X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=google_news_rss_renderer.py;h=c7442707b623aa97d6493306b1b675996accb5d0;hb=addd4980077f6e3857c5c035b49784dc3ceca49a;hp=ad92c26523cf690c0062ee00e1a0ab9332635b97;hpb=5e241dc47e497c547463cecc07946ea6882835a7;p=kiosk.git

diff --git a/google_news_rss_renderer.py b/google_news_rss_renderer.py
index ad92c26..c744270 100644
--- a/google_news_rss_renderer.py
+++ b/google_news_rss_renderer.py
@@ -1,32 +1,47 @@
-from bs4 import BeautifulSoup
-import generic_news_rss_renderer
+#!/usr/bin/env python3
+
+import logging
 import re
+from typing import Dict, List, Optional
+import xml
+import xml.etree.ElementTree as ET
+
+from bs4 import BeautifulSoup  # type: ignore
+
+import generic_news_rss_renderer
+
+logger = logging.getLogger(__file__)
 
 
 class google_news_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
-    def __init__(self, name_to_timeout_dict, feed_site, feed_uris, page_title):
-        super(google_news_rss_renderer, self).__init__(
+    def __init__(
+        self,
+        name_to_timeout_dict: Dict[str, int],
+        feed_site: str,
+        feed_uris: List[str],
+        page_title: str,
+    ) -> None:
+        super().__init__(
             name_to_timeout_dict, feed_site, feed_uris, page_title
         )
-        self.debug = 1
-
-    def debug_prefix(self):
-        return "google-news"
 
-    def get_headlines_page_prefix(self):
+    def get_headlines_page_prefix(self) -> str:
         return "google-news"
 
-    def get_details_page_prefix(self):
+    def get_details_page_prefix(self) -> str:
         return "google-news-details"
 
-    def find_description(self, item):
+    def find_description(self, item: xml.etree.ElementTree.Element) -> str:
         descr = item.findtext("description")
-        source = item.findtext("source")
-        if source is not None:
-            descr = descr + " (%s)" % source
+        if descr is not None:
+            source = item.findtext("source")
+            if source is not None:
+                descr = descr + f" ({source})"
+        else:
+            descr = ""
         return descr
 
-    def munge_description_internal(self, descr):
+    def munge_description_internal(self, descr: str, item: ET.Element) -> str:
         if len(descr) > 450:
             descr = descr[:450]
             descr = re.sub(r"\<[^\>]*$", "", descr)
@@ -34,23 +49,27 @@ class google_news_rss_renderer(generic_news_rss_renderer.generic_news_rss_render
         descr += "</A></LI></UL></OL></P>"
         return descr
 
-    def munge_description(self, description):
-        soup = BeautifulSoup(description)
+    def munge_description(self, description: str, item: ET.Element) -> str:
+        soup = BeautifulSoup(description, features="lxml")
         for a in soup.findAll("a"):
             del a["href"]
         descr = str(soup)
-        return munge_description_internal(descr)
+        return self.munge_description_internal(descr, item)
 
-    def find_image(self, item):
+    def find_image(self, item: xml.etree.ElementTree.Element) -> Optional[str]:
         return None
 
-    def should_use_https(self):
+    def should_use_https(self) -> bool:
         return True
 
-    def item_is_interesting_for_headlines(self, title, description, item):
+    def item_is_interesting_for_headlines(
+        self, title: str, description: str, item: xml.etree.ElementTree.Element
+    ) -> bool:
         return not self.is_item_older_than_n_days(item, 2)
 
-    def item_is_interesting_for_article(self, title, description, item):
+    def item_is_interesting_for_article(
+        self, title: str, description: str, item: xml.etree.ElementTree.Element
+    ) -> bool:
         return not self.is_item_older_than_n_days(item, 2)