calibre/recipes/curierulnational.recipe
2015-01-23 19:08:21 +05:30

55 lines
1.7 KiB
Python

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
curierulnational.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class CurierulNal(BasicNewsRecipe):
title = u'Curierul Na\u0163ional'
__author__ = u'Silviu Cotoar\u0103'
description = ''
publisher = 'Curierul Na\u0163ional'
oldest_article = 5
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Stiri'
encoding = 'utf-8'
cover_url = 'http://www.curierulnational.ro/logo.gif'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [
dict(name='div', attrs={'id':'col1'})
, dict(name='img', attrs={'id':'placeholder'})
]
remove_tags = [
dict(name='p', attrs={'id':['alteArticole']})
, dict(name='div', attrs={'id':['textSize']})
, dict(name='ul', attrs={'class':['unit-rating']})
, dict(name='div', attrs={'id':['comments']})
]
remove_tags_after = [
dict(name='ul', attrs={'class':'unit-rating'})
]
feeds = [
(u'Feeds', u'http://www.curierulnational.ro/feed.xml')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)