seattletimes_rss_renderer.py

   1 #!/usr/bin/env python3
   2
   3 import datetime
   4 from typing import Dict, List
   5 import xml
   6
   7 import generic_news_rss_renderer as gnrss
   8
   9
  10 class seattletimes_rss_renderer(gnrss.generic_news_rss_renderer):
  11     interesting_categories = frozenset(
  12         [
  13             "Nation",
  14             "World",
  15             "Life",
  16             "Technology",
  17             "Local News",
  18             "Food",
  19             "Drink",
  20             "Today File",
  21             "Seahawks",
  22             "Oddities",
  23             "Packfic NW",
  24             "Home",
  25             "Garden",
  26             "Travel",
  27             "Outdoors",
  28         ]
  29     )
  30
  31     def __init__(
  32         self,
  33         name_to_timeout_dict: Dict[str, int],
  34         feed_site: str,
  35         feed_uris: List[str],
  36         page_title: str,
  37     ):
  38         super(seattletimes_rss_renderer, self).__init__(
  39             name_to_timeout_dict, feed_site, feed_uris, page_title
  40         )
  41
  42     def debug_prefix(self) -> str:
  43         return "seattletimes"
  44
  45     def get_headlines_page_prefix(self) -> str:
  46         return "seattletimes-nonnews"
  47
  48     def get_details_page_prefix(self) -> str:
  49         return "seattletimes-details-nonnews"
  50
  51     def should_use_https(self) -> bool:
  52         return True
  53
  54     def item_is_interesting_for_headlines(
  55         self, title: str, description: str, item: xml.etree.ElementTree.Element
  56     ) -> bool:
  57         if item.tag != "item":
  58             self.debug_print("Item.tag isn't item?!")
  59             return False
  60         if self.is_item_older_than_n_days(item, 14):
  61             self.debug_print("%s: is too old!" % title)
  62             return False
  63
  64         details = {}
  65         for detail in item.getchildren():
  66             self.debug_print(f"detail {detail.tag} => {detail.attrib} ({detail.text})")
  67             if detail.text is not None:
  68                 details[detail.tag] = detail.text
  69         if "category" not in details:
  70             self.debug_print("No category in details?!")
  71             self.debug_print(details.__repr__())
  72             return False
  73         interesting = False
  74         for x in seattletimes_rss_renderer.interesting_categories:
  75             if x in details["category"]:
  76                 self.debug_print("%s looks like a good category." % x)
  77                 interesting = True
  78         return interesting
  79
  80     def item_is_interesting_for_article(
  81         self, title: str, description: str, item: xml.etree.ElementTree.Element
  82     ) -> bool:
  83         if self.is_item_older_than_n_days(item, 14):
  84             self.debug_print("%s: is too old!" % title)
  85             return False
  86         return len(description) >= 65
  87
  88
  89 # Test
  90 # x = seattletimes_rss_renderer({"Test", 123},
  91 #                              "www.seattletimes.com",
  92 #                              [ "/life/feed/" ],
  93 #                              "nonnews")
  94 # x.periodic_render("Fetch News")
  95 # x.periodic_render("Shuffle News")