Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #5685 (Updated recipe and icon for Clarin)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-04 07:11:20 -06:00
parent a60b414c7e
commit 4a1dcdb210
2 changed files with 28 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/news/clarin.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 330 B

After

Width:  |  Height:  |  Size: 820 B

51
resources/recipes/clarin.recipe
View File

@ -5,7 +5,6 @@ __copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
clarin.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Clarin(BasicNewsRecipe):
@ -18,11 +17,12 @@ class Clarin(BasicNewsRecipe):
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
cover_url = strftime('http://www.clarin.com/diario/%Y/%m/%d/portada.jpg')
encoding = 'cp1252'
language = 'es'
masthead_url = 'http://www.clarin.com/shared/v10/img/Hd/lg_Clarin.gif'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif} h2{font-family: Georgia,"Times New Roman",Times,serif; font-size: xx-large} .Volan,.Pie,.Autor{ font-size: x-small} .Copete,.Hora{font-size: large} '
encoding = 'utf8'
language = 'es_AR'
publication_type = 'newspaper'
INDEX = 'http://www.clarin.com'
masthead_url = 'http://www.clarin.com/static/CLAClarin/images/logo-clarin-print.jpg'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif} h2{font-family: Georgia,serif; font-size: xx-large} .hora{font-weight:bold} .hd p{font-size: small} .nombre-autor{color: #0F325A} '
conversion_options = {
'comment' : description
@ -31,27 +31,32 @@ class Clarin(BasicNewsRecipe):
, 'language' : language
}
remove_tags = [
dict(name='a' , attrs={'class':'Imp' })
,dict(name='div' , attrs={'class':'Perma' })
,dict(name='h1' , text='Imprimir' )
]
keep_only_tags = [dict(attrs={'class':['hd','mt']})]
feeds = [
(u'Ultimo Momento', u'http://www.clarin.com/diario/hoy/um/sumariorss.xml')
,(u'El Pais' , u'http://www.clarin.com/diario/hoy/elpais.xml' )
,(u'Opinion' , u'http://www.clarin.com/diario/hoy/opinion.xml' )
,(u'El Mundo' , u'http://www.clarin.com/diario/hoy/elmundo.xml' )
,(u'Sociedad' , u'http://www.clarin.com/diario/hoy/sociedad.xml' )
,(u'La Ciudad' , u'http://www.clarin.com/diario/hoy/laciudad.xml' )
,(u'Policiales' , u'http://www.clarin.com/diario/hoy/policiales.xml' )
,(u'Deportes' , u'http://www.clarin.com/diario/hoy/deportes.xml' )
(u'Pagina principal', u'http://www.clarin.com/rss/' )
,(u'Politica' , u'http://www.clarin.com/rss/politica/' )
,(u'Deportes' , u'http://www.clarin.com/rss/deportes/' )
,(u'Economia' , u'http://www.clarin.com/economia/' )
,(u'Mundo' , u'http://www.clarin.com/rss/mundo/' )
,(u'Espectaculos' , u'http://www.clarin.com/rss/espectaculos/')
,(u'Sociedad' , u'http://www.clarin.com/rss/sociedad/' )
,(u'Ciudades' , u'http://www.clarin.com/rss/ciudades/' )
,(u'Policiales' , u'http://www.clarin.com/rss/policiales/' )
,(u'Internet' , u'http://www.clarin.com/rss/internet/' )
,(u'Ciudades' , u'http://www.clarin.com/rss/ciudades/' )
]
def print_version(self, url):
rest = url.partition('-0')[-1]
lmain = rest.partition('.')[0]
lurl = u'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain
return lurl
return url + '?print=1'
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div',attrs={'class':'bb-md bb-md-edicion_papel'})
if cover_item:
ap = cover_item.find('a',attrs={'href':'/edicion-impresa/'})
if ap:
cover_url = self.INDEX + ap.img['src']
return cover_url