I've put together a recipe for News24, a popular South African news portal. The builtin IOL recipe was used as a sample and starting point, so if any credit is needed thank you to the author of that recipe.
Spoiler:
Code:
class AdvancedUserRecipe1375900744(BasicNewsRecipe):
title = u'News24'
description = "News24."
__author__ = 'Nicki de Wet'
publisher = 'Media24'
category = 'news, politics, South Africa'
oldest_article = 3
max_articles_per_feed = 20
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
auto_cleanup = False
language = 'en_ZA'
remove_empty_feeds = True
publication_type = 'newsportal'
masthead_url = 'http://www.24.com/images/widgethead_news.png'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{display: block}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(name=['object','embed','iframe','table','meta','link']),
dict(attrs={'class':['TwitterfacebookLink','superSportArticleBlock', 'videoHighlights', 'facebookComments','share', 'item_block','kalahari_product left', 'block red', 'credit']}),
dict(attrs={'id':['comments_wrap', 'article_toolbox_bot', 'inside_news','sponsored-links', 'lnkGalleries', 'relatedlinks_box', 'lnkUserGalleries', 'lnkNewsGalleries', 'relatedlinks', 'divRelatedLinks']})]
keep_only_tags = [dict(attrs={'class':['left col633', 'article col626', 'columnWrapperLeft', 'articlecolumn', 'article_img', 'picture_caption', 'DiveTable']})]
feeds = [(u'Top Stories', u'http://feeds.news24.com/articles/news24/TopStories/rss'), (u'South Africa', u'http://feeds.news24.com/articles/news24/SouthAfrica/rss'), (u'World', u'http://feeds.news24.com/articles/news24/World/rss'), (u'Sport', u'http://feeds.24.com/articles/sport/featured/topstories/rss')]