__license__ = 'GPL v3' __copyright__ = '2009-2010, Darko Miletic ' ''' spectator.org ''' from calibre.web.feeds.news import BasicNewsRecipe from css_selectors import Select class TheAmericanSpectator(BasicNewsRecipe): title = 'The American Spectator' __author__ = 'Kovid Goyal' description = 'News from USA' oldest_article = 7 max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False language = 'en' auto_cleanup = True encoding = 'utf-8' def parse_index(self): root = self.index_to_soup( 'http://spectator.org/issues/current', as_tree=True) select = Select(root) main = tuple(select('div#block-system-main'))[0] feeds = [] for div in select('div.item-list', main): for h3 in div.xpath('./h3'): section_title = self.tag_to_string(h3) self.log('\n' + section_title) break else: continue articles = [] for li in div.xpath('descendant::li'): for x in select('div.views-field-title', li): title = self.tag_to_string(x) break else: raise ValueError('No article title found') url = 'http://spectator.org' + li.xpath('./a/@href')[0] desc = '' for x in select('div.views-field-field-short-summary', li): desc = self.tag_to_string(x) break articles.append( {'title': title, 'url': url, 'description': desc}) self.log('\t', title, 'at', url) feeds.append((section_title, articles)) return feeds