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

Add padreydecano.recipe, update el_observador...

Browse Source 
Add padreydecano.recipe (C.A. Peñarol related news)
Update el_observador.recipe it was broken for a long time.
This commit is contained in:
Carlos Alves 2013-09-29 17:34:45 -03:00
parent e1d99a09ab
commit a342162cff
2 changed files with 69 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
recipes/el_observador.recipe
View File

@ -1,18 +1,23 @@
#!/usr/bin/env python
##
## Last Edited: 2013-09-29 Carlos Alves <carlosalves90@gmail.com>
##
__license__ = 'GPL v3'
__author__ = '2010, Yuri Alvarez<me at yurialvarez.com>'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
'''
observa.com.uy
elobservador.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ObservaDigital(BasicNewsRecipe):
title = 'Observa Digital'
class Noticias(BasicNewsRecipe):
title = 'El Observador'
__author__ = 'yrvn'
description = 'Noticias de Uruguay'
description = 'Noticias desde Uruguay'
tags = 'news, sports, entretainment'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
@ -23,13 +28,18 @@ class ObservaDigital(BasicNewsRecipe):
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(id=['contenido'])]
keep_only_tags = [
dict(name='div', attrs={'class':'story collapsed'})
]
remove_tags = [
dict(name='div', attrs={'id':'contenedorVinculadas'}),
dict(name='p', attrs={'id':'nota_firma'}),
dict(name='div', attrs={'class':['fecha', 'copyright', 'story_right']}),
dict(name='div', attrs={'class':['photo', 'social']}),
dict(name='div', attrs={'id':'widget'}),
dict(name=['object','link'])
]
remove_attributes = ['width','height', 'style', 'font', 'color']
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
@ -37,19 +47,9 @@ class ObservaDigital(BasicNewsRecipe):
p {font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
(u'Actualidad', u'http://www.observa.com.uy/RSS/actualidad.xml'),
(u'Deportes', u'http://www.observa.com.uy/RSS/deportes.xml'),
(u'Vida', u'http://www.observa.com.uy/RSS/vida.xml'),
(u'Ciencia y Tecnologia', u'http://www.observa.com.uy/RSS/ciencia.xml')
(u'Portada', u'http://elobservador.com.uy/rss/portada/'),
]
def get_cover_url(self):
index = 'http://www.observa.com.uy/'
soup = self.index_to_soup(index)
for image in soup.findAll('img',alt=True):
if image['alt'].startswith('Tapa El Observador'):
return image['src'].rstrip('b.jpg') + '.jpg'
return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):

50
recipes/padreydecano.recipe Normal file
View File

@ -0,0 +1,50 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
'''
padreydecano.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'Padre y Decano'
__author__ = 'Carlos Alves'
description = 'El sitio del pueblo'
tags = 'soccer, futbol, Peñarol'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = None
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [
dict(name='h1', attrs={'class':'entry-title'}),
dict(name='div', attrs={'class':'entry-content clearfix'})
]
remove_tags = [
dict(name='div', attrs={'class':['br', 'hr', 'titlebar', 'navigation']}),
dict(name='dl', attrs={'class':'gallery-item'}),
dict(name=['object','link'])
]
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
p {font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
(u'Padre y Decano | Club Atlético Peñarol', u'http://www.padreydecano.com/cms/feed/')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup