cnn_rss_renderer.py

   1 import generic_news_rss_renderer
   2 import re
   3
   4
   5 class cnn_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
   6     def __init__(self, name_to_timeout_dict, feed_site, feed_uris, page_title):
   7         super(cnn_rss_renderer, self).__init__(
   8             name_to_timeout_dict, feed_site, feed_uris, page_title
   9         )
  10         self.debug = 1
  11
  12     def debug_prefix(self):
  13         return "cnn(%s)" % (self.page_title)
  14
  15     def get_headlines_page_prefix(self):
  16         return "cnn-%s" % (self.page_title)
  17
  18     def get_details_page_prefix(self):
  19         return "cnn-details-%s" % (self.page_title)
  20
  21     def munge_description(self, description):
  22         description = re.sub("[Rr]ead full story for latest details.", "", description)
  23         description = re.sub("<[^>]+>", "", description)
  24         return description
  25
  26     def find_image(self, item):
  27         image = item.findtext("media:thumbnail")
  28         if image is not None:
  29             image_url = image.get("url")
  30             return image_url
  31         return None
  32
  33     def should_use_https(self):
  34         return False
  35
  36     def item_is_interesting_for_headlines(self, title, description, item):
  37         if self.is_item_older_than_n_days(item, 14):
  38             self.debug_print("%s: is too old!" % title)
  39             return False
  40         return re.search(r"[Cc][Nn][Nn][A-Za-z]*\.com", title) is None
  41
  42     def item_is_interesting_for_article(self, title, description, item):
  43         if self.is_item_older_than_n_days(item, 7):
  44             self.debug_print("%s: is too old!" % title)
  45             return False
  46         return (
  47             re.search(r"[Cc][Nn][Nn][A-Za-z]*\.com", title) is None
  48             and len(description) >= 65
  49         )
  50
  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()