Updates - El Periódico de Aragón, El Correo, Heraldo de Aragón [ES]

[desUBIKado]

Hi there:

Updates for these three newspapers in spanish from Spain

El Periódico de Aragón

Spoiler:

#!/usr/bin/env  python
# -*- coding: utf-8 -*-

__license__     = 'GPL v3'
__copyright__   = '04 December 2010, desUBIKado'
__author__      = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__     = 'v0.10'
__date__        = '09, September 2017'
'''
elperiodicodearagon.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe


class elperiodicodearagon(BasicNewsRecipe):
    title                 = u'El Periodico de Aragon'
    __author__            = u'desUBIKado'
    description           = u'Noticias desde Aragon'
    publisher             = u'elperiodicodearagon.com'
    category              = u'news, politics, Spain, Aragon'
    oldest_article        = 1
    delay                 = 1
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    language              = 'es'
    masthead_url          = 'http://pdf.elperiodicodearagon.com/img/logotipo.gif'
    encoding              = 'iso-8859-1'
    remove_empty_feeds    = True
    remove_javascript     = True

 
    feeds              = [
                           (u'Portada', u'http://zetaestaticos.com/aragon/rss/portada_es.xml'),
                           (u'Arag\xf3n', u'http://zetaestaticos.com/aragon/rss/2_es.xml'),
                           (u'Internacional', u'http://zetaestaticos.com/aragon/rss/4_es.xml'),
                           (u'Espa\xf1a', u'http://zetaestaticos.com/aragon/rss/3_es.xml'),                          
                           (u'Econom\xeda', u'http://zetaestaticos.com/aragon/rss/5_es.xml'),
                           (u'Deportes', u'http://zetaestaticos.com/aragon/rss/7_es.xml'),
                           (u'Real Zaragoza', u'http://zetaestaticos.com/aragon/rss/10_es.xml'),
                           (u'Tecnyconta Zaragoza', u'http://zetaestaticos.com/aragon/rss/91_es.xml'),
                           (u'Monta\xf1ismo', u'http://zetaestaticos.com/aragon/rss/354_es.xml'),
                           (u'Opini\xf3n', u'http://zetaestaticos.com/aragon/rss/103_es.xml'),
                           (u'Tema del d\xeda', u'http://zetaestaticos.com/aragon/rss/102_es.xml'),
                           (u'Escenarios', u'http://zetaestaticos.com/aragon/rss/105_es.xml'),
                           (u'Sociedad', u'http://zetaestaticos.com/aragon/rss/104_es.xml'),
                           (u'Gente', u'http://zetaestaticos.com/aragon/rss/330_es.xml'),
                           (u'Espacio 3', u'http://zetaestaticos.com/aragon/rss/328_es.xml'),
                           (u'Fiestas del Pilar', u'http://zetaestaticos.com/aragon/rss/107_es.xml'),
                           (u'Semana Santa', u'http://zetaestaticos.com/aragon/rss/385_es.xml')
                           ,(u'La crónica de Valdejal\xf3n', u'http://zetaestaticos.com/aragon/rss/206_es.xml')
                           ,(u'La crónica de Campo de Borja', u'http://zetaestaticos.com/aragon/rss/208_es.xml')
                           ,(u'La crónica de Ejea y sus pueblos', u'http://zetaestaticos.com/aragon/rss/212_es.xml')
                           ,(u'La crónica del Bajo Gállego', u'http://zetaestaticos.com/aragon/rss/205_es.xml')
                           ,(u'La crónica del Campo de Cariñena', u'http://zetaestaticos.com/aragon/rss/207_es.xml')
                           ,(u'La crónica de la Ribera Alta del Ebro', u'http://zetaestaticos.com/aragon/rss/211_es.xml')
                           ,(u'La crónica del Campo de Belchite', u'http://zetaestaticos.com/aragon/rss/331_es.xml')                           
                         ]

                         

    remove_tags_before = dict(name='div' , attrs={'class':'Pagina'})
    remove_tags_after  = dict(name='div' , attrs={'class':'ComentariosNew'})                                                                             
    
    keep_only_tags     = [dict(name='div', attrs={'class':'Pagina'})]     
    
    remove_tags        = [
                          dict(name='nav', attrs={'class':['Compartir','HerramientasConversacion Herramientas']}),
                          dict(name='h5', attrs={'class':['CintilloBox']}),
                          dict(name='div', attrs={'class':['BoxMenu BoxMenuConFoto','BxGalerias','ConStick','HerramientasComentarioNew Herramientas','NumeroComentarioNew']}),
                          dict(name='div', attrs={'class':['BoxPestanas','Box','ColumnaDerecha','NoticiasRelacionadasDeNoticia','CintilloNoticiasRelacionadasDeNoticia']}),
                          dict(name='a', attrs={'class':['IrA BotonLink']})
                         ]
                         
