home *** CD-ROM | disk | FTP | other *** search
- # -*- coding: utf-8 -*-
- __license__ = 'GPL v3'
- __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
- '''
- www.elpais.com/diario/
- '''
-
- from calibre import strftime
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class ElPaisImpresa(BasicNewsRecipe):
- title = 'El País - edicion impresa'
- __author__ = 'Darko Miletic'
- description = 'el periodico global en Espa├▒ol'
- publisher = 'EDICIONES EL PAIS, S.L.'
- category = 'news, politics,Spain,actualidad,noticias,informacion,videos,fotografias,audios,graficos,nacional,internacional,deportes,economia,tecnologia,cultura,gente,television,sociedad,opinion,blogs,foros,chats,encuestas,entrevistas,participacion'
- no_stylesheets = True
- encoding = 'latin1'
- use_embedded_content = False
- language = 'es'
- publication_type = 'newspaper'
- masthead_url = 'http://www.elpais.com/im/tit_logo_global.gif'
- index = 'http://www.elpais.com/diario/'
- extra_css = ' p{text-align: justify} body{ text-align: left; font-family: Georgia,"Times New Roman",Times,serif } h2{font-family: Arial,Helvetica,sans-serif} img{margin-bottom: 0.4em} '
-
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- feeds = [
- (u'Internacional' , index + u'internacional/' )
- ,(u'Espa├▒a' , index + u'espana/' )
- ,(u'Economia' , index + u'economia/' )
- ,(u'Opinion' , index + u'opinion/' )
- ,(u'Vi├▒etas' , index + u'vineta/' )
- ,(u'Sociedad' , index + u'sociedad/' )
- ,(u'Cultura' , index + u'cultura/' )
- ,(u'Tendencias' , index + u'tendencias/' )
- ,(u'Gente' , index + u'gente/' )
- ,(u'Obituarios' , index + u'obituarios/' )
- ,(u'Deportes' , index + u'deportes/' )
- ,(u'Pantallas' , index + u'radioytv/' )
- ,(u'Ultima' , index + u'ultima/' )
- ,(u'Educacion' , index + u'educacion/' )
- ,(u'Saludo' , index + u'salud/' )
- ,(u'Ciberpais' , index + u'ciberpais/' )
- ,(u'EP3' , index + u'ep3/' )
- ,(u'Cine' , index + u'cine/' )
- ,(u'Babelia' , index + u'babelia/' )
- ,(u'El viajero' , index + u'viajero/' )
- ,(u'Negocios' , index + u'negocios/' )
- ,(u'Domingo' , index + u'domingo/' )
- ,(u'El Pais semanal' , index + u'eps/' )
- ,(u'Quadern Catalunya' , index + u'quadern-catalunya/' )
- ]
-
- keep_only_tags=[dict(attrs={'class':['cabecera_noticia','contenido_noticia']})]
- remove_attributes=['width','height']
- remove_tags=[dict(name='link')]
-
- def parse_index(self):
- totalfeeds = []
- lfeeds = self.get_feeds()
- for feedobj in lfeeds:
- feedtitle, feedurl = feedobj
- self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
- articles = []
- soup = self.index_to_soup(feedurl)
- for item in soup.findAll('a',attrs={'class':['g19r003','g19i003','g17r003','g17i003']}):
- url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
- title = self.tag_to_string(item)
- date = strftime(self.timefmt)
- articles.append({
- 'title' :title
- ,'date' :date
- ,'url' :url
- ,'description':''
- })
- totalfeeds.append((feedtitle, articles))
- return totalfeeds
-
- def print_version(self, url):
- return url + '?print=1'
-