mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
73 lines
3.4 KiB
Plaintext
73 lines
3.4 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class GazetaPomorska(BasicNewsRecipe):
|
|
title = u'Gazeta Pomorska'
|
|
__author__ = 'Richard z forum.eksiazki.org, fenuks'
|
|
description = u'Gazeta Pomorska - portal regionalny'
|
|
category = 'newspaper'
|
|
language = 'pl'
|
|
encoding = 'iso-8859-2'
|
|
extra_css = 'ul {list-style: none; padding:0; margin:0;}'
|
|
INDEX = 'http://www.pomorska.pl'
|
|
masthead_url = INDEX + '/images/top_logo.png'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
|
|
feeds = [(u'Wszystkie', u'http://www.pomorska.pl/rss.xml'),
|
|
(u'Region', u'http://www.pomorska.pl/region.xml'),
|
|
(u'Bydgoszcz', u'http://www.pomorska.pl/bydgoszcz.xml'),
|
|
(u'Nakło', u'http://www.pomorska.pl/naklo.xml'),
|
|
(u'Koronowo', u'http://www.pomorska.pl/koronowo.xml'),
|
|
(u'Solec Kujawski', u'http://www.pomorska.pl/soleckujawski.xml'),
|
|
(u'Grudziądz', u'http://www.pomorska.pl/grudziadz.xml'),
|
|
(u'Inowrocław', u'http://www.pomorska.pl/inowroclaw.xml'),
|
|
(u'Toruń', u'http://www.pomorska.pl/torun.xml'),
|
|
(u'Włocławek', u'http://www.pomorska.pl/wloclawek.xml'),
|
|
(u'Aleksandrów Kujawski',
|
|
u'http://www.pomorska.pl/aleksandrow.xml'),
|
|
(u'Brodnica', u'http://www.pomorska.pl/brodnica.xml'),
|
|
(u'Chełmno', u'http://www.pomorska.pl/chelmno.xml'),
|
|
(u'Chojnice', u'http://www.pomorska.pl/chojnice.xml'),
|
|
(u'Ciechocinek', u'http://www.pomorska.pl/ciechocinek.xml'),
|
|
(u'Golub-Dobrzyń', u'http://www.pomorska.pl/golubdobrzyn.xml'),
|
|
(u'Mogilno', u'http://www.pomorska.pl/mogilno.xml'),
|
|
(u'Radziejów', u'http://www.pomorska.pl/radziejow.xml'),
|
|
(u'Rypin', u'http://www.pomorska.pl/rypin.xml'),
|
|
(u'Sępólno', u'http://www.pomorska.pl/sepolno.xml'),
|
|
(u'Świecie', u'http://www.pomorska.pl/swiecie.xml'),
|
|
(u'Tuchola', u'http://www.pomorska.pl/tuchola.xml'),
|
|
(u'Żnin', u'http://www.pomorska.pl/znin.xml'),
|
|
(u'Sport', u'http://www.pomorska.pl/sport.xml'),
|
|
(u'Zdrowie', u'http://www.pomorska.pl/zdrowie.xml'),
|
|
(u'Auto', u'http://www.pomorska.pl/moto.xml'),
|
|
(u'Dom', u'http://www.pomorska.pl/dom.xml'),
|
|
# (u'Reporta\u017c', u'http://www.pomorska.pl/reportaz.xml'),
|
|
(u'Gospodarka', u'http://www.pomorska.pl/gospodarka.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'
|