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

55 lines
1.8 KiB
Python

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'2011'
'''
socialdiva.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class SocialDiva(BasicNewsRecipe):
title = u'Social Diva'
__author__ = u'Silviu Cotoara'
description = u'When in doubt, wear red'
publisher = 'Social Diva'
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.socialdiva.ro/images/logo.png'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [
dict(name='div', attrs={'class':'col-alpha mt5 content_articol'}),
dict(name='div', attrs={'class':'mt5'})
]
remove_tags = [
dict(name='a', attrs={'class':['comments float-left scroll mt5']}),
dict(name='a', attrs={'class':['comments float-left scroll']}),
dict(name='div', attrs={'class':['rating-container relative float-left']}),
dict(name='div', attrs={'class':['float-right social_articol']})
]
remove_tags_after = [
dict(name='a', attrs={'class':['comments float-left scroll mt5']})
]
feeds = [
(u'Feeds', u'http://www.socialdiva.ro/rss.html')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)