                         
    # Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion)

    def get_cover_url(self):
        index = 'http://pdf.elperiodicodearagon.com/edicion.php'
        soup = self.index_to_soup(index)
        for image in soup.findAll('img',src=True):
           if image['src'].startswith('/funciones/img-public.php?key='):
              return 'http://pdf.elperiodicodearagon.com' + image['src']
        return None    
       
    extra_css = '''
                    h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:28px;}   
                    h2 {font-family:Arial,Helvetica,sans-serif; font-style:italic;font-size:14px;color:#4D4D4D;}             
                    h3 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:18px;}                        
                '''

El Correo

Spoiler:

#!/usr/bin/env  python
__license__     = 'GPL v3'
__copyright__   = '08 Januery 2011, desUBIKado'
__author__      = 'desUBIKado'
__description__ = 'Daily newspaper from Biscay'
__version__     = 'v0.14'
__date__        = '10, September 2017'
'''
http://www.elcorreo.com/
'''

import time
import re
from calibre.web.feeds.recipes import BasicNewsRecipe

class elcorreo(BasicNewsRecipe):
    author                = 'desUBIKado'
    description           = 'Daily newspaper from Biscay'
    title                 = u'El Correo'
    publisher             = 'Vocento'
    category              = 'News, politics, culture, economy, general interest'
    oldest_article        = 1
    delay                 = 1
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    masthead_url          = 'http://www.elcorreo.com/vizcaya/noticias/201002/02/Media/logo-elcorreo-nuevo.png'
    language              = 'es'
    timefmt               = '[%a, %d %b, %Y]'
    encoding              = 'utf-8'
    remove_empty_feeds    = True
    remove_javascript     = True

    feeds              = [                          
                           (u'Portada',      	 u'http://www.elcorreo.com/rss/atom/portada'),                           
                           (u'Mundo',       	 u'http://www.elcorreo.com/rss/atom/?section=internacional'),                                                   
                           (u'Bizkaia',          u'http://www.elcorreo.com/rss/atom/?section=bizkaia'),      
                           (u'Guipuzkoa',        u'http://www.elcorreo.com/rss/atom/?section=gipuzkoa'),
                           (u'Araba',            u'http://www.elcorreo.com/rss/atom/?section=araba'),
                           (u'La Rioja',         u'http://www.elcorreo.com/rss/atom/?section=larioja'),
                           (u'Miranda',          u'http://www.elcorreo.com/rss/atom/?section=miranda'),      
                           (u'Economía',         u'http://www.elcorreo.com/rss/atom/?section=economia'),                            
                           (u'Culturas',         u'http://www.elcorreo.com/rss/atom/?section=culturas'),
                           (u'Politica',         u'http://www.elcorreo.com/rss/atom/?section=politica'),                           
                           (u'Tecnología',       u'http://www.elcorreo.com/rss/atom/?section=tecnologia'),
                           (u'Gente - Estilo',   u'http://www.elcorreo.com/rss/atom/?section=gente-estilo'),                              
                           (u'Planes',           u'http://www.elcorreo.com/rss/atom/?section=planes'),
                           (u'Athletic',         u'http://www.elcorreo.com/rss/atom/?section=athletic'),   
                           (u'Alavés',           u'http://www.elcorreo.com/rss/atom/?section=alaves'),   
                           (u'Bilbao Basket',    u'http://www.elcorreo.com/rss/atom/?section=bilbaobasket'),   
                           (u'Baskonia',         u'http://www.elcorreo.com/rss/atom/?section=baskonia'),
                           (u'Deportes',         u'http://www.elcorreo.com/rss/atom/?section=deportes'),  
                           (u'Jaiak',            u'http://www.elcorreo.com/rss/atom/?section=jaiak'),
                           (u'La Blanca',        u'http://www.elcorreo.com/rss/atom/?section=la-blanca-vitoria'),
                           (u'Aste Nagusia',     u'http://www.elcorreo.com/rss/atom/?section=aste-nagusia-bilbao'),
                           (u'Semana Santa',     u'http://www.elcorreo.com/rss/atom/?section=semana-santa'),
                           (u'Festivales',       u'http://www.elcorreo.com/rss/atom/?section=festivales')     
                         ]

    keep_only_tags     = [
                          dict(name='div', attrs={'class':['col-xs-12 col-sm-12 col-md-8 col-lg-8']})                          
                         ]     

