cnn_rss_renderer.py

   1 #!/usr/bin/env python3
   2
   3 import generic_news_rss_renderer
   4 import re
   5 from typing import Dict, List
   6 import xml
   7
   8
   9 class cnn_rss_renderer(generic_news_rss_renderer.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(cnn_rss_renderer, self).__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"cnn({self.page_title})"
  24
  25     def get_headlines_page_prefix(self) -> str:
  26         return f"cnn-{self.page_title}"
  27
  28     def get_details_page_prefix(self) -> str:
  29         return f"cnn-details-{self.page_title}"
  30
  31     def munge_description(self, description: str) -> str:
  32         description = re.sub("[Rr]ead full story for latest details.", "", description)
  33         description = re.sub("<[^>]+>", "", description)
  34         return description
  35
  36     def find_image(self, item: xml.etree.ElementTree.Element) -> str:
  37         image = item.findtext("media:thumbnail")
  38         if image is not None:
  39             image_url = image.get("url")
  40             return image_url
  41         return None
  42
  43     def should_use_https(self) -> bool:
  44         return False
  45
  46     def item_is_interesting_for_headlines(
  47         self, title: str, description: str, item: xml.etree.ElementTree.Element
  48     ) -> bool:
  49         if self.is_item_older_than_n_days(item, 14):
  50             return False
  51         return re.search(r"[Cc][Nn][Nn][A-Za-z]*\.com", title) is None
  52
  53     def item_is_interesting_for_article(
  54         self, title, description, item: xml.etree.ElementTree.Element
  55     ):
  56         if self.is_item_older_than_n_days(item, 7):
  57             return False
  58         return (
  59             re.search(r"[Cc][Nn][Nn][A-Za-z]*\.com", title) is None
  60             and len(description) >= 65
  61         )
  62
  63
  64 # Test
  65 # x = cnn_rss_renderer(
  66 #    {"Fetch News" : 1,
  67 #     "Shuffle News" : 1},
  68 #    "rss.cnn.com",
  69 #    [ "/rss/cnn_topstories.rss",
  70 #      "/rss/money_latest.rss",
  71 #     "/rss/cnn_tech.rss",
  72 #    ],
  73 #    "Test" )
  74 # if x.fetch_news() == 0:
  75 #    print("Error fetching news, no items fetched.")
  76 # x.shuffle_news()