Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Pagina 12

Browse Source 
Fixes #1646825 [Updated recipe for Pagina 12](https://bugs.launchpad.net/calibre/+bug/1646825)
This commit is contained in:
Kovid Goyal 2016-12-02 19:12:23 +05:30
parent cf981fd447
commit c925629fe7
1 changed files with 57 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

91
recipes/pagina12.recipe
View File

@ -1,5 +1,8 @@
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2016, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
@ -14,21 +17,21 @@ class Pagina12(BasicNewsRecipe):
publisher = 'La Pagina S.A.'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'cp1252'
encoding = 'utf8'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
auto_cleanup = False
PREFIX = 'https://www.pagina12.com.ar'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
body{font-family: Lora,serif}
.article-date{font-size: small; margin-bottom: 0.4em;}
.article-title{font-size: x-large; font-weight: bold; display: block; margin-bottom: 1em; margin-top: 1em;}
.article-main-media{display: block; margin-bottom: 0.4em;}
.article-summary{margin-bottom: 0.4em; display:block}
img{margin-bottom: 0.4em; display:block}
#autor{font-weight: bold}
#fecha,#epigrafe{font-size: 0.9em; margin: 5px}
#imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px }
.fgprincipal{font-size: large; font-weight: bold}
"""
conversion_options = {
@ -36,49 +39,45 @@ class Pagina12(BasicNewsRecipe):
}
remove_tags = [
dict(name=['meta', 'link']), dict(name='div', attrs={
'id': ['volver', 'logo', 'logo_suple', 'fin', 'permalink']})
dict(name=['meta', 'link']),
]
keep_only_tags=[
dict(name='div', attrs={'class':[
'article-date',
'article-main-media-image',
'article-prefix',
'article-title',
'article-summary',
'article-text'
]})
]
remove_attributes = ['lang']
feeds = [
(u'Edicion impresa', u'http://www.pagina12.com.ar/diario/rss/principal.xml'),
(u'Espectaculos', u'http://www.pagina12.com.ar/diario/rss/espectaculos.xml'),
(u'Radar', u'http://www.pagina12.com.ar/diario/rss/radar.xml'),
(u'Radar libros', u'http://www.pagina12.com.ar/diario/rss/libros.xml'),
(u'Cash', u'http://www.pagina12.com.ar/diario/rss/cash.xml'),
(u'Turismo', u'http://www.pagina12.com.ar/diario/rss/turismo.xml'),
(u'Libero', u'http://www.pagina12.com.ar/diario/rss/libero.xml'),
(u'NO', u'http://www.pagina12.com.ar/diario/rss/no.xml'),
(u'Las/12', u'http://www.pagina12.com.ar/diario/rss/las12.xml'),
(u'Soy', u'http://www.pagina12.com.ar/diario/rss/soy.xml'),
(u'Futuro', u'http://www.pagina12.com.ar/diario/rss/futuro.xml'),
(u'M2', u'http://www.pagina12.com.ar/diario/rss/m2.xml'),
(u'Rosario/12', u'http://www.pagina12.com.ar/diario/rss/rosario.xml')
(u'Edicion impresa', u'https://www.pagina12.com.ar/rss/edicion-impresa'),
(u'Espectaculos' , u'https://www.pagina12.com.ar/rss/suplementos/cultura-y-espectaculos/notas'),
(u'Radar' , u'https://www.pagina12.com.ar/rss/suplementos/radar/notas'),
(u'Radar libros' , u'https://www.pagina12.com.ar/rss/suplementos/radar-libros/notas'),
(u'Cash' , u'https://www.pagina12.com.ar/rss/suplementos/cash/notas'),
(u'Turismo' , u'https://www.pagina12.com.ar/rss/suplementos/turismo/notas'),
(u'Libero' , u'https://www.pagina12.com.ar/rss/suplementos/libero/notas'),
(u'NO' , u'https://www.pagina12.com.ar/rss/suplementos/no/notas'),
(u'Las/12' , u'https://www.pagina12.com.ar/rss/suplementos/las12/notas'),
(u'Soy' , u'https://www.pagina12.com.ar/rss/suplementos/soy/notas'),
(u'Futuro' , u'http://www.pagina12.com.ar/diario/rss/futuro.xml'),
(u'M2' , u'https://www.pagina12.com.ar/rss/suplementos/m2/notas'),
(u'Rosario/12' , u'https://www.pagina12.com.ar/rss/suplementos/rosario12/notas')
]
def print_version(self, url):
return url.replace('http://www.pagina12.com.ar/', 'http://www.pagina12.com.ar/imprimir/')
def get_article_url(self, article):
url = article.get('guid', None)
if url.startswith('/'):
return self.PREFIX + url
return url
def get_cover_url(self):
soup = self.index_to_soup(
'http://www.pagina12.com.ar/diario/principal/diario/index.html')
soup = self.index_to_soup(self.PREFIX)
for image in soup.findAll('img', alt=True):
if image['alt'].startswith('Tapa de la fecha'):
return image['src']
if image['alt'].startswith('Tapa del dia'):
return self.PREFIX + image['data-src']
return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('span', attrs={'id': 'seccion'}):
it = item.a
it.name = 'span'
del it['href']
del it['title']
for item in soup.findAll('p'):
it = item.find('h3')
if it:
it.name = 'span'
return soup