__license__ = 'GPL v3' __copyright__ = '2010, Darko Miletic ' ''' www.lostiempos.com ''' from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe class LosTiempos_Bol(BasicNewsRecipe): title = 'Los Tiempos - Bolivia' __author__ = 'Darko Miletic' description = 'El periódico de mayor circulación en la ciudad de Cochabamba, Bolivia' publisher = 'Los Tiempos' category = 'news, politics, Bolivia' oldest_article = 1 max_articles_per_feed = 200 no_stylesheets = True encoding = 'cp1252' use_embedded_content = False language = 'es_BO' publication_type = 'newspaper' delay = 1 remove_empty_feeds = True cover_url = strftime( 'http://www.lostiempos.com/media_recortes/%Y/%m/%d/portada_gd_1.jpg') masthead_url = 'http://www.lostiempos.com/img_stat/logo_tiempos_sin_beta.jpg' extra_css = """ body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} h1,.hora,.breadcum,.pie_foto{font-family: Georgia,"Times New Roman",Times,serif} .hora,.breadcum,.pie_foto{font-size: small} .en_gris,.pie_foto{color: #666666} """ conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } keep_only_tags = [dict(name='div', attrs={'id': 'articulo'})] remove_tags = [ dict(name=['meta', 'link', 'form', 'iframe', 'embed', 'object', 'hr']), dict( attrs={'class': ['caja_fonts sin_border_bot', 'pub', 'twitter-share-button']}) ] remove_attributes = ['width', 'height'] feeds = [ (u'Nacional', u'http://www.lostiempos.com/rss/lostiempos-nacional.xml'), (u'Local', u'http://www.lostiempos.com/rss/lostiempos-local.xml'), (u'Deportes', u'http://www.lostiempos.com/rss/lostiempos-deportes.xml'), (u'Economía', u'http://www.lostiempos.com/rss/lostiempos-economia.xml'), (u'Internacional', u'http://www.lostiempos.com/rss/lostiempos-internacional.xml'), (u'Vida y Futuro', u'http://www.lostiempos.com/rss/lostiempos-vida-y-futuro.xml'), (u'Tragaluz', u'http://www.lostiempos.com/rss/lostiempos-tragaluz.xml'), (u'Opiniones', u'http://www.lostiempos.com/rss/lostiempos-opiniones.xml') ] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup