calibre/recipes/babyonline.recipe

60 lines
2.0 KiB
Plaintext

# -*- coding: utf-8 -*-
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
babyonline.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BabyOnline(BasicNewsRecipe):
title = u'Baby Online'
__author__ = u'Silviu Cotoar\u0103'
description = u'De la p\u0103rinte la p\u0103rinte'
publisher = u'Baby Online'
oldest_article = 50
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Reviste,Copii,Mame'
encoding = 'utf-8'
cover_url = 'http://www.babyonline.ro/images/default/logo.gif'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [
dict(name='div', attrs={'id':'article_container'})
]
remove_tags = [
dict(name='div', attrs={'id':'bar_nav'}),
dict(name='div', attrs={'id':'service_send'}),
dict(name='div', attrs={'id':'other_videos'}),
dict(name='div', attrs={'class':'dot_line_yellow'}),
dict(name='a', attrs={'class':'print'}),
dict(name='a', attrs={'class':'email'}),
dict(name='a', attrs={'class':'YM'}),
dict(name='a', attrs={'class':'comment'}),
dict(name='div', attrs={'class':'tombstone_cross'}),
dict(name='span', attrs={'class':'liketext'})
]
remove_tags_after = [
dict(name='div', attrs={'id':'service_send'})
]
feeds = [
(u'Feeds', u'http://www.babyonline.ro/rss_homepage.xml')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)