| 1 |
#!/usr/bin/env python |
| 2 |
__license__ = 'GPL v3' |
| 3 |
__author__ = 'Gabriele Marini, based on Darko Miletic' |
| 4 |
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' |
| 5 |
description = 'Italian daily newspaper - 02-05-2010' |
| 6 |
|
| 7 |
''' |
| 8 |
http://www.adnkronos.com/ |
| 9 |
''' |
| 10 |
|
| 11 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 12 |
|
| 13 |
|
| 14 |
class Adnkronos(BasicNewsRecipe): |
| 15 |
__author__ = 'Gabriele Marini' |
| 16 |
description = 'News agency' |
| 17 |
cover_url = 'http://www.adnkronos.com/IGN6/img/popup_ign.jpg' |
| 18 |
title = 'Adnkronos' |
| 19 |
publisher = 'Adnkronos Group - ews agency' |
| 20 |
category = 'News, politics, culture, economy, general interest' |
| 21 |
|
| 22 |
language = 'it' |
| 23 |
timefmt = '[%a, %d %b, %Y]' |
| 24 |
|
| 25 |
oldest_article = 7 |
| 26 |
max_articles_per_feed = 80 |
| 27 |
use_embedded_content = False |
| 28 |
recursion = 10 |
| 29 |
|
| 30 |
remove_javascript = True |
| 31 |
|
| 32 |
def get_article_url(self, article): |
| 33 |
link = article.get('id', article.get('guid', None)) |
| 34 |
return link |
| 35 |
|
| 36 |
extra_css = ' .newsAbstract{font-style: italic} ' |
| 37 |
keep_only_tags = [dict(name='div', attrs={'class': ['breadCrumbs', 'newsTop', 'newsText']})] |
| 38 |
|
| 39 |
remove_tags = [dict(name='div', attrs={'class': ['leogoo', 'leogoo2']})] |
| 40 |
|
| 41 |
feeds = [ |
| 42 |
('Prima Pagina', 'http://rss.adnkronos.com/RSS_PrimaPagina.xml'), |
| 43 |
('Ultima Ora', 'http://rss.adnkronos.com/RSS_Ultimora.xml'), |
| 44 |
('Politica', 'http://rss.adnkronos.com/RSS_Politica.xml'), |
| 45 |
('Esteri', 'http://rss.adnkronos.com/RSS_Esteri.xml'), |
| 46 |
('Cronoca', 'http://rss.adnkronos.com/RSS_Cronaca.xml'), |
| 47 |
('Economia', 'http://rss.adnkronos.com/RSS_Economia.xml'), |
| 48 |
('Finanza', 'http://rss.adnkronos.com/RSS_Finanza.xml'), |
| 49 |
('CyberNews', 'http://rss.adnkronos.com/RSS_CyberNews.xml'), |
| 50 |
('Spettacolo', 'http://rss.adnkronos.com/RSS_Spettacolo.xml'), |
| 51 |
('Cultura', 'http://rss.adnkronos.com/RSS_Cultura.xml'), |
| 52 |
('Sport', 'http://rss.adnkronos.com/RSS_Sport.xml'), |
| 53 |
('Sostenibilita', 'http://rss.adnkronos.com/RSS_Sostenibilita.xml'), |
| 54 |
('Salute', 'http://rss.adnkronos.com/RSS_Salute.xml'), |
| 55 |
] |