mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
51 lines
1.8 KiB
Plaintext
51 lines
1.8 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 novinkyRecipe(BasicNewsRecipe):
|
|
__author__ = 'bubak'
|
|
title = u'novinky.cz'
|
|
publisher = u'seznam.cz'
|
|
description = 'novinky.cz'
|
|
oldest_article = 1
|
|
max_articles_per_feed = 20
|
|
|
|
feeds = [
|
|
(u'Domácí', u'http://www.novinky.cz/rss2/domaci/'),
|
|
(u'Praha', u'http://www.novinky.cz/rss2/vase-zpravy/praha/'),
|
|
(u'Ekonomika', u'http://www.novinky.cz/rss2/ekonomika/'),
|
|
(u'Finance', u'http://www.novinky.cz/rss2/finance/'),
|
|
]
|
|
|
|
language = 'cs'
|
|
cover_url = 'http://www.novinky.cz/static/images/logo.gif'
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
|
|
remove_tags = [dict(name='div', attrs={'id': ['pictureInnerBox']}),
|
|
dict(name='div', attrs={'id': ['discussionEntry']}),
|
|
dict(name='span', attrs={
|
|
'id': ['mynews-hits', 'mynews-author']}),
|
|
dict(name='div', attrs={'class': ['related']}),
|
|
dict(name='div', attrs={'id': ['multimediaInfo']})]
|
|
remove_tags_before = dict(name='div', attrs={'class': ['articleHeader']})
|
|
remove_tags_after = dict(name='div', attrs={'class': 'related'})
|
|
|
|
keep_only_tags = []
|
|
|
|
# This source has identical articles under different links
|
|
# which are redirected to the common url. I've found
|
|
# just this API method that has the real URL
|
|
visited_urls = {}
|
|
|
|
def encoding(self, source):
|
|
url = source.newurl
|
|
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 source.decode('utf-8', 'replace')
|