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.',
  24                              '',
  25                              description)
  26         description = re.sub('<[^>]+>', '', description)
  27         return description
  28
  29     def find_image(self, item):
  30         image = item.findtext('media:thumbnail')
  31         if image is not None:
  32             image_url = image.get('url')
  33             return image_url
  34         return None
  35
  36     def should_use_https(self):
  37         return False
  38
  39     def item_is_interesting_for_headlines(self, title, description, item):
  40         if self.is_item_older_than_n_days(item, 14):
  41             self.debug_print("%s: is too old!" % title)
  42             return False
  43         return re.search(r'[Cc][Nn][Nn][A-Za-z]*\.com', title) is None
  44
  45     def item_is_interesting_for_article(self, title, description, item):
  46         if self.is_item_older_than_n_days(item, 7):
  47             self.debug_print("%s: is too old!" % title)
  48             return False
  49         return (re.search(r'[Cc][Nn][Nn][A-Za-z]*\.com', title) is None and
  50                 len(description) >= 65)
  51
  52 # Test
  53 #x = cnn_rss_renderer(
  54 #    {"Fetch News" : 1,
  55 #     "Shuffle News" : 1},
  56 #    "rss.cnn.com",
  57 #    [ "/rss/cnn_topstories.rss",
  58 #      "/rss/money_latest.rss",
  59 #     "/rss/cnn_tech.rss",
  60 #    ],
  61 #    "Test" )
  62 #if x.fetch_news() == 0:
  63 #    print("Error fetching news, no items fetched.")
  64 #x.shuffle_news()