mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Updated Expansion (spanish)
This commit is contained in:
Kovid Goyal
parent
803e1c297b
commit
c73b2569a1
@ -1,35 +1,43 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Gerardo Diez'
|
||||
__copyright__ = 'Gerardo Diez<gerardo.diez.garcia@gmail.com>'
|
||||
description = 'Main daily newspaper from Spain - v1.00 (05, Enero 2011)'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '5, January 2011 Gerardo Diez<gerardo.diez.garcia@gmail.com> & desUBIKado'
|
||||
__author__ = 'desUBIKado, based on an earlier version by Gerardo Diez'
|
||||
__version__ = 'v1.01'
|
||||
__date__ = '13, November 2011'
|
||||
|
||||
'''
|
||||
expansion.es
|
||||
[url]http://www.expansion.com/[/url]
|
||||
'''
|
||||
|
||||
import time
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
class Publico(BasicNewsRecipe):
|
||||
title =u'Expansion.com'
|
||||
__author__ ='Gerardo Diez'
|
||||
publisher =u'Unidad Editorial Información Económica, S.L.'
|
||||
category ='finances, catalunya'
|
||||
oldest_article =1
|
||||
|
||||
class expansion_spanish(BasicNewsRecipe):
|
||||
__author__ ='Gerardo Diez & desUBIKado'
|
||||
description ='Financial news from Spain'
|
||||
title =u'Expansion'
|
||||
publisher =u'Unidad Editorial Internet, S.L.'
|
||||
category ='news, finances, Spain'
|
||||
oldest_article = 2
|
||||
simultaneous_downloads = 10
|
||||
max_articles_per_feed =100
|
||||
simultaneous_downloads =10
|
||||
cover_url =u'http://estaticos01.expansion.com/iconos/v2.x/v2.0/cabeceras/logo_expansion.png'
|
||||
timefmt ='[%A, %d %B, %Y]'
|
||||
encoding ='latin'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
encoding ='iso-8859-15'
|
||||
language ='es'
|
||||
remove_javascript =True
|
||||
no_stylesheets =True
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
remove_empty_feeds = True
|
||||
|
||||
keep_only_tags =dict(name='div', attrs={'class':['noticia primer_elemento']})
|
||||
|
||||
remove_tags =[
|
||||
dict(name='div', attrs={'class':['compartir', 'metadata_desarrollo_noticia', 'relacionadas', 'mas_info','publicidad publicidad_textlink', 'ampliarfoto']}),
|
||||
dict(name='ul', attrs={'class':['bolos_desarrollo_noticia']}),
|
||||
dict(name='div', attrs={'class':['compartir', 'metadata_desarrollo_noticia', 'relacionadas', 'mas_info','publicidad publicidad_textlink', 'ampliarfoto','tit_relacionadas','interact','paginacion estirar','sumario derecha']}),
|
||||
dict(name='ul', attrs={'class':['bolos_desarrollo_noticia','not_logged']}),
|
||||
dict(name='span', attrs={'class':['comentarios']}),
|
||||
dict(name='p', attrs={'class':['cintillo_comentarios', 'cintillo_comentarios formulario']}),
|
||||
dict(name='div', attrs={'id':['comentarios_lectores_listado']})
|
||||
dict(name='div', attrs={'id':['comentarios_lectores_listado','comentar']})
|
||||
]
|
||||
feeds =[
|
||||
(u'Portada', u'http://estaticos.expansion.com/rss/portada.xml'),
|
||||
@ -38,42 +46,112 @@ class Publico(BasicNewsRecipe):
|
||||
(u'Euribor', u'http://estaticos.expansion.com/rss/mercadoseuribor.xml'),
|
||||
(u'Materias Primas', u'http://estaticos.expansion.com/rss/mercadosmateriasprimas.xml'),
|
||||
(u'Renta Fija', u'http://estaticos.expansion.com/rss/mercadosrentafija.xml'),
|
||||
|
||||
(u'Portada: Mi Dinero', u'http://estaticos.expansion.com/rss/midinero.xml'),
|
||||
(u'Hipotecas', u'http://estaticos.expansion.com/rss/midinerohipotecas.xml'),
|
||||
