mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
74 lines
2.9 KiB
Python
74 lines
2.9 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '30 October 2010, Jordi Balcells based on an earlier recipe by Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
elperiodico.cat
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
|
|
|
|
def new_tag(soup, name, attrs=()):
|
|
impl = getattr(soup, 'new_tag', None)
|
|
if impl is not None:
|
|
return impl(name, attrs=dict(attrs))
|
|
return Tag(soup, name, attrs=attrs or None)
|
|
|
|
|
|
class ElPeriodico_cat(BasicNewsRecipe):
|
|
title = 'El Periodico de Catalunya'
|
|
__author__ = 'Jordi Balcells/Darko Miletic'
|
|
description = 'Noticias desde Catalunya'
|
|
publisher = 'elperiodico.com'
|
|
category = 'news, politics, Spain, Catalunya'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
delay = 1
|
|
encoding = 'cp1252'
|
|
language = 'es'
|
|
|
|
html2lrf_options = [
|
|
'--comment', description, '--category', category, '--publisher', publisher
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + \
|
|
'"\ncomments="' + description + '"\ntags="' + category + '"'
|
|
|
|
feeds = [(u'Portada', u'http://www.elperiodico.com/es/rss/rss_portada.xml'),
|
|
(u'Internacional', u'http://elperiodico.com/es/rss/internacional/rss.xml'),
|
|
(u'Sociedad', u'http://elperiodico.com/es/rss/sociedad/rss.xml'),
|
|
(u'Ciencia y Tecnolog\xeda',
|
|
u'http://elperiodico.com/es/rss/ciencia-y-tecnologia/rss.xml'),
|
|
(u'Deportes', u'http://elperiodico.com/es/rss/deportes/rss.xml'),
|
|
(u'Gente', u'http://elperiodico.com/es/rss/gente/rss.xml'),
|
|
(u'Opini\xf3n', u'http://elperiodico.com/es/rss/opinion/rss.xml'),
|
|
(u'Pol\xedtica', u'http://elperiodico.com/es/rss/politica/rss.xml'),
|
|
(u'Barcelona', u'http://elperiodico.com/es/rss/barcelona/rss.xml'),
|
|
(u'Econom\xeda', u'http://elperiodico.com/es/rss/economia/rss.xml'),
|
|
(u'Cultura y espect\xe1culos',
|
|
u'http://elperiodico.com/es/rss/cultura-y-espectaculos/rss.xml'),
|
|
(u'Tele', u'http://elperiodico.com/es/rss/cultura-y-espectaculos/rss.xml')]
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'class': 'titularnoticia'}),
|
|
dict(name='div', attrs={'class': 'noticia_completa'})]
|
|
|
|
remove_tags = [dict(name='div', attrs={'class': ['opcionb', 'opcionb last', 'columna_noticia']}),
|
|
dict(name='span', attrs={'class': 'opcionesnoticia'})
|
|
]
|
|
|
|
def print_version(self, url):
|
|
return url.replace('/default.asp?', '/print.asp?')
|
|
|
|
def preprocess_html(self, soup):
|
|
mcharset = new_tag(soup, 'meta', [
|
|
("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")])
|
|
soup.head.insert(0, mcharset)
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|