google_news_rss_renderer.py

   1 from bs4 import BeautifulSoup
   2 import generic_news_rss_renderer
   3 import re
   4
   5 class google_news_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(google_news_rss_renderer, self).__init__(
   8             name_to_timeout_dict,
   9             feed_site,
  10             feed_uris,
  11             page_title)
  12         self.debug = 1
  13
  14     def debug_prefix(self):
  15         return "google-news"
  16
  17     def get_headlines_page_prefix(self):
  18         return "google-news"
  19
  20     def get_details_page_prefix(self):
  21         return "google-news-details"
  22
  23     def find_description(self, item):
  24         descr = item.findtext('description')
  25         source = item.findtext('source')
  26         if source is not None:
  27             descr = descr + " (%s)" % source
  28         return descr
  29
  30     def munge_description(self, description):
  31         soup = BeautifulSoup(description)
  32         for a in soup.findAll('a'):
  33             del a['href']
  34         return str(soup)
  35
  36     def find_image(self, item):
  37         return None
  38
  39     def should_use_https(self):
  40         return True
  41
  42     def item_is_interesting_for_headlines(self, title, description, item):
  43         return not self.is_item_older_than_n_days(item, 2)
  44
  45     def item_is_interesting_for_article(self, title, description, item):
  46         return not self.is_item_older_than_n_days(item, 2)
  47
  48 # Test
  49 #x = google_news_rss_renderer(
  50 #    {"Fetch News" : 1,
  51 #     "Shuffle News" : 1},
  52 #    "news.google.com",
  53 #    [ "/rss?hl=en-US&gl=US&ceid=US:en" ],
  54 #    "Test" )
  55 #if x.fetch_news() == 0:
  56 #    print("Error fetching news, no items fetched.")
  57 #x.shuffle_news()