(u'Créditos', u'http://estaticos.expansion.com/rss/midinerocreditos.xml'),
|
||||
(u'Cr\xe9ditos', u'http://estaticos.expansion.com/rss/midinerocreditos.xml'),
|
||||
(u'Pensiones', u'http://estaticos.expansion.com/rss/midineropensiones.xml'),
|
||||
(u'Fondos de Inversión', u'http://estaticos.expansion.com/rss/midinerofondos.xml'),
|
||||
(u'Fondos de Inversi\xf3n', u'http://estaticos.expansion.com/rss/midinerofondos.xml'),
|
||||
(u'Motor', u'http://estaticos.expansion.com/rss/midineromotor.xml'),
|
||||
|
||||
(u'Portada: Empresas', u'http://estaticos.expansion.com/rss/empresas.xml'),
|
||||
(u'Banca', u'http://estaticos.expansion.com/rss/empresasbanca.xml'),
|
||||
(u'TMT', u'http://estaticos.expansion.com/rss/empresastmt.xml'),
|
||||
(u'Energía', u'http://estaticos.expansion.com/rss/empresasenergia.xml'),
|
||||
(u'Inmobiliario y Construcción', u'http://estaticos.expansion.com/rss/empresasinmobiliario.xml'),
|
||||
(u'Energ\xeda', u'http://estaticos.expansion.com/rss/empresasenergia.xml'),
|
||||
(u'Inmobiliario y Construcci\xf3n', u'http://estaticos.expansion.com/rss/empresasinmobiliario.xml'),
|
||||
(u'Transporte y Turismo', u'http://estaticos.expansion.com/rss/empresastransporte.xml'),
|
||||
(u'Automoción e Industria', u'http://estaticos.expansion.com/rss/empresasauto-industria.xml'),
|
||||
(u'Distribución', u'http://estaticos.expansion.com/rss/empresasdistribucion.xml'),
|
||||
(u'Deporte y Negocio', u' http://estaticos.expansion.com/rss/empresasdeporte.xml'),
|
||||
(u'Automoci\xf3n e Industria', u'http://estaticos.expansion.com/rss/empresasauto-industria.xml'),
|
||||
(u'Distribuci\xf3n', u'http://estaticos.expansion.com/rss/empresasdistribucion.xml'),
|
||||
(u'Deporte y Negocio', u' [url]http://estaticos.expansion.com/rss/empresasdeporte.xml[/url]'),
|
||||
(u'Mi Negocio', u'http://estaticos.expansion.com/rss/empresasminegocio.xml'),
|
||||
(u'Interiores', u'http://estaticos.expansion.com/rss/empresasinteriores.xml'),
|
||||
(u'Digitech', u'http://estaticos.expansion.com/rss/empresasdigitech.xml'),
|
||||
|
||||
(u'Portada: Economía y Política', u'http://estaticos.expansion.com/rss/economiapolitica.xml'),
|
||||
(u'Política', u'http://estaticos.expansion.com/rss/economia.xml'),
|
||||
(u'Portada: Econom\xeda y Pol\xedtica', u'http://estaticos.expansion.com/rss/economiapolitica.xml'),
|
||||
(u'Pol\xedtica', u'http://estaticos.expansion.com/rss/economia.xml'),
|
||||
(u'Portada: Sociedad', u'http://estaticos.expansion.com/rss/entorno.xml'),
|
||||
|
||||
(u'Portada: Opinión', u'http://estaticos.expansion.com/rss/opinion.xml'),
|
||||
(u'Portada: Opini\xf3n', u'http://estaticos.expansion.com/rss/opinion.xml'),
|
||||
(u'Llaves y editoriales', u'http://estaticos.expansion.com/rss/opinioneditorialyllaves.xml'),
|
||||
(u'Tribunas', u'http://estaticos.expansion.com/rss/opiniontribunas.xml'),
|
||||
|
||||
(u'Portada: Jurídico', u'http://estaticos.expansion.com/rss/juridico.xml'),
|
||||
(u'Portada: Jur\xeddico', u'http://estaticos.expansion.com/rss/juridico.xml'),
|
||||
(u'Entrevistas', u'http://estaticos.expansion.com/rss/juridicoentrevistas.xml'),
|
||||
(u'Opinión', u'http://estaticos.expansion.com/rss/juridicoopinion.xml'),
|
||||
(u'Opini\xf3n', u'http://estaticos.expansion.com/rss/juridicoopinion.xml'),
|
||||
(u'Sentencias', u'http://estaticos.expansion.com/rss/juridicosentencias.xml'),
|
||||
|
||||
(u'Mujer', u'http://estaticos.expansion.com/rss/mujer-empresa.xml'),
|
||||
(u'Cataluña', u'http://estaticos.expansion.com/rss/catalunya.xml'),
