mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-01-03 02:30:21 -05:00
60 lines
2.0 KiB
Python
60 lines
2.0 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
__author__ = 'Ruben Scopacasa'
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2019, Ruben Scopacasa <ruben.scopacasa at gmail.com>'
|
|
__version__ = 'v1.00'
|
|
__date__ = '22, April 2019'
|
|
|
|
|
|
class CorriereDellaSeraRecipe(BasicNewsRecipe):
|
|
title = u'Il Corriere della sera'
|
|
publisher = 'RCS Digital'
|
|
category = 'News, politics, culture, economy, general interest'
|
|
|
|
language = 'it'
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
|
|
oldest_article = 3
|
|
max_articles_per_feed = 100
|
|
simultaneous_downloads = 5
|
|
|
|
no_stylesheets = True
|
|
remove_tags_before = dict(name='h1')
|
|
remove_tags = [dict(id='gallery')]
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
|
|
recipe_specific_options = {
|
|
'days': {
|
|
'short': 'Oldest article to download from this news source. In days ',
|
|
'long': 'For example, 0.5, gives you articles from the past 12 hours',
|
|
'default': str(oldest_article)
|
|
}
|
|
}
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
|
d = self.recipe_specific_options.get('days')
|
|
if d and isinstance(d, str):
|
|
self.oldest_article = float(d)
|
|
|
|
feeds = [
|
|
('Homepage', 'http://xml2.corriereobjects.it/rss/homepage.xml'),
|
|
('Editoriali', 'http://xml2.corriereobjects.it/rss/editoriali.xml'),
|
|
('Cronache', 'http://xml2.corriereobjects.it/rss/cronache.xml'),
|
|
('Politica', 'http://xml2.corriereobjects.it/rss/politica.xml'),
|
|
('Esteri', 'http://xml2.corriereobjects.it/rss/esteri.xml'),
|
|
('Economia', 'http://xml2.corriereobjects.it/rss/economia.xml'),
|
|
('Cultura', 'http://xml2.corriereobjects.it/rss/cultura.xml'),
|
|
]
|
|
|
|
def print_version(self, url):
|
|
return url.replace('.shtml', '_print.html')
|
|
|
|
def get_cover_url(self):
|
|
return 'http://www.corriere.it/rss/images/logo_small.gif'
|