| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from __future__ import absolute_import, division, print_function, unicode_literals |
| 4 |
|
| 5 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 6 |
|
| 7 |
__author__ = 'Ruben Scopacasa' |
| 8 |
__license__ = 'GPL v3' |
| 9 |
__copyright__ = '2019, Ruben Scopacasa <ruben.scopacasa at gmail.com>' |
| 10 |
__version__ = 'v1.00' |
| 11 |
__date__ = '22, April 2019' |
| 12 |
|
| 13 |
|
| 14 |
class CorriereDellaSeraRecipe(BasicNewsRecipe): |
| 15 |
title = 'Il Corriere della sera' |
| 16 |
publisher = 'RCS Digital' |
| 17 |
category = 'News, politics, culture, economy, general interest' |
| 18 |
|
| 19 |
language = 'it' |
| 20 |
timefmt = '[%a, %d %b, %Y]' |
| 21 |
|
| 22 |
oldest_article = 3 |
| 23 |
max_articles_per_feed = 100 |
| 24 |
simultaneous_downloads = 5 |
| 25 |
|
| 26 |
no_stylesheets = True |
| 27 |
remove_tags_before = dict(name='h1') |
| 28 |
remove_tags = [dict(id='gallery')] |
| 29 |
ignore_duplicate_articles = {'title', 'url'} |
| 30 |
|
| 31 |
recipe_specific_options = { |
| 32 |
'days': { |
| 33 |
'short': 'Oldest article to download from this news source. In days ', |
| 34 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 35 |
'default': str(oldest_article), |
| 36 |
} |
| 37 |
} |
| 38 |
|
| 39 |
def __init__(self, *args, **kwargs): |
| 40 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 41 |
d = self.recipe_specific_options.get('days') |
| 42 |
if d and isinstance(d, str): |
| 43 |
self.oldest_article = float(d) |
| 44 |
|
| 45 |
feeds = [ |
| 46 |
('Homepage', 'http://xml2.corriereobjects.it/rss/homepage.xml'), |
| 47 |
('Editoriali', 'http://xml2.corriereobjects.it/rss/editoriali.xml'), |
| 48 |
('Cronache', 'http://xml2.corriereobjects.it/rss/cronache.xml'), |
| 49 |
('Politica', 'http://xml2.corriereobjects.it/rss/politica.xml'), |
| 50 |
('Esteri', 'http://xml2.corriereobjects.it/rss/esteri.xml'), |
| 51 |
('Economia', 'http://xml2.corriereobjects.it/rss/economia.xml'), |
| 52 |
('Cultura', 'http://xml2.corriereobjects.it/rss/cultura.xml'), |
| 53 |
] |
| 54 |
|
| 55 |
def print_version(self, url): |
| 56 |
return url.replace('.shtml', '_print.html') |
| 57 |
|
| 58 |
def get_cover_url(self): |
| 59 |
return 'http://www.corriere.it/rss/images/logo_small.gif' |