calibre/recipes/gs24_pl.recipe

46 lines
1.6 KiB
Plaintext

# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
import re
import string
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1322322819(BasicNewsRecipe):
title = u'GS24.pl (Głos Szczeciński)'
description = u'Internetowy serwis Głosu Szczecińskiego'
__author__ = u'Michał Szkutnik'
__license__ = u'GPL v3'
language = 'pl'
publisher = 'Media Regionalne sp. z o.o.'
category = 'news, szczecin'
oldest_article = 2
max_articles_per_feed = 100
auto_cleanup = True
cover_url = "http://www.gs24.pl/images/top_logo.png"
feeds = [
# (u'Wszystko', u'http://www.gs24.pl/rss.xml'),
(u'Szczecin', u'http://www.gs24.pl/szczecin.xml'),
(u'Stargard', u'http://www.gs24.pl/stargard.xml'),
(u'Świnoujście', u'http://www.gs24.pl/swinoujscie.xml'),
(u'Goleniów', u'http://www.gs24.pl/goleniow.xml'),
(u'Gryfice', u'http://www.gs24.pl/gryfice.xml'),
(u'Kamień Pomorski', u'http://www.gs24.pl/kamienpomorski.xml'),
(u'Police', u'http://www.gs24.pl/police.xml'),
(u'Region', u'http://www.gs24.pl/region.xml'),
(u'Sport', u'http://www.gs24.pl/sport.xml'),
]
def get_article_url(self, article):
s = re.search("""/0L0S(gs24.*)/story01.htm""", article.link)
s = s.group(1)
replacements = {"0B": ".", "0C": "/",
"0H": ",", "0I": "_", "0D": "?", "0F": "="}
for (a, b) in replacements.items():
s = string.replace(s, a, b)
s = string.replace(s, "0A", "0")
return "http://" + s
def print_version(self, url):
return url + "&Template=printpicart"