mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
77 lines
2.5 KiB
Python
77 lines
2.5 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.lavanguardia.es
|
|
'''
|
|
|
|
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 LaVanguardia(BasicNewsRecipe):
|
|
title = 'La Vanguardia Digital'
|
|
__author__ = 'Darko Miletic'
|
|
description = u'Noticias desde España'
|
|
publisher = 'La Vanguardia'
|
|
category = 'news, politics, Spain'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
delay = 5
|
|
language = 'es'
|
|
|
|
direction = 'ltr'
|
|
|
|
html2lrf_options = [
|
|
'--comment', description, '--category', category, '--publisher', publisher
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + \
|
|
'"\ncomments="' + description + '"\ntags="' + category + '"'
|
|
|
|
feeds = [
|
|
|
|
(u'Portada', u'http://feeds.feedburner.com/lavanguardia/home'),
|
|
(u'Cultura', u'http://feeds.feedburner.com/lavanguardia/cultura'),
|
|
(u'Deportes', u'http://feeds.feedburner.com/lavanguardia/deportes'),
|
|
(u'Economia', u'http://feeds.feedburner.com/lavanguardia/economia'),
|
|
(u'El lector opina', u'http://feeds.feedburner.com/lavanguardia/lectoropina'),
|
|
(u'Gente y TV', u'http://feeds.feedburner.com/lavanguardia/gente'),
|
|
(u'Internacional', u'http://feeds.feedburner.com/lavanguardia/internacional'),
|
|
(u'Internet y tecnologia', u'http://feeds.feedburner.com/lavanguardia/internet'),
|
|
(u'Motor', u'http://feeds.feedburner.com/lavanguardia/motor'),
|
|
(u'Politica', u'http://feeds.feedburner.com/lavanguardia/politica'),
|
|
(u'Sucesos', u'http://feeds.feedburner.com/lavanguardia/sucesos')
|
|
]
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class': 'detalle noticia'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['object', 'link', 'script']), dict(
|
|
name='div', attrs={'class': ['colC', 'peu', 'jstoolbar']})
|
|
]
|
|
|
|
remove_tags_after = [dict(name='div', attrs={'class': 'text'})]
|
|
|
|
def preprocess_html(self, soup):
|
|
soup.html['dir'] = self.direction
|
|
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
|