calibre/recipes/tawernarpg_pl.recipe
2013-05-29 08:02:55 +05:30

38 lines
1.6 KiB
Plaintext

__license__ = 'GPL v3'
import re
from calibre.web.feeds.news import BasicNewsRecipe
class TawernaRPG(BasicNewsRecipe):
title = u'Tawerna RPG'
__author__ = 'fenuks'
description = u'Tawerna RPG to ogólnopolski serwis zajmujący się fantastyką i grami fantastycznymi. Znajdziesz u nas zarówno gry fabularne, karciane, planszowe i komputerowe, a także recenzje, opowiadania i sporą dawkę humoru.'
category = 'fantasy, rpg, board games'
#publication_type = ''
language = 'pl'
#encoding = ''
extra_css = '.slajd {list-style-type: none; padding-left: 0px; margin-left: 0px;} .lewanc {float: left; margin-right: 5px;} .srodek {display: block; margin-left: auto; margin-right: auto;}'
cover_url = 'http://www.tawerna.rpg.pl/img/logo.png'
#masthead_url = ''
preprocess_regexps = [(re.compile(ur'<h2>Dodaj komentarz</h2>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
use_embedded_content = False
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
remove_javascript = True
remove_attributes = ['style', 'font']
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [dict(id='site')]
remove_tags = [dict(id=['player', 'komentarz'])]
remove_tags_after = dict(id='komentarz')
#remove_tags_before = dict()
feeds = [(u'Artykuły', 'http://www.tawerna.rpg.pl/css/rss.rss')]
def preprocess_html(self, soup):
for r in soup.findAll(attrs={'class':'powi'}):
r.parent.extract()
for c in soup.findAll(name=['li', 'ol', 'ul']):
c.name = 'div'
return soup