Add some recipes of Uruguay.

Add 10minutos.recipe (News of Salto)
Add diario_el_pueblo.recipe (News of Salto)
Add diario_salto.recipe (News of Salto)
Add unoticias.recipe (News of Montevideo)
This commit is contained in:
Carlos Alves 2013-09-29 13:45:11 -03:00
parent 8920cf6cae
commit e1d99a09ab
4 changed files with 207 additions and 0 deletions

50
recipes/10minutos.recipe Normal file
View File

@ -0,0 +1,50 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
'''
10minutos.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = '10minutos'
__author__ = 'Carlos Alves'
description = 'Noticias de Salto - Uruguay'
tags = 'news, sports'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'utf8'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class':'post-content'})]
remove_tags = [
dict(name='div', attrs={'class':['hr', 'titlebar', 'navigation']}),
dict(name='p', attrs={'class':'post-meta'}),
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'Articulos', u'http://10minutos.com.uy/feed/')
]
def get_cover_url(self):
return 'http://10minutos.com.uy/a/img/logo.png'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

View File

@ -0,0 +1,51 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
'''
diarioelpueblo.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'Diario El Pueblo'
__author__ = 'Carlos Alves'
description = 'Noticias de Salto - Uruguay'
tags = 'news, sports'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'utf8'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class':'post-alt blog'})]
remove_tags = [
dict(name='div', attrs={'class':['hr', 'titlebar', 'volver-arriba-right','navigation']}),
dict(name='div', attrs={'id':'comment','id':'suckerfish','id':'crp_related'}),
dict(name='h3', attrs={'class':['post_date']}),
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'Articulos', u'http://www.diarioelpueblo.com.uy/feed')
]
def get_cover_url(self):
return 'http://www.diarioelpueblo.com.uy/wp-content/uploads/2013/06/Cabezal_Web1.jpg'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

View File

@ -0,0 +1,50 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
'''
diarisalto.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'Diario Salto'
__author__ = 'Carlos Alves'
description = 'Noticias de Salto - Uruguay'
tags = 'news, sports'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'utf8'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
remove_tags = [
dict(name='div', attrs={'class':['hr', 'titlebar', 'navigation']}),
dict(name='div', attrs={'id':'comment'}),
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'Articulos', u'http://www.diariosalto.com.uy/feed/atom')
]
def get_cover_url(self):
return 'http://diariosalto.com.uy/demo/wp-content/uploads/2011/12/diario-salto_logo-final-b-b.png'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

56
recipes/unoticias.recipe Normal file
View File

@ -0,0 +1,56 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
'''
unoticias.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'UNoticias'
__author__ = 'Carlos Alves'
description = 'Noticias Uruguay'
tags = 'news, sports, politics'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'ISO-8859-1'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [
dict(name='h1', attrs={'class':'nombre'}),
dict(name='h2', attrs={'class':'copete t20'}),
dict(name='div', attrs={'class':'desc'})
]
remove_tags = [
dict(name='div', attrs={'class':['br', 'hr', 'titlebar', 'navigation']}),
dict(name='div', attrs={'id':'comment'}),
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'Nacionales', u'http://www.unoticias.com.uy/RSS/nacionales.xml'),
(u'Deportes', u'http://www.unoticias.com.uy/RSS/deportes.xml'),
(u'Sociedad', u'http://www.unoticias.com.uy/RSS/Sociedad.xml')
]
def get_cover_url(self):
return 'http://www.unoticias.com.uy/artworks/logos/logo_small.gif'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup