mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
59 lines
2.5 KiB
Plaintext
59 lines
2.5 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class KurierPoranny(BasicNewsRecipe):
|
|
title = u'Kurier Poranny'
|
|
__author__ = 'fenuks'
|
|
description = u'Kurier Poranny | poranny.pl - portal miejski Białegostoku,informacje,wydarzenia'
|
|
category = 'newspaper'
|
|
language = 'pl'
|
|
encoding = 'iso-8859-2'
|
|
extra_css = 'ul {list-style: none; padding:0; margin:0;}'
|
|
INDEX = 'http://www.poranny.pl'
|
|
masthead_url = INDEX + '/images/top_logo.png'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
use_embedded_content = False
|
|
|
|
feeds = [(u'Wszystkie', u'http://www.poranny.pl/rss.xml'),
|
|
(u'Białystok', u'http://www.poranny.pl/bialystok.xml'),
|
|
(u'Bielsk Podlaski', u'http://www.poranny.pl/bielskpodlaski.xml'),
|
|
(u'Czarna Białostocka',
|
|
u'http://www.poranny.pl/czarnabialostocka.xml'),
|
|
(u'Hajnówka', u'http://www.poranny.pl/hajnowka.xml'),
|
|
(u'Łapy', u'http://www.poranny.pl/lapy.xml'),
|
|
(u'Sokółka', u'http://www.poranny.pl/sokolka.xml'),
|
|
(u'Supraśl', u'http://www.poranny.pl/suprasl.xml'),
|
|
(u'Wasilków', u'http://www.poranny.pl/wasilkow.xml'),
|
|
(u'Sport', u'http://www.poranny.pl/sport.xml'),
|
|
(u'Praca', u'http://www.poranny.pl/praca.xml'),
|
|
(u'Kultura', u'http://www.poranny.pl/kultura.xml'),
|
|
(u'Dom', u'http://www.poranny.pl/dom.xml'),
|
|
(u'Auto', u'http://www.poranny.pl/auto.xml'),
|
|
(u'Polityka', u'http://www.poranny.pl/polityka.xml')]
|
|
|
|
keep_only_tags = [dict(id='article')]
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup(
|
|
self.INDEX + '/apps/pbcs.dll/section?Category=JEDYNKI')
|
|
nexturl = self.INDEX + soup.find(id='covers').find('a')['href']
|
|
soup = self.index_to_soup(nexturl)
|
|
self.cover_url = self.INDEX + \
|
|
soup.find(id='cover').find(name='img')['src']
|
|
return getattr(self, 'cover_url', self.cover_url)
|
|
|
|
def decode_feedportal_url(self, url):
|
|
link = url.rpartition('l/0L0S')[2][:-12]
|
|
replaces = (('0B', '.'), ('0C', '/'), ('0H', ','),
|
|
('0D', '?'), ('0F', '='), ('0A', '0'), ('0I', '_'))
|
|
for t in replaces:
|
|
link = link.replace(*t)
|
|
return 'http://' + link
|
|
|
|
def print_version(self, url):
|
|
return self.decode_feedportal_url(url) + '&Template=printpicart'
|