| 1 |
#!/usr/bin/env python |
| 2 |
__license__ = 'GPL v3' |
| 3 |
__copyright__ = '5, January 2011 Gerardo Diez<[email protected]> & desUBIKado' |
| 4 |
__author__ = 'desUBIKado, based on an earlier version by Gerardo Diez' |
| 5 |
__version__ = 'v1.01' |
| 6 |
__date__ = '13, November 2011' |
| 7 |
|
| 8 |
''' |
| 9 |
[url]http://www.expansion.com/[/url] |
| 10 |
''' |
| 11 |
|
| 12 |
import re |
| 13 |
import time |
| 14 |
|
| 15 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 16 |
|
| 17 |
|
| 18 |
class expansion_spanish(BasicNewsRecipe): |
| 19 |
__author__ = 'Gerardo Diez & desUBIKado' |
| 20 |
description = 'Financial news from Spain' |
| 21 |
title = 'Expansion' |
| 22 |
publisher = 'Unidad Editorial Internet, S.L.' |
| 23 |
category = 'news, finances, Spain' |
| 24 |
oldest_article = 2 |
| 25 |
simultaneous_downloads = 10 |
| 26 |
max_articles_per_feed = 100 |
| 27 |
timefmt = '[%a, %d %b, %Y]' |
| 28 |
encoding = 'iso-8859-15' |
| 29 |
language = 'es' |
| 30 |
use_embedded_content = False |
| 31 |
remove_javascript = True |
| 32 |
no_stylesheets = True |
| 33 |
remove_empty_feeds = True |
| 34 |
|
| 35 |
keep_only_tags = dict(name='div', attrs={'class': ['noticia primer_elemento']}) |
| 36 |
|
| 37 |
remove_tags = [ |
| 38 |
dict( |
| 39 |
name='div', |
| 40 |
attrs={ |
| 41 |
'class': [ |
| 42 |
'compartir', |
| 43 |
'metadata_desarrollo_noticia', |
| 44 |
'relacionadas', |
| 45 |
'mas_info', |
| 46 |
'publicidad publicidad_textlink', |
| 47 |
'ampliarfoto', |
| 48 |
'tit_relacionadas', |
| 49 |
'interact', |
| 50 |
'paginacion estirar', |
| 51 |
'sumario derecha', |
| 52 |
] |
| 53 |
}, |
| 54 |
), # noqa: E501 |
| 55 |
dict(name='ul', attrs={'class': ['bolos_desarrollo_noticia', 'not_logged']}), |
| 56 |
dict(name='span', attrs={'class': ['comentarios']}), |
| 57 |
dict(name='p', attrs={'class': ['cintillo_comentarios', 'cintillo_comentarios formulario']}), |
| 58 |
dict(name='div', attrs={'id': ['comentarios_lectores_listado', 'comentar']}), |
| 59 |
] |
| 60 |
feeds = [ |
| 61 |
('Portada', 'http://estaticos.expansion.com/rss/portada.xml'), |
| 62 |
('Portada: Bolsas', 'http://estaticos.expansion.com/rss/mercados.xml'), |
| 63 |
('Divisas', 'http://estaticos.expansion.com/rss/mercadosdivisas.xml'), |
| 64 |
('Euribor', 'http://estaticos.expansion.com/rss/mercadoseuribor.xml'), |
| 65 |
('Materias Primas', 'http://estaticos.expansion.com/rss/mercadosmateriasprimas.xml'), |
| 66 |
('Renta Fija', 'http://estaticos.expansion.com/rss/mercadosrentafija.xml'), |
| 67 |
('Portada: Mi Dinero', 'http://estaticos.expansion.com/rss/midinero.xml'), |
| 68 |
('Hipotecas', 'http://estaticos.expansion.com/rss/midinerohipotecas.xml'), |
| 69 |
('Cr\xe9ditos', 'http://estaticos.expansion.com/rss/midinerocreditos.xml'), |
| 70 |
('Pensiones', 'http://estaticos.expansion.com/rss/midineropensiones.xml'), |
| 71 |
('Fondos de Inversi\xf3n', 'http://estaticos.expansion.com/rss/midinerofondos.xml'), |
| 72 |
('Motor', 'http://estaticos.expansion.com/rss/midineromotor.xml'), |
| 73 |
('Portada: Empresas', 'http://estaticos.expansion.com/rss/empresas.xml'), |
| 74 |
('Banca', 'http://estaticos.expansion.com/rss/empresasbanca.xml'), |
| 75 |
('TMT', 'http://estaticos.expansion.com/rss/empresastmt.xml'), |
| 76 |
('Energ\xeda', 'http://estaticos.expansion.com/rss/empresasenergia.xml'), |
| 77 |
('Inmobiliario y Construcci\xf3n', 'http://estaticos.expansion.com/rss/empresasinmobiliario.xml'), |
| 78 |
('Transporte y Turismo', 'http://estaticos.expansion.com/rss/empresastransporte.xml'), |
| 79 |
('Automoci\xf3n e Industria', 'http://estaticos.expansion.com/rss/empresasauto-industria.xml'), |
| 80 |
('Distribuci\xf3n', 'http://estaticos.expansion.com/rss/empresasdistribucion.xml'), |
| 81 |
('Deporte y Negocio', ' [url]http://estaticos.expansion.com/rss/empresasdeporte.xml[/url]'), |
| 82 |
('Mi Negocio', 'http://estaticos.expansion.com/rss/empresasminegocio.xml'), |
| 83 |
('Interiores', 'http://estaticos.expansion.com/rss/empresasinteriores.xml'), |
| 84 |
('Digitech', 'http://estaticos.expansion.com/rss/empresasdigitech.xml'), |