|
||||
(u'Función pública', u'http://estaticos.expansion.com/rss/funcion-publica.xml')
|
||||
(u'Catalu\xf1a', u'http://estaticos.expansion.com/rss/catalunya.xml'),
|
||||
(u'Funci\xf3n p\xfablica', u'http://estaticos.expansion.com/rss/funcion-publica.xml')
|
||||
]
|
||||
|
||||
# Obtener la imagen de portada
|
||||
|
||||
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
|
||||
#[url]http://img5.kiosko.net/2011/11/14/es/expansion.750.jpg[/url]
|
||||
cover='http://img5.kiosko.net/'+ year + '/' + month + '/' + day +'/es/expansion.750.jpg'
|
||||
br = BasicNewsRecipe.get_browser()
|
||||
try:
|
||||
br.open(cover)
|
||||
except:
|
||||
self.log("\nPortada no disponible")
|
||||
cover ='http://www.aproahp.org/enlaces/images/diario_expansion.gif'
|
||||
return cover
|
||||
|
||||
|
||||
|
||||
# Para que no salte la publicidad al recuperar la noticia, y que siempre se recupere
|
||||
# la página web, mando la variable "t" con la hora "linux" o "epoch" actual
|
||||
# haciendole creer al sitio web que justo se acaba de ver la publicidad
|
||||
|
||||
def print_version(self, url):
|
||||
st = time.time()
|
||||
segundos = str(int(st))
|
||||
parametros = '.html?t=' + segundos
|
||||
return url.replace('.html', parametros)
|
||||
|
||||
|
||||
|
||||
_processed_links = []
|
||||
|
||||
def get_article_url(self, article):
|
||||
|
||||
# Para obtener la url original del artículo a partir de la de "feedsportal"
|
||||
|
||||
link = article.get('link', None)
|
||||
if link is None:
|
||||
return article
|
||||
if link.split('/')[-1]=="story01.htm":
|
||||
link=link.split('/')[-2]
|
||||
a=['0B','0C','0D','0E','0F','0G','0N' ,'0L0S','0A']
|
||||
b=['.' ,'/' ,'?' ,'-' ,'=' ,'&' ,'.com','www.','0']
|
||||
for i in range(0,len(a)):
|
||||
link=link.replace(a[i],b[i])
|
||||
link="http://"+link
|
||||
|
||||
# Eliminar artículos duplicados en otros feeds
|
||||
|
||||
if not (link in self._processed_links):
|
||||
self._processed_links.append(link)
|
||||
else:
|
||||
link = None
|
||||
|
||||
return link
|
||||
|
||||
|
||||
|
||||
# Un poco de css para mejorar la presentación de las noticias
|
||||
|
||||
extra_css = '''
|
||||
.entradilla {font-family:Arial,Helvetica,sans-serif; font-weight:bold; font-style:italic; font-size:16px;}
|
||||
.fecha_publicacion,.autor {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:14px;}
|
||||
'''
|
||||
|
||||
|
||||
|
||||
# Para presentar la imagen de los videos incrustados
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'var 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 id_reproductor', re.DOTALL|re.IGNORECASE), lambda match: '<script language="Javascript" type="text/javascript"><!--'),
|
||||
]
|
||||
|
||||
@ -11,7 +11,7 @@ import datetime
|
||||
from urllib import quote_plus
|
||||
from Queue import Queue, Empty
|
||||
from lxml import etree, html
|
||||
from calibre import prints, as_unicode
|
||||
from calibre import as_unicode
|
||||
|
||||
from calibre.ebooks.chardet import xml_to_unicode
|
||||
|
||||
@ -54,7 +54,7 @@ class Ozon(Source):
|
||||
def create_query(self, log, title=None, authors=None, identifiers={}): # {{{
|
||||
# div_book -> search only books, ebooks and audio books
|
||||
search_url = self.ozon_url + '/webservice/webservice.asmx/SearchWebService?searchContext=div_book&searchText='
|
||||
|
||||
|
||||
# for ozon.ru search we have to format ISBN with '-'
|
||||
isbn = _format_isbn(log, identifiers.get('isbn', None))
