| 1 |
#!/usr/bin/env python |
| 2 |
__license__ = 'GPL v3' |
| 3 |
__author__ = 'Gabriele Marini, based on Darko Miletic' |
| 4 |
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' |
| 5 |
description = 'Italian daily newspaper - v1.00 05-05-2010' |
| 6 |
|
| 7 |
''' |
| 8 |
http://www.leggo.it |
| 9 |
''' |
| 10 |
import time |
| 11 |
|
| 12 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 13 |
|
| 14 |
|
| 15 |
class LeggoIT(BasicNewsRecipe): |
| 16 |
__author__ = 'Gabriele Marini' |
| 17 |
description = 'Italian Free daily newspaper' |
| 18 |
|
| 19 |
# cover_url = 'http://www.leggo.it/img/logo-leggo2.gif' |
| 20 |
title = 'Leggo.it' |
| 21 |
publisher = 'Ced Caltagirone Editore S.p.A.' |
| 22 |
category = 'News, politics, culture, economy, general interest' |
| 23 |
|
| 24 |
language = 'it' |
| 25 |
timefmt = '[%a, %d %b, %Y]' |
| 26 |
|
| 27 |
oldest_article = 5 |
| 28 |
max_articles_per_feed = 100 |
| 29 |
use_embedded_content = False |
| 30 |
recursion = 100 |
| 31 |
|
| 32 |
no_stylesheets = True |
| 33 |
remove_javascript = True |
| 34 |
conversion_options = {'linearize_tables': True} |
| 35 |
|
| 36 |
keep_only_tags = [dict(name='h1', attrs={'class': 'nero22'}), dict(name='div', attrs={'id': 'testodim'})] |
| 37 |
feeds = [ |
| 38 |
('Home Page', 'http://www.leggo.it/rss/home.xml'), |
| 39 |
('Italia', 'http://www.leggo.it/rss/italia.xml'), |
| 40 |
('Esteri', 'http://www.leggo.it/rss/esteri.xml'), |
| 41 |
('Economia', 'http://www.leggo.it/rss/economia.xml'), |
| 42 |
('Sport', 'http://www.leggo.it/rss/sport.xml'), |
| 43 |
('Gossip', 'http://www.leggo.it/rss/gossip.xml'), |
| 44 |
('Spettacoli', 'http://www.leggo.it/rss/spettacoli.xml'), |
| 45 |
('Salute', 'http://www.leggo.it/rss/salute.xml'), |
| 46 |
('Scienza', 'http://www.leggo.it/rss/scienza.xml'), |
| 47 |
] |
| 48 |
|
| 49 |
def get_cover_url(self): |
| 50 |
cover = None |
| 51 |
st = time.localtime() |
| 52 |
year = str(st.tm_year) |
| 53 |
month = '%.2d' % st.tm_mon |
| 54 |
day = '%.2d' % st.tm_mday |
| 55 |
cover = 'http://www.leggo.it/' + year + month + day + '/jpeg/LEGGO_ROMA_1.jpg' |
| 56 |
br = BasicNewsRecipe.get_browser(self) |
| 57 |
try: |
| 58 |
br.open(cover) |
| 59 |
except Exception: |
| 60 |
cover = 'http://www.leggo.it/' + year + month + day + '/jpeg/LEGGO_ROMA_3.jpg' |
| 61 |
br = BasicNewsRecipe.get_browser(self) |
| 62 |
try: |
| 63 |
br.open(cover) |
| 64 |
except Exception: |
| 65 |
self.log('\nCover unavailable') |
| 66 |
cover = 'http://www.leggo.it/img/logo-leggo2.gif' |
| 67 |
return cover |