wsj_rss_renderer.py

   1 #!/usr/bin/env python3
   2
   3 import xml
   4 from typing import Dict, List, Optional
   5
   6 import generic_news_rss_renderer as gnrssr
   7
   8
   9 class wsj_rss_renderer(gnrssr.generic_news_rss_renderer):
  10     def __init__(
  11         self,
  12         name_to_timeout_dict: Dict[str, int],
  13         feed_site: str,
  14         feed_uris: List[str],
  15         page_title: str,
  16     ):
  17         super().__init__(
  18             name_to_timeout_dict, feed_site, feed_uris, page_title
  19         )
  20         self.debug = True
  21
  22     def debug_prefix(self) -> str:
  23         return f"wsj({self.page_title})"
  24
  25     def get_headlines_page_prefix(self) -> str:
  26         return f"wsj-{self.page_title}"
  27
  28     def get_details_page_prefix(self) -> str:
  29         return f"wsj-details-{self.page_title}"
  30
  31     def find_image(self, item: xml.etree.ElementTree.Element) -> Optional[str]:
  32         return None
  33
  34     def should_use_https(self) -> bool:
  35         return True
  36
  37     def item_is_interesting_for_headlines(
  38         self, title: str, description: str, item: xml.etree.ElementTree.Element
  39     ) -> bool:
  40         if self.is_item_older_than_n_days(item, 7):
  41             return False
  42         return "WSJ.com" not in title and "WSJ.com" not in description
  43
  44     def item_is_interesting_for_article(
  45         self, title: str, description: str, item: xml.etree.ElementTree.Element
  46     ) -> bool:
  47         if self.is_item_older_than_n_days(item, 7):
  48             return False
  49         return "WSJ.com" not in title and "WSJ.com" not in description
  50
  51
  52 # Test
  53 # x = wsj_rss_renderer(
  54 #    {"Fetch News" : 1,
  55 #     "Shuffle News" : 1},
  56 #    "feeds.a.dj.com",
  57 #    [ "/rss/RSSWorldNews.xml" ],
  58 #    "Test" )
  59 # if x.fetch_news() == 0:
  60 #    print("Error fetching news, no items fetched.")
  61 # x.shuffle_news()