#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '08 Januery 2011, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Biscay'
__version__ = 'v0.08'
__date__ = '08, Januery 2011'
'''
http://www.elcorreo.com/
'''
import time
import re
from calibre.web.feeds.news import BasicNewsRecipe
class heraldo(BasicNewsRecipe):
author = 'desUBIKado'
description = 'Daily newspaper from Biscay'
title = u'El Correo'
publisher = 'Vocento'
category = 'News, politics, culture, economy, general interest'
oldest_article = 2
delay = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'es'
timefmt = '[%a, %d %b, %Y]'
encoding = 'iso-8859-1'
remove_empty_feeds = True
remove_javascript = False
feeds = [
(u'Portada', u'http://www.elcorreo.com/vizcaya/portada.xml'),
(u'Local', u'http://www.elcorreo.com/vizcaya/rss/feeds/vizcaya.xml'),
(u'Internacional', u'hhttp://www.elcorreo.com/vizcaya/rss/feeds/internacional.xml'),
(u'Econom\xeda', u'http://www.elcorreo.com/vizcaya/rss/feeds/economia.xml'),
(u'Pol\xedtica', u'http://www.elcorreo.com/vizcaya/rss/feeds/politica.xml'),
(u'Opini\xf3n', u'http://www.elcorreo.com/vizcaya/rss/feeds/opinion.xml'),
(u'Deportes', u'http://www.elcorreo.com/vizcaya/rss/feeds/deportes.xml'),
(u'Sociedad', u'http://www.elcorreo.com/vizcaya/rss/feeds/sociedad.xml'),
(u'Cultura', u'http://www.elcorreo.com/vizcaya/rss/feeds/cultura.xml'),
(u'Televisi\xf3n', u'http://www.elcorreo.com/vizcaya/rss/feeds/television.xml'),
(u'Gente', u'http://www.elcorreo.com/vizcaya/rss/feeds/gente.xml')
]
keep_only_tags = [
dict(name='div', attrs={'class':['grouphead','date','art_head','story-texto','text','colC_articulo','contenido_comentari os']}),
dict(name='div' , attrs={'id':['articulo','story-texto','story-entradilla']})
]
remove_tags = [
dict(name='div', attrs={'class':['art_barra','detalles-opinion','formdenunciar','modulo calculadoras','nubetags','pie']}),
dict(name='div', attrs={'class':['mod_lomas','bloque_lomas','blm_header','link-app3','link-app4','botones_listado']}),
dict(name='div', attrs={'class':['navegacion_galeria','modulocanalpromocion','separ a','separacion','compartir','tags_relacionados']}),
dict(name='div', attrs={'class':['moduloBuscadorDeportes','modulo-gente','moddestacadopeq','OpcArt','articulopinione s']}),
dict(name='div', attrs={'class':['modulo-especial','publiEspecial']}),
dict(name='div', attrs={'id':['articulopina']}),
dict(name='br', attrs={'class':'clear'}),
dict(name='form', attrs={'name':'frm_conversor2'})
]
remove_tags_before = dict(name='div' , attrs={'class':'articulo '})
remove_tags_after = dict(name='div' , attrs={'class':'comentarios'})
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/2011/01/02/es/elcorreo.750.jpg
#
http://info.elcorreo.com/pdf/06012011-viz.pdf
cover='http://info.elcorreo.com/pdf/'+ day + month + year +'-viz.pdf'
br = BasicNewsRecipe.get_browser()
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
extra_css = '''
h1, .headline {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:30px;}
h2, .subhead {font-family:Arial,Helvetica,sans-serif; font-style:italic; font-weight:normal;font-size:18px;}
h3, .overhead {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:16px;}
h4 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:16px;}
h5 {font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:16px;}
h6 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:16px;}
.date,.byline, .photo {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:14px;}
img{margin-bottom: 0.4em}
'''
preprocess_regexps = [
# To present the image of the embedded video
(re.compile(r'var RUTA_IMAGEN', re.DOTALL|re.IGNORECASE), lambda match: '</script><img src'),
(re.compile(r'.jpg";', re.DOTALL|re.IGNORECASE), lambda match: '.jpg">'),
(re.compile(r'var SITIO = "elcorreo";', re.DOTALL|re.IGNORECASE), lambda match: '<SCRIPT TYPE="text/JavaScript"'),
# To separate paragraphs with a blank line
(re.compile(r'<div class="p"', re.DOTALL|re.IGNORECASE), lambda match: '<p></p><div class="p"'),
# To put a blank line between the subtitle and the date and time of the news
(re.compile(r'<div class="date">', re.DOTALL|re.IGNORECASE), lambda match: '<br><div class="date">'),
# To put a blank line between the intro of the embedded videos and the previous text
(re.compile(r'<div class="video"', re.DOTALL|re.IGNORECASE), lambda match: '<br><div class="video"'),
# To view photos from the first when these are presented as a gallery
(re.compile(r'src="/img/shim.gif"', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'rel=', re.DOTALL|re.IGNORECASE), lambda match: 'src='),
# To remove the link of the title
(re.compile(r'<h1 class="headline">\n<a href="', re.DOTALL|re.IGNORECASE), lambda match: '<h1 class="'),
(re.compile(r'</a>\n</h1>', re.DOTALL|re.IGNORECASE), lambda match: '</h1>'),
]