#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' publika.md ''' from calibre.web.feeds.news import BasicNewsRecipe class Publika(BasicNewsRecipe): title = u'Publika' __author__ = u'Silviu Cotoar\u0103' description = u'\u015etiri din Moldova' publisher = u'Publika' oldest_article = 25 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Stiri,Moldova' encoding = 'utf-8' cover_url = 'http://assets.publika.md/images/logo.jpg' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='div', attrs={'id': 'colLeft'}) ] remove_tags = [ dict(name='div', attrs={'class': ['articleInfo']}), dict(name='div', attrs={'class': ['articleRelated']}), dict( name='div', attrs={'class': ['roundedBox socialSharing']}), dict(name='div', attrs={'class': ['comment clearfix']}) ] remove_tags_after = [ dict(name='div', attrs={'class': ['roundedBox socialSharing']}), dict( name='div', attrs={'class': ['comment clearfix']}) ] feeds = [ (u'Feeds', u'http://rss.publika.md/stiri.xml') ] def preprocess_html(self, soup): return self.adeify_images(soup)