#!/usr/bin/env python2 # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' csid.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class CSID(BasicNewsRecipe): title = u'Ce se \u00eent\u00e2mpl\u0103 doctore?' __author__ = u'Silviu Cotoar\u0103' description = u'Ce se \u00eent\u00e2mpl\u0103 doctore?' publisher = 'CSID' oldest_article = 5 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Reviste,Femei,Health,Beauty' encoding = 'utf-8' cover_url = 'http://www.csid.ro/images/default/csid.gif' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='div', attrs={'class': 'content floatleft'}) ] remove_tags = [ dict(name='div', attrs={'id': ['article_links']}), dict( name='div', attrs={'id': ['tags']}), dict(name='p', attrs={'id': ['tags']}) ] remove_tags_after = [ dict(name='p', attrs={'id': ['tags']}) ] feeds = [ (u'Feeds', u'http://www.csid.ro/rss/') ] def preprocess_html(self, soup): return self.adeify_images(soup)