From 09ff8524214cc51091f8ec8dca616e2675e40789 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 8 Jan 2011 06:53:24 -0700 Subject: [PATCH] El Publico by Gerardo Diez. Fixes #405 (New news feed) --- resources/recipes/deia.recipe | 2 +- resources/recipes/el_publico.recipe | 43 +++++++++++++++++++++++++ resources/recipes/elpais_impreso.recipe | 8 ++--- 3 files changed, 48 insertions(+), 5 deletions(-) create mode 100644 resources/recipes/el_publico.recipe diff --git a/resources/recipes/deia.recipe b/resources/recipes/deia.recipe index 980d59d3d1..5d39be9a10 100644 --- a/resources/recipes/deia.recipe +++ b/resources/recipes/deia.recipe @@ -22,7 +22,7 @@ class Deia(BasicNewsRecipe): cover_url ='http://2.bp.blogspot.com/_RjrWzC6tI14/TM6jrPLaBZI/AAAAAAAAFaI/ayffwxidFEY/s1600/2009-10-13-logo-deia.jpg' timefmt ='[%a, %d %b, %Y]' encoding ='utf8' - language ='es_ES' + language ='es' remove_javascript =True remove_tags_after =dict(id='Texto') remove_tags_before =dict(id='Texto') diff --git a/resources/recipes/el_publico.recipe b/resources/recipes/el_publico.recipe new file mode 100644 index 0000000000..d0da739b03 --- /dev/null +++ b/resources/recipes/el_publico.recipe @@ -0,0 +1,43 @@ +#!/usr/bin/env python +__license__ = 'GPL v3' +__author__ = 'Gerardo Diez' +__copyright__ = 'Gerardo Diez' +description = 'Main daily newspaper from Spain - v1.00 (05, Enero 2011)' +__docformat__ = 'restructuredtext en' + +''' +publico.es +''' +from calibre.web.feeds.recipes import BasicNewsRecipe +class Publico(BasicNewsRecipe): + title =u'Publico.es' + __author__ ='Gerardo Diez' + publisher =u'Mediapubli Sociedad de Publicaciones y Ediciones S.L.' + category ='news, politics, finances, world, spain, science, catalunya' + oldest_article =1 + max_articles_per_feed =100 + simultaneous_downloads =10 + cover_url =u'http://imagenes.publico.es/css/img/logo_publico.gif' + timefmt ='[%a, %d %b, %Y]' + encoding ='utf8' + language ='es' + remove_javascript =True + no_stylesheets =True + keep_only_tags =dict(id='main') + remove_tags =[ + dict(name='div', attrs={'class':['Noticias_642x50', 'contInfo ancho']}), + dict(name='ul', attrs={'class':['navComentarios', 'comentarios']}), + dict(name='div', attrs={'id':['commentsContext', 'toolbar', 'comentarios']}), + dict(name='h5', attrs={'id':'comentarios'}) + ] + feeds =[(u'Internacional', u'http://www.publico.es/estaticos/rss/internacional'), + (u'Espa\xf1a', u'http://www.publico.es/estaticos/rss/espana'), + (u'Dinero', u'http://www.publico.es/estaticos/rss/dinero'), + (u'Ciencias', u'http://www.publico.es/estaticos/rss/ciencias'), + (u'Culturas', u'http://www.publico.es/estaticos/rss/culturas'), + (u'Deportes', u'http://www.publico.es/estaticos/rss/deportes'), + (u'Televisi\xf3n y Gente', u'http://www.publico.es/estaticos/rss/televisionygente'), + (u'Catalu\xf1a', u'http://www.publico.es/estaticos/rss/catalunya'), + (u'Viajes', u'http://www.publico.es/estaticos/rss/viajes')] + + diff --git a/resources/recipes/elpais_impreso.recipe b/resources/recipes/elpais_impreso.recipe index 130013286c..b22a41dcec 100644 --- a/resources/recipes/elpais_impreso.recipe +++ b/resources/recipes/elpais_impreso.recipe @@ -17,7 +17,7 @@ class ElPais_RSS(BasicNewsRecipe): no_stylesheets = True encoding = 'cp1252' use_embedded_content = False - language = 'es_ES' + language = 'es' remove_empty_feeds = True publication_type = 'newspaper' masthead_url = 'http://www.elpais.com/im/tit_logo.gif' @@ -57,14 +57,14 @@ class ElPais_RSS(BasicNewsRecipe): ,(u'Madrid' , u'http://www.elpais.com/rss/feed.html?feedId=1016' ) ,(u'Pais Vasco' , u'http://www.elpais.com/rss/feed.html?feedId=17062') ,(u'Galicia' , u'http://www.elpais.com/rss/feed.html?feedId=17063') - ,(u'Opinion' , u'http://www.elpais.com/rss/feed.html?feedId=1003' ) - ,(u'Sociedad' , u'http://www.elpais.com/rss/feed.html?feedId=1004' ) + ,(u'Opinion' , u'http://www.elpais.com/rss/feed.html?feedId=1003' ) + ,(u'Sociedad' , u'http://www.elpais.com/rss/feed.html?feedId=1004' ) ,(u'Deportes' , u'http://www.elpais.com/rss/feed.html?feedId=1007' ) ,(u'Cultura' , u'http://www.elpais.com/rss/feed.html?feedId=1008' ) ,(u'Cine' , u'http://www.elpais.com/rss/feed.html?feedId=17052') ,(u'Literatura' , u'http://www.elpais.com/rss/feed.html?feedId=17053') ,(u'Musica' , u'http://www.elpais.com/rss/feed.html?feedId=17051') - ,(u'Arte' , u'http://www.elpais.com/rss/feed.html?feedId=17060') + ,(u'Arte' , u'http://www.elpais.com/rss/feed.html?feedId=17060') ,(u'Tecnologia' , u'http://www.elpais.com/rss/feed.html?feedId=1005' ) ,(u'Economia' , u'http://www.elpais.com/rss/feed.html?feedId=1006' ) ,(u'Ciencia' , u'http://www.elpais.com/rss/feed.html?feedId=17068')