calibre/recipes/catavencu.recipe

54 lines
1.6 KiB
Plaintext

# -*- coding: utf-8 -*-
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
catavencu.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Catavencu(BasicNewsRecipe):
title = u'Academia Ca\u0163avencu'
__author__ = u'Silviu Cotoar\u0103'
description = 'Tagma cum laude'
publisher = 'Catavencu'
oldest_article = 5
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare'
encoding = 'utf-8'
cover_url = 'http://upload.wikimedia.org/wikipedia/en/1/1e/Academia_Catavencu.jpg'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [
dict(name='ul', attrs={'class':'articles'})
]
remove_tags = [
dict(name='div', attrs={'class':['tools']})
, dict(name='div', attrs={'class':['share']})
, dict(name='div', attrs={'class':['category']})
, dict(name='div', attrs={'id':['comments']})
]
remove_tags_after = [
dict(name='div', attrs={'id':'comments'})
]
feeds = [
(u'Feeds', u'http://catavencu.ro/feed/rss')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)