| 1 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 2 |
|
| 3 |
|
| 4 |
class DziennikBaltycki(BasicNewsRecipe): |
| 5 |
title = 'Dziennik Ba\u0142tycki' |
| 6 |
__author__ = 'fenuks' |
| 7 |
description = 'Gazeta Regionalna Dziennik Bałtycki. Najnowsze Wiadomości Trójmiasto i Wiadomości Pomorskie. Czytaj!' |
| 8 |
category = 'newspaper' |
| 9 |
language = 'pl' |
| 10 |
masthead_url = 'http://s.polskatimes.pl/g/logo_naglowek/dziennikbaltycki.png?24' |
| 11 |
oldest_article = 7 |
| 12 |
max_articles_per_feed = 100 |
| 13 |
remove_empty_feeds = True |
| 14 |
no_stylesheets = True |
| 15 |
use_embedded_content = False |
| 16 |
ignore_duplicate_articles = {'title', 'url'} |
| 17 |
keep_only_tags = [dict(name='section', attrs={'class': 'zajawka'}), dict(name='section', attrs={'id': 'tresc'})] |
| 18 |
remove_tags = [ |
| 19 |
dict(name='div', attrs={'class': ['materialyZKategorii', 'materialyPodobne']}), |
| 20 |
dict(name='a', attrs={'class': 'czytajDalej'}), |
| 21 |
dict(attrs={'src': 'http://nm.dz.com.pl/dz.png'}), |
| 22 |
] |
| 23 |
|
| 24 |
feeds = [ |
| 25 |
('Wiadomo\u015bci', 'http://www.dziennikbaltycki.pl/rss/dziennikbaltycki_wiadomosci.xml?201302'), |
| 26 |
('Sport', 'http://dziennikbaltycki.feedsportal.com/c/32980/f/533756/index.rss?201302'), |
| 27 |
('Rejsy', 'http://www.dziennikbaltycki.pl/rss/dziennikbaltycki_rejsy.xml?201302'), |
| 28 |
('Biznes na Pomorzu', 'http://www.dziennikbaltycki.pl/rss/dziennikbaltycki_biznesnapomorzu.xml?201302'), |
| 29 |
('GOM', 'http://www.dziennikbaltycki.pl/rss/dziennikbaltycki_gom.xml?201302'), |
| 30 |
('Opinie', 'http://www.dziennikbaltycki.pl/rss/dziennikbaltycki_opinie.xml?201302'), |
| 31 |
('Pitawal Pomorski', 'http://www.dziennikbaltycki.pl/rss/dziennikbaltycki_pitawalpomorski.xml?201302'), |
| 32 |
] |
| 33 |
|
| 34 |
def print_version(self, url): |
| 35 |
return url.replace('artykul', 'drukuj') |
| 36 |
|
| 37 |
def skip_ad_pages(self, soup): |
| 38 |
if 'Advertisement' in soup.title: |
| 39 |
nexturl = soup.find('a')['href'] |
| 40 |
return self.index_to_soup(nexturl, raw=True) |
| 41 |
|
| 42 |
def get_cover_url(self): |
| 43 |
soup = self.index_to_soup('http://www.prasa24.pl/gazeta/dziennik-baltycki/') |
| 44 |
self.cover_url = soup.find(id='pojemnik').img['src'] |
| 45 |
return getattr(self, 'cover_url', self.cover_url) |