calibre/recipes/elcronista.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

57 lines
2.4 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.cronista.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Pagina12(BasicNewsRecipe):
title = 'El Cronista Comercial'
__author__ = 'Darko Miletic'
description = 'El Cronista Comercial es el Diario economico-politico mas valorado. Es la fuente mas confiable de informacion en temas de economia, finanzas y negocios enmarcados politicamente.' # noqa
publisher = 'Cronista.com'
category = 'news, politics, economy, finances, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.cronista.com/export/sites/diarioelcronista/arte/header-logo.gif'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
h2{font-family: Georgia,"Times New Roman",Times,serif }
img{margin-bottom: 0.4em; display:block}
.nom{font-weight: bold; vertical-align: baseline}
.autor-cfoto{border-bottom: 1px solid #D2D2D2;
border-top: 1px solid #D2D2D2;
display: inline-block;
margin: 0 10px 10px 0;
padding: 10px;
width: 210px}
.under{font-weight: bold}
.time{font-size: small}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(name=['meta', 'link', 'base', 'iframe', 'object', 'embed']), dict(
attrs={'class': ['user-tools', 'tabsmedia']})
]
remove_attributes = ['lang']
remove_tags_before = dict(attrs={'class': 'top'})
remove_tags_after = dict(attrs={'class': 'content-nota'})
feeds = [(u'Ultimas noticias', u'http://www.cronista.com/rss.html')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup