calibre/recipes/wallstreetro.recipe

55 lines
1.9 KiB
Plaintext

# -*- coding: utf-8 -*-
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
wall-street.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class WallStreetRo(BasicNewsRecipe):
title = u'Wall Street'
__author__ = u'Silviu Cotoar\u0103'
description = ''
publisher = 'Wall Street'
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://img.wall-street.ro/images/WS_new_logo.jpg'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [
dict(name='div', attrs={'class':'article_header'})
, dict(name='div', attrs={'class':'article_text'})
]
remove_tags = [
dict(name='p', attrs={'class':['page_breadcrumbs']})
, dict(name='div', attrs={'id':['article_user_toolbox']})
, dict(name='p', attrs={'class':['comments_count_container']})
, dict(name='div', attrs={'class':['article_left_column']})
]
remove_tags_after = [
dict(name='div', attrs={'class':'clearfloat'})
]
feeds = [
(u'Feeds', u'http://img.wall-street.ro/rssfeeds/wall-street.xml')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)