mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
59 lines
2.2 KiB
Plaintext
59 lines
2.2 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Hans Donner <hans.donner at pobox.com>'
|
|
'''
|
|
www.standardmedia.co.ke
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class NationKeRecipe(BasicNewsRecipe):
|
|
|
|
__author__ = 'Hans Donner'
|
|
|
|
title = u'Sunday Nation'
|
|
description = 'News from Kenia'
|
|
language = 'en'
|
|
country = 'KE'
|
|
publication_type = 'newspaper'
|
|
publisher = 'nation.co.ke'
|
|
category = 'news, politics, Kenia'
|
|
|
|
masthead_url = 'http://www.nation.co.ke/image/view/-/465228/medRes/33884/-/maxh/85/-/12e8pptz/-/Sunday_Logo.gif'
|
|
|
|
max_articles_per_feed = 200
|
|
oldest_article = 2
|
|
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
|
|
no_stylesheets = True
|
|
extra_css = ' body{font-family: Verdana,Arial,Helvetica,sans-serif; font-size:0.7em } ' + \
|
|
' .image{margin-bottom: 1em} '
|
|
|
|
keep_only_tags = dict(id='articlebody')
|
|
|
|
feeds = [(u'News', u'http://www.nation.co.ke/News/-/1056/1056/-/view/asFeed/-/14nfs48z/-/index.xml'),
|
|
(u'Business', u'http://www.nation.co.ke/business/-/996/996/-/view/asFeed/-/14lpkvc/-/index.xml'),
|
|
(u'InDepth', u'http://www.nation.co.ke/InDepth/-/452898/452898/-/view/asFeed/-/14ndbk6/-/index.xml'),
|
|
(u'Sports', u'http://www.nation.co.ke/sports/-/1090/1090/-/view/asFeed/-/hlukmj/-/index.xml'),
|
|
(u'Magazines', u'http://www.nation.co.ke/magazines/-/1190/1190/-/view/asFeed/-/fcxm6jz/-/index.xml'),
|
|
(u'Op/Ed', u'http://www.nation.co.ke/oped/-/1192/1192/-/view/asFeed/-/unsp8mz/-/index.xml'),
|
|
(u'Blogs', u'http://www.nation.co.ke/blogs/-/620/620/-/view/asFeed/-/28ia05z/-/index.xml')]
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
def print_version(self, url):
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
soup = BeautifulSoup(self.browser.open(url).read())
|
|
printversion = soup.find('a', text='Print')
|
|
if printversion is None:
|
|
return url
|
|
else:
|
|
return 'http://www.nation.co.ke' + printversion.parent['href']
|
|
|
|
def preprocess_html(self, soup):
|
|
return self.adeify_images(soup)
|