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

Update Hola magazine

Browse Source
This commit is contained in:
Kovid Goyal 2012-07-11 09:29:44 +05:30
parent 1ac5c914f7
commit 4e2031dacc
1 changed files with 58 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
recipes/hola.recipe
View File

@ -1,38 +1,73 @@
#!/usr/bin/env python #!/usr/bin/env python
__license__ = 'GPL v3' # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
__copyright__ = '2010, Brendan Sleight <bms.calibre at barwap.com>' __license__ = 'GPL v3'
__copyright__ = '30 June 2012, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Diario de actualidad, moda y belleza'
__version__ = 'v0.01'
__date__ = '30, June 2012'
''' '''
hola.com http://www.hola.com/
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Hackaday(BasicNewsRecipe): class hola_es(BasicNewsRecipe):
title = u'Hola' __author__ = 'desUBIKado'
__author__ = 'bmsleight' description = 'Diario de actualidad, moda y belleza'
description = 'diario de actualidad, moda y belleza.' title = u'¡Hola!'
oldest_article = 10 publisher = 'Hola S.L.'
category = 'Spanish celebrities, Entertainment News, Royalty, Daily Variety, Hollywood'
language = 'es'
masthead_url = 'http://imagenes.hola.com/comunes/2008/logo-holacom.gif'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 7
delay = 1
encoding = 'utf-8'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True
language = 'es'
use_embedded_content = False use_embedded_content = False
remove_empty_feeds = True
keep_only_tags = [ remove_javascript = True
dict(name='div', attrs={'id':'cuerpo'}) no_stylesheets = True
]
feeds = [ feeds = [
(u'Famosos' , u'http://www.hola.com/famosos/rss.xml' ), (u'Famosos' , u'http://www.hola.com/famosos/rss.xml' )
(u'Realeza' , u'http://www.hola.com/realeza/rss.xml' ), ,(u'Realeza' , u'http://www.hola.com/realeza/rss.xml' )
(u'Cine' , u'http://www.hola.com/cine/rss.xml' ), ,(u'Cine' , u'http://www.hola.com/cine/rss.xml' )
(u'Música' , u'http://www.hola.com/musica/rss.xml' ), ,(u'M\xfasica' , u'http://www.hola.com/musica/rss.xml' )
(u'Moda y modelos' , u'http://www.hola.com/moda/portada/rss.xml' ), ,(u'Moda y modelos' , u'http://www.hola.com/moda/portada/rss.xml' )
(u'Belleza y salud', u'http://www.hola.com/belleza/portada/rss.xml' ), ,(u'Belleza y salud', u'http://www.hola.com/belleza/portada/rss.xml' )
(u'Niños' , u'http://www.hola.com/ninos/rss.xml' ), ,(u'Ni\xf1os' , u'http://www.hola.com/ninos/rss.xml' )
(u'Todas las noticias', u'http://int2.hola.com/app/feeds/rss_hola.php'), ]
keep_only_tags = [dict(name='div', attrs={'id':['cuerpo','com']})]
remove_tags = [dict(name='div', attrs={'id':['relacionadas','slide-enlaces-patrocinados','comentarios']}),
dict(name='div', attrs={'class':['slide-enlaces-patricinados-tit','compartir']})
] ]
remove_tags_after = dict(name='div' , attrs={'id':'comentarios'})
# Recuperamos la portada de papel (la imagen 520 tiene mayor resolucion)
def get_cover_url(self):
index = 'http://www.hola.com/abono/ediciondigital/'
soup = self.index_to_soup(index)
for image in soup.findAll('img',src=True):
if image['src'].endswith('portada-revista-hola-520.jpg'):
return 'http://www.hola.com/' + image['src']
return None
def get_article_url(self, article): def get_article_url(self, article):
url = article.get('guid', None) url = article.get('guid', None)
return url return url
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:30px;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal; font-style:italic; font-size:18px;}
'''