Updated recipe: El periódico de Aragón (Spanish)

[desUBIKado]

Hi there:

I updated the recipe for El Periódico de Aragón.

Basically I changed the font style and now present an image when there is an embedded YouTube video.

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

__license__     = 'GPL v3'
__copyright__   = '04 December 2010, desUBIKado'
__author__      = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__     = 'v0.07'
__date__        = '06, February 2011'
'''
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        = 2
    delay                 = 0
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    language              = 'es'
    encoding              = 'utf8'
    remove_empty_feeds    = True
    remove_javascript     = True


    conversion_options = {
                             'comments'  : description
                            ,'tags'      : category
                            ,'language'  : language
                            ,'publisher' : publisher
                         }

    feeds              = [
                           (u'Arag\xf3n', u'http://elperiodicodearagon.com/RSS/2.xml'),
                           (u'Internacional', u'http://elperiodicodearagon.com/RSS/4.xml'),
                           (u'Espa\xf1a', u'http://elperiodicodearagon.com/RSS/3.xml'),                          
                           (u'Econom\xeda', u'http://elperiodicodearagon.com/RSS/5.xml'),
                           (u'Deportes', u'http://elperiodicodearagon.com/RSS/7.xml'),
                           (u'Real Zaragoza', u'http://elperiodicodearagon.com/RSS/10.xml'),
                           (u'Opini\xf3n', u'http://elperiodicodearagon.com/RSS/103.xml'),
                           (u'Escenarios', u'http://elperiodicodearagon.com/RSS/105.xml'),
                           (u'Sociedad', u'http://elperiodicodearagon.com/RSS/104.xml'),
                           (u'Gente', u'http://elperiodicodearagon.com/RSS/330.xml')
                         ]


    extra_css = '''
                    h3 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:30px;}
                    h2 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:18px;}
                    h4 {font-family:Arial,Helvetica,sans-serif; font-style:italic; font-weight:normal;font-size:20px;}
                    .columnaDeRecursosRelacionados {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:14px;}
                    img{margin-bottom: 0.4em}
		'''

    remove_attributes = ['height','width']

    keep_only_tags     = [dict(name='div', attrs={'id':'contenidos'})]                          


    # Quitar toda la morralla 

    remove_tags        = [dict(name='ul', attrs={'class':'herramientasDeNoticia'}),
                          dict(name='span', attrs={'class':'MasInformacion '}),
                          dict(name='span', attrs={'class':'MasInformacion'}),
                          dict(name='div', attrs={'class':'Middle'}),
                          dict(name='div', attrs={'class':'MenuCabeceraRZaragoza'}),
                          dict(name='div', attrs={'id':'MenuCabeceraRZaragoza'}),
                          dict(name='div', attrs={'class':'MenuEquipo'}),
                          dict(name='div', attrs={'class':'TemasRelacionados'}),
                          dict(name='div', attrs={'class':'GaleriaEnNoticia'}),
                          dict(name='div', attrs={'class':'Recorte'}),
                          dict(name='div', attrs={'id':'NoticiasenRecursos'}),
                          dict(name='div', attrs={'id':'NoticiaEnPapel'}),
                          dict(name='p', attrs={'class':'RecorteEnNoticias'}),
                          dict(name='div', attrs={'id':'Comparte'}),
                          dict(name='div', attrs={'id':'CajaComparte'}),
                          dict(name='a', attrs={'class':'EscribirComentario'}),
                          dict(name='a', attrs={'class':'AvisoComentario'}),
                          dict(name='div', attrs={'class':'CajaAvisoComentario'}),                        
                          dict(name='div', attrs={'class':'navegaNoticias'}),
                          dict(name='div', attrs={'class':'Mensaje'}), 
                          dict(name='div', attrs={'id':'PaginadorDiCom'}),
                          dict(name='div', attrs={'id':'CajaAccesoCuentaUsuario'}),
                          dict(name='div', attrs={'id':'CintilloComentario'}),
                          dict(name='div', attrs={'id':'EscribeComentario'}),
                          dict(name='div', attrs={'id':'FormularioComentario'}),
                          dict(name='div', attrs={'id':'FormularioNormas'})]

    # Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion)

    def get_cover_url(self):
        index = 'http://pdf.elperiodicodearagon.com/'
        soup = self.index_to_soup(index)
        for image in soup.findAll('img',src=True):
           if image['src'].startswith('http://pdf.elperiodicodearagon.com/funciones/portada-preview.php?eid='):
              return image['src'].rstrip('format=2') + 'format=1'
        return None    
   
    # Para quitar espacios entre la noticia y los comentarios (lineas 1 y 2)
    # El indice no apuntaba correctamente al empiece de la noticia (linea 3)

    preprocess_regexps = [
        (re.compile(r'<p>&nbsp;</p>', re.DOTALL|re.IGNORECASE), lambda match: ''),
        (re.compile(r'<p> </p>', re.DOTALL|re.IGNORECASE), lambda match: ''),
        (re.compile(r'<p id="">', re.DOTALL|re.IGNORECASE), lambda match: '<p>') 
        ]
  
    # Para sustituir el video incrustado de YouTube por una imagen

    def preprocess_html(self, soup):
        for video_yt in soup.findAll('iframe',{'title':'YouTube video player'}):
            if video_yt:
               video_yt.name = 'img'
               fuente = video_yt['src']
               fuente2 = fuente.replace('http://www.youtube.com/embed/','http://img.youtube.com/vi/')
               video_yt['src'] = fuente2 + '/0.jpg'

        return soup

Bye