wsj_rss_renderer.py

   1 import generic_news_rss_renderer
   2
   3 class wsj_rss_renderer(generic_news_rss_renderer.generic_news_rss_renderer):
   4     def __init__(self, name_to_timeout_dict, feed_site, feed_uris, page_title):
   5         super(wsj_rss_renderer, self).__init__(
   6             name_to_timeout_dict,
   7             feed_site,
   8             feed_uris,
   9             page_title)
  10         self.debug = 1
  11
  12     def debug_prefix(self):
  13         return "wsj(%s)" % (self.page_title)
  14
  15     def get_headlines_page_prefix(self):
  16         return "wsj-%s" % (self.page_title)
  17
  18     def get_details_page_prefix(self):
  19         return "wsj-details-%s" % (self.page_title)
  20
  21     def find_image(self, item):
  22         image = item.findtext('image')
  23         if image is not None:
  24             url = image.get('url')
  25             return url
  26         return None
  27
  28     def should_use_https(self):
  29         return True
  30
  31     def item_is_interesting_for_headlines(self, title, description, item):
  32         if self.is_item_older_than_n_days(item, 7):
  33             self.debug_print("%s: is too old!" % title)
  34             return False
  35         return ("WSJ.com" not in title and
  36                 "WSJ.com" not in description)
  37
  38     def item_is_interesting_for_article(self, title, description, item):
  39         if self.is_item_older_than_n_days(item, 7):
  40             self.debug_print("%s: is too old!" % title)
  41             return False
  42         return ("WSJ.com" not in title and
  43                 "WSJ.com" not in description)
  44
  45 # Test
  46 #x = wsj_rss_renderer(
  47 #    {"Fetch News" : 1,
  48 #     "Shuffle News" : 1},
  49 #    "feeds.a.dj.com",
  50 #    [ "/rss/RSSWorldNews.xml" ],
  51 #    "Test" )
  52 #if x.fetch_news() == 0:
  53 #    print "Error fetching news, no items fetched."
  54 #x.shuffle_news()