                         
    remove_tags        = [                          
                          dict(name='div', attrs={'class':['voc-topics voc-detail-grid ','voc-newsletter ','voc-author-social']}),
                          dict(name='section', attrs={'class':['voc-ficha-detail voc-file-sports']})
                         ]

                         
    remove_tags_before = dict(name='div' , attrs={'class':'col-xs-12 col-sm-12 col-md-8 col-lg-8'})
    remove_tags_after  = dict(name='div' , attrs={'class':'col-xs-12 col-sm-12 col-md-8 col-lg-8'})  
    
    
    
    _processed_links = []
          
    def get_article_url(self, article):
       
       link = article.get('link', None)
       
       if link is None:
           return article               
              
       # modificamos la url de las noticias de los equipos deportivos para que funcionen, por ejemplo:
       # http://athletic.elcorreo.com/noticias/201407/27/muniain-estrella-athletic-para-20140727093046.html
       # http://m.elcorreo.com/noticias/201407/27/muniain-estrella-athletic-para-20140727093046.html?external=deportes/athletic
       
       parte = link.split('/')
       
       if parte[2] == 'athletic.elcorreo.com':
	  link = 'http://www.elcorreo.com/' + parte[3] + '/' + parte[4] + '/' + parte[5] + '/' + parte[6] + '?external=deportes/athletic'
       else:
	   if parte[2] == 'baskonia.elcorreo.com':
	      link = 'http://www.elcorreo.com/' + parte[3] + '/' + parte[4] + '/' + parte[5] + '/' + parte[6] + '?external=deportes/baskonia'
	   else:
	       if parte[2] == 'bilbaobasket.elcorreo.com':
	          link = 'http://www.elcorreo.com/' + parte[3] + '/' + parte[4] + '/' + parte[5] + '/' + parte[6] + '?external=deportes/bilbaobasket'
	       else:   
		   if parte[2] == 'alaves.elcorreo.com':
	              link = 'http://www.elcorreo.com/' + parte[3] + '/' + parte[4] + '/' + parte[5] + '/' + parte[6] + '?external=deportes/alaves'
       
       
       # A veces el mismo articulo aparece en la versión de Alava y en la de Bizkaia. Por ejemplo:
       # http://www.elcorreo.com/alava/deportes/motor/formula-1/201407/27/ecclestone-quiere-briatore-ayude-20140727140820-rc.html
       # http://www.elcorreo.com/bizkaia/deportes/motor/formula-1/201407/27/ecclestone-quiere-briatore-ayude-20140727140820-rc.html
       # para controlar los duplicados, unificamos las url para que sean siempre de bizkaia (excepto para la sección "araba")
       
       if ((parte[3] == 'alava') and (parte[4] != 'araba')):
	  link = link.replace('elcorreo.com/alava', 'elcorreo.com/bizkaia')
                               
       
       # Controlamos si el artículo ha sido incluido en otro feed para eliminarlo 
	
       if not (link in self._processed_links):
            self._processed_links.append(link)
       else:
            link = None                       
       
       
       return link

    # Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion)
          
    def get_cover_url(self):
       cover = None
       st = time.localtime()
       year = str(st.tm_year)       
       month = "%.2d" % st.tm_mon
       day = "%.2d" % st.tm_mday
		#http://info.elcorreo.com/pdf/07082013-viz.pdf
       cover='http://info.elcorreo.com/pdf/'+ day +  month + year +'-viz.pdf'       
       br = BasicNewsRecipe.get_browser(self)
       try:
           br.open(cover)
       except:
           self.log("\nPortada no disponible")
           cover ='http://www.elcorreo.com/vizcaya/noticias/201002/02/Media/logo-elcorreo-nuevo.png'
       return cover             
                          
    # Para cambiar el estilo del texto
 
    extra_css = '''
		    h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:28px;}   
                    h2 {font-family:georgia,serif; font-style:italic; font-weight:normal;font-size:16px;color:#4D4D4D;}             
                    h3 {font-family:georgia,serif; font-weight:bold;font-size:18px;}
                '''      

    preprocess_regexps = [     

    # Para presentar la imagen de los video incrustados                           
                           (re.compile(r'stillURLVideo: \'', re.DOTALL|re.IGNORECASE), lambda match: '</script><img src="'),  
                           (re.compile(r'.jpg\',', re.DOTALL|re.IGNORECASE), lambda match: '.jpg"><SCRIPT TYPE="text/JavaScript"'),

