mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
0889ee85ec
Command used: futurize --no-diffs -f libfuturize.fixes.fix_print_with_import -f lib2to3.fixes.fix_throw -f lib2to3.fixes.fix_numliterals -f lib2to3.fixes.fix_except -f lib2to3.fixes.fix_exec -f lib2to3.fixes.fix_raise -f lib2to3.fixes.fix_tuple_params -f lib2to3.fixes.fix_ne -j20 -w -n setup recipes src manual setup.py recipes/*.recipe And manual adjustments of print((...)) -> print(...)
115 lines
5.1 KiB
Plaintext
115 lines
5.1 KiB
Plaintext
from __future__ import print_function
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini; minor fixes by faber1971'
|
|
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>, faber1971'
|
|
|
|
'''
|
|
http://www.repubblica.it/
|
|
'''
|
|
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class LaRepubblica(BasicNewsRecipe):
|
|
title = 'La Repubblica'
|
|
__author__ = 'Lorenzo Vigentini, Gabriele Marini, Darko Miletic, faber1971'
|
|
description = 'il quotidiano online con tutte le notizie in tempo reale. News e ultime notizie. Tutti i settori: politica, cronaca, economia, sport, esteri, scienza, tecnologia, internet, spettacoli, musica, cultura, arte, mostre, libri, dvd, vhs, concerti, cinema, attori, attrici, recensioni, chat, cucina, mappe. Le citta di Repubblica: Roma, Milano, Bologna, Firenze, Palermo, Napoli, Bari, Torino.' # noqa
|
|
masthead_url = 'http://www.repubblica.it/static/images/homepage/2010/la-repubblica-logo-home-payoff.png'
|
|
publisher = 'Gruppo editoriale L\'Espresso'
|
|
category = 'News, politics, culture, economy, general interest'
|
|
language = 'it'
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
oldest_article = 1
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
publication_type = 'newspaper'
|
|
articles_are_obfuscated = True
|
|
temp_files = []
|
|
extra_css = """
|
|
img{display: block}
|
|
"""
|
|
|
|
remove_attributes = ['width', 'height', 'lang', 'xmlns:og', 'xmlns:fb']
|
|
|
|
def get_article_url(self, article):
|
|
link = BasicNewsRecipe.get_article_url(self, article)
|
|
if link and '.repubblica.it/' not in link:
|
|
link2 = article.get('id', article.get('guid', None))
|
|
if link2:
|
|
link = link2
|
|
return link.rpartition('?')[0]
|
|
|
|
def get_obfuscated_article(self, url):
|
|
count = 0
|
|
while (count < 10):
|
|
try:
|
|
response = self.browser.open(url)
|
|
html = response.read()
|
|
count = 10
|
|
except:
|
|
print("Retrying download...")
|
|
count += 1
|
|
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
|
self.temp_files[-1].write(html)
|
|
self.temp_files[-1].close()
|
|
return self.temp_files[-1].name
|
|
|
|
keep_only_tags = [
|
|
dict(attrs={'class': 'articolo'}),
|
|
dict(attrs={'class': 'body-text'}),
|
|
dict(name='p', attrs={'class': 'disclaimer clearfix'}),
|
|
dict(name='div', attrs={'id': 'main'}),
|
|
dict(attrs={'id': 'contA'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['object', 'link', 'meta', 'iframe', 'embed']),
|
|
dict(name='span', attrs={'class': 'linkindice'}),
|
|
dict(name='div', attrs={
|
|
'class': ['bottom-mobile', 'adv adv-middle-inline']}),
|
|
dict(name='div', attrs={
|
|
'id': ['rssdiv', 'blocco', 'fb-like-head', 'sidebar']}),
|
|
dict(name='div', attrs={
|
|
'class': ['utility', 'fb-like-button', 'archive-button']}),
|
|
dict(name='div', attrs={'class': 'generalbox'}),
|
|
dict(name='ul', attrs={'id': 'hystory'})
|
|
]
|
|
|
|
feeds = [
|
|
(u'Homepage', u'http://www.repubblica.it/rss/homepage/rss2.0.xml'),
|
|
(u'Cronaca', u'http://www.repubblica.it/rss/cronaca/rss2.0.xml'),
|
|
(u'Esteri', u'http://www.repubblica.it/rss/esteri/rss2.0.xml'),
|
|
(u'Economia', u'http://www.repubblica.it/rss/economia/rss2.0.xml'),
|
|
(u'Politica', u'http://www.repubblica.it/rss/politica/rss2.0.xml'),
|
|
(u'Scienze', u'http://www.repubblica.it/rss/scienze/rss2.0.xml'),
|
|
(u'Tecnologia',
|
|
u'http://www.repubblica.it/rss/tecnologia/rss2.0.xml'),
|
|
(u'Scuola e Universita',
|
|
u'http://www.repubblica.it/rss/scuola_e_universita/rss2.0.xml'),
|
|
(u'Ambiente', u'http://www.repubblica.it/rss/ambiente/rss2.0.xml'),
|
|
(u'Cultura', u'http://www.repubblica.it/rss/spettacoli_e_cultura/rss2.0.xml'),
|
|
(u'Persone', u'http://www.repubblica.it/rss/persone/rss2.0.xml'),
|
|
(u'Sport', u'http://www.repubblica.it/rss/sport/rss2.0.xml'),
|
|
(u'Calcio', u'http://www.repubblica.it/rss/sport/calcio/rss2.0.xml'),
|
|
(u'Motori', u'http://www.repubblica.it/rss/motori/rss2.0.xml'),
|
|
(u'Roma', u'http://roma.repubblica.it/rss/rss2.0.xml'),
|
|
(u'Torino', u'http://torino.repubblica.it/rss/rss2.0.xml'),
|
|
(u'Milano', u'feed://milano.repubblica.it/rss/rss2.0.xml'),
|
|
(u'Napoli', u'feed://napoli.repubblica.it/rss/rss2.0.xml'),
|
|
(u'Bari', u'http://bari.repubblica.it/rss/rss2.0.xml'),
|
|
(u'Palermo', u'feed://palermo.repubblica.it/rss/rss2.0.xml')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(['hgroup', 'deresponsabilizzazione', 'per']):
|
|
item.name = 'div'
|
|
item.attrs = []
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|
|
|
|
def preprocess_raw_html(self, raw, url):
|
|
return '<html><head>' + raw[raw.find('</head>'):]
|