#!/usr/bin/env python __copyright__ = '2008, Kovid Goyal ' __license__ = 'GPL v3' ''' calibre recipe for prospectmagazine.co.uk (subscription) ''' from calibre.web.feeds.recipes import BasicNewsRecipe from css_selectors import Select class ProspectMagUK(BasicNewsRecipe): title = u'Prospect Magazine' description = 'A general-interest publication offering analysis and commentary about politics, news and business.' __author__ = 'barty, duluoz' timefmt = ' [%d %B %Y]' no_stylesheets = True publication_type = 'magazine' category = 'news, UK' language = 'en_GB' max_articles_per_feed = 100 needs_subscription = True INDEX = 'http://www.prospectmagazine.co.uk/issue/' keep_only_tags = [dict(id='post_content')] def get_browser(self): br = BasicNewsRecipe.get_browser(self) if self.username is not None and self.password is not None: br.open('http://www.prospectmagazine.co.uk/wp-login.php') br.select_form(name='loginform') br['log'] = self.username br['pwd'] = self.password br.submit() return br def parse_index(self): root = self.index_to_soup(self.INDEX, as_tree=True) sel = Select(root) for img in sel('.block_this_month .img_wrap img'): self.cover_url = img.get('src').partition('?')[0] feeds = [] for h2 in sel('h2.block-title'): current_section = self.tag_to_string(h2) articles = [] self.log('Found section:', current_section) for div in sel('div.block_home_post', h2.getparent()): for a in sel('div.title a[href]', div): articles.append({'title':self.tag_to_string(a), 'url':a.get('href')}) self.log('\tFound article:', articles[-1]['title']) if articles: feeds.append((current_section, articles)) return feeds