Update El Periodica de Aragon and El Correo

This commit is contained in:
Kovid Goyal 2013-08-09 15:29:29 +05:30
parent 4ce6bb4378
commit 840f316703
2 changed files with 30 additions and 35 deletions

View File

@ -3,10 +3,10 @@ __license__ = 'GPL v3'
__copyright__ = '08 Januery 2011, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Biscay'
__version__ = 'v0.08'
__date__ = '08, Januery 2011'
__version__ = 'v0.10'
__date__ = '07, August 2013'
'''
[url]http://www.elcorreo.com/[/url]
http://www.elcorreo.com/
'''
import time
@ -24,6 +24,7 @@ class heraldo(BasicNewsRecipe):
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 = 'iso-8859-1'
@ -33,15 +34,15 @@ class heraldo(BasicNewsRecipe):
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'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'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')
(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 = [
@ -54,14 +55,14 @@ class heraldo(BasicNewsRecipe):
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','separa','separacion','compartir','tags_relacionados']}),
dict(name='div', attrs={'class':['moduloBuscadorDeportes','modulo-gente','moddestacadopeq','OpcArt','articulopiniones']}),
dict(name='div', attrs={'class':['modulo-especial','publiEspecial']}),
dict(name='div', attrs={'id':['articulopina']}),
dict(name='div', attrs={'class':['modulo-especial','publiEspecial','carruselNoticias','vj','modulocomun2']}),
dict(name='div', attrs={'id':['articulopina','webs_asociadas']}),
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'})
remove_tags_after = dict(name='div' , attrs={'class':'robapaginas'})
def get_cover_url(self):
cover = None
@ -69,10 +70,8 @@ class heraldo(BasicNewsRecipe):
year = str(st.tm_year)
month = "%.2d" % st.tm_mon
day = "%.2d" % st.tm_mday
#[url]http://img.kiosko.net/2011/01/02/es/elcorreo.750.jpg[/url]
#[url]http://info.elcorreo.com/pdf/06012011-viz.pdf[/url]
cover='http://info.elcorreo.com/pdf/'+ day + month + year +'-viz.pdf'
# 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)
@ -92,29 +91,27 @@ class heraldo(BasicNewsRecipe):
img{margin-bottom: 0.4em}
'''
preprocess_regexps = [
# To present the image of the embedded video
# Para presentar la imagen de los video incrustados
(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
# Para separar los parrafos con una linea en blanco
(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
# Para poner una linea en blanco entre el subttulo y la fecha y hora de la noticia
(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
# Para poner una linea en blanco entre la entradilla de los videos incrustados y el texto anterior
(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
# Para sacar las fotos a partir de la primera cuando se presentan como una galeria
(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
# Para quitar el enlace del titulo
(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>'),

View File

@ -5,8 +5,8 @@ __license__ = 'GPL v3'
__copyright__ = '04 December 2010, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__ = 'v0.08'
__date__ = '13, November 2011'
__version__ = 'v0.09'
__date__ = '07, August 2013'
'''
elperiodicodearagon.com
'''
@ -25,11 +25,11 @@ class elperiodicodearagon(BasicNewsRecipe):
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
conversion_options = {
'comments' : description
,'tags' : category
@ -56,23 +56,21 @@ class elperiodicodearagon(BasicNewsRecipe):
(u'Fiestas del Pilar', u'http://zetaestaticos.com/aragon/rss/107_es.xml')
]
remove_attributes = ['height','width']
keep_only_tags = [dict(name='div', attrs={'id':'Noticia'})]
# Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion)
def get_cover_url(self):
index = 'http://pdf.elperiodicodearagon.com/'
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('http://pdf.elperiodicodearagon.com/funciones/portada-preview.php?eid='):
return image['src'].rstrip('format=2') + 'format=1'
if image['src'].startswith('/funciones/img-public.php?key='):
return 'http://pdf.elperiodicodearagon.com' + image['src']
return None
# Usamos la versión para móviles
def print_version(self, url):
return url.replace('http://www.elperiodicodearagon.com/', 'http://www.elperiodicodearagon.com/m/')
return url.replace('http://www.elperiodicodearagon.com/', 'http://www.elperiodicodearagon.com/m/')