         return description
 
-    def should_use_https(self):
+    def find_image(self, item: xml.etree.ElementTree.Element) -> Optional[str]:
+        image = item.findtext("media:thumbnail")
+        if image is not None:
+            image_url = image.get("url")
+            return image_url
+        return None
+
+    def should_use_https(self) -> bool:
         return False
 
-    def item_is_interesting_for_headlines(self, title, description, item):
-        return re.search(r'[Cc][Nn][Nn][A-Za-z]*\.com', title) is None
+    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, 14, default=False):
+            return False
+        return re.search(r"[Cc][Nn][Nn][A-Za-z]*\.com", title) is None
+
+    def item_is_interesting_for_article(
+        self, title, description, item: xml.etree.ElementTree.Element
+    ):
+        if self.is_item_older_than_n_days(item, 7):
+            return False
+        return (
+            re.search(r"[Cc][Nn][Nn][A-Za-z]*\.com", title) is None
+            and len(description) >= 65
+        )
 
-    def item_is_interesting_for_article(self, title, description, item):
-        return (re.search(r'[Cc][Nn][Nn][A-Za-z]*\.com', title) is None and
-                len(description) >= 65)
 
 # Test
-#x = cnn_rss_renderer(
+# x = cnn_rss_renderer(
 #    {"Fetch News" : 1,
 #     "Shuffle News" : 1},
 #    "rss.cnn.com",
@@ -44,6 +67,6 @@ class cnn_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
 #     "/rss/cnn_tech.rss",
 #    ],
 #    "Test" )
-#if x.fetch_news() == 0:
+# if x.fetch_news() == 0:
 #    print("Error fetching news, no items fetched.")
-#x.shuffle_news()
+# x.shuffle_news()