calibre/recipes/ba_herald.recipe
Kovid Goyal 921769bd6a ...
2012-04-06 09:00:37 +05:30

81 lines
3.4 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.buenosairesherald.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class BuenosAiresHerald(BasicNewsRecipe):
title = 'Buenos Aires Herald'
__author__ = 'Darko Miletic'
description = 'A world of information in a few words'
publisher = 'Editorial Nefir S.A.'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en_AR'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.buenosairesherald.com/img/logo.jpg'
INDEX = 'http://www.buenosairesherald.com'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block}
h1{font-family: Georgia,serif}
#fecha{text-align: right; font-size: small}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(name=['meta','link','iframe'])]
keep_only_tags = [dict(attrs={'class':'nota_texto p'})]
feeds = [
(u'Argentina' , u'http://www.buenosairesherald.com/argentina' )
,(u'World' , u'http://www.buenosairesherald.com/world' )
,(u'Latin America' , u'http://www.buenosairesherald.com/latin-america' )
,(u'Entertainment' , u'http://www.buenosairesherald.com/entertainment' )
,(u'Sports' , u'http://www.buenosairesherald.com/sports' )
]
def print_version(self, url):
artidraw = url.rpartition('/article/')[2]
artid = artidraw.partition('/')[0]
return 'http://www.buenosairesherald.com/articles/print.aspx?ix=' + artid
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, ('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('div', attrs={'class':'nota_texto_seccion'}):
description = self.tag_to_string(item.h2)
atag = item.h2.find('a')
if atag and atag.has_key('href'):
url = self.INDEX + atag['href']
title = description
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
totalfeeds.append((feedtitle, articles))
return totalfeeds