    # Para quitar el punto de la lista                                             
                           (re.compile(r'<li class="destacada">', re.DOTALL|re.IGNORECASE), lambda match: '<div class="destacada"></div>')                         

                         ]

Heraldo de Aragón

Spoiler:

#!/usr/bin/env  python
__license__     = 'GPL v3'
__copyright__   = '04 December 2010, desUBIKado'
__author__      = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__     = 'v0.08'
__date__        = '10, September 2017'
'''
http://www.heraldo.es/
'''

import time
import re
from calibre.web.feeds.news import BasicNewsRecipe

class heraldo(BasicNewsRecipe):
    author        = 'desUBIKado'
    description   = 'Daily newspaper from Aragon'
    title          = u'Heraldo de Aragon'
    publisher      = 'Grupo Heraldo'
    category       = 'News, politics, culture, economy, general interest'
    language       = 'es'
    timefmt        = '[%a, %d %b, %Y]'
    oldest_article = 2
    delay          = 1
    max_articles_per_feed = 100
    use_embedded_content  = False
    masthead_url          = 'http://aureel.com/es/wp-content/uploads/sites/4/2016/07/Heraldo_de_Arago%CC%81n.png'
    remove_empty_feeds    = True
    remove_javascript = True
    no_stylesheets = True
    

    feeds          = [
                        (u'Noticias', u'http://www.heraldo.es/index.php/mod.portadas/mem.rss')
                     ]

          
    keep_only_tags     = [dict(name='div', attrs={'class':['row-f2 brd-row-f4 bck-row-f1-f1 padd-t padd-btt con n-marg-btt']}),
			  dict(name='div', attrs={'id':['dts','com']}),
			  dict(name='img', attrs={'class':['lazy']})]			  			  
	  	
    remove_tags        = [dict(name='a', attrs={'class':['com flo-r','enl-if','enl-df','next_com']}),
                          dict(name='div', attrs={'class':['brb-b-s con marg-btt','cnt-rel con','col5-f1','tit txt-wh f-s con','con cont-top ','col5-f1 flo-l','cnt-rel brr','caj_part con','caj_topic con']}),
			  dict(name='div', attrs={'id':['cont-Top-8760','caj-pub','8760-cpt1','caj_topic con','slider-oferplan','cont-Top-']}),
                          dict(name='form', attrs={'class':'form'}), 
			  dict(name='ul', attrs={'class':['tabs-nav','men_nav con hg_2n','lst-not-f2 con  ']}),
			  dict(name='span', attrs={'class':['flo-r']}),
                          dict(name='ul', attrs={'id':['cont-tags','pag-1','pag-cnt-I-']})]
  	

    remove_tags_before = dict(name='div' , attrs={'id':'dts'})
    remove_tags_after  = dict(name='div' , attrs={'id':'com'})
   
    
    def get_cover_url(self):
       cover = None
       st = time.localtime()
       year = str(st.tm_year)
       month = "%.2d" % st.tm_mon
       day = "%.2d" % st.tm_mday                
       
       #http://img.kiosko.net/2017/09/10/es/heraldo_aragon.750.jpg
       cover='http://img.kiosko.net/'+ year +'/'+  month + '/' + day +'/es/heraldo_aragon.750.jpg'
       
       br = BasicNewsRecipe.get_browser(self)
       try:
           br.open(cover)
       except:
           self.log("\nPortada no disponible")
           cover ='http://aureel.com/es/wp-content/uploads/sites/4/2016/07/Heraldo_de_Arago%CC%81n.png'
       return cover
    

    extra_css = '''                    
                    h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:28px;}   
                    h2 {font-family:georgia,serif; font-style:italic; font-weight:normal;font-size:22px;color:#4D4D4D;}             
                    .ladillo {font-family:georgia,serif; font-weight:bold;font-size:18px;}                      
		    .firm, .sp, .fech, ".com flo-r" {font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:12px;}                                   
                    img{margin-bottom: 0.4em}
                '''      

    preprocess_regexps = [     
    
# Para separar los comentarios con una linea en blanco
                           (re.compile(r'<div class="tit-f2">', re.DOTALL|re.IGNORECASE), lambda match: '<br /><br /><div class="tit-f2">'),
                           (re.compile(r'<div id="com"', re.DOTALL|re.IGNORECASE), lambda match: '<br><div id="com"'),
                           
# Para ver las imágenes de las noticias
                           (re.compile(r'<img class="lazy" data-original="', re.DOTALL|re.IGNORECASE), lambda match: '<img src="http://www.heraldo.es')

                         ]

Regards

desUBIKado