mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
82 lines
3.1 KiB
Python
82 lines
3.1 KiB
Python
#!/usr/bin/env python2
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'Lorenzo Vigentini'
|
|
__copyright__ = '2009, Lorenzo Vigentini <l.vigentini at gmail.com>'
|
|
__version__ = 'v1.02'
|
|
__date__ = '10, January 2010'
|
|
__description__ = 'Sport news from the most read sport newspaper in Italy'
|
|
|
|
'''www.gazzetta.it'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class laGazzetta(BasicNewsRecipe):
|
|
__author__ = 'Lorenzo Vigentini'
|
|
description = 'Sport news from the most read sport newspaper in Italy'
|
|
|
|
cover_url = 'http://www.gazzetta.it/primapagina/images/prima_pagina_grande.png'
|
|
title = 'La Gazzetta dello Sport '
|
|
publisher = 'RCS Digital'
|
|
category = 'Sport News'
|
|
|
|
language = 'it'
|
|
encoding = 'cp1252'
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
|
|
oldest_article = 2
|
|
max_articles_per_feed = 20
|
|
use_embedded_content = False
|
|
recursion = 10
|
|
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'id': 'articolo'})]
|
|
|
|
remove_tags = [
|
|
dict(name='ul', attrs={'id': ['service-toolbar', 'sections-menu']}),
|
|
dict(name='div', attrs={'id': [
|
|
'header', 'rightcol', 'sponsored', 'vxFlashPlayer', 'footer', 'print-box']}),
|
|
dict(name='iframe', attrs={'id': 'mirago-feed'}),
|
|
dict(name='a', attrs={'id': 'commenta-up'}),
|
|
dict(name='cite', attrs={'class': ['signature', 'parag-title']}),
|
|
dict(name='a', attrs={'class': ['last-comment', 'button-bold2']}),
|
|
dict(name=['base', 'object', 'link', 'a', 'script', 'noscript'])
|
|
]
|
|
|
|
extra_css = '''
|
|
h1 {font: sans-serif large;}
|
|
h2 {font: sans-serif medium;}
|
|
h3 {font: sans-serif small;}
|
|
h4 {font: sans-serif bold small;}
|
|
p {font:10pt helvetica}
|
|
dd {font:8pt helvetica}
|
|
'''
|
|
|
|
feeds = [
|
|
(u'Calcio', u'http://www.gazzetta.it/rss/Calcio.xml'),
|
|
(u'Formula 1', u'http://www.gazzetta.it/rss/Formula1.xml'),
|
|
(u'Motomodiale', u'http://www.gazzetta.it/rss/Motomondiale.xml'),
|
|
(u'Motori', u'http://www.gazzetta.it/rss/Motori.xml'),
|
|
(u'Ciclismo', u'http://www.gazzetta.it/rss/Ciclismo.xml'),
|
|
(u'Basket', u'http://www.gazzetta.it/rss/Basket.xml'),
|
|
(u'Tennis', u'http://www.gazzetta.it/rss/Tennis.xml'),
|
|
(u'Pallavolo', u'http://www.gazzetta.it/rss/Pallavolo.xml'),
|
|
(u'Vela', u'http://www.gazzetta.it/rss/Vela.xml'),
|
|
(u'Atletica', u'http://www.gazzetta.it/rss/Atletica.xml'),
|
|
(u'Altri Sport', u'http://www.gazzetta.it/rss/Sport_Vari.xml')
|
|
]
|
|
|
|
def print_version(self, url):
|
|
segments = url.split('/')
|
|
basename = '/'.join(segments[:3]) + '/'
|
|
subPath = '/'.join(segments[3:7]) + '/'
|
|
articleURL = (segments[len(segments) - 1])[:-6]
|
|
myArticleSegs = articleURL.split('.')
|
|
myArticle = myArticleSegs[0]
|
|
printVerString = myArticle + '_print.html'
|
|
myURL = basename + subPath + printVerString
|
|
print 'this is the url: ' + myURL
|
|
return basename + subPath + printVerString
|