| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
cubadebate.cu |
| 5 |
''' |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 8 |
|
| 9 |
|
| 10 |
class CubaDebate(BasicNewsRecipe): |
| 11 |
title = 'CubaDebate' |
| 12 |
__author__ = 'Darko Miletic' |
| 13 |
description = 'Contra el Terorismo Mediatico' |
| 14 |
oldest_article = 15 |
| 15 |
language = 'es_CU' |
| 16 |
max_articles_per_feed = 100 |
| 17 |
no_stylesheets = True |
| 18 |
use_embedded_content = False |
| 19 |
publisher = 'Cubadebate' |
| 20 |
category = 'news, politics, Cuba' |
| 21 |
encoding = 'utf-8' |
| 22 |
masthead_url = 'http://www.cubadebate.cu/wp-content/themes/cubadebate/images/logo.gif' |
| 23 |
publication_type = 'newsportal' |
| 24 |
extra_css = ''' |
| 25 |
#BlogTitle{font-size: xx-large; font-weight: bold} |
| 26 |
body{font-family: Verdana, Arial, Tahoma, sans-serif} |
| 27 |
''' |
| 28 |
|
| 29 |
conversion_options = {'comments': description, 'tags': category, 'language': language, 'publisher': publisher} |
| 30 |
|
| 31 |
keep_only_tags = [dict(name='div', attrs={'id': 'Outline'})] |
| 32 |
remove_tags_after = dict(name='div', attrs={'id': 'BlogContent'}) |
| 33 |
remove_tags = [dict(name=['link', 'base', 'embed', 'object', 'meta', 'iframe']), dict(attrs={'id': 'addthis_container'})] |
| 34 |
|
| 35 |
feeds = [('Articulos', 'http://www.cubadebate.cu/feed/')] |
| 36 |
remove_attributes = ['width', 'height', 'lang'] |
| 37 |
|
| 38 |
def print_version(self, url): |
| 39 |
return url + 'print/' |
| 40 |
|
| 41 |
def preprocess_html(self, soup): |
| 42 |
for item in soup.findAll(style=True): |
| 43 |
del item['style'] |
| 44 |
for item in soup.findAll('img', alt=False): |
| 45 |
item['alt'] = 'image' |
| 46 |
return soup |