cnn_rss_renderer.py

   1 import generic_news_rss_renderer
   2 import re
   3
   4 class cnn_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
   5     def __init__(self, name_to_timeout_dict, feed_site, feed_uris, page_title):
   6         super(cnn_rss_renderer, self).__init__(
   7             name_to_timeout_dict,
   8             feed_site,
   9             feed_uris,
  10             page_title)
  11         self.debug = 1
  12
  13     def debug_prefix(self):
  14         return "cnn(%s)" % (self.page_title)
  15
  16     def get_headlines_page_prefix(self):
  17         return "cnn-%s" % (self.page_title)
  18
  19     def get_details_page_prefix(self):
  20         return "cnn-details-%s" % (self.page_title)
  21
  22     def munge_description(self, description):
  23         description = re.sub('[Rr]ead full story for latest details.', '', description)
  24         description = re.sub('<[^>]+>', '', description)
  25         return description
  26
  27     def should_use_https(self):
  28         return False
  29
  30     def item_is_interesting_for_headlines(self, title, description, item):
  31         return re.search(r'[Cc][Nn][Nn][A-Za-z]*\.com', title) is None
  32
  33     def item_is_interesting_for_article(self, title, description, item):
  34         return (re.search(r'[Cc][Nn][Nn][A-Za-z]*\.com', title) is None and
  35                 len(description) >= 65)
  36
  37 # Test
  38 #x = cnn_rss_renderer(
  39 #    {"Fetch News" : 1,
  40 #     "Shuffle News" : 1},
  41 #    "rss.cnn.com",
  42 #    [ "/rss/cnn_topstories.rss",
  43 #      "/rss/money_latest.rss",
  44 #     "/rss/cnn_tech.rss",
  45 #    ],
  46 #    "Test" )
  47 #if x.fetch_news() == 0:
  48 #    print("Error fetching news, no items fetched.")
  49 #x.shuffle_news()