| 1 |
#!/usr/bin/env python |
| 2 |
# -*- coding: utf-8 -*- |
| 3 |
|
| 4 |
__license__ = 'GPL v3' |
| 5 |
__copyright__ = '2010, Francisco Javier Nieto <frjanibo at gmail.com>' |
| 6 |
''' |
| 7 |
www.hoy.es |
| 8 |
''' |
| 9 |
|
| 10 |
from calibre.ebooks.BeautifulSoup import Tag |
| 11 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 12 |
|
| 13 |
|
| 14 |
def new_tag(soup, name, attrs=()): |
| 15 |
impl = getattr(soup, 'new_tag', None) |
| 16 |
if impl is not None: |
| 17 |
return impl(name, attrs=dict(attrs)) |
| 18 |
return Tag(soup, name, attrs=attrs or None) |
| 19 |
|
| 20 |
|
| 21 |
class Hoy(BasicNewsRecipe): |
| 22 |
title = 'HOY' |
| 23 |
__author__ = 'Fco Javier Nieto' |
| 24 |
description = 'Noticias desde Extremadura' |
| 25 |
publisher = 'HOY' |
| 26 |
category = 'news, politics, Spain, Extremadura' |
| 27 |
oldest_article = 2 |
| 28 |
max_articles_per_feed = 100 |
| 29 |
no_stylesheets = True |
| 30 |
use_embedded_content = False |
| 31 |
delay = 1 |
| 32 |
encoding = 'cp1252' |
| 33 |
language = 'es' |
| 34 |
|
| 35 |
feeds = [ |
| 36 |
('Portada', 'http://www.hoy.es/portada.xml'), |
| 37 |
('Regional', 'http://www.hoy.es/rss/feeds/regional.xml'), |
| 38 |
('Prov de Badajoz', 'http://www.hoy.es/rss/feeds/prov_badajoz.xml'), |
| 39 |
('Prov de Caceres', 'http://www.hoy.es/rss/feeds/prov_caceres.xml'), |
| 40 |
('Badajoz', 'http://www.hoy.es/rss/feeds/badajoz.xml'), |
| 41 |
('Caceres', 'http://www.hoy.es/rss/feeds/caceres.xml'), |
| 42 |
('Merida', 'http://www.hoy.es/rss/feeds/merida.xml'), |
| 43 |
('Opinion', 'http://www.hoy.es/rss/feeds/opinion.xml'), |
| 44 |
('Nacional', 'http://www.hoy.es/rss/feeds/nacional.xml'), |
| 45 |
('Internacional', 'http://www.hoy.es/rss/feeds/internacional.xml'), |
| 46 |
('Economia', 'http://www.hoy.es/rss/feeds/economia.xml'), |
| 47 |
('Deportes', 'http://www.hoy.es/rss/feeds/deportes.xml'), |
| 48 |
('Sociedad', 'http://www.hoy.es/rss/feeds/sociedad.xml'), |
| 49 |
('Cultura', 'http://www.hoy.es/rss/feeds/cultura.xml'), |
| 50 |
('Television', 'http://www.hoy.es/rss/feeds/television.xml'), |
| 51 |
('contraportada', 'http://www.hoy.es/rss/feeds/contraportada.xml'), |
| 52 |
] |
| 53 |
|
| 54 |
keep_only_tags = [ |
| 55 |
dict(name='h1', attrs={'class': ['headline']}), |
| 56 |
dict(name='h2', attrs={'class': ['subhead']}), |
| 57 |
dict(name='div', attrs={'class': ['text']}), |
| 58 |
] |
| 59 |
|
| 60 |
remove_tags = [dict(name=['object', 'link', 'script']), dict(name='div', attrs={'class': ['colC_articulo', 'peu']})] |
| 61 |
|
| 62 |
remove_tags_after = [dict(name='div', attrs={'class': 'text'})] |
| 63 |
|
| 64 |
extra_css = '.headline {font: sans-serif 2em;}\n.subhead,h2{font: sans-serif 1.5em\n' |
| 65 |
|
| 66 |
def preprocess_html(self, soup): |
| 67 |
soup.html['dir'] = self.direction |
| 68 |
mcharset = new_tag(soup, 'meta', [('http-equiv', 'Content-Type'), ('content', 'text/html; charset=utf-8')]) |
| 69 |
soup.head.insert(0, mcharset) |
| 70 |
for item in soup.findAll(style=True): |
| 71 |
del item['style'] |
| 72 |
return soup |