calibre/recipes/unica.recipe

57 lines
1.7 KiB
Plaintext

# -*- coding: utf-8 -*-
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
unica.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Unica(BasicNewsRecipe):
title = u'Unica'
__author__ = u'Silviu Cotoar\u0103'
description = 'Asa cum esti tu'
publisher = 'Unica'
oldest_article = 5
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Reviste,Femei'
encoding = 'utf-8'
cover_url = 'http://www.unica.ro/fileadmin/images/logo.gif'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [
dict(name='div', attrs={'id':'sticky'})
, dict(name='p', attrs={'class':'bodytext'})
]
remove_tags = [
dict(name='div', attrs={'class':['top-links']})
, dict(name='div', attrs={'id':['autor_name']})
, dict(name='div', attrs={'class':['box-r']})
, dict(name='div', attrs={'class':['category']})
, dict(name='div', attrs={'class':['data']})
]
remove_tags_after = [
dict(name='ul', attrs={'class':'pager'})
]
feeds = [
(u'Feeds', u'http://www.unica.ro/rss.html')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)