mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
30 lines
1.1 KiB
Plaintext
30 lines
1.1 KiB
Plaintext
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class eMuzyka(BasicNewsRecipe):
|
|
title = u'eMuzyka'
|
|
__author__ = 'fenuks'
|
|
description = u'Emuzyka to największa i najpopularniejsza strona o muzyce w Polsce'
|
|
category = 'music'
|
|
language = 'pl'
|
|
index = 'http://www.emuzyka.pl'
|
|
cover_url = 'http://s.emuzyka.pl/img/emuzyka_invert_small.jpg'
|
|
no_stylesheets = True
|
|
oldest_article = 7
|
|
remove_empty_feeds = True
|
|
max_articles_per_feed = 100
|
|
remove_attributes = ['style']
|
|
keep_only_tags = [dict(name='div', attrs={'id': 'news_container'}), dict(
|
|
name='h3'), dict(name='div', attrs={'class': 'review_text'})]
|
|
remove_tags = [dict(name='span', attrs={'id': 'date'})]
|
|
feeds = [(u'Aktualno\u015bci', u'http://www.emuzyka.pl/rss.php?f=1'),
|
|
(u'Recenzje', u'http://www.emuzyka.pl/rss.php?f=2')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for a in soup('a'):
|
|
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
|
|
a['href'] = self.index + a['href']
|
|
return soup
|