|
||||
# TODO: format isbn!
|
||||
@ -79,7 +79,7 @@ class Ozon(Source):
|
||||
return search_url
|
||||
# }}}
|
||||
|
||||
def identify(self, log, result_queue, abort, title=None, authors=None,
|
||||
def identify(self, log, result_queue, abort, title=None, authors=None,
|
||||
identifiers={}, timeout=30): # {{{
|
||||
if not self.is_configured():
|
||||
return
|
||||
@ -112,13 +112,13 @@ class Ozon(Source):
|
||||
def get_metadata(self, log, entries, title, authors, identifiers): # {{{
|
||||
# some book titles have extra characters like this
|
||||
# TODO: make a twick
|
||||
reRemoveFromTitle = None
|
||||
reRemoveFromTitle = None
|
||||
#reRemoveFromTitle = re.compile(r'[?!:.,;+-/&%"\'=]')
|
||||
|
||||
|
||||
title = unicode(title).upper() if title else ''
|
||||
if reRemoveFromTitle:
|
||||
title = reRemoveFromTitle.sub('', title)
|
||||
authors = map(_normalizeAuthorNameWithInitials,
|
||||
title = reRemoveFromTitle.sub('', title)
|
||||
authors = map(_normalizeAuthorNameWithInitials,
|
||||
map(unicode.upper, map(unicode, authors))) if authors else None
|
||||
ozon_id = identifiers.get('ozon', None)
|
||||
|
||||
@ -320,7 +320,7 @@ class Ozon(Source):
|
||||
displ_lang = lng_splt[0].strip()
|
||||
metadata.language = _translageLanguageToCode(displ_lang)
|
||||
#log.debug(u'language: %s'%displ_lang)
|
||||
|
||||
|
||||
# can be set before from xml search responce
|
||||
if not metadata.pubdate:
|
||||
xpt = u'normalize-space(//div[@class="product-misc"]//text()[contains(., "г.")])'
|
||||
@ -434,13 +434,13 @@ def _translageLanguageToCode(displayLang): # {{{
|
||||
# [В.П. Колесников | Колесников В.П.]-> В. П. BКолесников
|
||||
def _normalizeAuthorNameWithInitials(name): # {{{
|
||||
res = name
|
||||
if name:
|
||||
re1 = u'^(?P<lname>\S+)\s+(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?$'
|
||||
if name:
|
||||
re1 = u'^(?P<lname>\S+)\s+(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?$'
|
||||
re2 = u'^(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?\s+(?P<lname>\S+)$'
|
||||
matcher = re.match(re1, unicode(name), re.UNICODE)
|
||||
if not matcher:
|
||||
matcher = re.match(re2, unicode(name), re.UNICODE)
|
||||
|
||||
|
||||
if matcher:
|
||||
d = matcher.groupdict()
|
||||
res = ' '.join(x for x in (d['fname'], d['mname'], d['lname']) if x)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user