| 85 |
('Portada: Econom\xeda y Pol\xedtica', 'http://estaticos.expansion.com/rss/economiapolitica.xml'), |
| 86 |
('Pol\xedtica', 'http://estaticos.expansion.com/rss/economia.xml'), |
| 87 |
('Portada: Sociedad', 'http://estaticos.expansion.com/rss/entorno.xml'), |
| 88 |
('Portada: Opini\xf3n', 'http://estaticos.expansion.com/rss/opinion.xml'), |
| 89 |
('Llaves y editoriales', 'http://estaticos.expansion.com/rss/opinioneditorialyllaves.xml'), |
| 90 |
('Tribunas', 'http://estaticos.expansion.com/rss/opiniontribunas.xml'), |
| 91 |
('Portada: Jur\xeddico', 'http://estaticos.expansion.com/rss/juridico.xml'), |
| 92 |
('Entrevistas', 'http://estaticos.expansion.com/rss/juridicoentrevistas.xml'), |
| 93 |
('Opini\xf3n', 'http://estaticos.expansion.com/rss/juridicoopinion.xml'), |
| 94 |
('Sentencias', 'http://estaticos.expansion.com/rss/juridicosentencias.xml'), |
| 95 |
('Mujer', 'http://estaticos.expansion.com/rss/mujer-empresa.xml'), |
| 96 |
('Catalu\xf1a', 'http://estaticos.expansion.com/rss/catalunya.xml'), |
| 97 |
('Funci\xf3n p\xfablica', 'http://estaticos.expansion.com/rss/funcion-publica.xml'), |
| 98 |
] |
| 99 |
|
| 100 |
# Obtener la imagen de portada |
| 101 |
|
| 102 |
def get_cover_url(self): |
| 103 |
cover = None |
| 104 |
st = time.localtime() |
| 105 |
year = str(st.tm_year) |
| 106 |
month = '%.2d' % st.tm_mon |
| 107 |
day = '%.2d' % st.tm_mday |
| 108 |
cover = 'http://img5.kiosko.net/' + '/'.join([year, month, day]) + '/es/expansion.750.jpg' |
| 109 |
br = BasicNewsRecipe.get_browser(self) |
| 110 |
try: |
| 111 |
br.open(cover) |
| 112 |
except Exception: |
| 113 |
self.log('\nPortada no disponible') |
| 114 |
cover = 'http://www.aproahp.org/enlaces/images/diario_expansion.gif' |
| 115 |
return cover |
| 116 |
|
| 117 |
# Para que no salte la publicidad al recuperar la noticia, y que siempre se recupere |
| 118 |
# la página web, mando la variable "t" con la hora "linux" o "epoch" actual |
| 119 |
# haciendole creer al sitio web que justo se acaba de ver la publicidad |
| 120 |
|
| 121 |
def print_version(self, url): |
| 122 |
st = time.time() |
| 123 |
segundos = str(int(st)) |
| 124 |
parametros = '.html?t=' + segundos |
| 125 |
return url.replace('.html', parametros) |
| 126 |
|
| 127 |
_processed_links = [] |
| 128 |
|
| 129 |
def get_article_url(self, article): |
| 130 |
|
| 131 |
# Para obtener la url original del artículo a partir de la de |
| 132 |
# "feedsportal" |
| 133 |
|
| 134 |
link = article.get('link', None) |
| 135 |
if link is None: |
| 136 |
return article |
| 137 |
if link.split('/')[-1] == 'story01.htm': |
| 138 |
link = link.split('/')[-2] |
| 139 |
t = ( |
| 140 |
('0B', '.'), |
| 141 |
('0C', '/'), |
| 142 |
('0D', '?'), |
| 143 |
('0E', '-'), |
| 144 |
('0F', '='), |
| 145 |
('0G', '&'), |
| 146 |
('0N', '.com'), |
| 147 |
('0L0S', 'www.'), |
| 148 |
('0A', '0'), |
| 149 |
) |
| 150 |
for a, b in t: |
| 151 |
link = link.replace(a, b) |
| 152 |
link = 'http://' + link |
| 153 |
|
| 154 |
# Eliminar artículos duplicados en otros feeds |
| 155 |
|
| 156 |
if link not in self._processed_links: |
| 157 |
self._processed_links.append(link) |
| 158 |
else: |
| 159 |
link = None |
| 160 |
|
| 161 |
return link |
| 162 |
|
| 163 |
# Un poco de css para mejorar la presentación de las noticias |
| 164 |
|
| 165 |
extra_css = ''' |
| 166 |
.entradilla {font-family:Arial,Helvetica,sans-serif; font-weight:bold; font-style:italic; font-size:16px;} |
| 167 |
.fecha_publicacion,.autor {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:14px;} |
| 168 |
''' |
| 169 |
|
| 170 |
# Para presentar la imagen de los videos incrustados |
| 171 |
|
| 172 |
preprocess_regexps = [ |
| 173 |
(re.compile(r'var imagen', re.DOTALL | re.IGNORECASE), lambda match: '--></script><img src'), |
| 174 |
(re.compile(r'.jpg";', re.DOTALL | re.IGNORECASE), lambda match: '.jpg">'), |
| 175 |
(re.compile(r'var id_reproductor', re.DOTALL | re.IGNORECASE), lambda match: '<script language="Javascript" type="text/javascript"><!--'), |
| 176 |
] |