wsj_rss_renderer.py

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