mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
45 lines
1.3 KiB
Plaintext
45 lines
1.3 KiB
Plaintext
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
|
from __future__ import unicode_literals
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
class tydenRecipe(BasicNewsRecipe):
|
|
__author__ = 'bubak'
|
|
title = u'Tyden.cz'
|
|
publisher = u''
|
|
description = ''
|
|
oldest_article = 1
|
|
max_articles_per_feed = 20
|
|
|
|
feeds = [
|
|
(u'Domácí', u'http://www.tyden.cz/rss/rss.php?rubrika_id=6'),
|
|
(u'Politika', u'http://www.tyden.cz/rss/rss.php?rubrika_id=173'),
|
|
(u'Kauzy', u'http://www.tyden.cz/rss/rss.php?rubrika_id=340')
|
|
]
|
|
|
|
|
|
#encoding = 'iso-8859-2'
|
|
language = 'cs'
|
|
cover_url = 'http://www.tyden.cz/img/tyden-logo.png'
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
remove_attributes = []
|
|
remove_tags_before = dict(name='p', attrs={'id':['breadcrumbs']})
|
|
remove_tags_after = dict(name='p', attrs={'class':['author']})
|
|
|
|
visited_urls = {}
|
|
def get_article_url(self, article):
|
|
url = BasicNewsRecipe.get_article_url(self, article)
|
|
if url in self.visited_urls:
|
|
self.log.debug('Ignoring duplicate: ' + url)
|
|
return None
|
|
else:
|
|
self.visited_urls[url] = True
|
|
self.log.debug('Accepting: ' + url)
|
|
return url
|
|
|
|
|
|
|
|
|
|
|
|
|