#!/usr/bin/env python2 __copyright__ = '2008, Kovid Goyal ' __license__ = 'GPL v3' ''' calibre recipe for slate.com ''' from calibre.web.feeds.recipes import BasicNewsRecipe class Slate(BasicNewsRecipe): title = 'Slate' description = 'A general-interest publication offering analysis and commentary about politics, news and culture.' __author__ = 'Kovid Goyal' timefmt = '' no_stylesheets = True language = 'en' encoding = 'utf-8' masthead_url = 'http://img.slate.com/images/redesign2008/slate_logo.gif' remove_attributes = ['style'] INDEX = 'http://slate.com' compress_news_images = True keep_only_tags = [ dict(name='header', attrs={'class':'article-header'}), dict(name='section', attrs={'class':lambda x: x and 'content' == x.strip()}), ] remove_tags = [ dict(id='header_social'), dict(attrs={'class':['prop-name', 'prop-desc', 'authorbox', 'twitter', 'email', 'facebook', 'follow-links', 'join-in']}), dict(attrs={'class':lambda x: x and 'sharing-buttons' in x.split()}), ] def print_version(self, url): return url.replace('.html', '.single.html') def parse_index(self) : ans = [] for sectitle, url in ( ('News & Politics', '/articles/news_and_politics.html'), ('Technology', '/articles/technology.html'), ('Business', '/articles/business.html'), ('Arts', '/articles/arts.html'), ('Life', '/articles/life.html'), ('Health & Science', '/articles/health_and_science.html'), ('Sports', '/articles/sports.html'), ('Double X', '/articles/double_x.html'), ): url = self.INDEX + url self.log('\nFound section:', sectitle) articles = self.slate_section_articles(self.index_to_soup(url)) if articles: ans.append((sectitle, articles)) if self.test and len(ans) > 1: break return ans def slate_section_articles(self, soup): ans = [] main = soup.find('article', attrs={'class':'main'}) for a in main.findAll('a', attrs={'class':'primary'}): url = a['href'] if url.endswith('/'): continue p = a.parent title = p.find(attrs={'class':'hed'}) if title is None: continue title = self.tag_to_string(title) span = p.find(attrs={'class':'byline'}) desc = '' if span is not None: desc = self.tag_to_string(span) self.log('\t' + title) self.log('\t\t' + url) ans.append({'title':title, 'description':desc, 'date':'', 'url':url}) return ans